Search results for: machine failures

Authors: Camilo Souza, Lidia Melo, Fernanda Terra, Francisco Caio, Marcelo Reis

Abstract:

SIDIA is a research and development (R&D) institute that belongs to Samsung’s global software development process. The SIDIA’s Model Team (MT) is a part of Samsung’s Mobile Division Area, which is responsible for the development of Android releases embedded in Samsung mobile devices. Basically, in this software development process, the kickoff occurs in some strategic countries (e.g., South Korea) where some software requirements are applied and the initial software tests are performed. When the software achieves a more mature level, a new branch is derived, and the development continues in subsidiaries from other strategic countries (e.g., SIDIA-Brazil). However, even in the newly created branches, there are several interactions between developers from different nationalities in order to fix bugs reported during test activities, apply some specific requirements from partners and develop new features as well. Despite the GSD strategy contributes to improving software development, some challenges are also introduced as well. In this paper, we share the initial results about the application of the failure modes and effect analysis (FMEA) concept in the software development process followed by the SIDIA’s model team. The main goal was to identify and mitigate the process potential failures through the application of recommended actions. The initial results show that the application of the FMEA concept allows us to identify the potential failures in our GSD process as well as to propose corrective actions to mitigate them. Finally, FMEA encouraged members of different teams to take actions that contribute to improving our GSD process.

Keywords: global software development, potential failures, FMEA, recommended actions

Procedia PDF Downloads 224

Authors: Fuad M. Alkoot

Abstract:

The main component of a machine learning system is the classifier. Classifiers are mathematical models that can perform classification tasks for a specific application area. Additionally, many classifiers are combined using any of the available methods to reduce the classifier error rate. The benefits gained from the combination of multiple classifier designs has motivated the development of diverse approaches to multiple classifiers. We aim to investigate using fractal geometry to develop an improved classifier combiner. Initially we experiment with measuring the fractal dimension of data and use the results in the development of a combiner strategy.

Keywords: fractal geometry, machine learning, classifier, fractal dimension

Procedia PDF Downloads 215

Authors: Muhammad Fathurridho

Abstract:

Grammar as a rule used by every language to be understood by everyone is always related to syntax and morphology. Arabic grammar is different with another languages’ grammars. It has more rules and difficulties. This paper aims to investigate and describe the English grammatical errors of machine translation systems in translating Arabic sentences, including declarative, exclamation, imperative, and interrogative sentences, specifically in year 2018 which can be supported with artificial intelligence’s role. The Arabic sample sentences which are divided into two; verbal and nominal sentence of several Arabic published texts will be examined as the source language samples. The translated sentences done by several popular online machine translation systems, including Google Translate, Microsoft Bing, Babylon, Facebook, Hellotalk, Worldlingo, Yandex Translate, and Tradukka Translate are the material objects of this research. Descriptive method that will be taken to finish this research will show the grammatical errors of English target language, and classify them. The conclusion of this paper has showed that the grammatical errors of machine translation results are varied and generally classified into morphological, syntactical, and semantic errors in all type of Arabic words (Noun, Verb, and Particle), and it will be one of the evaluations for machine translation’s providers to correct them in order to improve their understandable results.

Keywords: Arabic, Arabic-English translation, machine translation, grammatical errors

Procedia PDF Downloads 154

Authors: U. Borasi, Amit Kr. Jain, Rakesh, Piyush Jain

Abstract:

Data collection, data preparation, model training, model evaluation, and deployment are all processes in a typical machine learning workflow. Training data needs to be gathered and organised. This often entails collecting a sizable dataset and cleaning it to remove or correct any inaccurate or missing information. Preparing the data for use in the machine learning model requires pre-processing it after it has been acquired. This often entails actions like scaling or normalising the data, handling outliers, selecting appropriate features, reducing dimensionality, etc. This pre-processed data is then used to train a model on some machine learning algorithm. After the model has been trained, it needs to be assessed by determining metrics like accuracy, precision, and recall, utilising a test dataset. Every time a new model is built, both data pre-processing and model training—two crucial processes in the Machine learning (ML) workflow—must be carried out. Thus, there are various Machine Learning algorithms that can be employed for every single approach to data pre-processing, generating a large set of combinations to choose from. Example: for every method to handle missing values (dropping records, replacing with mean, etc.), for every scaling technique, and for every combination of features selected, a different algorithm can be used. As a result, in order to get the optimum outcomes, these tasks are frequently repeated in different combinations. This paper suggests a simple architecture for organizing this largely produced “combination set of pre-processing steps and algorithms” into an automated workflow which simplifies the task of carrying out all possibilities.

Keywords: machine learning, automation, AUTOML, architecture, operator pool, configuration, scheduler

Procedia PDF Downloads 56

Authors: Suhani Srivastava

Abstract:

This research delves into the classification of orbital debris through machine learning (ML): it will categorize the intensity of the threat orbital debris poses through multiple ML models to gain an insight into effectively estimating the danger specific orbital debris can pose to future space missions. As the space industry expands, orbital debris becomes a growing concern in Low Earth Orbit (LEO) because it can potentially obfuscate space missions due to the increased orbital debris pollution. Moreover, detecting orbital debris and identifying its characteristics has become a major concern in Space Situational Awareness (SSA), and prior methods of solely utilizing physics can become inconvenient in the face of the growing issue. Thus, this research focuses on approaching orbital debris concerns through machine learning, an efficient and more convenient alternative, in detecting the potential threat certain orbital debris pose. Our findings found that the Logistic regression machine worked the best with a 98% accuracy and this research has provided insight into the accuracies of specific machine learning models when classifying orbital debris. Our work would help provide space shuttle manufacturers with guidelines about mitigating risks, and it would help in providing Aerospace Engineers facilities to identify the kinds of protection that should be incorporated into objects traveling in the LEO through the predictions our models provide.

Keywords: aerospace, orbital debris, machine learning, space, space situational awareness, nasa

Procedia PDF Downloads 20

Authors: Nigar Hussain

Abstract:

It is a subset of big data. Dark data means those data in which we fail to use for future decisions. There are many issues in existing work, but some need powerful tools for utilizing dark data. It needs sufficient techniques to deal with dark data. That enables users to exploit their excellence, adaptability, speed, less time utilization, execution, and accessibility. Another issue is the way to utilize dark data to extract helpful information to settle on better choices. In this paper, we proposed upgrade strategies to remove the dark side from dark data. Using a supervised model and machine learning techniques, we utilized dark data and achieved an F1 score of 89.48%.

Keywords: big data, dark data, machine learning, heatmap, random forest

Procedia PDF Downloads 27

Authors: Mohammed Benmostefa

Abstract:

In the industrial production of large series or even medium series, there are vibration problems. In continuous operations, technical devices result in vibrations in solid bodies and machine components, which generate solid noise and/or airborne noise. This is because vibrations are the mechanical oscillations of an object near its equilibrium point. In response to the problems resulting from these vibrations, a number of remedial acts and solutions have been put forward. These include insulation of machines, insulation of concrete masses, insulation under screeds, insulation of sensitive equipment, point insulation of machines, linear insulation of machines, full surface insulation of machines, and the like. Following this, the researcher sought not only to raise awareness on the possibility of lowering the vibration frequency in industrial machines but also to stress the significance of procedures involving the pre-installation process of machinery, namely, setting appropriate installation and start-up methods of the machine, allocating and updating imprint folders to each machine, and scheduling maintenance of each machine all year round to have reliable equipment, gain cost reduction and maintenance efficiency to eventually ensure the overall economic performance of the company.

Keywords: maintenance, vibration, efficiency, production, machinery

Procedia PDF Downloads 86

Authors: Asra Yousuf, Ajaykumar Tannirkulum

Abstract:

Inferring rural-urban migration trends can help design effective policies that promote better urban planning and rural development. In this paper, we describe how machine learning algorithms can be applied to predict internal migration decisions of people. We consider data collected from household surveys in Tamil Nadu to train our model. To measure the performance of the model, we use data on past migration from National Sample Survey Organisation of India. The factors for training the model include socioeconomic characteristic of each individual like age, gender, place of residence, outstanding loans, strength of the household, etc. and his past migration history. We perform a comparative analysis of the performance of a number of machine learning algorithm to determine their prediction accuracy. Our results show that machine learning algorithms provide a stronger prediction accuracy as compared to statistical models. Our goal through this research is to propose the use of data science techniques in understanding human decisions and behaviour in developing countries.

Keywords: development, migration, internal migration, machine learning, prediction

Procedia PDF Downloads 270

Authors: Lilian Ogechi Iheukwumere-Esotu, Akilu Yunusa-Kaltungo, Paul Chan

Abstract:

Industrial assets are prone to degradation and eventual failures due to repetitive loads and harsh environments in which they operate. These failures often lead to costly downtimes, which may involve loss of critical assets and/or human lives. The rising pressures from stakeholders for optimized systems’ outputs have further placed strains on business organizations. Traditional means of combating such failures are by adopting strategies capable of predicting, controlling, and/or reducing the likelihood of systems’ failures. Turnarounds, shutdowns, and outages (TSOs) projects are popular maintenance management activities conducted over a certain period of time. However, despite the critical and significant cost implications of TSOs, the management of the interface of knowledge between academia and industry to our best knowledge has not been fully explored in comparison to other aspects of industrial operations. This is perhaps one of the reasons for the limited knowledge transfer between academia and industry, which has affected the outcomes of most TSOs. Prior to now, the study of knowledge development trends as a failure analysis tool in the management of TSOs projects have not gained the required level of attention. Hence, this review provides useful references and their implications for future studies in this field. This study aims to harmonize the existing research trends of TSOs through a systematic review of more than 3,000 research articles published over 7 decades (1940- till date) which were extracted using very specific research criteria and later streamlined using nominated inclusion and exclusion parameters. The information obtained from the analysis were then synthesized and coded into 8 parameters, thereby allowing for a transformation into actionable outputs. The study revealed a variety of information, but the most critical findings can be classified into 4 folds: (1) Empirical validation of available conceptual frameworks and models is still a far cry in practice, (2) traditional project management views for managing uncertainties are still dominant, (3) Inconsistent approaches towards the adoption and promotion of knowledge management systems which supports creation, transfer and application of knowledge within and outside the project organization and, (4) exploration of social practices in industrial maintenance project environments are under-represented within the existing body of knowledge. Thus, the intention of this study is to depict the usefulness of a framework which incorporates fact findings emanating from careful analysis and illustrations of evidence based results as a suitable approach which can tackle reoccurring failures in industrial maintenance projects.

Keywords: industrial maintenance, knowledge management, maintenance projects, systematic review, TSOs

Procedia PDF Downloads 115

Authors: Usman Abubakar, Xiaoyuan Wang, Sayyed Haleem Shah, Sadiq Ur Rahman, Rabiu Saleh Zakariyya

Abstract:

High-speed Permanent magnet synchronous machine (HSPMSM) uses in different industrial applications like blowers, compressors as a result of its superb performance. Nevertheless, the over-temperature rise of both winding and PM is one of their substantial problem for a high-power HSPMSM, which affects its lifespan and performance. According to the literature, HSPMSM with a Hybrid cooling configuration has a much lower temperature rise than non-hybrid cooling. This paper presents the design 185kW, 26K rpm with two different cooling configurations, i.e., hybrid cooling configuration (forced air and housing spiral water jacket) and non-hybrid (forced air cooling assisted with winding’s potting material and sleeve’s material) to enhance the heat dissipation of winding and PM respectively. Firstly, the machine’s electromagnetic design is conducted by the finite element method to accurately account for machine losses. Then machine’s cooling configurations are introduced, and their effectiveness is validated by lumped parameter thermal network (LPTN). Investigation shows that using potting, sleeve materials to assist non-hybrid cooling configuration makes the machine’s winding and PM temperature closer to hybrid cooling configuration. Therefore, the machine with non-hybrid cooling is prototyped and tested due to its simplicity, lower energy consumption and can still maintain the lifespan and performance of the HSPMSM.

Keywords: airflow network, axial ventilation, high-speed PMSM, thermal network

Procedia PDF Downloads 229

Authors: Kyle Saltmarsh

Abstract:

Acoustic testing possesses many benefits due to its non-destructive nature and practicality. There hence exists many scenarios in which using acoustic testing for condition testing shows powerful feasibility. A wealth of information is contained within the acoustic and vibration characteristics of structures, allowing the development meaningful features for the classification of their respective condition. In this paper, methods, results, and discussions are presented on the use of non-destructive acoustic testing coupled with acoustic feature extraction and machine learning techniques for the condition testing of manufactured circular steel plates subjected to varied levels of damage.

Keywords: plates, deformation, acoustic features, machine learning

Procedia PDF Downloads 336

Authors: María Laura Guevara Campos

Abstract:

The increasing number of vending machines makes it easy for people to find them more frequently in stores, universities, workplaces, and even hospitals. These machines usually offer products with high contents of sugar and fat, which, if consumed regularly, can result in serious health threats, as overweight and obesity. Additionally, the energy consumption of these machines tends to be high, which has an impact on the environment as well. In order to promote the consumption of healthy food, a vending machine was designed to give the customer the opportunity to choose between a customized fruit salad and a customized fruit juice, both of them prepared instantly with the ingredients selected by the customer. The main parameters considered to design the machine were: the storage of the preferred fruits in a salad and/or in a juice according to a survey, the size of the machine, the use of ecologic recipients, and the overall energy consumption. The methodology used for the design was the one proposed by the German Association of Engineers for mechatronics systems, which breaks the design process in several stages, from the elaboration of a list of requirements through the establishment of the working principles and the design concepts to the final design of the machine, which was done in a 3D modelling software. Finally, with the design of this machine, the aim is to contribute to the development and implementation of healthier vending machines that offer freshly-made products, which is not being widely attended at present.

Keywords: design, design methodology, mechatronics systems, vending machines

Procedia PDF Downloads 131

Authors: Patience Muchini, Electdom Matandiroya, Emmanuel Mashonjowa

Abstract:

A ground-end manifestation of space weather phenomena is known as geomagnetically induced currents (GICs). GICs flow along the electric power transmission cables connecting the transformers and between the grounding points of power transformers during significant geomagnetic storms. Geomagnetically induced currents have been studied in other regions and have been noted to affect the power grid network. In Zimbabwe, grid failures have been experienced, but it is yet to be proven if these failures have been due to GICs. The purpose of this paper is to characterize geomagnetically induced currents with a power grid network. This paper analyses data collected, which is geomagnetic data, which includes the Kp index, DST index, and the G-Scale from geomagnetic storms and also analyses power grid data, which includes reactive power, relay tripping, and alarms from high voltage substations and then correlates the data. This research analysis was first theoretically analyzed by studying geomagnetic parameters and then experimented upon. To correlate, MATLAB was used as the basic software to analyze the data. Latitudes of the substations were also brought into scrutiny to note if they were an impact due to the location as low latitudes areas like most parts of Zimbabwe, there are less severe geomagnetic variations. Based on theoretical and graphical analysis, it has been proven that there is a slight relationship between power system failures and GICs. Further analyses can be done by implementing measuring instruments to measure any currents in the grounding of high-voltage transformers when geomagnetic storms occur. Mitigation measures can then be developed to minimize the susceptibility of the power network to GICs.

Keywords: adverse space weather, DST index, geomagnetically induced currents, KP index, reactive power

Procedia PDF Downloads 114

Authors: Shivani Singh, Shantanu Nakhare, Kalyani Nair, Rohan Shetty

Abstract:

As social networking is growing at a rapid pace today it is vital that we work on improving its management. Research has shown that the content present in online social networks may have significant influence on impressionable minds. If such platforms are misused, it will lead to negative consequences. Detecting insults or inappropriate messages continues to be one of the most challenging aspects of Online Social Networks (OSNs) today. We address this problem through a Machine Learning Based Soft Text Classifier approach using Support Vector Machine algorithm. The proposed system acts as a screening mechanism the alerts the user about such messages. The messages are classified according to their subject matter and each comment is labeled for the presence of profanity and insults.

Keywords: machine learning, online social networks, soft text classifier, support vector machine

Procedia PDF Downloads 507

Authors: Jared Beard, Ali Baheri

Abstract:

As autonomous systems become more prominent in society, ensuring their safe application becomes increasingly important. This is clearly demonstrated with autonomous cars traveling through a crowded city or robots traversing a warehouse with heavy equipment. Human environments can be complex, having high dimensional state and action spaces. This gives rise to two problems. One being that analytic solutions may not be possible. The other is that in simulation based approaches, searching the entirety of the problem space could be computationally intractable, ruling out formal methods. To overcome this, approximate solutions may seek to find failures or estimate their likelihood of occurrence. One such approach is adaptive stress testing (AST) which uses reinforcement learning to induce failures in the system. The premise of which is that a learned model can be used to help find new failure scenarios, making better use of simulations. In spite of these failures AST fails to find particularly sparse failures and can be inclined to find similar solutions to those found previously. To help overcome this, multi-fidelity learning can be used to alleviate this overuse of information. That is, information in lower fidelity can simulations can be used to build up samples less expensively, and more effectively cover the solution space to find a broader set of failures. Recent work in multi-fidelity learning has passed information bidirectionally using “knows what it knows” (KWIK) reinforcement learners to minimize the number of samples in high fidelity simulators (thereby reducing computation time and load). The contribution of this work, then, is development of the bidirectional multi-fidelity AST framework. Such an algorithm, uses multi-fidelity KWIK learners in an adversarial context to find failure modes. Thus far, a KWIK learner has been used to train an adversary in a grid world to prevent an agent from reaching its goal; thus demonstrating the utility of KWIK learners in an AST framework. The next step is implementation of the bidirectional multi-fidelity AST framework described. Testing will be conducted in a grid world containing an agent attempting to reach a goal position and adversary tasked with intercepting the agent as demonstrated previously. Fidelities will be modified by adjusting the size of a time-step, with higher-fidelity effectively allowing for more responsive closed loop feedback. Results will compare the single KWIK AST learner with the multi-fidelity algorithm with respect to number of samples, distinct failure modes found, and relative effect of learning after a number of trials.

Keywords: multi-fidelity reinforcement learning, multi-fidelity simulation, safety validation, falsification

Procedia PDF Downloads 156

Authors: Jan Schmidt, Pierre Köhring

Abstract:

Permanently excited machines are set up with magnets that are made of highly energetic magnetic materials. Inherently, the permanent magnets warm up while the machine is operating. With an increasing temperature, the electromotive force and hence the degree of efficiency decrease. The reasons for this are slot harmonics and distorted armature currents arising from frequency inverter operation. To prevent or avoid demagnetizing of the permanent magnets it is necessary to ensure that the magnets do not excessively heat up. Demagnetizations of permanent magnets are irreversible and a breakdown of the electrical machine is inevitable. For the design of an electrical machine, the knowledge of the behavior of heating under operating conditions of the permanent magnet is of crucial importance. Therefore, a calculation model is presented with which the machine designer can easily calculate the eddy current losses in the magnetic material.

Keywords: analytical model, eddy current, losses, lattice network, permanent magnet

Procedia PDF Downloads 418

Authors: Hasan Al Dabbas

Abstract:

In this paper, it is addressed that the mechanical machinery captures a major share of innovation in drilling and milling chucks technology. Users demand higher speeds in milling because they are cutting more aluminum and are relying on higher speeds to eliminate secondary finishing operations. To meet that demand, milling-machine builders have enhanced their machine’s rigidity. Moreover, faster cutting has caught up with boring mills. Cooling these machine’s internal components is a challenge at high speeds. Another trend predicted that it is more use of controlled axes to let the machines do many more operations on 5 sides without having to move or re-fix the work. Advances of technology in mechanical engineering have helped to make high-speed machining equipment. To accompany these changes in milling and drilling machines chucks, the demand of easiest software is increased. An open architecture controller is being sought that would allow flexibility and information exchange.

Keywords: drilling, milling, chucks, cutting edges, tools, machines

Procedia PDF Downloads 570

Authors: Omar Alsetoohy, Mohamed Ezzat, Mahmoud Abou Kamar

Abstract:

The success of a restaurant or hotel depends very much on the quality and quantity of its human resources. Thus, establishing a competitive edge through human assets requires careful attention to the practices that best leverage these assets. Usually, hotel or restaurant employees recognize customer defection as an unfavorable or unpleasant occurrence associated with failure. These failures could be in handling, communication, learning, or encouragement. Besides, employees could be afraid of blame from their colleagues and managers, which prevents them from freely discussing these mistakes with them. Such behaviors, in turn, would push employees to withdraw from the workplace. However, we have a good knowledge of the leadership outcomes, but less is known about how and why these effects occur. Accordingly, mindful leaders usually analyze the causes and underlying mechanisms of failures for work improvement. However, despite the excessive literature in the field of leadership and employee behaviors, to date, no research studies had investigated the impact of a failure-tolerant restaurant culture on the employees’ withdrawal behaviors considering the moderating role of psychological empowerment and mindful leadership. Thus, this study seeks to investigate the impact of a failure-tolerant culture on the employees’ withdrawal behaviors in fast-food restaurants in Egypt considering the moderating effects of employee empowerment and mindful leaders. This study may contribute to the existing literature by filling the gap between failure-tolerant cultures and employee withdrawal behaviors in the hospitality literature. The study may also identify the best practices for restaurant operators and managers to deal with employees' failures as an improvement tool for their performance.

Keywords: failure-tolerant culture, employees’ withdrawal behaviors psychological empowerment, mindful leadership, restaurants

Procedia PDF Downloads 108

Authors: Amarnath M., Ramachandra C. G., H. Chelladurai, P..Sateesh Kumar, K. Santhosh Kumar

Abstract:

Journal bearings are extensively used sliding contact machine elements to support radial/axial loaded rotors used in various applications viz. automobile crankshaft, turbine propeller shaft, rope conveyer, heavy duty electric motors. The primary reasons for the failures of these bearings include unstable lubricant film, oil degradation, misalignment, etc. This paper describes the results of experimental investigations carried out to detect surface fatigue wear developed on load bearing the contact surfaces of journal bearing. The test bearing was subjected to fatigue load cycles over a period of 600 hours. The vibration signals were acquired from the journal bearing at regular intervals of 100 hrs. These signals were post-processed by using the vibration analysis technique to obtain diagnostic information of wear propagated in the journal-bearing system.

Keywords: fatigue, journal bearing, sound signals, vibration signals, wear

Procedia PDF Downloads 80

Authors: C. J. Rossouw, T. I. van Niekerk

Abstract:

The global manufacturing industry is utilizing the internet and cloud-based services to further explore the anatomy and optimize manufacturing processes in support of the movement into the Fourth Industrial Revolution (4IR). The 4IR from a third world and African perspective is hindered by the fact that many manufacturing systems that were developed in the third industrial revolution are not inherently equipped to utilize the internet and services of the 4IR, hindering the progression of third world manufacturing industries into the 4IR. This research focuses on the development of a non-invasive and cost-effective cyber-physical IoT system that will exploit a machine’s vibration to expose semantic characteristics in the manufacturing process and utilize these results through a real-time cloud-based machine condition monitoring system with the intention to optimize the system. A microcontroller-based IoT sensor was designed to acquire a machine’s mechanical vibration data, process it in real-time, and transmit it to a cloud-based platform via Wi-Fi and the internet. Time-frequency Fourier analysis was applied to the vibration data to form an image representation of the machine’s behaviour. This data was used to train a Convolutional Neural Network (CNN) to learn semantic characteristics in the machine’s behaviour and relate them to a state of operation. The same data was also used to train a Convolutional Autoencoder (CAE) to detect anomalies in the data. Real-time edge-based artificial intelligence was achieved by deploying the CNN and CAE on the sensor to analyse the vibration. A cloud platform was deployed to visualize the vibration data and the results of the CNN and CAE in real-time. The cyber-physical IoT system was deployed on a semi-automated metal granulation machine with a set of trained machine learning models. Using a single sensor, the system was able to accurately visualize three states of the machine’s operation in real-time. The system was also able to detect a variance in the material being granulated. The research demonstrates how non-IoT manufacturing systems can be equipped with edge-based artificial intelligence to establish a remote machine condition monitoring system.

Keywords: IoT, cyber-physical systems, artificial intelligence, manufacturing, vibration analytics, continuous machine condition monitoring

Procedia PDF Downloads 87

Authors: Mehmet Savsar

Abstract:

One of the most important factors affecting power plant performance is the reliability of the turbine units operated under different conditions. Reliability directly affects plant availability and performance. Therefore, it is very important to be able to analyze turbine units, as well as power plant system reliability and availability under various operational conditions. In this paper, data related to power station failures are collected and analyzed in detail for all power stations in the state of Kuwait. Failures are characterized and categorized. Reliabilities of various power plants are analyzed and availabilities are quantified. Based on calculated availabilities of all installed power plants, actual power output is estimated. Furthermore, based on the past 15 years of data, power consumption trend is determined and the demand for power in the future is forecasted. Estimated power output is compared to the forecasted demand in order to determine the need for future capacity expansion.

Keywords: power plants, reliability, availability, capacity, preventive maintenance, forecasting

Procedia PDF Downloads 357

Authors: Shuyuan Lin, Zhaohui Huang, Mizi Fan

Abstract:

In the majority of previous research into modelling large scale composite floor subjected to fire, the beam-to-column and beam-to-beam connections were assumed to behave either as pinned or rigid for simplicity, and the vertical shear and axial tension failures of the connection were not taken into account. We have recently developed robust two-noded connection models for modeling endplate and partial endplate steel connections under fire conditions. The main objective of this research is to systematically investigate the impact of the connections of protected beams, on the tensile membrane actions of supported floor slabs in which the failures of the connections, such as, axial tension, vertical shear and bending are accounted for. The models developed have very good numerical stability under a static solver condition, and can be used for large scale modelling of composite buildings in fire.

Keywords: fire, steel structure, component-based model, beam-to-column connections

Procedia PDF Downloads 449

Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter

Abstract:

Due to increasing cost pressure in global markets, artificial intelligence is becoming a technology that is decisive for competition. Predictive quality enables machinery and plant manufacturers to ensure product quality by using data-driven forecasts via machine learning models as a decision-making basis for test results. The use of cross-process Bosch production data along the value chain of hydraulic valves is a promising approach to classifying the quality characteristics of workpieces.

Keywords: predictive quality, hydraulics, machine learning, classification, supervised learning

Procedia PDF Downloads 229

Authors: Xinyi Le

Abstract:

In this paper, 3D printing orientations were determined through our perceptual model. Some FDM (Fused Deposition Modeling) 3D printers, which are widely used in universities and industries, often require support structures during the additive manufacturing. After removing the residual material, some surface artifacts remain at the contact points. These artifacts will damage the function and visual effect of the model. To prevent the impact of these artifacts, we present a fuzzy extreme learning machine approach to find printing directions that avoid placing supports in perceptually significant regions. The proposed approach is able to solve the evaluation problem by combing both the subjective knowledge and objective information. Our method combines the advantages of fuzzy theory, auto-encoders, and extreme learning machine. Fuzzy set theory is applied for dealing with subjective preference information, and auto-encoder step is used to extract good features without supervised labels before extreme learning machine. An extreme learning machine method is then developed successfully for training and learning perceptual models. The performance of this perceptual model will be demonstrated on both natural and man-made objects. It is a good human-computer interaction practice which draws from supporting knowledge on both the machine side and the human side.

Keywords: 3d printing, perceptual model, fuzzy evaluation, data-driven approach

Procedia PDF Downloads 438

Authors: Vishnu Pratap Singh Kirar, Madhuri Saxena

Abstract:

Advancement in sequence data generation technologies is churning out voluminous omics data and posing a massive challenge to annotate the biological functional features. With so much data available, the use of machine learning methods and tools to make novel inferences has become obvious. Machine learning methods have been successfully applied to a lot of disciplines, including computational biology and bioinformatics. Researchers in computational biology are interested to develop novel machine learning frameworks to classify the huge amounts of biological data. In this proposal, it plan to employ novel machine learning approaches to aid the understanding of how apparently innocuous mutations (in intergenic DNA and at synonymous sites) cause diseases. We are also interested in discovering novel functional sites in the genome and mutations in which can affect a phenotype of interest.

Keywords: genome wide association studies (GWAS), next generation sequencing (NGS), deep learning, omics

Procedia PDF Downloads 96

Authors: Meruert Serik, Nassipzhan Duisegaliyeva, Danara Tleumagambetova

Abstract:

The article highlights and describes the characteristic features of real-time face detection in images and videos using machine learning algorithms. Students of educational programs reviewed the research work "6B01511-Computer Science", "7M01511-Computer Science", "7M01525- STEM Education," and "8D01511-Computer Science" of Eurasian National University named after L.N. Gumilyov. As a result, the advantages and disadvantages of Haar Cascade (Haar Cascade OpenCV), HoG SVM (Histogram of Oriented Gradients, Support Vector Machine), and MMOD CNN Dlib (Max-Margin Object Detection, convolutional neural network) detectors used for face detection were determined. Dlib is a general-purpose cross-platform software library written in the programming language C++. It includes detectors used for determining face detection. The Cascade OpenCV algorithm is efficient for fast face detection. The considered work forms the basis for the development of machine learning methods by future computer science teachers.

Keywords: algorithm, artificial intelligence, education, machine learning

Procedia PDF Downloads 73

Authors: Khadija Refouh

Abstract:

Culture bound-expressions have been a bottleneck for Natural Language Processing (NLP) and comprehension, especially in the case of machine translation (MT). In the last decade, the field of machine translation has greatly advanced. Neural machine translation NMT has recently achieved considerable development in the quality of translation that outperformed previous traditional translation systems in many language pairs. Neural machine translation NMT is an Artificial Intelligence AI and deep neural networks applied to language processing. Despite this development, there remain some serious challenges that face neural machine translation NMT when translating culture bounded-expressions, especially for low resources language pairs such as Arabic-English and Arabic-French, which is not the case with well-established language pairs such as English-French. Machine translation of opaque idioms from English into French are likely to be more accurate than translating them from English into Arabic. For example, Google Translate Application translated the sentence “What a bad weather! It runs cats and dogs.” to “يا له من طقس سيء! تمطر القطط والكلاب” into the target language Arabic which is an inaccurate literal translation. The translation of the same sentence into the target language French was “Quel mauvais temps! Il pleut des cordes.” where Google Translate Application used the accurate French corresponding idioms. This paper aims to perform NMT experiments towards better translation of opaque idioms using high quality clean multilingual corpus. This Corpus will be collected analytically from human generated idiom translation. AutoML translation, a Google Neural Machine Translation Platform, is used as a custom translation model to improve the translation of opaque idioms. The automatic evaluation of the custom model will be compared to the Google NMT using Bilingual Evaluation Understudy Score BLEU. BLEU is an algorithm for evaluating the quality of text which has been machine-translated from one natural language to another. Human evaluation is integrated to test the reliability of the Blue Score. The researcher will examine syntactical, lexical, and semantic features using Halliday's functional theory.

Keywords: multilingual corpora, natural language processing (NLP), neural machine translation (NMT), opaque idioms

Procedia PDF Downloads 148

Authors: Golnush Masghati-Amoli, Paul Chin

Abstract:

Over the past recent years, with the rapid increases in data availability and computing power, Machine Learning (ML) techniques have been called on in a range of different industries for their strong predictive capability. However, the use of Machine Learning in commercial banking has been limited due to a special challenge imposed by numerous regulations that require lenders to be able to explain their analytic models, not only to regulators but often to consumers. In other words, although Machine Leaning techniques enable better prediction with a higher level of accuracy, in comparison with other industries, they are adopted less frequently in commercial banking especially for scoring purposes. This is due to the fact that Machine Learning techniques are often considered as a black box and fail to provide information on why a certain risk score is given to a customer. In order to bridge this gap between the explain-ability and performance of Machine Learning techniques, a Hybrid Model is developed at Dun and Bradstreet that is focused on blending Machine Learning algorithms with traditional approaches such as scorecards. The Hybrid Model maximizes efficiency of traditional scorecards by merging its practical benefits, such as explain-ability and the ability to input domain knowledge, with the deep insights of Machine Learning techniques which can uncover patterns scorecard approaches cannot. First, through development of Machine Learning models, engineered features and latent variables and feature interactions that demonstrate high information value in the prediction of customer risk are identified. Then, these features are employed to introduce observed non-linear relationships between the explanatory and dependent variables into traditional scorecards. Moreover, instead of directly computing the Weight of Evidence (WoE) from good and bad data points, the Hybrid Model tries to match the score distribution generated by a Machine Learning algorithm, which ends up providing an estimate of the WoE for each bin. This capability helps to build powerful scorecards with sparse cases that cannot be achieved with traditional approaches. The proposed Hybrid Model is tested on different portfolios where a significant gap is observed between the performance of traditional scorecards and Machine Learning models. The result of analysis shows that Hybrid Model can improve the performance of traditional scorecards by introducing non-linear relationships between explanatory and target variables from Machine Learning models into traditional scorecards. Also, it is observed that in some scenarios the Hybrid Model can be almost as predictive as the Machine Learning techniques while being as transparent as traditional scorecards. Therefore, it is concluded that, with the use of Hybrid Model, Machine Learning algorithms can be used in the commercial banking industry without being concerned with difficulties in explaining the models for regulatory purposes.

Keywords: machine learning algorithms, scorecard, commercial banking, consumer risk, feature engineering

Procedia PDF Downloads 132

Authors: Xiaobo Xi, Ruihong Zhang

Abstract:

At present, the orchard ditching and fertilizing technology has a series of problems, such as easy tree roots damage, high energy consumption and uneven fertilizing. In this paper, a gas explosion subsoiling and fertilizer injection machine was designed, which used high pressure gas to shock soil body and then injected fertilizer. The drill pipe mechanism with pneumatic chipping hammer excitation and hydraulic assistance was designed to drill the soil. The operation of gas and liquid fertilizer supply was controlled by PLC system. The 3D model of the whole machine was established by using SolidWorks software. The machine prototype was produced, and field experiments were carried out. The results showed that soil fractures were created and diffused by gas explosion, and the subsoiling effect radius reached 40 cm under the condition of 0.8 MPa gas pressure and 30 cm drilling depth. What’s more, the work efficiency is 0.048 hm²/h at least. This machine could meet the agronomic requirements of orchard, garden and city greening fertilization, and the tree roots were not easily damaged and the fertilizer evenly distributed, which was conducive to nutrient absorption of root growth.

Keywords: gas explosion subsoiling, fertigation, pneumatic chipping hammer exciting, soil compaction

Procedia PDF Downloads 208

Authors: S. Meguenni, A. Djahbar, K. Tounsi

Abstract:

Electric railway traction systems are complex; they have electrical couplings, magnetic and solid mechanics. These couplings impose several constraints that complicate the modeling and analysis of these systems. An example of drive systems, which combine the advantages of the use of multiphase machines, power electronics and computing means, is mono convert isseur multi-machine system which can control a fully decoupled so many machines whose electric windings are connected in series. In this approach, our attention especially on modeling and independent control of two five phase synchronous machine with permanent magnet connected in series and fed by a matrix converter application to the rail traction (bogie of a locomotive BB 36000).

Keywords: synchronous machine, vector control Multi-machine/ Multi-inverter, matrix inverter, Railway traction

Procedia PDF Downloads 370