Stéphane Ploix

Publications

2 Performing Diagnosis in Building with Partially Valid Heterogeneous Tests

Authors: Mahendra Pratap Singh, Houda Najeh, Stéphane Ploix, Karim Chabir, Mohamed Naceur Abdelkrim, Antoine Caucheteux

Abstract:

Building system is highly vulnerable to different kinds of faults and human misbehaviors. Energy efficiency and user comfort are directly targeted due to abnormalities in building operation. The available fault diagnosis tools and methodologies particularly rely on rules or pure model-based approaches. It is assumed that model or rule-based test could be applied to any situation without taking into account actual testing contexts. Contextual tests with validity domain could reduce a lot of the design of detection tests. The main objective of this paper is to consider fault validity when validate the test model considering the non-modeled events such as occupancy, weather conditions, door and window openings and the integration of the knowledge of the expert on the state of the system. The concept of heterogeneous tests is combined with test validity to generate fault diagnoses. A combination of rules, range and model-based tests known as heterogeneous tests are proposed to reduce the modeling complexity. Calculation of logical diagnoses coming from artificial intelligence provides a global explanation consistent with the test result. An application example shows the efficiency of the proposed technique: an office setting at Grenoble Institute of Technology.

Keywords: Diagnosis, Validity, fault detection and isolation, building system, heterogeneous tests, sensor fault, sensor grids

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 165
1 Automatic Thresholding for Data Gap Detection for a Set of Sensors in Instrumented Buildings

Authors: Mahendra Pratap Singh, Houda Najeh, Stéphane Ploix, Karim Chabir, Mohamed Naceur Abdelkrim

Abstract:

Building systems are highly vulnerable to different kinds of faults and failures. In fact, various faults, failures and human behaviors could affect the building performance. This paper tackles the detection of unreliable sensors in buildings. Different literature surveys on diagnosis techniques for sensor grids in buildings have been published but all of them treat only bias and outliers. Occurences of data gaps have also not been given an adequate span of attention in the academia. The proposed methodology comprises the automatic thresholding for data gap detection for a set of heterogeneous sensors in instrumented buildings. Sensor measurements are considered to be regular time series. However, in reality, sensor values are not uniformly sampled. So, the issue to solve is from which delay each sensor become faulty? The use of time series is required for detection of abnormalities on the delays. The efficiency of the method is evaluated on measurements obtained from a real power plant: an office at Grenoble Institute of technology equipped by 30 sensors.

Keywords: Diagnosis, Time series, delay, outliers, building system, data gap

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 442

Abstracts

4 Uncertainty Analysis of a Hardware in Loop Setup for Testing Products Related to Building Technology

Authors: Stéphane Ploix, Prasaant Balasundaram, Benoit Delinchant, Muresan Cristain

Abstract:

Hardware in Loop (HIL) testing is done to test and validate a particular product especially in building technology. When it comes to building technology it is more important to test the products for their efficiency. The test rig in the HIL simulator may contribute to some uncertainties on measured efficiency. The uncertainties include physical uncertainties and scenario based uncertainties. In this paper a simple uncertainty analysis frame work for a HIL setup is shown considering only the physical uncertainties. The entire modelling of the HIL setup is done in DYMOLA. The uncertain sources are considered based on available knowledge of the components and also based on expert knowledge. For the propagation of uncertainty Monte Carlo Simulation is used, since it is the most reliable and easy to use. This article it is shown how a HIL setup can be modelled and how uncertainty propagation can be performed on it. Such an approach is not common in building energy analysis.

Keywords: Monte Carlo Simulation, Uncertainty Propagation, energy in buildings, hardware in loop testing, modelica modelling

Procedia PDF Downloads 1
3 Performing Diagnosis in Building with Partially Valid Heterogeneous Tests

Authors: Mahendra Pratap Singh, Houda Najeh, Stéphane Ploix, Karim Chabir, Mohamed Naceur Abdelkrim, Antoine Caucheteux

Abstract:

Building system is highly vulnerable to different kinds of faults and human misbehaviors. Energy efficiency and user comfort are directly targeted due to abnormalities in building operation. The available fault diagnosis tools and methodologies particularly rely on rules or pure model-based approaches. It is assumed that model or rule-based test could be applied to any situation without taking into account actual testing contexts. Contextual tests with validity domain could reduce a lot of the design of detection tests. The main objective of this paper is to consider fault validity when validate the test model considering the non-modeled events such as occupancy, weather conditions, door and window openings and the integration of the knowledge of the expert on the state of the system. The concept of heterogeneous tests is combined with test validity to generate fault diagnoses. A combination of rules, range and model-based tests known as heterogeneous tests are proposed to reduce the modeling complexity. Calculation of logical diagnoses coming from artificial intelligence provides a global explanation consistent with the test result. An application example shows the efficiency of the proposed technique: an office setting at Grenoble Institute of Technology.

Keywords: Diagnosis, Validity, fault detection and isolation, building system, heterogeneous tests, sensor grids, sensor fault

Procedia PDF Downloads 126
2 Automatic Thresholding for Data Gap Detection for a Set of Sensors in Instrumented Buildings

Authors: Mahendra Pratap Singh, Houda Najeh, Stéphane Ploix, Karim Chabir, Mohamed Naceur Abdelkrim

Abstract:

Building systems are highly vulnerable to different kinds of faults and failures. In fact, various faults, failures and human behaviors could affect the building performance. This paper tackles the detection of unreliable sensors in buildings. Different literature surveys on diagnosis techniques for sensor grids in buildings have been published but all of them treat only bias and outliers. Occurences of data gaps have also not been given an adequate span of attention in the academia. The proposed methodology comprises the automatic thresholding for data gap detection for a set of heterogeneous sensors in instrumented buildings. Sensor measurements are considered to be regular time series. However, in reality, sensor values are not uniformly sampled. So, the issue to solve is from which delay each sensor become faulty? The use of time series is required for detection of abnormalities on the delays. The efficiency of the method is evaluated on measurements obtained from a real power plant: an office at Grenoble Institute of technology equipped by 30 sensors.

Keywords: Diagnosis, Time series, delay, outliers, building system, data gap

Procedia PDF Downloads 21
1 Estimating Occupancy in Residential Context Using Bayesian Networks for Energy Management

Authors: Stéphane Ploix, Manar Amayri, Hussain Kazimi, Quoc-Dung Ngo

Abstract:

A general approach is proposed to determine occupant behavior (occupancy and activity) in residential buildings and to use these estimates for improved energy management. Occupant behaviour is modelled with a Bayesian Network in an unsupervised manner. This algorithm makes use of domain knowledge gathered via questionnaires and recorded sensor data for motion detection, power, and hot water consumption as well as indoor CO₂ concentration. Two case studies are presented which show the real world applicability of estimating occupant behaviour in this way. Furthermore, experiments integrating occupancy estimation and hot water production control show that energy efficiency can be increased by roughly 5% over known optimal control techniques and more than 25% over rule-based control while maintaining the same occupant comfort standards. The efficiency gains are strongly correlated with occupant behaviour and accuracy of the occupancy estimates.

Keywords: Sensor Networks, Artificial Intelligence, Energy, Management, Optimization, Control, Buildings, Learning theory, Bayesian Methods, knowledge modelling and knowledge based systems

Procedia PDF Downloads 241