Sensor placement and fault detection using an efficient fuzzy feature selection approach

Abstract

Process monitoring and fault diagnosis are of great importance for operation safety and efficiency of complex industrial plants. The present article proposes a novel methodology to address the sensor location problem for fault detection. Firstly, all the process situations are identified based on a fuzzy learning algorithm using measurements generated from the whole available set of sensors. Then, a fuzzy feature selection approach is used to select the optimal number of sensors that characterize accurately the set of process situations (abnormal and normal). This method optimizes the performance of the learning algorithm within a membership margin framework, and thereby, it is capable to address correlation and redundancy issues. A behavioral pattern of the process is constructed with the selected sensors and is used to associate new online observations to previously characterized process situations. The proposed strategy has been applied for fault diagnosis to a pharmaceutical synthesis carried out in a new intensified heat-exchanger reactor.

Fuzzy Unordered Rule Using Greedy Hill Climbing Feature Selection Method: An Application to Diabetes Classification

“…The performance of this method was evaluated by using UCI datasets, and the results showed superior performance as compared to correlation-based feature selection methods. Hedjazi et al (2010) applied fuzzy logic to solve efficiency and operation safety of sensors in the industrial plant domain. Fuzzy logic was used in the learning algorithm for sensor situation identification.…”

Feature-Selection based PMU Placement for Detection of Faults in Power Grids

“…The second group of methods utilizes data-driven approaches to achieve an acceptable detection performance. For example, [6] proposes a sensor placement technique based on fuzzy feature selection for the detection of faults in the process of pharmaceutical synthesis in a heat-exchanger reactor. There are two main advantages of the data-driven approaches.…”

Optimal sensor placement for model-based fault detectability and isolability

“…In [92,93], a minimum cost solution is sought by a pre-specified algorithm in the data-driven model, fulfilling a desired fault isolability performance. In [94], the fuzzy learning and classification technique is used to optimally place sensors for fault detection. In [95], the optimal sensor configuration is obtained by the simultaneous perturbation stochastic approximation (SPSA), for maximizing the overall sensor response and minimizing the correlation among the sensor outputs.…”