Using Artificial Intelligence for Multiple Fault Diagnosis
Fault diagnosis is the process of identifying the cause of failure in systems.
Multiple Fault Diagnosis is the process of identifying the causes of multiple failures or compound failures in a system.
Fault Diagnosis Process & Fault Masking
Fault diagnosis involves monitoring dynamic signals of a machine or system in real-time, when the system creates faults. Compound faults lead to serious performance degradation and are more difficult to recognize. This leaves the challenging task to identify multiple faults effectively.
In multiple faults we can have the problem of ‘fault masking’, where the presence of one fault may make it impossible to even see symptoms to detect or isolate some other faults. The most effective fault diagnosis technique is feature learning from the monitoring information.
Any single-fault-based diagnostic algorithm uses single-fault simulation behavior to match the observed failure responses to the given test patterns. However, in reality, a pattern may activate multiple faults and create a multiple fault behavior.
Using Expert Systems
The problem of multiple faults, which is an actual reflection of reality, can be solved by using multiple faults diagnosis that can be implemented by an expert system, effectively and efficiently. This is possible if an expert system, which can multi-task, can be used to monitor real-time faults, through dynamic signals generated every time an error occurs. The expert system can then, through machine learning, learn all system features from information monitoring, known as feature extraction. The expert system would then need only a few failing feature patterns to accurately diagnose a given system’s failure responses. The expert system would also manage a featured diagnostic framework to handle any specific feature fault model and invoke an appropriate diagnostic algorithm.
SUPPORT [[:thetqweb:]] VIA
Multiple Fault Diagnosis with Expert Systems
Artificial Intelligence | thetqweb