Application ofT2Control Charts and Hidden Markov Models in Condition-Based Maintenance at Thermoelectric Power Plants

Abstract

An innovative approach to condition-based maintenance of coal grinding subsystems at thermoelectric power plants is proposed in the paper. Coal mill grinding tables become worn over time and need to be replaced through time-based maintenance, after a certain number of service hours. At times such replacement is necessary earlier or later than prescribed, depending on the quality of the coal and of the grinding table itself. Considerable financial losses are incurred when the entire coal grinding subsystem is shut down and the grinding table found to not actually require replacement. The only way to determine whether replacement is necessary is to shut down and open the entire subsystem for visual inspection. The proposed algorithm supports condition-based maintenance and involves the application ofT2control charts to distinct acoustic signal parameters in the frequency domain and the construction of Hidden Markov Models whose observations are coded samples from the control charts. In the present research, the acoustic signals were collected by coal mill monitoring at the thermoelectric power plant “Kostolac” in Serbia. The proposed approach provides information about the current condition of the grinding table.

Control charts for monitoring a Poisson hidden Markov process

“…The two possible hidden states are caused by the incoming raw material (two quality levels, good vs. medium), and the state‐dependent Poisson distribution () has a lower mean for the good‐quality batches than for the medium‐quality ones. This setup is similar to the coal mill example in Kisić et al, 13 where the wear of the grinding table depends on the quality of the processed coal. Another example for a two‐state HMM would be a production environment with two load conditions (normal load vs. overload).…”

“…Two of these hidden states are interpreted as fault states which require an immediate maintenance action. Similar HMM designs are commonly used in machining and maintenance applications, where the hidden states express increasing tool wear, see, for example, other works 11‐13 . In summary, an HMM could be used within control charting in two ways.…”

Impact of Remediation-Based Maintenance on the Reliability of a Coal-Fired Power Plant Using Generalized Stochastic Petri Nets

“…Thus, substantial research interest in the field of process monitoring and fault diagnosis of coal mills is not surprising. Remarkable examples of intelligent solutions for faults' detection in coal mills are given in [18][19][20], while methods for modeling a coal mill for fault monitoring and diagnosis are considered in [21,22]. Another interesting model capable of predicting power plant availability implemented using a generalized stochastic Petri net has been carried out in [23].…”

Health indicator construction and application of coal mill based on the dynamic model

“…Despite several studies having established HIs for coal mills, their accuracy and practicality find it hard to meet the requirements. Present studies on coal mill condition monitoring are commonly concerned with the real-time diagnosis of typical faults [16][17][18][19][20][21][22] . Though these studies can analyze and diagnose partial faults of the coal mill, they cannot provide an accurate assessment of the real-time operating status of the equipment, thus are employed only as the reference when faults occur in the field.…”