Fault diagnosis of the paper machine short circulation process using novel dynamic causal digraph reasoning

Abstract

This paper presents a novel dynamic causal digraph reasoning method for fault diagnosis and its application to the short circulation process of a paper machine. In order to improve the fault detection ability of the original causal digraph method, a residual modification approach that takes into account the direction of different fault effects is presented. An improvement of the isolation capability of the original method, an inference mechanism between the arcs of the graph, is also proposed to locate process faults on the arcs. The results from the application show that the proposed method, compared to the conventional method, is able to detect the correct nodes and to identify the responsible arcs when the system is affected by a process fault.

Detection and isolation of oscillations using the dynamic causal digraph method

“…In order to decrease the number of possible results, an inference mechanism between the arcs proposed in [16] is used. The inference mechanism is based on an inter-arc knowledge matrix M defined for node U as follows…”

Application of the Enhanced Dynamic Causal Digraph Method on a Three-Layer Board Machine

“…The effects of different faults may be cancelled out when they are acting in different directions. Cheng et al proposed a method in [26] to reduce problem by testing the fault effect cancelling and then reevaluating the corresponding nodes with modified residuals. The residuals are recalculated after excluding the propagated fault effects which cancel the local faults.…”

“…This has increased interest in further diagnosis development. An inference mechanism between the arcs has also been developed in [26] in order to diagnose the process faults more accurately.…”

“…Due to the qualitative rules used for separation of the fault effects in [26] the statistic used in fault detection is not robust with respect to the fault effect values. In other words, a minor change in a fault effect value may vary the result of the detection of fault effect cancellation completely.…”

“…Due to the deficiency in the fault effect separation approach in [26], the investigation of fault effect separation is expanded in this brief to evaluate the fault effect contributions quantitatively. The positive and negative fault effects are separated and evaluated independently in order to achieve improved isolation and diagnosis.…”