An Integrated Approach for Process Control Valves Diagnosis Using Fuzzy Logic ()
Abstract
Control valves are widely
used in industry to control fluid flow in several applications. In nuclear
power systems they are crucial for the safe operation of plants. Therefore, the
necessity of improvements in monitoring and diagnosis methods started to be of
extreme relevance, establishing as main goal of the reliability and readiness
of the system components. The main focus of this work is to study the
development of a model of non-intrusive monitoring and diagnosis applied to process
control valves using artificial intelligence by fuzzy logic technique,
contributing to the development of predictive methodologies identifying faults in
incipient state. Specially in nuclear power plants, the predictive maintenance
contributes to the security factor in order to diagnose in advance the
occurrence of a possible failure, preventing severs situations. The control
valve analyzed belongs to a steam plant which simulates the secondary circuit of
a PWR—Pressurized Water Reactor. The maintenance programs are being implemented
based on the ability to diagnose modes of degradation and to take measures to
prevent incipient failures, improving plant reliability and reducing
maintenance costs. The approach described in this paper represents an
alternative departure from the conventional qualitative techniques of system
analysis. The methodology used in this project is based on signatures analysis,
considering the pressure (psi) in the actuator and the stem displacement (mm)
of the valve. Once the measurements baseline of the control valve is taken, it
is possible to detect long-term deviations during valve lifetime, detecting in
advance valve failures. This study makes use of MATLAB language through the “fuzzy
logic toolbox” which uses the method of inference “Mamdani”, acting by fuzzy conjunction,
through Triangular Norms (t-norm) and Triangular Conorms (t-conorm). The main
goal is to obtain more detailed information contained in the measured data,
correlating them to failure situations in the incipient stage.
Table 1 shows the values of the variables and the respective valve status as output variable. The “status” closed represents that the stem touched the base. And closed strongly represents the excess air pressure to ensure that the valve is sealed to avoid leakage. The diagnosis due to the status of the valve is represented by Table2 It shows when the stem is working normally, or is locked, or with motion difficulties or need maintenance.
Table 3 shows the membership functions and input/output variables.
Figure 9 shows an anomaly on the left in the upper cycle (close). This anomaly indicates difficulty in movement, and is transferred to the inputs of the FLS through Valvelink®, module of Delta V® automation system. The data are treated according to the rule base (Table 4) and will provide an output, which in this case will then automatically diagnose as an incipient failure.
Figures 10-12 present the MATLAB® chart of membership functions of inputs “excvalv” and “pressat”, and the output “statvalv” respectively.
Figure 13 shows the rules’ viewer with emphasis on the 8, which the intensity of the two inputs gene-
Table 2. Diagnosis by “Status” of the valve.
rates a diagnosis, showing a type of failure. Due the entries “excvalv” and “pressat” present as “open” and “a quarter”, the output variable “statvalv” present itself with the diagnosis “difficult to close”, demonstrating an incipient failure, at the beginning of the closing valve.
4. Conclusions
The paper shows that expert system technology has brought significant improvements on predictive/proactive maintenance, considering the specific case, using Artificial Intelligence by the Fuzzy Logic Technique, detecting failures in advance which is a relevant contribution to condition monitoring and diagnose system.
Figure 10. The input variable “excvalv”.
Figure 11. The input variable “pressat”.
The use of the MATLAB® platform aggregated to the Fuzzylogic toolbox has proved to be a powerful tool, using the tacit knowledge of the experts allowing the expert systems to create a favorable scenario, becoming possible to learn about the correct diagnosis of a final control element (valves) of great importance to control in industrial plant, and particularly in nuclear plant, where the availability of the equipment should be high and unexpected intervention should be avoided.
However, this technique should be improved, testing different situations of failures in order to check the per-
Figure 12. The output variable “statvalv”.
formance of the expert system mainly for failures on incipient stage. Furthermore the system must also be able to analyze different types of valves.