Fault Diagnosis Method for Circuit Boards Based on Weighted Sum of Squares of Sensor Signal Residual Sequences

Abstract

The present invention provides a method for diagnosing the faults of a board card based on the weighted sum of squares of the sensor signal residual sequence, which relates to the technical field of fault diagnosis of electronic controllers. The method includes: obtaining the original temperature process signals of each temperature sensor from a gas turbine electronic controller system, performing data preprocessing to form an original data set; inputting the original data set into a calculation model for the weighted sum of squares of the residual sequence; selecting the weighted sum of squares of all sensors associated with the IO board card and inputting it into a calculation model for the health degree of the IO board card to obtain the health degree value of the board card; calculating the difference between the health degree value of the board card and the boundary line of the preset normal range, and judging whether the board card has a fault according to the difference. This method can quickly diagnose the fault state of a thermocouple IO board card in an engineering manner, provide an engineering-applicable means for timely identifying the faults of the IO board card of an electronic controller, and provide important support for the fault diagnosis of the control system loop of a gas turbine.

Description

Technical Field

[0001] The invention relates to the technical field of electronic controller fault diagnosis, and in particular to a board fault diagnosis method based on the weighted square sum of sensor signal residual sequence. Background Art

[0002] The gas turbine control system is a complex nonlinear dynamic system composed of a large number of components in a certain way, function and requirement. The electronic controller (DCS system) in the gas turbine control system is the core and key of the entire gas turbine control system. How to effectively diagnose the fault of the electronic controller of the gas turbine control system has always been a difficult problem in the industry. The traditional electronic controller fault diagnosis method based on BIT technology requires adding a large number of redundant diagnostic circuits in the electronic components, which increases the system cost on the one hand and adds new fault points on the other hand. Different gas turbine control system manufacturers have built-in many professional system diagnostic functions in their respective DCS systems. These functions must be viewed in the engineer operation station with corresponding permissions, and the information acquisition process is passive. The operator needs to find various alarm information in different locations by himself, and then combine it with various paper drawings and materials, and even need to check the hardware indication status in the DCS cabinet to determine the fault point of the system. To further determine the cause of the fault, it is more about the personal ability and experience of the engineer. This seriously restricts the rapid judgment of gas turbine power plants when system faults occur. As a result, unplanned shutdowns caused by false alarms of the electronic controller system often occur, causing great economic losses to the power plant.

[0003] At present, the method adopted for maintaining the industrial equipment in the factory is "prevention first, planned maintenance first, and temporary repair as a supplement". Specifically, the factory sets a period of three to five years according to the new and old conditions of the industrial equipment to carry out a major overhaul of all the industrial equipment in the factory, that is, to shut down, dismantle, maintain and reinstall all the industrial equipment, without considering whether a certain industrial equipment needs maintenance. Generally, a major overhaul lasts for more than two months, requiring more than 100 professional maintenance personnel and nearly 1,000 construction personnel of all kinds. During the two major overhauls, the industrial equipment is repaired once every one to two years, that is, the auxiliary working equipment in the factory, such as the steam turbine generator set in the power plant and most of the industrial equipment other than other large core equipment, is dismantled, maintained and reinstalled, generally for a period of more than ten days to two months. At the same time, while the factory is carrying out "planned maintenance", it is assisted by "temporary repair", that is, temporary repair of industrial equipment that has failed and cannot operate.

[0004] In the gas turbine power generation industry, this routine maintenance working method is not suitable for electronic controller systems represented by DCS. The DCS system is composed of high-precision and high-density electronic components / chips. The working principles and failure mechanisms of various components are completely different, and its failure mode is often "sudden". It is simply impossible to effectively solve the fault detection problem only by means of daily inspection and testing. During the daily operation of a gas turbine, the temperature of the combustion chamber is the most important control and monitoring parameter. The stability and consistency of this set of parameters (31 circumferentially arranged measuring points for a 9F unit) are directly related to whether the unit can continue to operate. Once the measured value is distorted due to a thermocouple IO board card failure, it may be necessary to immediately shut down the machine, and the consequences are very serious.

[0005] Studying the data-driven fault diagnosis method for the IO board cards of electronic controllers, how to conveniently and quickly determine the faults of the IO board cards of electronic controllers and find an engineering realizable fault diagnosis method has always been a difficult problem in the industrial field. Summary of the Invention

[0006] The purpose of the present invention is to provide a board card fault diagnosis method based on the weighted sum of squares of the sensor signal residual sequence in view of the above-mentioned deficiencies of the prior art, so as to solve the engineering fault diagnosis problem of the thermocouple IO board cards of electronic controllers in a gas turbine control system.

[0007] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0008] The present invention provides a board card fault diagnosis method based on the weighted sum of squares of the sensor signal residual sequence. This method is used for fault diagnosis of the thermocouple IO board cards of a gas turbine electronic controller. The method includes:

[0009] Obtain the original temperature process signals of each temperature sensor from the gas turbine electronic controller system, perform data preprocessing to form an original signal data set;

[0010] Input the signals in the original signal data set into the sensor residual sequence weighted sum of squares calculation model to obtain the weighted sum of squares of the signal residual sequences of each temperature sensor;

[0011] Select the weighted sum of squares of the signal residual sequences of all temperature sensors associated with the thermocouple IO board card, and input the selected weighted sum of squares of the signal residual sequences into the preset thermocouple IO board card health calculation model to obtain the health value of the thermocouple IO board card;

[0012] Calculate the difference between the health value of the thermocouple IO board card and the boundary line of the normal range of the preset health value, and judge whether the thermocouple IO board card has a fault according to the difference, so as to realize the fault diagnosis of the thermocouple IO board card.

[0013] Optionally, the original temperature process signals of each temperature sensor are obtained from the gas turbine electronic controller system in the OPC UA industrial protocol.

[0014] Optionally, from the gas turbine electronic controller system, all real-time temperature process signals of the temperature sensors associated with the thermocouple IO board are obtained through the OPC UA industrial protocol interface. The data preprocessing includes redundant sample elimination operation, abnormal sample removal operation, and data normalization operation.

[0015] Optionally, the weighted sum of squares calculation model of the sensor residual sequence is the weighted sum of squares calculation model of the sensor residual sequence based on the unscented Kalman filter.

[0016]

[0017] ∑=(diag(σ)) 2

[0018] where R i is the weighted sum of the residual sequence of the temperature sensor corresponding to the i-th channel of the thermocouple IO board. Based on the unscented Kalman filter, filters corresponding to m sensors associated with the thermocouple IO board are established. The input of each filter is m - 1 measured parameter values. The input of the i-th filter is the measured parameters of the remaining m - 1 sensors except the i-th sensor. σ is the standard deviation of the measured parameters, and y (i) is the measured parameter of the i-th filter. is the non-linear model prediction output of the i-th filter; m is the total number of temperature sensors associated with the thermocouple IO board.

[0019] Optionally, the health calculation model of the thermocouple IO board is as follows:

[0020]

[0021] where R IO-card is the health value of the thermocouple IO board, and k i is the weighted weight of the i-th channel of the thermocouple IO board.

[0022] Optionally, it is determined whether the thermocouple IO board fails according to the following formula:

[0023] F IOcard = 1 if R IO-card >R high limit

[0024] where F IOcard is the fault judgment flag bit of the thermocouple IO board. When FIOcard When it is equal to 1, it is determined that the thermocouple IO board has a fault;

[0025] R high limit is the upper limit of the preset normal range of the health value. When the difference between the health value of the thermocouple IO board and the boundary line of the preset normal range of the health value is greater than zero, that is, R IO-card >R high limit in the case of, F IOcard = 1.

[0026] Optionally, the value of R high limit is equal to 3σ.

[0027] The beneficial effects of the present invention include:

[0028] The board fault diagnosis method based on the weighted sum of squares of the sensor signal residual sequence provided by the present invention includes: obtaining the original temperature process signals of each temperature sensor from the gas turbine electronic controller system, performing data preprocessing to form an original signal data set; inputting the signals in the original signal data set into the sensor residual sequence weighted sum of squares calculation model to obtain the weighted sum of squares of the signal residual sequences of each temperature sensor; selecting the weighted sum of squares of the signal residual sequences of all temperature sensors associated with the thermocouple IO board, and inputting the selected weighted sum of squares of the signal residual sequences into the preset thermocouple IO board health calculation model to obtain the health value of the thermocouple IO board; calculating the difference between the health value of the thermocouple IO board and the boundary line of the preset normal range of the health value, and judging whether the thermocouple IO board has a fault according to the difference, so as to realize the fault diagnosis of the thermocouple IO board. This method can quickly diagnose the fault state of the thermocouple IO board in an engineering way, provide an engineering applicable means for timely identifying the IO board fault of the electronic controller, and provide important support for the fault diagnosis of the gas turbine control system loop. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0030] Figure 1 Shows a schematic flow chart of the board fault diagnosis method based on the weighted sum of squares of the sensor signal residual sequence provided by the embodiment of the present invention;

[0031] Figure 2The figure shows the actual operation flowchart of the board card fault diagnosis method based on the weighted sum of squares of sensor signal residual sequences provided by the embodiments of the present invention. Detailed implementation manners

[0032] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0033] The electronic controller in a gas turbine control system is a complex system composed of highly integrated electronic components. The fault diagnosis method based on BIT not only has a high implementation cost, but also the newly added fault diagnosis circuit increases the complexity of the system on the one hand and the probability of system failure on the other hand. The fault diagnosis method based on data is a recent research hotspot. However, the fault diagnosis method based on data requires a large number of high-quality fault samples for algorithm training and verification. The industrial field cannot generate enough fault samples (this is easy to understand. If there are abundant fault samples in the industrial field, it means that the process method is not mature and it is impossible to obtain wide industrial applications). This results in that the fault diagnosis method based on data often only performs well in the laboratory environment and cannot be truly used in the industrial field.

[0034] To solve the above problems, the present invention provides a convenient and feasible fault diagnosis method for a thermocouple IO board card.

[0035] Figure 1 The figure shows a schematic flowchart of the board card fault diagnosis method based on the weighted sum of squares of sensor signal residual sequences provided by the embodiments of the present invention. As Figure 1 shown, the board card fault diagnosis method based on the weighted sum of squares of sensor signal residual sequences provided by the present invention is used for fault diagnosis of the thermocouple IO board card of a gas turbine electronic controller. The method includes:

[0036] Step 101: Obtain the original temperature process signals of each temperature sensor from the gas turbine electronic controller system, perform data preprocessing, and form an original signal data set.

[0037] Step 102: Input the signals in the original signal data set into the sensor residual sequence weighted sum calculation model to obtain the weighted sum of squares of the signal residual sequences of each temperature sensor.

[0038] Step 103: Select the weighted sum of squares of the signal residuals of all temperature sensors associated with the thermocouple IO board, and input the selected weighted sum of squares of the signal residuals into a preset health calculation model for the thermocouple IO board to obtain the health value of the thermocouple IO board.

[0039] Step 104: Calculate the difference between the health value of the thermocouple IO board and the boundary line of the preset normal range of the health value, and determine whether the thermocouple IO board has a fault based on the difference, so as to realize the fault diagnosis of the thermocouple IO board.

[0040] This method can quickly diagnose the fault state of the thermocouple IO board in an engineering way, provide an engineering applicable means for timely identifying the faults of the IO board of the electronic controller, and provide important support for the fault diagnosis of the gas turbine control system loop.

[0041] Optionally, connect to the OPC Server data source of the gas turbine electronic controller system in the OPC UA industrial protocol from the gas turbine electronic controller system to obtain the original temperature process signals of each temperature sensor. The gas turbine electronic controller system can be, for example, the gas turbine electronic controller system of a 9F unit.

[0042] Optionally, obtain the real-time temperature process signals of all temperature sensors associated with the thermocouple IO board from the gas turbine electronic controller DCS system through the OPC UA industrial protocol interface. The data preprocessing includes operations such as removing redundant samples, removing abnormal samples, and data normalization, and converting the data into a Gaussian distribution form with a mean of 0 and a variance of 1.

[0043] Optionally, the weighted sum of squares calculation model of the sensor residual sequence is a weighted sum of squares calculation model of the sensor residual sequence based on the unscented Kalman filter.

[0044]

[0045] ∑=(diag(σ)) 2

[0046] where R i is the weighted sum of the residual sequences of the temperature sensor corresponding to the i-th channel of the thermocouple IO board. Based on the unscented Kalman filter, filters corresponding to m sensors associated with the thermocouple IO board are established. The input of each filter is the measured parameter values of m - 1 sensors. The input of the i-th filter is the measured parameters of the remaining m - 1 sensors except the i-th sensor. σ is the standard deviation of the measured parameters, and y (i) is the measured parameter of the i-th filter. is the predicted output of the non - linear model of the i - th filter; m is the total number of temperature sensors associated with the thermocouple IO board.

[0047]

[0048] As can be seen from the above formula, the unscented Kalman filter can estimate the health parameter p based on the residual between the measured parameter y of the gas turbine k and the predicted output of the non - linear model to update the health parameter of the non - linear model, making the output parameter of the model track the output of the real gas turbine, thereby establishing a gas path fault diagnosis system based on the unscented Kalman filter to realize the estimation of the health parameters of the gas turbine.

[0049] Optionally, the health calculation model of the thermocouple IO board is as follows:

[0050]

[0051] where R IO-card is the health value of the thermocouple IO board, and k i is the weighted weight of the i - th channel of the thermocouple IO board.

[0052] Optionally, it is determined whether the thermocouple IO board fails according to the following formula:

[0053] F IOcard = 1 if R IO-card > R high limit

[0054] where F IOcard is the fault judgment flag bit of the thermocouple IO board. When F IOcard = 1, it is determined that the thermocouple IO board fails;

[0055] R high limit is the upper limit of the preset normal range of the health value. When the difference between the health value of the thermocouple IO board and the boundary line of the preset normal range of the health value is greater than zero, that is, R IO-card > R high limit in the case of, F IOcard = 1.

[0056] Optionally, the value of R high limit is equal to 3σ.

[0057] After a failure occurs in the thermocouple IO board of the electronic controller, the state of the sensor signals collected by this board will become abnormal. For example, the value suddenly jumps (step fault), the value suddenly jumps and then returns to normal (pulse fault), the value continuously increases or decreases (time-varying / temperature drift fault), there are periodic interferences in the value (often because there are strong electrical induction signals entering the board), or the signal stability deteriorates (white noise interference, often caused by poor contact or abnormal grounding). The first reaction to a failure of the IO board is these abnormal sensor signals. When the sensor-collected data changes abnormally, calculate the weighted square of the residual sequence of the sensor; use the health model of the IO board to calculate the health of the IO board. When the health exceeds the normal range, it can be determined that the board has failed. Figure 2 The figure shows the actual operation flowchart of the board failure diagnosis method based on the weighted sum of squares of the residual sequence of sensor signals provided by the embodiment of the present invention.

[0058] In summary, the present invention uses the real-time process sampling signals obtained from the DCS of the gas turbine control system to calculate the weighted sum of squares of the residual sequence of sensor signals, and then sums up the health values of all sensors associated with the thermocouple IO board as the health index value of this IO board. If it is determined that this health index exceeds the normal range, it is determined that the IO board has failed, thereby realizing the engineering failure diagnosis of the IO board.

[0059] The above embodiments are only used to illustrate the technical concept and characteristics of the present invention, and their purpose is to enable those of ordinary skill in the art to understand the content of the present invention and implement it. However, the protection scope of the present invention cannot be limited by this. Any equivalent changes or modifications made according to the spirit and essence of the present invention should be covered within the protection scope of the present invention.

Claims

1. A board card fault diagnosis method based on the weighted sum of squares of sensor signal residual sequences, characterized in that, The method is used for fault diagnosis of a thermocouple IO board of a gas turbine electronic controller, and the method includes: Obtain the original temperature process signals of each temperature sensor from the gas turbine electronic controller system, perform data preprocessing, and form an original signal data set; Input the signals in the original signal data set into a calculation model for the weighted sum of squares of sensor residual sequences to obtain the weighted sum of squares of the signal residual sequences of each temperature sensor; Select the weighted sum of squares of the signal residual sequences of all temperature sensors associated with the thermocouple IO board, and input the selected weighted sum of squares of the signal residual sequences into a preset calculation model for the health degree of the thermocouple IO board to obtain the health degree value of the thermocouple IO board; Calculate the difference between the health degree value of the thermocouple IO board and the boundary line of the normal range of the preset health degree value, and judge whether the thermocouple IO board has a fault according to the difference, so as to realize the fault diagnosis of the thermocouple IO board, The calculation model for the weighted sum of squares of sensor residual sequences is a calculation model for the weighted sum of squares of sensor residual sequences based on an unscented Kalman filter, ， Among them, is the weighted sum of the residual sequences of the temperature sensors corresponding to the th channels of the thermocouple IO board. Based on the unscented Kalman filter, filters corresponding to the sensors associated with the thermocouple IO board are established. The input of each filter is measurement parameter values. The input of the th filter is the measurement parameters of the remaining sensors except the th sensor. is the standard deviation of the measurement parameters. is the measurement parameter of the th filter. is the predicted output of the nonlinear model of the th filter. is the total number of temperature sensors associated with the thermocouple IO board. The calculation model for the health degree of the thermocouple IO board is as follows: ， Among them, is the health value of the thermocouple IO board, is the weighted weight of the th channel of the thermocouple IO board.

2. The board card fault diagnosis method based on the weighted sum of squares of sensor signal residual sequences according to claim 1, wherein, Obtain the original temperature process signals of each temperature sensor from the gas turbine electronic controller system by using the OPC UA industrial protocol.

3. The board card fault diagnosis method based on the weighted sum of squares of sensor signal residual sequences according to claim 2, wherein From the gas turbine electronic controller system, obtain the real-time temperature process signals of all temperature sensors associated with the thermocouple IO board through the OPC UA industrial protocol interface from the DCS system of the gas turbine electronic controller. The data preprocessing includes operations of removing redundant samples, removing abnormal samples, and data normalization.

4. The board card fault diagnosis method based on the weighted sum of squares of sensor signal residual sequences according to claim 1, characterized in that Judge whether the thermocouple IO board has a fault according to the following formula: ， Among them, is the fault judgment identification bit of the thermocouple IO board. When , it is determined that the thermocouple IO board has a fault; is the upper limit of the normal range of the pre-set health value. When the difference between the health value of the thermocouple IO board and the boundary line of the normal range of the pre-set health value is greater than zero, that is in the case of = 1.

5. The board card fault diagnosis method based on the weighted sum of squares of the sensor signal residual sequence according to claim 4, characterized in that The value is equal to 3 .

Images