Fault detection method and system for reluctance type rotating speed sensor of gas turbine

Abstract

The invention relates to a fault detection method and system for a reluctance type rotating speed sensor of a gas turbine, and relates to the technical field of gas turbines. According to the method, a fuzzy observer with fuel flow as input and gas turbine rotating speed as output is established by using running data when the gas turbine is free of faults; inputting the fuel flow of the actually running gas turbine into the fuzzy observer, and comparing the actually measured rotating speed with the estimated rotating speed output by the fuzzy observer to obtain an estimated relative difference; and comparing the estimated relative difference with a self-adaptive fault threshold value, and when the relative difference is greater than the threshold value, sending out a fault alarm of the rotating speed sensor by the control system. Real-time fault detection can be carried out on the gas turbine reluctance type rotating speed sensor by establishing the fuzzy observer, an alarm is given to prompt a gas turbine operator to overhaul a rotating speed measuring loop in time when a fault occurs, and the uncertainty of modeling and disturbance caused by the characteristics of the rotating speed sensor can be eliminated; the method is of great significance to stable operation of the gas turbine.

Description

Technical Field

[0001] The invention belongs to the technical field of gas turbines, and in particular relates to a gas turbine reluctance speed sensor fault detection method and system. Background Art

[0002] The speed of a gas turbine is an important monitoring input for the control system of a gas turbine. Since gas turbines operate in harsh environments such as high temperature, oil mist, and vibration, a magnetoresistive speed sensor is usually selected, and it is also one of the most prone to failures in the control system of a gas turbine. After a speed sensor fails, drift failures, step failures, and loss failures in its measured values ​​will cause the control loop to be inaccurate, and it is very easy to cause protection actions such as downgrades and emergency shutdowns, affecting the safe operation of the unit. Therefore, it is of great significance to quickly and accurately detect the failure of the magnetoresistive speed sensor of a gas turbine and repair the sensor circuit in a timely manner. Summary of the invention

[0003] In order to solve the above technical problems, the present disclosure provides a method and system for detecting faults of a gas turbine reluctance speed sensor.

[0004] To achieve the above objectives, some embodiments of the present application provide a method for detecting a fault of a gas turbine reluctance speed sensor, the method comprising the following steps: Step 1: Using the gas turbine running data without fault, through the fuzzy reasoning base, setting fuzzy rules, and establishing a fuzzy observer; Step 2: When the gas turbine is running, real-time speed measurement is performed through a speed acquisition module; Step 3, inputting the real-time fuel flow and speed measurement values ​​into the fuzzy observer, the fuzzy observer estimates the current speed value according to the fuel flow, and uses the input speed at the previous moment to calculate the compensation gain, and estimates the estimated value of the current speed value; Step 4: compare the real-time speed measurement value with the estimated speed output by the fuzzy observer in step 3 to obtain an estimated relative difference. If the absolute value of the estimated relative difference is greater than the adaptive fault threshold, the control system issues a magnetoresistive speed sensor fault alarm.

[0005] Furthermore, the step 1 further comprises: representing the actual operating state of the gas turbine by the following gas turbine model: ; in, u is the system input, indicating the fuel flow rate, is the measurable state quantity, N h 、N p Represent the speeds of the high pressure compressor and power turbine respectively; f(x) is an unknown nonlinear smooth function;y and x Same dimension, which is the system output; M(t) is an unknown bounded fault function; A , B , C , D is a reversible matrix of known appropriate dimension.

[0006] Furthermore, the fuzzy observer is established based on the operating data of the gas turbine when there is no fault in the step 1, which specifically includes: collecting the test data of multiple gas turbines when there is no fault, using the actual fuel flow rate of the gas turbine u , Real-time engine speed x As the input of the fuzzy observer, the fuel flow u The corresponding nonlinear part estimate x 1 is the output of the fuzzy observer, the real-time speed of the gas turbine x It is used to calculate the compensation of the fuzzy observer, and the compensation is used to correct the output speed. The specific formula is: ; in, A, B, D is a reversible matrix of known appropriate dimension, L is the observer gain; Fuzzy function is used to represent the nonlinear part of the model f(x) , through defuzzification, we have ; In the formula, is the weight vector, is the fuzzy basis function vector, g i (x) is a Gaussian fuzzy membership function, which is expressed as follows: ; in, and x Same dimension, is the center vector; is the width of the Gaussian function.

[0007] Furthermore, the step 1 further includes: based on the fuzzy observer, the following Riccati equation is given: ; In the formula, the symmetric array , β is a given positive constant; then its positive definite symmetric solution can be found P ; Thus, the relative error of speed estimation is defined as , then the observer gain is , the weight vector w The update rate is: .

[0008] Furthermore, the step 4 further comprises: calculating the estimated relative difference according to the estimated value obtained by the fuzzy observer The relative estimated difference is compared with the fault threshold by a comparator to detect the fault. The adaptive fault threshold is selected as , we can get: .

[0009] Furthermore, the step 4 further includes: the adaptive fault threshold Y 1The calculation method is: ; in Z g1 The calculation expression is as follows: ; in, x(t) is the current speed sampling value, x L and x H For a given gas turbine speed range, a 0. a 1. a 2. a 3 and a 4 is the adjustment coefficient; Z g0 is the reference threshold under ideal conditions, taking the maximum difference between the estimated speed value and the actual sampling value under fault-free conditions; Z g1 It is the adaptive adjustment part; if the absolute value of the estimated relative difference is greater than the adaptive fault threshold, the control system will issue a magnetoresistive speed sensor fault alarm.

[0010] On the other hand, the present application also provides a gas turbine reluctance speed sensor fault detection system, which includes a memory for storing computer program instructions and a processor for executing program instructions, wherein when the computer program instructions are executed by the processor, the system is triggered to execute the above-mentioned gas turbine reluctance speed sensor fault detection method.

[0011] Compared with the prior art, the gas turbine reluctance speed sensor fault detection method and system provided by the present application establishes a fuzzy observer by using the gas turbine operation data when there is no fault, estimates the real-time speed of the gas turbine by using the fuel flow rate input to the gas turbine, and corrects the estimated speed by using the speed acquisition value at the previous moment, compares the real-time acquisition speed of the gas turbine with the estimated speed output by the fuzzy observer, and compares the absolute value of the estimated relative difference with the adaptive fault threshold. If the absolute value of the estimated relative difference is greater than the adaptive fault threshold, the control system issues a "speed sensor fault" alarm. The present application can perform real-time fault detection on the gas turbine reluctance speed sensor by establishing a fuzzy observer, and when a fault occurs, an alarm prompts the gas turbine operator to promptly repair the speed measurement circuit, which is of great significance to the stable operation of the gas turbine. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flow chart of a gas turbine reluctance speed sensor fault detection method provided in an embodiment of the present disclosure.

[0013] In the figure, u Input fuel flow for gas turbine, x is the measured value of the engine speed, x 1 is the estimated value of the fuzzy observer speed, y To estimate the relative difference, Y 1 is the fault threshold. DETAILED DESCRIPTION

[0014] In order to more clearly understand the purpose, features and advantages of the present disclosure, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. It should be noted that the embodiments of the present disclosure and their features can be combined with each other without conflict. Many specific details are provided in the following description to fully understand the present disclosure, but in fact the present disclosure can be implemented in other ways, which may be different from the following description. Obviously, the embodiments in the specification only represent some embodiments of the present disclosure, not all embodiments.

[0015] Since gas turbines work in harsh environments such as high temperature, oil mist, and vibration, magnetoresistive speed sensors are usually selected. As the working time of the magnetoresistive speed sensor increases, the probability of its failure gradually increases, which in turn brings major hidden dangers of failure to the gas turbine control system. The present invention aims to quickly and accurately detect the failure of the magnetoresistive speed sensor, avoid the gas turbine control system from taking protective actions such as downgrade and emergency shutdown due to abnormal speed, and thus send out an alarm to remind the gas turbine operator to promptly repair the speed measurement circuit to reduce or eliminate the impact of the failure.

[0016] The gas turbine magnetoresistive speed sensor is generally installed on the gas turbine casing. When the turbine shaft rotates, the sensor generates an induced pulse electromotive force of a certain frequency. By measuring the pulse frequency, the actual speed of the gas turbine can be calculated.

[0017] Since the speed sensor works in harsh environments such as high temperature, oil mist, and vibration, it is a component that is prone to failure. Due to its own characteristics, the signal strength of the magnetoresistive speed sensor is weak at low speeds, and it is easily affected by external interference, resulting in speed fluctuations. Through the fault detection method and the design of the fault threshold, the sensor failure and the speed fluctuation caused by interference can be distinguished to avoid unnecessary downtime losses.

[0018] In view of the above problems, the present disclosure provides a method for detecting a fault of a gas turbine reluctance speed sensor. Next, the method will be described in conjunction with a specific embodiment.

[0019] Below Figure 1 The method for detecting a fault of a gas turbine reluctance speed sensor shown in the figure is introduced, and the specific steps of the method are as follows: Step 1: Use the operating data of multiple gas turbines without failure to input the fuel flow rate of the gas turbine u , gas turbine speed measurement value As the input of the fuzzy observer, Nh and Np represent the speed of the high-pressure compressor and the power turbine respectively; the fuzzy observer speed estimation value x1 is used as the output of the fuzzy observer. Through the fuzzy inference base, fuzzy rules are set to establish a fuzzy observer. The fuzzy inference base is a description tool based on fuzzy set theory, which is used to perform mathematical logic expansion on the description object, that is, the test data is normalized and fuzzified to give the corresponding fuzzy rules. Fuzzy rules refer to fuzzy relations defined in a binary domain. It is a knowledge representation method based on fuzzy logic, which is used to describe knowledge or rules in the field of object control.

[0020] The fuzzy observer model is as follows: ; (1) in, A, B, D is a known observable matrix of suitable dimension, L is the observer gain; Fuzzy function is used to represent the nonlinear part of the model f(x) , and there is ; In the formula, is the weight vector, is the fuzzy basis function vector, g i (x) is a Gaussian fuzzy membership function, which is expressed as follows: ; (2) in, and x Same dimension, is the center vector; is the width of the Gaussian function.

[0021] Based on the Gaussian fuzzy membership function, the appropriate number of fuzzy sets and inference rules can be selected through multiple experiments. The gas turbine high-pressure compressor speed and the actual fuel flow rate are used as input, and the fuzzy function estimates of the nonlinear part of the model high-pressure compressor speed are used as output. The following high-pressure compressor speed fuzzy rule table is used, see Table 1: ; The gas turbine power turbine speed and the actual fuel flow are taken as input, and the estimated value of the nonlinear part of the model power turbine speed by the fuzzy function is taken as output. The following power turbine speed fuzzy rule table is used, see Table 2: ; Based on the above fuzzy observer, the following Riccati equation is given: ; (3) In the formula, the symmetric array , β is a given positive constant; then its positive definite symmetric solution can be found P ; Thus, the relative error of speed estimation is defined as , then the observer gain is , the weight vector w The update rate is: ; (4) In some embodiments, the following gas turbine model is given to represent the actual operating state of the gas turbine: ; in, u is the system input, indicating the fuel flow rate, is the measurable state quantity, N h 、N p Represent the speeds of the high pressure compressor and power turbine respectively; f(x) is an unknown nonlinear smooth function; y and x Same dimension, which is the system output; M(t) is an unknown bounded fault function; A , B , C , D is a reversible matrix of known appropriate dimension.

[0022] Step 2: When the gas turbine is running, the current fuel flow rate is obtained through the fuel flow meter, and the high-pressure compressor speed N is obtained through the speed acquisition module.h , power turbine speed N p ; Step 3: When the gas turbine is running, the real-time fuel flow rate and speed measurement values ​​are input into the fuzzy observer established in step 1. As described in formula (1), the fuzzy observer estimates the current speed value based on the fuel flow rate and the speed value at the previous moment, and uses the input speed at the previous moment to calculate the compensation gain and correct the current speed estimate; In step 4, the real-time measured speed is compared with the estimated speed output by the fuzzy observer in step 3 to obtain an estimated relative difference. If the absolute value of the estimated relative difference is greater than the adaptive fault threshold, the control system issues a "speed sensor fault" alarm.

[0023] Furthermore, in step 4, the relative estimated difference is calculated based on the estimated value obtained by the fuzzy observer. , by comparing with the fault threshold, the fault detection is realized, and the adaptive fault threshold is selected as , can be obtained ; In practice, the signal strength of the gas turbine's magnetoresistive speed sensor is weak at low speeds, and there is even an unstable sampling interval at the beginning of startup. In this interval, the speed signal is easily distorted by external disturbances. As the speed increases, the signal strength and stability gradually increase, and the disturbance to the measurement signal decreases. When it rises to the high speed zone, a small change in the speed will produce a large change in the operating condition, and corresponding micro-compensation is required. Therefore, using traditional fixed threshold detection, not only is the threshold difficult to determine, but it is also prone to false detection and missed detection. Therefore, the present invention proposes an adaptive fault threshold design method.

[0024] Specifically, due to the characteristics of the magnetoresistive speed sensor, at low speed, the signal is weak and unstable, and as the speed increases, its signal strength and stability will gradually increase, so the adaptive fault threshold in step 4 is defined as Y 1The calculation method is: ; in Z g1 The calculation expression is as follows: ; in, x(t) is the current speed sampling value, x L and x H For a given gas turbine speed range, a 0. a 1. a 2. a 3 anda 4 is the adjustment coefficient; Z g0 is the reference threshold under ideal conditions, taking the maximum difference between the estimated speed value and the actual sampling value under fault-free conditions; Z g1 It is the adaptive adjustment part; if the absolute value of the estimated relative difference is greater than the adaptive fault threshold, the control system will issue a magnetoresistive speed sensor fault alarm.

[0025] After the alarm occurs, the gas turbine operator should stop the engine in time to check and repair the speed measurement circuit according to the actual situation to prevent more serious faults from occurring.

[0026] The present invention also provides a gas turbine reluctance speed sensor fault detection system, which includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the system is triggered to execute the aforementioned gas turbine reluctance speed sensor fault detection method.

[0027] In summary, the gas turbine magnetoresistive speed sensor fault detection method and system provided by the present invention utilizes the operating data of the gas turbine when there is no fault to establish a fuzzy observer with fuel flow as input and gas turbine speed as output; the fuel flow of the actual operating gas turbine is input into the observer, and the estimated speed is compared with the estimated speed output by the fuzzy observer to obtain an estimated relative difference; by setting an adaptive threshold, the uncertainty of the modeling and the disturbance caused by the characteristics of the magnetoresistive speed sensor itself are eliminated, and the gas turbine magnetoresistive speed sensor is detected by comparing the estimated relative difference with the threshold. When the relative difference is greater than the threshold, the control system issues a "speed sensor fault" alarm to remind the gas turbine operator to promptly repair the speed measurement circuit to reduce or eliminate the impact of the fault.

[0028] It should be noted that the system of the present invention may also include one or more of the following components: a processor and a memory.

[0029] Optionally, the processor uses various interfaces and lines to connect various parts within the entire autonomous operation equipment, and executes various functions of the autonomous operation equipment and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory, and calling data stored in the memory. Optionally, the processor can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a neural network processor (NPU). Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content that needs to be displayed on the touch display; and the NPU is used to implement artificial intelligence (AI) functions.

[0030] The memory may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory includes a non-transitory computer-readable storage medium. The memory may be used to store instructions, programs, codes, code sets, or instruction sets. The memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function, instructions for implementing each of the above method embodiments, etc.; the data storage area may store data created according to the use of the autonomous operation device, etc.

[0031] The present disclosure also provides a computer-readable storage medium storing a computer program, wherein the computer program is used to be executed by a processor to implement the positioning control method of the autonomous working equipment as described in the above embodiment.

[0032] Although the present invention has been described in detail by referring to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention or any person skilled in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and shall be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the attached claims.

Claims

1. A method for detecting faults of a gas turbine reluctance speed sensor, characterized in that: The method comprises the following steps: Step 1: Using the gas turbine running data without fault, through the fuzzy reasoning base, setting fuzzy rules, and establishing a fuzzy observer; Step 2: When the gas turbine is running, real-time speed measurement is performed through a speed acquisition module; Step 3, inputting the real-time fuel flow and speed measurement values ​​into the fuzzy observer, the fuzzy observer estimates the current speed value according to the fuel flow, and uses the input speed at the previous moment to calculate the compensation gain, and estimates the estimated value of the current speed value; Step 4: compare the real-time speed measurement value with the estimated speed output by the fuzzy observer in step 3 to obtain an estimated relative difference. If the absolute value of the estimated relative difference is greater than the adaptive fault threshold, the control system issues a magnetoresistive speed sensor fault alarm.

2. The method according to claim 1, characterized in that The step 1 further comprises: representing the actual operating state of the gas turbine by the following gas turbine model: ； in, u is the system input, indicating the fuel flow rate, is the measurable state quantity, N h 、N p Represent the speeds of the high pressure compressor and power turbine respectively; f(x) is an unknown nonlinear smooth function; y and x Same dimension, which is the system output; M(t) is an unknown bounded fault function; A , B , C , D is a reversible matrix of known appropriate dimension.

3. The method according to claim 1, characterized in that In step 1, the fuzzy observer is established based on the operating data of the gas turbine without faults, which specifically includes: collecting the test data of multiple gas turbines without faults, and using the actual fuel flow rate of the gas turbine u , Real-time engine speed x As the input of the fuzzy observer, the fuel flow u The corresponding nonlinear part estimate x 1 is the output of the fuzzy observer, the real-time speed of the gas turbine x It is used to calculate the compensation of the fuzzy observer, and the compensation is used to correct the output speed. The specific formula is: ； in, A, B, D is a reversible matrix of known appropriate dimension, L is the observer gain; Fuzzy function is used to represent the nonlinear part of the model f(x) , and there is ; In the formula, is the weight vector, is the fuzzy basis function vector, g i (x) is a Gaussian fuzzy membership function, which is expressed as follows: ； in, and x Same dimension, it is the center vector; is the width of the Gaussian function.

4. The method according to claim 3, characterized in that The step 1 further includes: based on the fuzzy observer, the following Riccati equation is given: ； In the formula, the symmetric array , β is a given positive constant; then its positive definite symmetric solution can be found P ; Thus, the relative error of speed estimation is defined as , then the observer gain is , the weight vector w The update rate is: 。 5. The method according to claim 2, characterized in that: The step 4 further comprises: calculating the estimated relative difference according to the estimated value obtained by the fuzzy observer , estimated by the relative difference Y The absolute value of the adaptive fault threshold Y 1 comparison, fault detection, the expression is: 。 6. The method according to claim 5, characterized in that The step 4 further includes: the adaptive fault threshold Y 1The calculation method is: ； in Z g1 The calculation expression is as follows: ； in, x(t) is the current speed sampling value, x L and x H For a given gas turbine speed range, a 0. a 1. a 2. a 3 and a 4 is the adjustment coefficient; Z g0 is the reference threshold under ideal conditions, taking the maximum difference between the estimated speed value and the actual sampling value under fault-free conditions; Z g1 It is the adaptive adjustment part; if the absolute value of the estimated relative difference is greater than the adaptive fault threshold, the control system will issue a magnetoresistive speed sensor fault alarm.

7. A gas turbine reluctance speed sensor fault detection system, the system comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein: When the computer program instructions are executed by the processor, the system is triggered to execute the gas turbine reluctance speed sensor fault detection method according to any one of claims 1 to 6.

Images