Servomotor internal leakage fault comprehensive diagnosis and early warning method, servomotor internal leakage fault comprehensive diagnosis and early warning equipment and medium

Abstract

The invention relates to the technical field of hydroelectric generating set fault diagnosis, and provides a servomotor internal leakage fault comprehensive diagnosis and early warning method, device and medium, and the method comprises the steps: collecting operation condition monitoring data of a hydroelectric generating set servomotor hydraulic cylinder, making a test data set and a test data set, and extracting characteristic values; fitting a corresponding conversion relation between the characteristic value and the leakage rate in the target value through a multivariate nonlinear regression analysis model; adopting a least square method to realize model parameter estimation; testing the accuracy of the model by using the test data set, and calculating the internal leakage rate of the hydroelectric generating set servomotor hydraulic cylinder after the requirement is met; and based on the fault threshold value index, quantitative diagnosis and graded early warning of the internal leakage fault are realized. According to the method, the influence of the coupling effect among the monitoring data under the multi-source operation condition on the internal leakage amount is considered, the corresponding conversion relation between the characteristic value and the internal leakage amount is analyzed through multiple nonlinear regression, and the accuracy of servomotor hydraulic cylinder internal leakage fault detection is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault diagnosis of hydropower units, and in particular to a comprehensive diagnosis and early warning method, equipment and medium for internal leakage faults of a servomotor. Background Art

[0002] The safety and reliability of hydropower unit operation is not only a technical issue, but also the key to achieving energy security and promoting green development.

[0003] The servo is one of the most critical components in a hydroelectric unit. It regulates the turbine output power by precisely adjusting the guide vane opening to control the water flow rate, matching it with the external load and ensuring the stable operation of the unit. A common servo failure is micro-internal leakage from the high-pressure chamber to the low-pressure chamber inside the servo hydraulic cylinder. This failure is difficult to identify early through sensors and will cause the response speed of the servo hydraulic cylinder in the turbine unit speed control system to decrease, making it difficult to synchronize the guide vane opening and unable to achieve the purpose of millisecond-level peak and frequency regulation. Therefore, it is crucial to diagnose and warn of micro-internal leakage of the servo before it affects the normal operation of the unit to improve the unit reliability and reduce the failure rate.

[0004] After searching the literature and patents of the prior art, it was found that the common relay internal leakage detection methods are mainly divided into the following categories:

[0005] Method 1: Liu Chuandong et al. conducted a fault test on the leakage of a servo in "Leakage Test and Fault Analysis of a Turbine Servomotor in a Pumped Storage Power Station". They analyzed the intrinsic relationship between fault detection parameters and leakage faults, revealed the mutual connection between fault parameters under servo leakage, and found that the change characteristics of parameters such as temperature can be used to intuitively determine whether the servo has a leakage fault.

[0006] Method 2: Wang Yifeng et al. proposed a servo leakage fault diagnosis system based on vibration signals in "Research on Single Guide Vane Servomotor Fault Diagnosis Technology Based on Vibration Signals". The system reveals the servo leakage fault by analyzing the spectral characteristics of the acquired vibration signal, thus solving the problem of online servo leakage fault diagnosis.

[0007] Method 3: Chinese Patent Publication No.: CN117606709A, Patent Name: Method and Device for Detecting Oil Cross-Contamination Fault in the Upper and Lower Chambers of a Cylinder Valve Servomotor. The patent describes itself as: A method for detecting oil cross-contamination fault in the upper and lower chambers of a cylinder valve servomotor is proposed. By obtaining the lower chamber pressure values ​​of multiple servomotors connected to the target cylinder valve at the first moment, the lower chamber pressure deviation between two adjacent servomotors is determined. According to the lower chamber pressure deviation of each servomotor and the preset deviation threshold, it is possible to detect whether there is an oil cross-contamination fault in the upper and lower chambers of each servomotor, and at the same time, the faulty servomotor can be quickly located.

[0008] In summary, the turbine servo is one of the most critical components in the hydropower unit. The micro-internal leakage fault of the servo is difficult to identify early through sensors and will cause the turbine unit guide vane opening to be difficult to synchronize, resulting in the unit being unable to operate normally and even causing accidents. Existing servo internal leakage detection methods all focus on significant internal leakage. The diagnosis of servo internal leakage is achieved by using single signals such as vibration, temperature, and pressure. This will lead to incomplete characterization of the internal leakage fault feature information and thus affect the detection accuracy. The internal leakage of the servo is essentially a complex process affected by multiple operating conditions. Especially in the micro-internal leakage state, the coupling effect between various operating conditions requires higher accuracy of the detection method. The slight change of a single feature information is not enough to achieve accurate detection of micro-internal leakage. Therefore, it is necessary to fuse multi-source state information to improve the diagnosis accuracy of early micro-internal leakage faults. Summary of the Invention

[0009] In view of the shortcomings of the current relay hydraulic cylinder micro-internal leakage detection technology, the present invention provides a relay internal leakage fault comprehensive diagnosis and early warning method, equipment and medium.

[0010] In a first aspect, the present invention provides a comprehensive diagnosis and early warning method for internal leakage faults in a servomotor, comprising:

[0011] Collect operating condition monitoring data of the hydraulic cylinder of the hydropower unit servomotor;

[0012] Producing an experimental data set and a test data set based on the operating condition monitoring data;

[0013] Extracting characteristic values ​​of operating condition monitoring data;

[0014] The corresponding conversion relationship between the characteristic value of the operating condition monitoring data in the test data set and the target value internal leakage is fitted by a multivariate nonlinear regression analysis model;

[0015] The least square method is used to estimate the parameters of the multivariate nonlinear regression analysis model;

[0016] Using the test data set to test the accuracy of the multivariate nonlinear regression analysis model, and using the multivariate nonlinear regression analysis model that meets the accuracy requirements to calculate the internal leakage of the hydraulic cylinder of the hydropower unit relay;

[0017] Based on the fault threshold index, quantitative diagnosis and graded early warning of leakage faults in the hydraulic cylinder of the hydropower unit relay are realized.

[0018] In some embodiments, the operating condition monitoring data includes the following three categories:

[0019] The first category is the operation history monitoring data of the hydraulic cylinder of the hydropower unit relay, including pressure P1, piston rod displacement x1 and oil temperature T1;

[0020] The second category is the multi-operating condition test data of the hydropower unit relay test bench, including multi-operating condition pressure P2, piston rod displacement x2, oil temperature T2 and internal leakage Q2;

[0021] The third category is simulation data generated by the high-fidelity governor simulation model, including multi-condition pressure P3, piston rod displacement x3, oil temperature T3 and internal leakage Q3.

[0022] In some embodiments, the absolute value of the difference between the operating condition monitoring data and the corresponding initial preset value is used as the corresponding characteristic value, including the pressure characteristic value, the displacement characteristic value and the temperature characteristic value.

[0023] In some embodiments, the multivariate nonlinear regression analysis model is expressed as:

[0024] Q=f[(ΔP, Δx, ΔT),θ]+μ

[0025] Where f(.) is a multivariate nonlinear function, ΔP is the pressure eigenvalue, Δx is the displacement eigenvalue, ΔT is the temperature eigenvalue, Q is the internal leakage, θ is an unknown parameter, and μ is the random error term.

[0026] In some embodiments, the least squares method is used to implement parameter estimation of the multivariate nonlinear regression analysis model, including:

[0027] By solving minΣe 2 The parameter value that minimizes the sum of squared errors is the desired parameter estimate; the sum of squared errors is expressed as:

[0028]

[0029] Where, is the i-th monitoring value Q of the internal leakage Q2 in the multi-condition test data 2i The corresponding fitting value, n is the number of monitoring data of internal leakage Q2 in the multi-condition test data; is the jth simulation value Q of the internal leakage Q3 in the simulation data 3i The corresponding fitting value, m is the number of simulation data of internal leakage Q2 in the simulation data.

[0030] In some embodiments, the coefficient of determination is used as a judgment indicator for the accuracy test of the multivariate nonlinear regression analysis model;

[0031] The coefficient of determination R 2 Expressed as:

[0032]

[0033] in:

[0034] SST is the total sum of squares, expressed as

[0035] SSR is the regression sum of squares, expressed as

[0036] SSE is the residual sum of squares, expressed as

[0037] In some embodiments, the fault threshold indicator includes an internal leakage threshold indicator; the calculated internal leakage of the hydraulic cylinder of the hydropower unit relay is quantitatively diagnosed and graded early warning by presetting different internal leakage threshold ranges corresponding to different fault grades.

[0038] In some embodiments, the fault threshold indicator also includes a guide vane opening deviation threshold indicator; by presetting different guide vane opening deviation threshold ranges corresponding to different fault levels, the internal leakage threshold indicator and the guide vane opening deviation threshold indicator are integrated to perform quantitative diagnosis and graded warning.

[0039] In a second aspect, the present invention provides an electronic device, comprising:

[0040] at least one processor; and a memory communicatively coupled to the at least one processor;

[0041] The memory stores instructions that can be executed by the at least one processor, and the at least one processor executes the above method by executing the instructions stored in the memory.

[0042] In a third aspect, the present invention provides a computer-readable storage medium for storing instructions, which implement the above method when the instructions are executed.

[0043] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0044] 1. The present invention considers the influence of the coupling effect between multi-source operating condition monitoring data on the internal leakage amount, and analyzes the corresponding conversion relationship between the characteristic values ​​of each motion condition monitoring data and the internal leakage amount through multivariate nonlinear regression. It breaks through the difficulties of the existing method of using easy-to-monitor indicators to indirectly judge whether the internal leakage amount is qualified, which lacks a theoretical basis and has low accuracy, and improves the accuracy of relay hydraulic cylinder internal leakage fault detection.

[0045] 2. By integrating the internal leakage threshold index and the guide vane opening deviation index, the present invention realizes a quantitative hierarchical early warning of two-dimensional relay faults, comprehensively characterizes the overall macroscopic performance of the equipment, and provides highly reliable information for the safe and reliable operation of the hydropower unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 The present invention provides a flowchart of a comprehensive diagnosis and early warning method for internal leakage faults in a relay.

[0047] Figure 2 Schematic diagram of data fitting of the multivariate nonlinear regression analysis model in an embodiment of the present invention.

[0048] Figure 3 Schematic diagram of fault classification integrating the internal leakage threshold index and the guide vane opening deviation index in an embodiment of the present invention.

[0049] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0051] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort are intended to fall within the scope of protection of the present invention.

[0052] Example

[0053] like Figure 1 As shown, an embodiment of the present invention provides a comprehensive diagnosis and early warning method for internal leakage faults in a servomotor, comprising the following steps:

[0054] S100, collecting operating condition monitoring data of the hydraulic cylinder of the hydropower unit servomotor;

[0055] S200, generating an experimental data set and a test data set based on the operating condition monitoring data;

[0056] S300, extracting characteristic values ​​of the operating condition monitoring data;

[0057] S400, fitting a corresponding conversion relationship between characteristic values ​​of the operating condition monitoring data in the test data set and a target internal leakage amount through a multivariate nonlinear regression analysis model;

[0058] S500, using the least squares method to estimate the parameters of the multivariate nonlinear regression analysis model;

[0059] S600, using the test data set to test the accuracy of the multivariate nonlinear regression analysis model, and using the multivariate nonlinear regression analysis model that meets the accuracy requirements to calculate the internal leakage of the hydraulic cylinder of the hydropower unit servomotor;

[0060] S700, based on fault threshold indicators, realizes quantitative diagnosis and graded warning of leakage faults in the hydraulic cylinder of the relay of hydropower units.

[0061] The specific implementation is as follows:

[0062] S100, collecting operating condition monitoring data of the hydraulic cylinder of the hydropower unit servomotor.

[0063] In this embodiment, the operating condition monitoring data includes the following three categories:

[0064] The first category is the historical monitoring data of the hydraulic cylinder of the hydropower unit relay, including pressure P1, piston rod displacement x1 and oil temperature T1. (P3, x3, T3, Q3)

[0065] The second category is the multi-operating condition test data of the hydropower unit relay test bench, including multi-operating condition pressure P2, piston rod displacement x2, oil temperature T2 and internal leakage Q2.

[0066] The third category is simulation data generated by the high-fidelity governor simulation model, including multi-condition pressure P3, piston rod displacement x3, oil temperature T3 and internal leakage Q3.

[0067] For example, existing sensors are deployed and available for collecting operating condition monitoring data. Simulation data is derived from a high-fidelity governor simulation model of the turbine governor system, which can be used to simulate the operating data of the turbine servomotor under extreme operating conditions. This expands the data sources for multiple operating conditions and improves the stability and reliability of the multivariate nonlinear regression analysis model fit. The servomotor test bench can be used to calibrate the simulation model to ensure accuracy and provide high-quality data. All types of data are time series.

[0068] S200: Producing a test dataset and a test dataset based on the operating condition monitoring data. The complete dataset is composed of the historical operating monitoring data of the hydropower unit servo hydraulic cylinder, the multi-operating condition test data from the hydropower unit servo test bench, and a large amount of simulation data generated by a high-fidelity governor simulation model. The dataset is divided into the test dataset and the test dataset in a certain proportion.

[0069] S300: extracting characteristic values ​​of the operating condition monitoring data.

[0070] In this embodiment, the characteristic values ​​of monitoring variables such as pressure, displacement, and temperature are extracted. Since internal leakage will affect the pressurization process, the actual loading pressure p y (t) Deviation from the initial preset pressure P y (0), thereby affecting the displacement of the piston rod and causing abnormal changes in the oil temperature. Therefore, in this embodiment, the absolute value of the difference between the operating condition monitoring data and the corresponding initial preset value is used as the corresponding characteristic value, which is as follows:

[0071] The steady-state pressure p during the actual loading time y (t) and the initial preset pressure P y The absolute value of the difference between (0) is the pressure characteristic value, as shown in formula (1);

[0072] The piston rod displacement x within the actual loading time y (t) and the initial preset displacement x y The absolute value of the difference between (0) is taken as the displacement characteristic value, as shown in formula (2);

[0073] The oil temperature T during the actual loading time y (t) and the initial preset temperature T y The absolute value of the difference between (0) and (1) is taken as the temperature characteristic value, as shown in formula (3).

[0074] ΔP=|P y (t)-P y (0)| (1)

[0075] Δx=|x y (t)-x y (0)| (2)

[0076] ΔT=|T y (t)-T y (0)| (3)

[0077] Among them, y=1, 2, 3.

[0078] S400 , fitting a corresponding conversion relationship between characteristic values ​​of the operating condition monitoring data in the test data set and a target value of internal leakage through a multivariate nonlinear regression analysis model.

[0079] A regression model is a statistical analysis method used to study the relationship between independent variables (explanatory variables) and dependent variables (explained variables). By establishing mathematical equations to quantify the dependencies between variables, it is possible to predict and explain the dependent variable. Common regression models include linear regression, polynomial regression, and logistic regression. Regression models are widely used in fields such as forecasting and data analysis, providing a scientific basis for decision-making.

[0080] In this embodiment, it is assumed that there is a certain nonlinear relationship between the characteristic values ​​of the operating condition monitoring data such as pressure, displacement, and temperature and the internal leakage amount. Therefore, the corresponding conversion relationship between the characteristic values ​​of the operating condition monitoring data in the test data set and the target value internal leakage amount is fitted by a multivariate nonlinear regression analysis model, as shown in formula (4), where the data distribution fitting diagram is shown in FIG. Figure 2 shown.

[0081] Q=f[(ΔP,Δx,ΔT),θ]+μ (4)

[0082] Where f(.) is a multivariate nonlinear function, Q is the internal leakage, θ is an unknown parameter, and μ is a random error term.

[0083] S500, using the least squares method to estimate the parameters of the multivariate nonlinear regression analysis model.

[0084] The least squares method is the most commonly used estimation method. In order to make the sample regression model as close as possible to the overall regression model, the ordinary least squares estimation is achieved by minimizing the sum of squared errors. In this embodiment, the monitoring data of the internal leakage amount includes the internal leakage amount Q2 in the multi-condition test data and the internal leakage amount Q3 in the simulation data. The fitting value of the corresponding internal leakage amount calculated according to the multivariate nonlinear regression analysis model is The error between the internal leakage monitoring data and the corresponding fitting value is expressed as:

[0085]

[0086] Where, is the i-th monitoring value Q of the internal leakage Q2 in the multi-condition test data 2i The corresponding fitting value, n is the number of monitoring data of internal leakage Q2 in the multi-condition test data; is the jth simulation value Q of the internal leakage Q3 in the simulation data 3i The corresponding fitting value, m is the number of simulation data of internal leakage Q2 in the simulation data.

[0087] The least squares method requires that the sum of squared errors be minimized, that is, the sum of squared errors between the monitoring data of the internal leakage amount and the corresponding fitting value is required to be minimized. The sum of squared errors is shown in formula (6).

[0088]

[0089] By solving min∑e 2 The parameter value that minimizes the sum of squared errors is the desired parameter estimate.

[0090] S600, using the test data set to test the accuracy of the multivariate nonlinear regression analysis model; if the accuracy does not meet the requirements, reconfirming the form of the regression equation in the multivariate nonlinear regression analysis model until a multivariate nonlinear regression analysis model that meets the accuracy requirements is obtained; and calculating the internal leakage of the hydraulic cylinder of the hydropower unit relay using the multivariate nonlinear regression analysis model that meets the accuracy requirements.

[0091] In this embodiment, the specific judgment index of the excellence of the multivariate nonlinear regression analysis model is the determination coefficient, which is expressed as R 2 It means that when the regression square sum SSR is larger, the regression effect is better. The basic idea of ​​this method is to compare the ratio of the variance explained by the multivariate nonlinear regression analysis model to the total variance, as shown in Equation (7) and Equation (8).

[0092]

[0093] Where:

[0094] is the total sum of squares SST;

[0095] is the regression sum of squares SSR;

[0096] is the residual sum of squares SSE.

[0097] It can be further simplified to SST=SSR+SSE.

[0098]

[0099] S700, based on fault threshold indicators, realizes quantitative diagnosis and graded warning of leakage faults in the hydraulic cylinder of the relay of hydropower units.

[0100] The fault threshold indicators can be established based on relevant standards, such as the machinery industry standard "Technical Specifications for Guide Vane Servomotors for Large and Medium-Sized Hydraulic Turbines," or enterprise specifications. In this embodiment, there are two types of faults. Therefore, the fault threshold indicators include an internal leakage threshold indicator Q and a macro guide vane opening deviation threshold indicator B. The corresponding fault classification table is shown in Table 1.

[0101] Table 1, fault classification table in this embodiment:

[0102]

[0103] In Table 1, Level 0 indicates a normal state with no internal leakage, Level 1 indicates a slight internal leakage that does not affect normal operation, but requires an early warning and maintenance preparation plan, and Level 2 indicates a serious internal leakage that requires immediate shutdown for maintenance. Specific levels can be further divided as needed.

[0104] The calculation formula of guide vane opening deviation is shown in formula (9):

[0105]

[0106] Where K s is the actual monitoring value of the guide vane opening, and K0 is the system preset target opening.

[0107] In this embodiment, a multi-dimensional fault quantitative graded warning is achieved by integrating the internal leakage threshold index and the macro guide vane opening deviation threshold index, such as Figure 3 As shown, the overall performance of the equipment can be further comprehensively characterized, the detection accuracy of micro-internal leakage can be improved, and the stable operation of the unit can be guaranteed.

[0108] Based on the same technical concept, an embodiment of the present invention also provides an electronic device that can implement the comprehensive diagnosis and early warning method process of the relay internal leakage fault provided by the above embodiment of the present invention. In one embodiment, the electronic device can be a server, or a terminal device or other electronic device. Figure 4 As shown, the electronic device may include:

[0109] At least one processor, and a memory connected to the at least one processor. The embodiment of the present invention does not limit the specific connection medium between the processor and the memory. Figure 4 The example in this article is that the processor and memory are connected via a bus. Figure 4 The connections between the other components are shown in bold lines, which are only for illustration and not intended to be limiting. The bus can be divided into address bus, data bus, control bus, etc. Figure 4 The processor is represented by a single thick line, but this does not mean that there is only one bus or only one type of bus. Alternatively, the processor can also be called a controller, without any limitation on the name.

[0110] In an embodiment of the present invention, the memory stores instructions that can be executed by at least one processor. The at least one processor can execute the above-mentioned comprehensive diagnosis and early warning method for internal leakage fault of a relay by executing the instructions stored in the memory. The processor can implement Figure 4 The functions of each module in the device shown.

[0111] Among them, the processor is the control center of the device, which can use various interfaces and lines to connect the various parts of the entire control device, and monitor the device as a whole by running or executing instructions stored in the memory and calling data stored in the memory, the various functions of the device and processing data.

[0112] In an optional design, the processor may include one or more processing units, and the processor may integrate an application processor and a modem processor, wherein the application processor primarily processes the operating system, user interface, and application programs, and the modem processor primarily processes wireless communications. It is understood that the modem processor may not be integrated into the processor. In some embodiments, the processor and memory may be implemented on the same chip, or in some embodiments, they may be implemented on separate chips.

[0113] The processor can be a general-purpose processor, such as a CPU, digital signal processor, application-specific integrated circuit, field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, and can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the comprehensive diagnosis and early warning method for internal leakage faults in a relay disclosed in the embodiments of the present invention can be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0114] As a non-volatile computer-readable storage medium, memory can be used to store non-volatile software programs, non-volatile computer executable programs and modules. Memory can include at least one type of storage medium, for example, can include flash memory, hard disk, multimedia card, card-type memory, random access memory (Random Access Memory, RAM), static random access memory (Static Random Access Memory, SRAM), programmable read-only memory (Programmable Read Only Memory, PROM), read-only memory (Read Only Memory, ROM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), magnetic memory, disk, optical disk, etc. Memory is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory in the embodiment of the present invention can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0115] By designing and programming a processor, the code corresponding to the comprehensive diagnosis and early warning method for internal leakage faults in a relay described in the aforementioned embodiment can be embedded in the chip, enabling the chip to execute the steps of the method described in the aforementioned embodiment during operation. Designing and programming a processor is well known to those skilled in the art and will not be further described here.

[0116] Based on the same inventive concept, an embodiment of the present invention further provides a storage medium storing computer instructions. When the computer instructions are executed on a computer, the computer executes the comprehensive diagnosis and early warning method for internal leakage faults of a relay discussed above.

[0117] In some optional embodiments, the present invention also provides various aspects of a comprehensive diagnosis and early warning method for internal leakage faults in a relay, which can also be implemented in the form of a program product, which includes program code. When the program product is run on an apparatus, the program code is used to cause the control device to execute the steps of a comprehensive diagnosis and early warning method for internal leakage faults in a relay according to various exemplary embodiments of the present invention described above in this specification.

[0118] It should be noted that although several units or subunits of the device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of a unit described above can be further divided into multiple units to be embodied. In addition, although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0119] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0120] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a server, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] Program code for performing the operations of the present invention may be written using any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0122] Where a remote computing device is involved, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0123] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0125] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A comprehensive diagnosis and early warning method for internal leakage faults in a relay, characterized in that: include: Collect operating condition monitoring data of the hydraulic cylinder of the hydropower unit servomotor; Producing an experimental data set and a test data set based on the operating condition monitoring data; Extracting characteristic values ​​of the operating condition monitoring data; The corresponding conversion relationship between the characteristic value of the operating condition monitoring data in the test data set and the target value internal leakage is fitted by a multivariate nonlinear regression analysis model; The least square method is used to estimate the parameters of the multivariate nonlinear regression analysis model; Using the test data set to test the accuracy of the multivariate nonlinear regression analysis model, and using the multivariate nonlinear regression analysis model that meets the accuracy requirements to calculate the internal leakage of the hydraulic cylinder of the hydropower unit relay; Based on the fault threshold index, quantitative diagnosis and graded early warning of leakage faults in the hydraulic cylinder of the hydropower unit relay are realized.

2. The comprehensive diagnosis and early warning method for internal leakage fault of a servomotor according to claim 1, characterized in that: The operating condition monitoring data includes the following three categories: The first category is the operation history monitoring data of the hydraulic cylinder of the hydropower unit relay, including pressure P1, piston rod displacement x1 and oil temperature T1; The second category is the multi-operating condition test data of the hydropower unit relay test bench, including multi-operating condition pressure P2, piston rod displacement x2, oil temperature T2 and internal leakage Q2; The third category is simulation data generated by the high-fidelity governor simulation model, including multi-condition pressure P3, piston rod displacement x3, oil temperature T3 and internal leakage Q3.

3. The comprehensive diagnosis and early warning method for internal leakage fault of a servomotor according to claim 2, characterized in that: The absolute value of the difference between the operating condition monitoring data and the corresponding initial preset value is used as the corresponding characteristic value, including the pressure characteristic value, the displacement characteristic value and the temperature characteristic value.

4. The comprehensive diagnosis and early warning method for internal leakage fault of a servomotor according to claim 3, characterized in that: The multivariate nonlinear regression analysis model is expressed as: Q=f[(ΔP, Δx, ΔT),θ]+μ Where f(.) is a multivariate nonlinear function, ΔP is the pressure eigenvalue, Δx is the displacement eigenvalue, ΔT is the temperature eigenvalue, Q is the internal leakage, θ is an unknown parameter, and μ is the random error term.

5. The comprehensive diagnosis and early warning method for internal leakage fault of a servomotor according to claim 4, characterized in that: The method of least squares is used to estimate the parameters of the multivariate nonlinear regression analysis model, including: By solving minΣe 2 The parameter value that minimizes the sum of squared errors is the desired parameter estimate; the sum of squared errors is expressed as: Where, is the i-th monitoring value Q of the internal leakage Q2 in the multi-condition test data 2i The corresponding fitting value, n is the number of monitoring data of internal leakage Q2 in the multi-condition test data; is the jth simulation value Q of the internal leakage Q3 in the simulation data 3i The corresponding fitting value, m is the number of simulation data of internal leakage Q2 in the simulation data.

6. The comprehensive diagnosis and early warning method for internal leakage fault of a servomotor according to claim 1, characterized in that: The coefficient of determination is used as a judgment indicator for the accuracy test of the multivariate nonlinear regression analysis model; The coefficient of determination R 2 Expressed as: in: SST is the total sum of squares, expressed as SSR is the regression sum of squares, expressed as SSE is the residual sum of squares, expressed as 7. The comprehensive diagnosis and early warning method for internal leakage fault of a servomotor according to claim 1, characterized in that: The fault threshold index includes an internal leakage threshold index; for the calculated internal leakage of the hydraulic cylinder of the hydropower unit relay, quantitative diagnosis and graded warning are performed by presetting different internal leakage threshold ranges corresponding to different fault grades.

8. The comprehensive diagnosis and early warning method for internal leakage fault of a servomotor according to claim 7, characterized in that: The fault threshold index also includes a guide vane opening deviation threshold index; by presetting different guide vane opening deviation threshold ranges corresponding to different fault grades, the internal leakage threshold index and the guide vane opening deviation threshold index are integrated to perform quantitative diagnosis and graded warning.

9. An electronic device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor executes the method according to any one of claims 1 to 8 by executing the instructions stored in the memory.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store instructions, and when the instructions are executed, the method according to any one of claims 1 to 8 is implemented.

Images