Executor leakage fault diagnosis method and device, storage medium and electronic equipment

Abstract

The invention discloses an actuator leakage fault diagnosis method and device, a storage medium and electronic equipment. Relates to the technical field of actuator fault diagnosis. The method comprises the steps of obtaining first output data and second output data of a to-be-diagnosed actuator under a current working condition, the first output data being actual response data of the to-be-diagnosed actuator under an excitation signal, and the second output data being actual response data of the to-be-diagnosed actuator under an excitation signal; the second output data is output data, under the excitation signal, of the to-be-diagnosed actuator obtained through prediction of a preset output prediction model, and the preset output prediction model is used for predicting output of the actuator under the condition of no leakage fault; obtaining an output difference value based on the first output data and the second output data; and determining a fault diagnosis result according to a preset leakage fault diagnosis model based on the current working condition and the output difference value. The influence of working conditions on leakage faults is fully considered, and the accuracy of leakage fault diagnosis is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of actuator fault diagnosis, in particular to an actuator leakage fault diagnosis method, an actuator leakage fault diagnosis device, a machine readable storage medium and an electronic device. BACKGROUND

[0002] An actuator is a key component of industrial equipment, which is used to convert a control signal into an actual physical action, so as to realize various functions of the industrial equipment. The actuator includes a hydraulic cylinder, a hydraulic motor, various hydraulic valves, etc. The actuator leakage fault diagnosis has important guiding significance for formulating an active maintenance strategy of the actuator and ensuring safe and reliable operation of construction equipment such as engineering machinery.

[0003] For example, the hydraulic cylinder is widely used as an actuator of engineering machinery. In extreme high and low temperature, high pressure, high impact, high dust, water-rich and other harsh service environments, typical faults such as leakage, component damage and abnormal action frequently occur. Among them, the leakage fault is the most common fault mode of the hydraulic cylinder, and is also the root cause of the fault phenomena such as low-speed crawling, power deficiency and poor pressure maintaining performance of the hydraulic cylinder. Real-time monitoring of the leakage type and level of the hydraulic cylinder is of great significance to ensure its running accuracy, reliability and efficient and safe implementation of the project.

[0004] The existing actuator leakage fault diagnosis methods mainly include bench testing, expert prior knowledge and data-driven methods. The bench testing process is complex and has poor on-site applicability. The method based on expert prior knowledge has difficulty in horizontal expansion application. The data-driven method has strong correlation between fault feature values and working conditions, strong subjectivity in fault feature selection and insufficient feature extraction, and has difficulty in application. These methods all have the problem of low accuracy of leakage fault diagnosis. SUMMARY

[0005] The purpose of the embodiments of the present application is to provide an actuator leakage fault diagnosis method, an actuator leakage fault diagnosis device, a machine readable storage medium and an electronic device, to solve the problem of low accuracy of leakage fault diagnosis in the prior art.

[0006] In order to achieve the above-mentioned purpose, the first aspect of the present application provides an actuator leakage fault diagnosis method, comprising: obtaining first output data and second output data of a to-be-diagnosed actuator under a current working condition, the first output data being actual response data of the to-be-diagnosed actuator under an excitation signal, and the second output data being output data of the to-be-diagnosed actuator under the excitation signal obtained by using a preset output prediction model, the preset output prediction model being used to predict the output of the actuator under no leakage fault; obtaining an output difference value based on the first output data and the second output data; Based on the current working condition and the output difference value, a fault diagnosis result is determined according to a preset leakage fault diagnosis model.

[0007] In the embodiments of the present application, the construction process of the preset output prediction model comprises: Actual output data corresponding to the first test excitation under each working condition of the hydraulic system without leakage fault is obtained. The output corresponding to the first test excitation under each working condition is predicted by using the preset hydraulic system mathematical model, to obtain predicted output data corresponding to the first test excitation under each working condition. Based on the actual output data and the predicted output data corresponding to the first test excitation under each working condition, the preset hydraulic system mathematical model is adjusted to obtain an output prediction model.

[0008] In the embodiments of the present application, the preset hydraulic system mathematical model comprises a hydraulic system state space model and an optimization module. The output corresponding to the first test excitation under each working condition is predicted by using the preset hydraulic system mathematical model, to obtain predicted output data corresponding to the first test excitation under each working condition, comprising: The first test excitation under each working condition is input into the hydraulic system state space model respectively, to obtain initial predicted data corresponding to the first test excitation under each working condition. The initial predicted data corresponding to the first test excitation under each working condition is optimized by using the optimization module, to obtain predicted output data corresponding to the first test excitation under each working condition.

[0009] In the embodiments of the present application, the construction process of the preset leakage fault diagnosis model comprises: Response data and predicted response data corresponding to the second test excitation under each working condition of each first test actuator are obtained, the predicted response data being output data corresponding to the second test excitation under each working condition of each first test actuator predicted by using the preset output prediction model, each first test actuator being provided with a fault seal with different damage scales, the leakage fault levels corresponding to each first test actuator being different. Based on the response data and the predicted response data corresponding to the second test excitation under each working condition of each first test actuator, leakage fault threshold values corresponding to each leakage fault level under each working condition are determined. Based on the each working condition, each leakage fault level and the leakage fault threshold values corresponding to each leakage fault level under each working condition, a leakage fault diagnosis model is constructed.

[0010] In the embodiments of the present application, further comprising: obtain the leakage amount of each first test actuator under a fault diagnosis working condition, the fault diagnosis working condition being a working condition combination with the highest frequency in a working process of the actuator to be diagnosed under preset boundary conditions, the working condition combination at least including pressure, speed and temperature; determine the fault level corresponding to each first test actuator based on the leakage amount of each first test actuator under the fault diagnosis working condition.

[0011] In the embodiments of the present application, further comprising: obtain the leakage amount threshold of the actuator to be diagnosed; obtain the leakage amount of a second test actuator under a fault diagnosis working condition, the second test actuator being provided with a damaged sealing element; determine a sealing element damage threshold based on the leakage amount of the second test actuator under the fault diagnosis working condition and the leakage amount threshold; determine a plurality of sealing element damage sizes based on the sealing element damage threshold, to obtain fault sealing elements with different damage sizes.

[0012] In the embodiments of the present application, the fault diagnosis result is determined based on the current working condition and the output difference value according to a preset leakage fault diagnosis model, comprising: determine whether the output difference value exceeds a preset threshold value; determine the fault diagnosis result based on the current working condition and the output difference value according to a preset leakage fault diagnosis model in a case where it is determined that the output difference value exceeds the preset threshold value.

[0013] In the embodiments of the present application, the preset leakage fault diagnosis model is a relationship database of working condition, leakage fault threshold and leakage fault level.

[0014] The second aspect of the present application provides an actuator leakage fault diagnosis device, comprising: an obtaining module, configured to obtain first output data and second output data of an actuator to be diagnosed under a current working condition, the first output data being actual response data of the actuator to be diagnosed under an excitation signal, and the second output data being output data of the actuator to be diagnosed under the excitation signal predicted by a preset output prediction model, the preset output prediction model being used to predict the output of an actuator under no leakage fault; a calculating module, configured to obtain an output difference value based on the first output data and the second output data; a diagnosis module, configured to determine a fault diagnosis result based on the current working condition and the output difference value according to a preset leakage fault diagnosis model.

[0015] The third aspect of the present application provides an electronic device, which comprises: at least one processor; a memory connected with the at least one processor; The memory stores instructions executable by the at least one processor, and the at least one processor implements the actuator leakage fault diagnosis method by executing the instructions stored in the memory.

[0016] The fourth aspect of the present application provides a machine readable storage medium, which stores instructions, and the instructions, when executed by a processor, cause the processor to be configured to execute the actuator leakage fault diagnosis method.

[0017] According to the above technical solution, the first output data and the second output data of the to-be-diagnosed actuator under the current working condition are obtained, the first output data is the actual response data of the to-be-diagnosed actuator under the excitation signal, the second output data is the output data of the to-be-diagnosed actuator under the excitation signal predicted by using a preset output prediction model, and the preset output prediction model is used to predict the output of the actuator under no leakage fault; based on the first output data and the second output data, an output difference value is obtained; and based on the current working condition and the output difference value, a fault diagnosis result is determined according to a preset leakage fault diagnosis model. The first output data is the actual response data, the second output data is the predicted output data under no leakage fault, and the first output data and the second output data are obtained under the same working condition and excitation signal, so that the output difference value can better reflect the actual fault characteristics of the to-be-diagnosed actuator. The working condition parameters affect the sealing leakage level, and then affect the output difference value. By combining the output difference value and the current working condition, the influence of the working condition on the leakage fault is fully considered when the fault diagnosis is performed, and the accuracy of the leakage fault diagnosis is improved.

[0018] Other features and advantages of the embodiments of the present application will be described in detail in the following specific implementation part. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings are included to provide a further understanding of the embodiments of the present application, and constitute a part of the specification, and are used to explain the embodiments of the present application together with the following specific implementation, but do not constitute a limitation to the embodiments of the present application. In the drawings: Figure 1 A flowchart of an actuator leakage fault diagnosis method according to an embodiment of the present application is schematically shown; Figure 2 A schematic diagram of a man-made pre-prepared fault sealing member damage range according to an embodiment of the present application is schematically shown; Figure 3A schematic diagram of a hydraulic cylinder leakage fault diagnosis scheme development process based on a mechanism model according to an embodiment of the present application is shown; Figure 4 A schematic diagram of a hydraulic cylinder leakage fault diagnosis method flowchart based on a mechanism model according to an embodiment of the present application is shown; Figure 5 A schematic diagram of an actuator leakage fault diagnosis device according to an embodiment of the present application is shown; Figure 6 A schematic diagram of the internal structure of a computer device according to an embodiment of the present application is shown.

[0020] Explanation of reference numerals 410 - acquisition module; 420 - calculation module; 430 - diagnosis module; A01 - processor; A02 - network interface; A03 - internal memory; A04 - display screen; A05 - input device; A06 - non-volatile storage medium; B01 - operating system; B02 - computer program. DETAILED DESCRIPTION

[0021] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. It should be understood that the specific embodiments described herein are only used to explain and illustrate the embodiments of the present application and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0022] It should be noted that the acquisition, transmission, storage, use, processing, etc. of data in the technical solutions of the present application comply with relevant provisions of national laws and regulations. In the embodiments of the present application, some industry existing solutions, components, models, etc. may be mentioned, which should be considered as exemplary, and the purpose is only to illustrate the feasibility of the implementation of the technical solutions of the present application, but it does not mean that the applicant has or will necessarily use the solutions.

[0023] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative positional relationship, movement, etc. between components in a certain posture (as shown in the drawings), and if the certain posture changes, the directional indications also change accordingly.

[0024] In addition, if the description of "first", "second" and the like is involved in the embodiments of the present application, the description of "first", "second" and the like is only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features limited by "first", "second" can be explicitly or implicitly included at least one of the features. In addition, the technical solutions of various embodiments can be combined with each other, but it must be based on the realization of ordinary skilled in the art, when the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, nor in the protection scope claimed by the present application.

[0025] Please refer to Figure 1 , Figure 1 The flowchart of the actuator leakage fault diagnosis method according to the embodiments of the present application is schematically shown. The embodiments provide an actuator leakage fault diagnosis method, which measures the pressure output difference extreme value of the unknown leakage fault hydraulic system under the excitation signal and the high-precision prediction model of the pre-established fault-free hydraulic system under the same working condition, judges the leakage type and grade according to the pre-established diagnosis rule. It can be applied to hydraulic cylinders, hydraulic motors, various hydraulic valves and other actuators. In order to facilitate the description of the scheme, the embodiments mainly take the actuators in working machines as an example for detailed description, and further take the hydraulic cylinder as an example for detailed description.

[0026] The embodiments provide an actuator leakage fault diagnosis method, which includes the following steps: Step 210: obtaining the first output data and the second output data of the actuator to be diagnosed under the current working condition, the first output data being the actual response data of the actuator to be diagnosed under the excitation signal, and the second output data being the output data of the actuator to be diagnosed under the excitation signal predicted by the pre-set output prediction model, the pre-set output prediction model being used to predict the output of the actuator under no leakage fault; Step 220: obtaining the output difference value based on the first output data and the second output data; Step 230: determining the fault diagnosis result according to the pre-set leakage fault diagnosis model based on the current working condition and the output difference value.

[0027] By the technical solution, the first output data of the to-be-diagnosed actuator under the current working condition is obtained, the first output data is actual response data of the to-be-diagnosed actuator under an excitation signal, the second output data is output data of the to-be-diagnosed actuator under the excitation signal predicted by using a preset output prediction model, and the preset output prediction model is used to predict the output of an actuator under a non-leakage fault; based on the first output data and the second output data, an output difference value is obtained; and based on the current working condition and the output difference value, a fault diagnosis result is determined according to a preset leakage fault diagnosis model. The first output data is actual response data, the second output data is predicted output data under a non-leakage fault, and the first output data and the second output data are obtained under the same working condition and excitation signal, so that the output difference value can better reflect the actual fault characteristics of the to-be-diagnosed actuator. The working condition parameter affects the leakage level of the sealing element, and then affects the output difference value. By combining the output difference value and the current working condition, the influence of the working condition on the leakage fault is fully considered when the fault diagnosis is performed, and the accuracy of the leakage fault diagnosis is improved.

[0028] The first output data and the current working condition can be detected, and the second output data can be predicted by using the preset output prediction model, so that the leakage fault diagnosis is relatively simple and convenient.

[0029] In step 210, the excitation signal can be a displacement input signal in the form of a step, a slope, a sine, a rectangle, a triangle wave, etc. The first output data can be response data such as pressure and displacement of the to-be-diagnosed actuator, and correspondingly, the second output data can be predicted output data such as pressure and displacement. Among them, the power requirement and cost are relatively low when taking the pressure time domain response difference under the step and slope displacement signal as the diagnosis standard. The first output data can be obtained by installing a sensor, and the second output data can be predicted by inputting the first excitation signal to the preset output prediction model. The preset output prediction model can be constructed in advance. Taking a hydraulic cylinder as an example, the pressure and temperature of the hydraulic cylinder are collected by pre-installed pressure and temperature sensors to obtain the current working condition, and the actual pressure response of the hydraulic cylinder under unknown leakage fault types and levels under step and slope signals is measured to obtain the first output data.

[0030] In some embodiments, the construction process of the preset output prediction model includes: First, the actual output data corresponding to the first test excitation of the non-leakage fault hydraulic system under each working condition is obtained; In the embodiment, the first test excitation described above can be a displacement input signal in the form of a step, a ramp, a sine, a rectangle, a triangle wave, etc. The actual output data can be obtained by detecting the hydraulic system with no leakage fault under various working conditions, and can be output data such as pressure and displacement.

[0031] It should be noted that which kind of output data is used as the actual output data when the output prediction model is constructed, and correspondingly, the second output data uses the corresponding kind of output data. For example, when the output prediction model is constructed, pressure is used as the actual output data, and the second output data is pressure data.

[0032] Then, the output corresponding to the first test excitation under each working condition is predicted by using the preset hydraulic system mathematical model, to obtain the predicted output data corresponding to the first test excitation under each working condition; In the embodiment, the preset hydraulic system mathematical model is an output prediction model of a hydraulic system without fault, which can be obtained by constructing a neural network model, etc., or can be composed of a hydraulic system state space model and an optimization module. The prediction can be to predict the corresponding output data by taking the first test excitation under each working condition as input, to obtain the predicted data.

[0033] In some embodiments, the preset hydraulic system mathematical model includes a hydraulic system state space model and an optimization module; correspondingly, the prediction of the output corresponding to the first test excitation under each working condition by using the preset hydraulic system mathematical model to obtain the predicted output data corresponding to the first test excitation under each working condition includes: Firstly, the first test excitation under each working condition is input into the hydraulic system state space model respectively, to obtain the initial predicted data corresponding to the first test excitation under each working condition; In the embodiment, the hydraulic system state space model is a mathematical model used to describe the dynamic characteristics of the hydraulic system. Taking an actuator as an example, the hydraulic system state space model can be established according to the flow formula of the valve port of the electromagnetic reversing valve of the hydraulic system and the force balance equation, the flow continuity equation and the force balance equation of the hydraulic cylinder, etc. The hydraulic system state space model can be expressed as: , wherein, is the valve port flow coefficient; is the oil density; is the valve port circumference; is the spool displacement; , is the pressure of the two cavities; is the system pressure; is the piston area of the hydraulic cylinder; is the mass of the spool. is the spool viscous damping coefficient of the valve; is the spool spring stiffness of the valve; is the hydraulic cylinder piston and load mass; is the hydraulic cylinder piston viscous damping coefficient; is the hydraulic cylinder time-varying dynamic and static friction and external load, which can be estimated by an extended Kalman filter algorithm, is the hydraulic valve spool displacement, is the hydraulic cylinder chamber pressure , is the hydraulic cylinder another chamber pressure , is the hydraulic cylinder piston motion acceleration, is the derivative of the hydraulic cylinder piston motion acceleration, is the hydraulic cylinder piston motion speed, is the hydraulic cylinder load, is the hydraulic cylinder chamber initial volume, is the hydraulic cylinder another chamber initial volume, is the valve port circumference, is the electromagnetic directional valve input current, is the ratio coefficient of the electromagnetic directional valve input current and the spool control force. In a specific implementation, a certain pressure-velocity-temperature working condition combination can be selected in a load spectrum, and then model parameters are set in combination with hydraulic system element structure parameters and experience coefficients corresponding to the first test excitation under the working condition. The initial prediction data, including multiple state parameters, can be predicted by the hydraulic system state space model.

[0034] Secondly, the optimization module is used to optimize the initial prediction data corresponding to the first test excitation under the various working conditions to obtain prediction output data corresponding to the first test excitation under the various working conditions.

[0035] In the embodiment, the above-mentioned hydraulic system state space model is a mathematical model for describing the dynamic characteristics of the hydraulic system. Considering that the no-leakage fault hydraulic system will also have a dynamic load and be affected by nonlinear factors, in order to make the output prediction model closer to the actual no-leakage fault hydraulic system, the initial prediction data can be further optimized. The optimization module can be constructed by using an extended Kalman filter, an unscented Kalman filter, a particle filter and the like, and is used to linearize and approximate the initial prediction data to realize real-time estimation of the system state.

[0036] Taking the actuator as a hydraulic cylinder and the optimization module constructed by using the extended Kalman filter algorithm as an example, in the state prediction and state update stages of the extended Kalman filter algorithm, the system state variables and covariance matrices thereof can be represented as: , , In the formula: is the state variable value calculated according to the system mathematical model at the moment, is the system mathematical model, is the system state variable value after correction at the moment, is the system input at the moment, is the system covariance matrix at the moment, is the system covariance matrix after correction at the moment, is the system prediction Jacobian matrix at the moment, is the system prediction noise at the moment; is the Kalman gain, is the system measurement matrix at the moment, is the system measurement noise at the moment, is the system state variable value after correction at the moment, is the system measured variable value at the moment, is the conversion matrix for converting the system state variable value into the measured variable, is the system covariance matrix after correction at the moment.

[0037] Finally, based on the actual output data and the predicted output data corresponding to the first test excitation under each working condition, the preset hydraulic system mathematical model is adjusted to obtain an output prediction model.

[0038] In this embodiment, for each working condition, the parameters of the hydraulic system mathematical model can be adjusted to make the actual output data close to the predicted output data, for example, the difference between the two can be within a preset range (e.g., 5%). The above process is repeated until the actual output data and the predicted output data under all working condition combinations in the load spectrum are less than the preset range, thereby obtaining the output prediction model.

[0039] It should be noted that the adjustment of the preset hydraulic system mathematical model can be adjustment of the parameters in the hydraulic system state space model, or adjustment of the parameters of the optimization module, which is determined according to the actual situation.

[0040] In the above example, a certain pressure-velocity-temperature working condition combination is selected in the load spectrum, the model parameter initial value is set in combination with the hydraulic system element structure parameter and the experience coefficient, then for each working condition, the system prediction noise and the measurement noise is adjusted so that the difference between the actual output data and the predicted output data is less than 5% of the preset range, and finally the output prediction model is obtained. The output of the hydraulic system mathematical model is corrected by using the extended Kalman filtering algorithm, so as to have the load estimation and nonlinear factor compensation functions, and the actual pressure response of the hydraulic system without leakage failure can be accurately reflected.

[0041] By respectively inputting the first test excitation under each working condition into the hydraulic system state space model, the initial prediction data corresponding to the first test excitation under each working condition is obtained, the initial prediction data corresponding to the first test excitation under each working condition is optimized by using the optimization module, and the prediction output data corresponding to the first test excitation under each working condition is obtained. Based on the actual output data and the prediction output data corresponding to the first test excitation under each working condition, the preset hydraulic system mathematical model is adjusted to obtain an output prediction model. The optimization module can optimize the output of the hydraulic system state space model to realize real-time estimation of the system state, and then adjust the hydraulic system mathematical model in combination with the actual output data, so that the prediction output data obtained by real-time estimation of the system state is close to the actual output data, thereby improving the accuracy of the output prediction model and helping to accurately predict the output of the actuator under the no-leakage failure.

[0042] It should be noted that the above output prediction model can also be obtained by a machine learning algorithm, for example, the output prediction model can be obtained by using a neural network algorithm, a neural network model is first constructed, then the input features under the first test excitation under each working condition are used to predict the prediction output data by using the neural network model, and then the parameters of the neural network model are adjusted according to the actual output data and the prediction output data to obtain the output prediction model. The specific construction process can be realized by using the prior art, and will not be described here.

[0043] The actual output data corresponding to the first test excitation under each working condition is obtained, the output corresponding to the first test excitation under each working condition is predicted by using the preset mathematical model of the hydraulic system, the predicted output data corresponding to the first test excitation under each working condition is obtained, and the preset mathematical model of the hydraulic system is adjusted based on the actual output data and the predicted output data corresponding to the first test excitation under each working condition, so that the predicted output data is close to the actual output data, thereby obtaining a high-precision output prediction model of a fault-free hydraulic system, and the output of the fault-free hydraulic system can be more accurately predicted.

[0044] In step 220, the output difference value can be obtained by calculating the difference between the first output data and the second output data. Since the second output data is the predicted output data under the no-leakage fault, it is equivalent to a reference value, and the actual fault characteristics of the current output to be diagnosed actuator can be reflected by calculating the output difference value.

[0045] In step 230, the preset leakage fault diagnosis model is used for fault diagnosis according to the current working condition and the output difference value. The preset leakage fault diagnosis model can be obtained in advance.

[0046] In some embodiments, the construction process of the preset leakage fault diagnosis model includes: First, the response data and the predicted response data corresponding to the second test excitation under each working condition of each first test actuator are obtained, the predicted response data is the output data of the first test actuator under each working condition corresponding to the second test excitation, which is predicted by using the preset output prediction model, each first test actuator is provided with a fault seal with different damage scales, and the leakage fault levels of the first test actuators are different. In this embodiment, the first test actuators are of the same type as the actuators to be diagnosed, each first test actuator can be a new actuator assembled with a man-made fault seal with different leakage fault levels, or an actuator with a used fault seal with different leakage fault levels. The response data of each first test actuator under each working condition corresponding to the second test excitation can be obtained by a sensor installed on the first test actuator. The second test excitation signal can be a displacement input signal in the form of step, ramp, sine, rectangle, triangle, etc. The response data can be pressure, displacement, etc. of the actuator to be diagnosed, and the predicted response data can be predicted pressure, displacement, etc.

[0047] In some embodiments, in the case that the first test actuator is to assemble a man-made fault seal with different leakage fault levels to a brand-new actuator respectively, the determination of the fault seal on the first test actuator comprises the following steps: Firstly, obtain the leakage threshold of the to-be-diagnosed actuator. In the present embodiment, the leakage threshold can be obtained by testing the fault actuator removed from the mechanical equipment, can be the leakage threshold required to be met by the actuator according to the industry regulations, or can be the leakage at the designed time length or movement distance under the highest pressure, speed and thermal equilibrium temperature based on the adhesion wear mechanism, so as to restore the damage degree of the seal of the to-be-diagnosed actuator to the maximum extent and obtain the leakage at the designed service life of the to-be-diagnosed actuator. That is, the durability test of the to-be-diagnosed actuator under the highest working condition can be performed, and when the test actuator reaches the theoretical service life, the leakage of the test actuator under the fault diagnosis working condition is detected, and the highest working condition is the working condition combination with the highest values of the to-be-diagnosed actuator in the working process under the preset boundary conditions.

[0048] It should be noted that, considering that the leakage threshold test of the test actuator only needs to be performed under the uniform pressure, speed and oil temperature, for example, taking the to-be-diagnosed actuator as a hydraulic cylinder, the leakage threshold can also be obtained by closing the oil way of the two cavities of the hydraulic cylinder, applying an external force on the piston rod axis by a loading device, making the pressure of the one cavity of the hydraulic cylinder reach a set value, and converting the piston rod displacement per unit time into the leakage; or the leakage threshold can be obtained by measuring the leakage by a special test platform.

[0049] For example, taking a hydraulic cylinder as an example, the durability test platform can be selected from a working machine actual vehicle, a hydraulic cylinder standard type test platform, and a special platform for durability test of a hydraulic cylinder piston and a piston rod seal. Through parameter setting of a specific attitude of a working device, a pressure control unit, a speed control unit, and an oil temperature control unit, the hydraulic cylinder seal is operated under the highest pressure, speed, and thermal equilibrium temperature conditions in the actual service environment for a design life length or a piston movement distance. When detecting the hydraulic cylinder leakage threshold, the pressure, speed, and thermal equilibrium temperature conditions with the highest frequency in the load spectrum are defined as the fault diagnosis conditions, and the hydraulic cylinder pressure, speed, and oil temperature are set as the fault diagnosis condition parameters. For hydraulic cylinder external leakage detection, the rod seal after durability test is used to replace the seal at the corresponding position of the new hydraulic cylinder, and the difference between the output flow of the rod cavity and the input flow of the rod cavity and the demand flow generated by the piston movement is measured as the external leakage threshold of the rod cavity with and without the rod cavity. For hydraulic cylinder internal leakage detection, the piston seal after durability test is used to replace the seal at the corresponding position of the new hydraulic cylinder, and the difference between the output flow of the rod cavity or the input flow of the rod cavity and the demand flow generated by the piston movement is measured as the internal leakage threshold of the hydraulic cylinder.

[0050] By conducting durability test under extreme pressure, speed, and thermal equilibrium temperature, the damage state of the seal and the leakage change caused thereby are maximally restored, the leakage threshold under the design life is obtained, and the fault level diagnosis within the leakage threshold is more in line with the actual needs of maintenance decision making.

[0051] In a second step, a leakage of a second test actuator under the fault diagnosis conditions is obtained, wherein the second test actuator is provided with a damaged seal. In this embodiment, the pressure, speed, and thermal equilibrium temperature conditions with the highest frequency in the load spectrum are defined as the fault diagnosis conditions, and the second test actuator is detected under the fault diagnosis conditions to obtain the leakage of the second test actuator under the fault diagnosis conditions. The second test actuator is of the same type as the actuator to be diagnosed. The damage form of the damaged seal can be eccentric wear, uniform wear around the circumference, wear at a specific edge, etc. The damaged seal can be obtained by artificial preparation.

[0052] In a third step, a seal damage threshold is determined based on the leakage of the second test actuator under the fault diagnosis conditions and the leakage threshold. In this embodiment, the size of the damaged seal is continuously adjusted by human beings so that the error between the leakage of the second test actuator under the fault diagnosis conditions and the leakage threshold is within a preset range. At this time, the size of the damaged seal is the seal damage threshold.

[0053] Fourthly, based on the seal damage threshold, a plurality of seal damage sizes are determined to obtain the faulty seals of different damage scales.

[0054] In this embodiment, a plurality of damage sizes can be selected at equal intervals within the non-damage and seal damage threshold to obtain a plurality of seal damage sizes, and then the seals are respectively manufactured according to the respective seal damage sizes to obtain the faulty seals of different damage scales.

[0055] Taking the hydraulic cylinder as an example, the second test executor is taken as a bias grinding as the damage form of the artificially pre-fault seal, please refer to Figure 2 , Figure 2 The damage range of the artificially pre-fault seal according to the embodiment of the application is schematically shown. The damage range is a circular ring corresponding to an arbitrary circumferential angle value (i.e. ) in the circumferential range of the seal, and the damage surface is selected according to the surface that seals. The damage mode is selected according to the material of the seal, such as fine sandpaper, a lathe, an art knife, etc. The damage degree test standard is that the damaged seal is assembled to a brand new hydraulic cylinder, and the error between the leakage detection value under the fault diagnosis working condition and the leakage threshold is within a preset range (such as 5%). The damage size is defined as the radius change value of the artificially pre-fault damage. The damage size measurement mode is selected according to the material of the seal, such as a vernier caliper or a projection method. The damage size that meets the damage degree test standard is defined as the damage threshold. A plurality of damage sizes are selected at equal intervals within the non-damage and damage threshold, and the faulty seal is artificially pre-faulted according to the above principles.

[0056] According to the actual damage form of the seal, the faulty seal is constructed within the leakage threshold range in a pre-fault manner, which helps to shorten the cost and time of obtaining the fault data on the basis of ensuring the consistency with the actual executor response.

[0057] In some embodiments, the determination process of the fault level corresponding to each first test executor includes: Firstly, the leakage of each first test executor under the fault diagnosis working condition is obtained, the fault diagnosis working condition is the working condition combination with the highest frequency in the working process of the to-be-diagnosed executor under the preset boundary condition, and the working condition combination at least includes pressure, speed and temperature. In this embodiment, the pressure, speed and thermal equilibrium temperature working condition with the highest frequency in the load spectrum can be defined as the fault diagnosis working condition, and each first test executor is detected under the fault diagnosis working condition to obtain the leakage of each first test executor under the fault diagnosis working condition. The construction of the above load spectrum can be through the engineering machinery vehicle controller, the Internet of Things platform and the like to record the pressure, speed and system oil temperature information of the to-be-diagnosed executor, and to draw the three-dimensional load spectrum of the hydraulic cylinder pressure-speed-temperature at a fixed pressure, speed and temperature interval.

[0058] In the second step, the fault level corresponding to each first test executor is determined based on the leakage amount of each first test executor under the fault diagnosis working condition.

[0059] In the present embodiment, the fault level can be defined according to the size of the leakage amount under the fault diagnosis working condition according to a preset rule, for example, the larger the leakage amount, the higher the fault level. The above-mentioned fault level includes the leakage fault type and level.

[0060] By obtaining the leakage amount of each first test executor under the fault diagnosis working condition, the leakage amount difference caused by the change of the sealing element wear state within the leakage amount threshold is uniformly measured, and the fault level corresponding to each first test executor can be more accurately determined.

[0061] Then, based on the response data and the predicted response data corresponding to the second test excitation of each first test executor under each working condition, the leakage fault threshold corresponding to each leakage fault level under each working condition is determined; In the present embodiment, the difference extreme value of the response data and the predicted response data corresponding to the second test excitation of each first test executor under each working condition is compared, and the difference extreme value is taken as the leakage fault threshold under the working condition and the leakage fault level. The above-mentioned process is repeated until the leakage fault threshold under all pressure-velocity-temperature working condition combinations and all leakage fault levels in the load spectrum is obtained.

[0062] Finally, based on the above-mentioned each working condition, each leakage fault level, and the leakage fault threshold corresponding to each leakage fault level under each working condition, a leakage fault diagnosis model is constructed.

[0063] In the present embodiment, the above-mentioned construction of the leakage fault diagnosis model can be to establish a relational database of each working condition, each leakage fault level, and the leakage fault threshold corresponding to each leakage fault level under each working condition, that is, each working condition corresponds to each leakage fault level and the leakage fault threshold corresponding to each leakage fault level under the working condition, that is, the preset leakage fault diagnosis model is a relational database of working condition, leakage fault threshold, and leakage fault level. The above-mentioned leakage fault diagnosis model can also be a model constructed based on traditional machine learning algorithms such as BP neural network, random forest, LIBSVM, decision tree, or neural networks such as CNN, RNN, and LSTM. In the model construction, each working condition and the output difference value (which can include the leakage fault threshold) can be taken as the input feature, and the leakage fault level can be taken as the output for model training. The above-mentioned training process belongs to the prior art, and will not be described here. That is, the preset leakage fault diagnosis model is a prediction model constructed based on working condition, leakage fault threshold, and leakage fault level.

[0064] Since the leakage amount of the actuator is affected by multiple factors such as operation parameters and sealing state parameters, in order to improve the applicability of the diagnosis scheme under different operation parameters and uniformly measure the leakage amount difference caused by sealing damage, by obtaining the relationship between the sealing damage degree and the system response under all working condition combinations in the load spectrum, i.e., the leakage fault threshold corresponding to each leakage fault level under each working condition, each working condition, each leakage fault level and the leakage fault threshold corresponding to each leakage fault level under each working condition can be determined, which is helpful to obtain a more accurate leakage fault diagnosis model.

[0065] In step 230, in the case that the preset leakage fault diagnosis model is a working condition, leakage fault threshold and leakage fault level relationship database, the current working condition can be matched in the preset leakage fault diagnosis model, and then the leakage fault threshold closest to the output difference value is found under the working condition, and the corresponding leakage fault level is obtained, i.e., the fault diagnosis result is obtained. Each of the above leakage fault levels can correspond to a leakage fault threshold interval. After matching the current working condition, the corresponding leakage fault threshold interval can be determined according to the output difference value, and the corresponding leakage fault level can be obtained according to the leakage fault threshold interval. In the case that the preset leakage fault diagnosis model is a prediction model constructed based on working conditions, output difference values and leakage fault levels, the current working condition and the output difference value can be input as features into the preset leakage fault diagnosis model, and the corresponding leakage fault level is predicted, i.e., the fault diagnosis result is obtained.

[0066] In some embodiments, the fault diagnosis result is determined according to the preset leakage fault diagnosis model based on the current working condition and the output difference value, including the following steps: Firstly, it is judged whether the output difference value exceeds a preset threshold value; In this embodiment, the above-mentioned preset threshold value can be set according to experience in advance, and the above-mentioned judgment can be a comparison between the output difference value and the preset threshold value.

[0067] Then, in the case that it is determined that the output difference value exceeds the preset threshold value, the fault diagnosis result is determined according to the preset leakage fault diagnosis model based on the current working condition and the output difference value.

[0068] In this embodiment, if the output difference value exceeds the preset threshold value, it indicates that there is a leakage fault, and the fault diagnosis result is determined according to the preset leakage fault diagnosis model based on the current working condition and the output difference value; if the output difference value does not exceed the preset threshold value, it indicates that there is no leakage fault, and no leakage fault diagnosis will be performed.

[0069] Taking a hydraulic cylinder as an example, initial values of parameters of a hydraulic system state space model are set according to collected pressure data of two cavities of the hydraulic cylinder and oil temperature data, pressure responses of an output prediction model under the same step and ramp signals are calculated, and a difference extreme value between the pressure responses and actual pressure responses of the hydraulic system is compared. Under the step signal, if the difference extreme value of the pressure of the two cavities of the hydraulic cylinder does not exceed a preset value, there is no external leakage fault, if the difference extreme value of the pressure of the two cavities of the hydraulic cylinder is higher than the preset value, there is an external leakage fault, a chamber of the external leakage fault is a chamber with a higher difference extreme value of the pressure, and a leakage fault level is a fault level corresponding to an external leakage fault threshold value closest to the difference extreme value under the same pressure-velocity-temperature working condition combination. Under the ramp signal, a leakage fault level of the hydraulic cylinder is a fault level corresponding to an internal leakage fault threshold value closest to the difference extreme value under the same pressure-velocity-temperature working condition combination.

[0070] By judging whether the output difference value exceeds a preset threshold value, only in the case where it is determined that the output difference value exceeds the preset threshold value, a fault diagnosis result is determined based on the current working condition and the output difference value according to a preset leakage fault diagnosis model, so that the efficiency of leakage fault diagnosis of the actuator can be improved.

[0071] Taking a hydraulic cylinder as an example, the scheme is described in detail below, please refer to Figures 3-4 , Figure 3 A development process diagram of a hydraulic cylinder leakage fault diagnosis scheme based on a mechanism model according to an embodiment of the application is schematically shown; Figure 4 A flowchart of a hydraulic cylinder leakage fault diagnosis method based on a mechanism model according to an embodiment of the application is schematically shown. Specifically, the method comprises the following steps: 1. Determination of a hydraulic cylinder leakage fault diagnosis scheme, please refer to Figure 3 , comprising the following steps: First, a hydraulic cylinder load spectrum is established: taking fixed load pressure, running speed and temperature interval as boundary conditions, a three-dimensional load spectrum of the hydraulic cylinder is drawn.

[0072] Then, a high-precision output prediction model of a fault-free hydraulic system is developed. A hydraulic system state space model is established, according to an extended Kalman filter algorithm, an iteration method of system state variables and covariance matrices in state prediction and state update stages is calculated, and system prediction and measurement noise is adjusted, so that the output error of the step and ramp signals of the fault-free actual system under all pressure, velocity and temperature combination working conditions in the load spectrum is less than a preset range.

[0073] Then, faulty seals are prefabricated artificially. Based on the load spectrum, durability tests are conducted under the conditions of maximum pressure and speed, and thermal equilibrium temperature. When the design life is reached, performance tests are conducted under fault diagnosis conditions to obtain the leakage amount under these conditions, i.e., the leakage threshold. Faulty seals with leakage amounts equal to the leakage threshold are fabricated artificially, and their damage dimensions are measured. Within these damage dimensions, several leakage fault levels are defined, and faulty seals are prefabricated.

[0074] Finally, a hydraulic cylinder leakage fault diagnosis scheme is designed based on the mechanism model. The prefabricated seals of various fault levels from step 2 are assembled onto the hydraulic cylinder. Using all combinations of pressure, speed, and temperature in the load spectrum as boundary conditions, the extreme values ​​of pressure output differences between the high-precision output prediction model of a fault-free hydraulic system under step and ramp signal inputs and the hydraulic system with known leakage faults are compared. Based on this comparison, diagnostic rules for hydraulic cylinder leakage fault types and levels are established, thus obtaining the system leakage fault diagnosis scheme.

[0075] 2. For troubleshooting hydraulic cylinder leakage, please refer to [link / reference]. Figure 4 This includes the following steps: Step 1: Collect the initial pressure and oil temperature of the hydraulic cylinder, and measure the pressure output of the hydraulic system with unknown leakage faults under step and ramp signals; Step 2: Under the same initial pressure and oil temperature, calculate the pressure output of the high-precision prediction model of the fault-free hydraulic system under step and ramp signals; Step 3: Calculate the extreme values ​​of the pressure output difference between the two signals under step and ramp signals, and determine the leakage type and level based on the pre-established hydraulic cylinder leakage fault type and level diagnosis rules.

[0076] Figure 1 This is a flowchart illustrating the actuator leakage fault diagnosis method in this embodiment. It should be understood that, although... Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0077] Please refer to Figure 5 , Figure 5A structural schematic diagram of an actuator leakage fault diagnosis device according to an embodiment of the present application is shown schematically. The embodiment provides an actuator leakage fault diagnosis device, which comprises an acquisition module 410, a calculation module 420 and a diagnosis module 430, wherein: The acquisition module 410 is configured to acquire first output data and second output data of an actuator to be diagnosed under a current working condition, the first output data being actual response data of the actuator to be diagnosed under an excitation signal, and the second output data being output data of the actuator to be diagnosed under the excitation signal predicted by using a preset output prediction model, the preset output prediction model being used to predict output of an actuator under no leakage fault; The calculation module 420 is configured to obtain an output difference value based on the first output data and the second output data. The diagnosis module 430 is configured to determine a fault diagnosis result according to a preset leakage fault diagnosis model based on the current working condition and the output difference value.

[0078] The actuator leakage fault diagnosis device comprises a processor and a memory, and the acquisition module 410, the calculation module 420 and the diagnosis module 430 are stored in the memory as program units and are executed by the processor to realize corresponding functions.

[0079] The processor comprises a core, and the core retrieves corresponding program units from the memory. The core can be set as one or more, and the actuator leakage fault diagnosis is realized by adjusting core parameters.

[0080] The memory can comprise a non-permanent memory in a computer readable medium, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM), and the memory comprises at least one memory chip.

[0081] The embodiment of the present application provides a processor, which is used to run a program, wherein the program is executed to perform the actuator leakage fault diagnosis method.

[0082] The embodiment of the present application provides a machine readable storage medium, which stores a program, and the program is executed by a processor to realize the actuator leakage fault diagnosis method.

[0083] In one embodiment, a computer device can be provided, which can be a terminal, and an internal structure diagram of the computer device can be as shown in Figure 6As shown in FIG. 1, the computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure). Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operating system B01 and the computer program B02 in the non-volatile storage medium A06 to run. The network interface A02 of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor A01 to implement an actuator leakage fault diagnosis method. The display screen A04 of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device A05 of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0084] Those skilled in the art can understand that, Figure 6 The structure shown in FIG. 1 is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0085] In one embodiment, the actuator leakage fault diagnosis apparatus provided by the present application can be implemented in the form of a computer program, which can run on a computer device as shown in Figure 6 The memory of the computer device can store various program modules constituting the actuator leakage fault diagnosis apparatus, such as the acquisition module 410, the calculation module 420 and the diagnosis module 430 shown in FIG. 1. The computer program constituted by various program modules makes the processor execute the steps in the actuator leakage fault diagnosis method of each embodiment of the present application described in the specification. Figure 5

[0086] Figure 6 The computer device can execute step 210 through the acquisition module 410 in the actuator leakage fault diagnosis apparatus as shown in Figure 5 The computer device can execute step 220 through the calculation module 420. The computer device can execute step 230 through the diagnosis module 430.

[0087] ​The embodiment of the present application provides an electronic device, which comprises: at least one processor; a memory connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements the above-mentioned actuator leakage fault diagnosis method by executing the instructions stored in the memory, and the processor executes the instructions to implement the following steps: obtaining first output data and second output data of a to-be-diagnosed actuator under a current working condition, the first output data being actual response data of the to-be-diagnosed actuator under an excitation signal, and the second output data being output data of the to-be-diagnosed actuator under the excitation signal obtained by using a preset output prediction model, and the preset output prediction model being used for predicting the output of the actuator under a non-leakage fault; obtaining an output difference value based on the first output data and the second output data; obtaining a fault diagnosis result based on the current working condition and the output difference value according to a preset leakage fault diagnosis model.

[0088] In one embodiment, the construction process of the preset output prediction model comprises: obtaining actual output data corresponding to a first test excitation under each working condition of a non-leakage fault hydraulic system; predicting the output corresponding to the first test excitation under each working condition by using a preset hydraulic system mathematical model to obtain predicted output data corresponding to the first test excitation under each working condition; adjusting the preset hydraulic system mathematical model based on the actual output data and the predicted output data corresponding to the first test excitation under each working condition to obtain an output prediction model.

[0089] In one embodiment, the preset hydraulic system mathematical model comprises a hydraulic system state space model and an optimization module; the step of predicting the output corresponding to the first test excitation under each working condition by using the preset hydraulic system mathematical model to obtain predicted output data corresponding to the first test excitation under each working condition comprises: inputting the first test excitation under each working condition into the hydraulic system state space model respectively to obtain initial predicted data corresponding to the first test excitation under each working condition; optimizing the initial predicted data corresponding to the first test excitation under each working condition by using the optimization module to obtain predicted output data corresponding to the first test excitation under each working condition.

[0090] In one embodiment, the construction process of the preset leakage fault diagnosis model comprises: Obtaining response data and predicted response data of each first test executor under each working condition corresponding to the second test excitation, the predicted response data being output data of each first test executor under each working condition corresponding to the second test excitation predicted by using the preset output prediction model, each first test executor being respectively provided with a fault seal with different damage scales, and each first test executor corresponding to a different leakage fault level; Based on the response data and the predicted response data of each first test executor under each working condition corresponding to the second test excitation, a leakage fault threshold corresponding to each leakage fault level under each working condition is determined; Based on the working conditions, the leakage fault levels, and the leakage fault threshold corresponding to each leakage fault level under each working condition, a leakage fault diagnosis model is constructed.

[0091] In one embodiment, further comprising: Obtaining the leakage amount of each first test executor under a fault diagnosis working condition, the fault diagnosis working condition being a working condition combination with the highest frequency in the working process of the to-be-diagnosed executor under a preset boundary condition, the working condition combination at least including pressure, speed, and temperature; Based on the leakage amount of each first test executor under the fault diagnosis working condition, a fault level corresponding to each first test executor is determined.

[0092] In one embodiment, further comprising: Obtaining a leakage amount threshold of the to-be-diagnosed executor; Obtaining the leakage amount of a second test executor under a fault diagnosis working condition, the second test executor being provided with a damaged seal; Based on the leakage amount of the second test executor under the fault diagnosis working condition and the leakage amount threshold, a seal damage threshold is determined; Based on the seal damage threshold, a plurality of seal damage sizes are determined to obtain fault seals with different damage scales.

[0093] In one embodiment, the leakage fault diagnosis result is determined based on the current working condition and the output difference value according to a preset leakage fault diagnosis model, comprising: Determining whether the output difference value exceeds a preset threshold value; In a case where it is determined that the output difference value exceeds the preset threshold value, the leakage fault diagnosis result is determined based on the current working condition and the output difference value according to a preset leakage fault diagnosis model.

[0094] In one embodiment, the preset leakage fault diagnosis model is a relationship database of working conditions, leakage fault thresholds, and leakage fault levels.

[0095] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, apparatus or computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer readable storage media (including, but not limited to, disk memory, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0096] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing device or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams block or blocks. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams block or blocks. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams block or blocks.

[0097] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowchart illustrations and / or block diagrams block or blocks. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams block or blocks. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams block or blocks.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flowchart illustrations and / or block diagrams block or blocks. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams block or blocks. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams block or blocks.

[0099] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0100] Memory can include non-persistent memory, Random Access Memory (RAM), and / or non-volatile memory, such as Read Only Memory (ROM) or flash memory, in a computer readable medium. Memory is an example of computer readable media.

[0101] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic disks storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0102] It should also be noted that the terms "comprising", "containing", or any other similar term are intended to encompass non-exclusive inclusions, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements in the list, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without more limitations, an element defined by the phrase "comprising a" does not exclude the existence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0103] The above merely provides an example of the present application and is not intended to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. An actuator leakage fault diagnosis method characterized by, The method comprises the following steps: obtaining first output data and second output data of an actuator to be diagnosed under a current working condition, the first output data being actual response data of the actuator to be diagnosed under an excitation signal, and the second output data being output data of the actuator to be diagnosed under the excitation signal predicted by using a preset output prediction model, the preset output prediction model being used for predicting output of an actuator under a non-leakage fault; obtaining an output difference value based on the first output data and the second output data; determining a fault diagnosis result based on the current working condition and the output difference value according to a preset leakage fault diagnosis model.

2. The method of claim 1, wherein, The construction process of the preset output prediction model comprises the following steps: obtaining actual output data corresponding to a first test excitation under each working condition of a non-leakage fault hydraulic system; predicting the output corresponding to the first test excitation under each working condition by using a preset hydraulic system mathematical model to obtain predicted output data corresponding to the first test excitation under each working condition; adjusting the preset hydraulic system mathematical model based on the actual output data and the predicted output data corresponding to the first test excitation under each working condition to obtain an output prediction model.

3. The method of claim 2, wherein, The preset hydraulic system mathematical model comprises a hydraulic system state space model and an optimization module. The step of predicting the output corresponding to the first test excitation under each working condition by using the preset hydraulic system mathematical model to obtain predicted output data corresponding to the first test excitation under each working condition comprises the following steps: inputting the first test excitation under each working condition into the hydraulic system state space model respectively to obtain initial predicted data corresponding to the first test excitation under each working condition; optimizing the initial predicted data corresponding to the first test excitation under each working condition by using the optimization module to obtain predicted output data corresponding to the first test excitation under each working condition.

4. The method of claim 1, wherein, The construction process of the preset leakage fault diagnosis model comprises the following steps: obtaining response data and predicted response data corresponding to a second test excitation under each working condition of each first test actuator, the predicted response data being output data of the each first test actuator under each working condition corresponding to the second test excitation predicted by using the preset output prediction model, each first test actuator being provided with a fault seal with different damage scales, and each first test actuator corresponding to a different leakage fault level; determining leakage fault threshold values corresponding to each leakage fault level under each working condition based on the response data and the predicted response data corresponding to the second test excitation under each working condition of each first test actuator; constructing a leakage fault diagnosis model based on each working condition, each leakage fault level, and the leakage fault threshold values corresponding to each leakage fault level under each working condition.

5. The method of claim 4, wherein, The method further comprises the following steps: obtaining a leakage amount of each first test actuator under a fault diagnosis working condition, the fault diagnosis working condition being a working condition combination with the highest frequency in a working process of the actuator to be diagnosed under preset boundary conditions, and the working condition combination at least comprising pressure, speed and temperature. Determine a fault level corresponding to each first test executor based on the leakage amount of each first test executor under the fault diagnosis working condition.

6. The method of claim 4, wherein, Further comprising: Obtain a leakage amount threshold of the to-be-diagnosed executor; Obtain a leakage amount of a second test executor under a fault diagnosis working condition, wherein the second test executor is provided with a damaged seal; Determine a seal damage threshold based on the leakage amount of the second test executor under the fault diagnosis working condition and the leakage amount threshold; Determine a plurality of seal damage sizes based on the seal damage threshold to obtain fault seals of different damage sizes.

7. The method of claim 1, wherein, The determination of the fault diagnosis result based on the current working condition and the output difference value according to the preset leakage fault diagnosis model comprises: Determine whether the output difference value exceeds a preset threshold value; In a case where it is determined that the output difference value exceeds the preset threshold value, determine the fault diagnosis result based on the current working condition and the output difference value according to the preset leakage fault diagnosis model.

8. The method of claim 1, wherein, The preset leakage fault diagnosis model is a relationship database of working conditions, leakage fault threshold values, and leakage fault levels.

9. An actuator leakage fault diagnosis apparatus characterized by comprising: Comprise: An acquisition module is configured to acquire first output data and second output data of a to-be-diagnosed executor under a current working condition, the first output data being actual response data of the to-be-diagnosed executor under an excitation signal, and the second output data being output data of the to-be-diagnosed executor under the excitation signal predicted by a preset output prediction model, the preset output prediction model being used to predict the output of an executor under no leakage fault; A calculation module is configured to obtain an output difference value based on the first output data and the second output data; A diagnosis module is configured to determine a fault diagnosis result based on the current working condition and the output difference value according to a preset leakage fault diagnosis model.

10. An electronic device, comprising: The electronic device comprises: At least one processor; A memory connected with the at least one processor; The memory stores instructions executable by the at least one processor, and the at least one processor implements the executor leakage fault diagnosis method in any one of claims 1 to 8 by executing the instructions stored in the memory.

11. A machine-readable storage medium having instructions stored thereon, the instructions comprising: The instructions, when executed by the processor, cause the processor to be configured to perform the executor leakage fault diagnosis method according to any one of claims 1 to 8. The instructions, when executed by the processor, cause the processor to be configured to perform the executor leakage fault diagnosis method according to any one of claims 1 to 8.

Images