A fault diagnosis method and intelligent early warning device for a hydraulic system

Abstract

The present invention discloses a fault diagnosis method and an intelligent early warning device for a hydraulic system, and relates to the technical field of hydraulic systems. The present invention establishes an operation model of the hydraulic system according to ideal environmental parameters, imports standard operation parameters into the operation model to obtain an ideal performance coefficient of the hydraulic system, and calculates an equipment operation deviation coefficient according to the ideal environmental parameters, presets a system operation early warning threshold according to the equipment operation deviation coefficient, establishes an environmental prediction model, integrates multiple groups of predicted environmental change data to obtain an environmental deviation waveform, and then delineates normal monitoring periods, peak monitoring periods and key monitoring periods, sets corresponding monitoring frequency bands, performs early warning judgments according to the deviation value between the actual performance coefficient of the equipment and the ideal performance coefficient, and combines the interference effect of environmental factors on the operation of the hydraulic system to realize fault prediction before the hydraulic system fails due to interference from environmental factors, thereby avoiding economic losses caused by discovering the problem after the failure occurs.

Description

Technical Field

[0001] The present invention relates to the technical field of hydraulic systems, and in particular to a fault diagnosis method and an intelligent early warning device for a hydraulic system. Background Art

[0002] A hydraulic system uses a liquid (usually oil) as a working medium to transmit power through pressure. It is widely used in a variety of fields, including industry, aerospace, construction, and transportation, primarily to perform various mechanical movements such as lifting, pushing, pulling, and rotating. The basic working principle of a hydraulic system is to transmit power through the pressure of a liquid. When a hydraulic pump drives the hydraulic oil to flow, the oil is pressurized and transported through pipelines to the actuator. The oil in the hydraulic cylinder pushes the piston according to the pressure, thus achieving mechanical action.

[0003] Hydraulic systems can experience various equipment failures during operation due to the influence of other factors. Existing technologies offer a variety of fault diagnosis methods for hydraulic systems in operating machinery. However, current methods only utilize sensor data from the operating machinery's hydraulic system for early warning and expert knowledge to determine whether the operating machinery has experienced a failure. These methods fail to fully consider the operating conditions of the operating machinery, such as altitude and weather information in the operating area. Furthermore, for certain large-scale operating machinery or operating machinery in special working environments, early warnings after a problem occurs often require the machine to be shut down for maintenance, significantly impacting the operating process and efficiency.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the Invention

[0005] The purpose of the present invention is to combine the interference effects of environmental factors on the operation of the hydraulic system to realize fault prediction before the hydraulic system fails due to interference from environmental factors, thereby avoiding economic losses caused by discovering the problem after the failure occurs.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a fault diagnosis method for a hydraulic system, comprising the following steps:

[0007] Step 1: Acquire the real-time equipment operating parameters of the hydraulic system through the sensor group, and perform signal amplification, filtering, and precise analog-to-digital conversion on the real-time equipment operating parameters to obtain an equipment operating data set;

[0008] Step 2: Obtain ideal environmental parameters and standard operating parameters for the hydraulic system, establish an operating model for the hydraulic system based on the ideal environmental parameters, and import the standard operating parameters into the operating model to obtain an ideal performance coefficient of the hydraulic system;

[0009] Step 3: Obtain the actual environmental parameters of the hydraulic system, calculate the equipment operation deviation coefficient based on the ideal environmental parameters, and preset the system operation warning threshold based on the equipment operation deviation coefficient;

[0010] Step 4: Establish an environmental prediction model based on a convolutional neural network, import the actual environmental parameters into the environmental prediction model to obtain predicted environmental parameters, and integrate multiple sets of predicted environmental change data within a preset prediction period to obtain an environmental deviation waveform. Based on the environmental deviation waveform, normal monitoring periods, peak monitoring periods, and key monitoring periods are delineated;

[0011] Step 5. Set the corresponding monitoring frequency bands according to the normal monitoring period, peak monitoring period and key monitoring period, obtain the equipment operation data set to calculate the actual performance coefficient of the equipment, make early warning judgments based on the deviation value between the actual performance coefficient of the equipment and the ideal performance coefficient, and generate an early warning report.

[0012] Furthermore, the sensor group includes a pressure sensor, a temperature sensor, a flow sensor, a vibration sensor and an oil quality sensor, wherein:

[0013] Pressure sensors are used to monitor the pressure of various components in the hydraulic system and detect abnormal pressure conditions;

[0014] The temperature sensor is used to monitor the temperature of the hydraulic oil to prevent overheating that may cause oil degradation or system damage;

[0015] Flow sensors are used to detect fluid flow in hydraulic systems to ensure that the system operates within the designed flow range;

[0016] Vibration sensors are used to monitor the vibration of hydraulic pumps, motors, valves, and other core components in hydraulic systems to identify mechanical failures in advance.

[0017] Oil quality sensors are used to detect the contamination level and viscosity changes of hydraulic oil to prevent oil deterioration.

[0018] Furthermore, the specific process of obtaining the ideal performance coefficient of the hydraulic system is as follows:

[0019] S101. Acquire ideal environmental parameters and standard operating parameters for the hydraulic system. The ideal environmental parameters include ideal ambient temperature data, ideal ambient humidity data, and maximum ambient vibration data. The standard operating parameters include flow data, pressure data, and power data of the power source, flow data and flow direction of the directional valve, working pressure data of the pressure valve, flow data of the flow valve, speed of the actuator, and oil transmission path.

[0020] S102. The specific process of establishing the power source model based on mechanical principles is as follows:

[0021] The hydraulic pump model established based on mechanics principles is expressed as follows: , where Qp is the theoretical flow data, N is the theoretical speed data of the power source output, Vd is the theoretical displacement data of the hydraulic pump in the power source, and ηp is the actual output efficiency of the hydraulic pump;

[0022] The hydraulic cylinder model established based on mechanics principles is expressed as follows: , where F is the theoretical thrust data of the hydraulic cylinder, P is the theoretical pressure data of the hydraulic oil, and A is the piston area of ​​the cylinder;

[0023] S103. Based on the flow-pressure characteristic curve of the hydraulic pump, the relationship between the output flow and pressure data of the hydraulic pump is represented, and the dynamic equation of the hydraulic pump is obtained as follows: , where P(t) is the dynamic function of real-time pressure data, Q(t) is the real-time flow data, and θ is the load parameter;

[0024] S104. Based on the flow control equation and the pressure control equation, a pressure-flow relationship model in the hydraulic system is obtained, which is expressed as follows: , where P0 is the initial pressure data in the hydraulic system, and Vtotal is the total volume data of the hydraulic system;

[0025] S105. Input the ideal environmental parameters into the simulation software to construct a basic environmental model. Dynamically simulate the above models using the simulation software. Simultaneously, import the standard operating parameters into the operating model to obtain simulated oil viscosity data μr, simulated pressure change data Pr, simulated oil flow data Qr of the hydraulic system, and simulated motion speed data Vr of the actuator.

[0026] S106. After normalizing and de-dimensionalizing the data, calculate the ideal performance coefficient Wk of the hydraulic system according to the following equation: , where e1, e2, e3 and e4 are preset weight coefficients, and the ideal performance coefficient Wk is used to reflect the performance of the hydraulic system under ideal conditions. A larger ideal performance coefficient indicates a better performance of the hydraulic system under ideal conditions, and a smaller ideal performance coefficient indicates a worse performance of the hydraulic system under ideal conditions.

[0027] Furthermore, the specific process of presetting the system operation warning threshold according to the equipment operation deviation coefficient is as follows:

[0028] S201, obtaining actual environmental parameters of the hydraulic system, wherein the actual environmental parameters include actual environmental temperature data Tj, actual environmental humidity data RHj, and actual maximum vibration data Hj, and the ideal environmental parameters include ideal environmental temperature data Ti, ideal environmental humidity data RHi, and maximum environmental vibration data Hi;

[0029] S202. After normalizing and de-dimensionalizing the data, calculate the equipment operation deviation coefficient Yk according to the following formula: , where m=1, 2, 3, ..., n, α, β, and γ are all preset weight coefficients. The equipment operation deviation coefficient is used to reflect the degree of deviation between the operating state of the hydraulic system in the actual environment and the operating state in the ideal environment. The larger the equipment operation deviation coefficient, the greater the degree of deviation. Conversely, the smaller the equipment operation deviation coefficient, the smaller the degree of deviation.

[0030] S203. Obtain a preset warning judgment interval (Pmin, Pmax). If the equipment operation deviation coefficient is less than or equal to Pmin, the system operation warning thresholds include the oil viscosity risk threshold μ1, the pressure change risk threshold P1, the oil flow risk threshold Q1, and the actuator movement speed risk threshold V1.

[0031] If the equipment operation deviation coefficient is less than Pmin or greater than Pmax, the system operation warning thresholds include the oil viscosity risk threshold μ2, the pressure change risk threshold P2, the oil flow risk threshold Q2, and the actuator movement speed risk threshold V2;

[0032] If the equipment operation deviation coefficient is greater than or equal to Pmax, the system operation warning thresholds include the oil viscosity risk threshold μ3, the pressure change risk threshold P3, the oil flow risk threshold Q3, and the actuator movement speed risk threshold V3.

[0033] Furthermore, the specific process of demarcating normal monitoring periods, peak monitoring periods, and key monitoring periods based on the environmental deviation waveform is as follows:

[0034] S301. Acquire historical environmental change data of the actual environment in which the hydraulic equipment is located, wherein the historical environmental change data includes historical environmental temperature data, historical environmental humidity data, and historical environmental vibration data; establish an environmental change graph based on a time axis; integrate the environmental change graph as a training sample; and split the training sample into a training set and a test set in a ratio of 8:2;

[0035] S302: Build an environment prediction model based on a convolutional neural network, download the weight file and load it onto the corresponding network to initialize the migration network parameters;

[0036] S303, modify the last fully connected layer of the network, keep the input unchanged, set the output to the predicted environment data, initialize the weights of the last layer, use the gradient descent algorithm for learning, and use fixed step size decay to optimize the training parameters, retrain the entire network, and obtain the environment prediction model;

[0037] S304: During the training process, small batches of training samples are randomly extracted from the training set without duplication. The extraction of all training samples constitutes one training cycle. The training is completed after a certain number of iterations to obtain an environment prediction model.

[0038] S305. Establish a time axis with a preset prediction period, delineate multiple time nodes on the time axis, import the actual environmental parameters into the environmental prediction model to obtain predicted environmental parameters, and mark multiple groups of predicted environmental parameters on the time axis according to the corresponding time nodes to obtain an environmental deviation waveform diagram, and delineate the normal monitoring period, peak monitoring period and key monitoring period on the environmental deviation waveform diagram according to the preset deviation amplitude A1, deviation amplitude A2 and deviation amplitude A3.

[0039] Furthermore, the specific process of generating an early warning report is as follows:

[0040] S401, obtaining a device operation data set, wherein the device operation data set includes actual oil viscosity data μd, actual pressure change data Pd, actual oil flow data Qd, and actual motion speed data Vd of the actuator;

[0041] S402. Calculate the actual performance coefficient Yd of the equipment according to the formula in S202 above, and calculate the deviation value ΔY between the actual performance coefficient of the equipment and the ideal performance coefficient: ;

[0042] S403: If the deviation value ΔY is greater than or equal to a preset deviation judgment threshold, a warning report is generated, where the warning report includes a warning signal and a device operation data set.

[0043] The present invention also provides an intelligent early warning device for a hydraulic system, comprising a data acquisition module, a performance simulation module, a performance evaluation module, an environmental analysis module, and an intelligent early warning module, wherein:

[0044] The data acquisition module is used to obtain the real-time equipment operating parameters of the hydraulic system through the sensor group, and perform signal amplification, filtering and accurate analog-to-digital conversion on the real-time equipment operating parameters to obtain the equipment operation data set;

[0045] The performance simulation module is used to obtain the ideal environmental parameters and standard operating parameters of the hydraulic system, establish an operating model of the hydraulic system based on the ideal environmental parameters, and import the standard operating parameters into the operating model to obtain the ideal performance coefficient of the hydraulic system;

[0046] The performance evaluation module is used to obtain the actual environmental parameters of the hydraulic system, calculate the equipment operation deviation coefficient based on the ideal environmental parameters, and preset the system operation warning threshold based on the equipment operation deviation coefficient;

[0047] The environmental analysis module is used to establish an environmental prediction model based on a convolutional neural network, import actual environmental parameters into the environmental prediction model to obtain predicted environmental parameters, and integrate multiple sets of predicted environmental change data within a preset prediction period to obtain an environmental deviation waveform. Based on the environmental deviation waveform, normal monitoring periods, peak monitoring periods, and key monitoring periods are delineated;

[0048] The intelligent early warning module is used to set corresponding monitoring frequency bands according to normal monitoring periods, peak monitoring periods and key monitoring periods, obtain equipment operation data sets to calculate the actual performance coefficient of the equipment, make early warning judgments based on the deviation value between the actual performance coefficient of the equipment and the ideal performance coefficient, and generate early warning reports.

[0049] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0050] The intelligent early warning device and fault diagnosis method for a hydraulic system, the present invention establishes an operation model of the hydraulic system according to ideal environmental parameters, imports standard operation parameters into the operation model to obtain an ideal performance coefficient of the hydraulic system, and calculates the equipment operation deviation coefficient according to the ideal environmental parameters, presets the system operation early warning threshold according to the equipment operation deviation coefficient, establishes an environmental prediction model based on a convolutional neural network, integrates multiple sets of predicted environmental change data to obtain an environmental deviation waveform, and then delineates normal monitoring periods, peak monitoring periods and key monitoring periods, sets corresponding monitoring frequency bands, and performs early warning judgments based on the deviation value between the actual performance coefficient of the equipment and the ideal performance coefficient, combines the interference effect of environmental factors on the operation of the hydraulic system, and realizes fault prediction before the hydraulic system fails due to interference from environmental factors, thereby avoiding economic losses caused by discovering problems only after the failure occurs. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 Shown is a schematic diagram of the overall method flow of the present invention;

[0052] Figure 2 FIG. 2 shows a schematic structural diagram of the early warning device of the present invention. DETAILED DESCRIPTION

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0054] Example 1:

[0055] like Figure 1 As shown, a fault diagnosis method for a hydraulic system includes the following steps:

[0056] Step 1: Acquire the real-time equipment operating parameters of the hydraulic system through the sensor group, and perform signal amplification, filtering, and precise analog-to-digital conversion on the real-time equipment operating parameters to obtain an equipment operating data set;

[0057] The sensor group includes a pressure sensor, a temperature sensor, a flow sensor, a vibration sensor and an oil quality sensor, wherein:

[0058] Pressure sensors are used to monitor the pressure of various components in the hydraulic system and detect abnormal pressure conditions;

[0059] The temperature sensor is used to monitor the temperature of the hydraulic oil to prevent overheating that may cause oil degradation or system damage;

[0060] Flow sensors are used to detect fluid flow in hydraulic systems to ensure that the system operates within the designed flow range;

[0061] Vibration sensors are used to monitor the vibration of hydraulic pumps, motors, valves, and other core components in hydraulic systems to identify mechanical failures in advance.

[0062] Oil quality sensors are used to detect the contamination level and viscosity changes of hydraulic oil to prevent oil deterioration.

[0063] Step 2: Obtain ideal environmental parameters and standard operating parameters for the hydraulic system, establish an operating model for the hydraulic system based on the ideal environmental parameters, and import the standard operating parameters into the operating model to obtain an ideal performance coefficient of the hydraulic system;

[0064] The specific process of obtaining the ideal performance coefficient of the hydraulic system is as follows:

[0065] S101. Acquire ideal environmental parameters and standard operating parameters for the hydraulic system. The ideal environmental parameters include ideal ambient temperature data, ideal ambient humidity data, and maximum ambient vibration data. The standard operating parameters include flow data, pressure data, and power data of the power source, flow data and flow direction of the directional valve, working pressure data of the pressure valve, flow data of the flow valve, speed of the actuator, and oil transmission path.

[0066] S102. The specific process of establishing the power source model based on mechanical principles is as follows:

[0067] The hydraulic pump model established based on mechanics principles is expressed as follows: , where Qp is the theoretical flow data, N is the theoretical speed data of the power source output, Vd is the theoretical displacement data of the hydraulic pump in the power source, and ηp is the actual output efficiency of the hydraulic pump;

[0068] The hydraulic cylinder model established based on mechanics principles is expressed as follows: , where F is the theoretical thrust data of the hydraulic cylinder, P is the theoretical pressure data of the hydraulic oil, and A is the piston area of ​​the cylinder;

[0069] S103. Based on the flow-pressure characteristic curve of the hydraulic pump, the relationship between the output flow and pressure data of the hydraulic pump is represented, and the dynamic equation of the hydraulic pump is obtained as follows: , where P(t) is the dynamic function of real-time pressure data, Q(t) is the real-time flow data, and θ is the load parameter;

[0070] S104. Based on the flow control equation and the pressure control equation, a pressure-flow relationship model in the hydraulic system is obtained, which is expressed as follows: , where P0 is the initial pressure data in the hydraulic system, and Vtotal is the total volume data of the hydraulic system;

[0071] S105. Input the ideal environmental parameters into the simulation software to construct a basic environmental model. Dynamically simulate the above models using the simulation software. Simultaneously, import the standard operating parameters into the operating model to obtain simulated oil viscosity data μr, simulated pressure change data Pr, simulated oil flow data Qr of the hydraulic system, and simulated motion speed data Vr of the actuator.

[0072] S106. After normalizing and de-dimensionalizing the data, calculate the ideal performance coefficient Wk of the hydraulic system according to the following equation: , where e1, e2, e3 and e4 are preset weight coefficients, and the ideal performance coefficient Wk is used to reflect the performance of the hydraulic system under ideal conditions. A larger ideal performance coefficient indicates a better performance of the hydraulic system under ideal conditions, and a smaller ideal performance coefficient indicates a worse performance of the hydraulic system under ideal conditions.

[0073] Step 3: Obtain the actual environmental parameters of the hydraulic system, calculate the equipment operation deviation coefficient based on the ideal environmental parameters, and preset the system operation warning threshold based on the equipment operation deviation coefficient;

[0074] The specific process of presetting the system operation warning threshold according to the equipment operation deviation coefficient is as follows:

[0075] S201, obtaining actual environmental parameters of the hydraulic system, wherein the actual environmental parameters include actual environmental temperature data Tj, actual environmental humidity data RHj, and actual maximum vibration data Hj, and the ideal environmental parameters include ideal environmental temperature data Ti, ideal environmental humidity data RHi, and maximum environmental vibration data Hi;

[0076] S202. After normalizing and de-dimensionalizing the data, calculate the equipment operation deviation coefficient Yk according to the following formula: , where m=1, 2, 3, ..., n, α, β, and γ are all preset weight coefficients. The equipment operation deviation coefficient is used to reflect the degree of deviation between the operating state of the hydraulic system in the actual environment and the operating state in the ideal environment. The larger the equipment operation deviation coefficient, the greater the degree of deviation. Conversely, the smaller the equipment operation deviation coefficient, the smaller the degree of deviation.

[0077] S203. Obtain a preset warning judgment interval (Pmin, Pmax). If the equipment operation deviation coefficient is less than or equal to Pmin, the system operation warning thresholds include the oil viscosity risk threshold μ1, the pressure change risk threshold P1, the oil flow risk threshold Q1, and the actuator movement speed risk threshold V1.

[0078] If the equipment operation deviation coefficient is less than Pmin or greater than Pmax, the system operation warning thresholds include the oil viscosity risk threshold μ2, the pressure change risk threshold P2, the oil flow risk threshold Q2, and the actuator movement speed risk threshold V2;

[0079] If the equipment operation deviation coefficient is greater than or equal to Pmax, the system operation warning thresholds include the oil viscosity risk threshold μ3, the pressure change risk threshold P3, the oil flow risk threshold Q3, and the actuator movement speed risk threshold V3.

[0080] Step 4: Establish an environmental prediction model based on a convolutional neural network, import the actual environmental parameters into the environmental prediction model to obtain predicted environmental parameters, and integrate multiple sets of predicted environmental change data within a preset prediction period to obtain an environmental deviation waveform. Based on the environmental deviation waveform, normal monitoring periods, peak monitoring periods, and key monitoring periods are delineated;

[0081] The specific process of demarcating normal monitoring periods, peak monitoring periods, and key monitoring periods based on the environmental deviation waveform is as follows:

[0082] S301. Acquire historical environmental change data of the actual environment in which the hydraulic equipment is located, wherein the historical environmental change data includes historical environmental temperature data, historical environmental humidity data, and historical environmental vibration data; establish an environmental change graph based on a time axis; integrate the environmental change graph as a training sample; and split the training sample into a training set and a test set in a ratio of 8:2;

[0083] S302: Build an environment prediction model based on a convolutional neural network, download the weight file and load it onto the corresponding network to initialize the migration network parameters;

[0084] S303, modify the last fully connected layer of the network, keep the input unchanged, set the output to the predicted environment data, initialize the weights of the last layer, use the gradient descent algorithm for learning, and use fixed step size decay to optimize the training parameters, retrain the entire network, and obtain the environment prediction model;

[0085] S304: During the training process, small batches of training samples are randomly extracted from the training set without duplication. The extraction of all training samples constitutes one training cycle. The training is completed after a certain number of iterations to obtain an environment prediction model.

[0086] S305. Establish a time axis with a preset prediction period, delineate multiple time nodes on the time axis, import the actual environmental parameters into the environmental prediction model to obtain predicted environmental parameters, and mark multiple groups of predicted environmental parameters on the time axis according to the corresponding time nodes to obtain an environmental deviation waveform diagram, and delineate the normal monitoring period, peak monitoring period and key monitoring period on the environmental deviation waveform diagram according to the preset deviation amplitude A1, deviation amplitude A2 and deviation amplitude A3.

[0087] Step 5. Set the corresponding monitoring frequency bands according to the normal monitoring period, peak monitoring period and key monitoring period, obtain the equipment operation data set to calculate the actual performance coefficient of the equipment, make early warning judgments based on the deviation value between the actual performance coefficient of the equipment and the ideal performance coefficient, and generate an early warning report.

[0088] The specific process of generating an early warning report is as follows:

[0089] S401, obtaining a device operation data set, wherein the device operation data set includes actual oil viscosity data μd, actual pressure change data Pd, actual oil flow data Qd, and actual motion speed data Vd of the actuator;

[0090] S402. Calculate the actual performance coefficient Yd of the equipment according to the formula in S202 above, and calculate the deviation value ΔY between the actual performance coefficient of the equipment and the ideal performance coefficient: ;

[0091] S403: If the deviation value ΔY is greater than or equal to a preset deviation judgment threshold, a warning report is generated, where the warning report includes a warning signal and a device operation data set.

[0092] The present invention establishes an operation model of the hydraulic system according to ideal environmental parameters, imports standard operation parameters into the operation model to obtain the ideal performance coefficient of the hydraulic system, calculates the equipment operation deviation coefficient according to the ideal environmental parameters, presets the system operation early warning threshold according to the equipment operation deviation coefficient, establishes an environmental prediction model based on a convolutional neural network, integrates multiple groups of predicted environmental change data to obtain an environmental deviation waveform, and then delineates normal monitoring periods, peak monitoring periods and key monitoring periods, sets corresponding monitoring frequency bands, and makes early warning judgments based on the deviation value between the actual performance coefficient of the equipment and the ideal performance coefficient. It combines the interference effect of environmental factors on the operation of the hydraulic system, and realizes fault prediction before the hydraulic system fails due to interference from environmental factors, thereby avoiding economic losses caused by discovering problems only after the failure occurs.

[0093] Example 2:

[0094] like Figure 2 As shown, an intelligent early warning device for a hydraulic system includes a data acquisition module, a performance simulation module, a performance evaluation module, an environmental analysis module, and an intelligent early warning module, wherein:

[0095] The data acquisition module is used to obtain the real-time equipment operating parameters of the hydraulic system through the sensor group, and perform signal amplification, filtering and accurate analog-to-digital conversion on the real-time equipment operating parameters to obtain the equipment operation data set;

[0096] The performance simulation module is used to obtain the ideal environmental parameters and standard operating parameters of the hydraulic system, establish an operating model of the hydraulic system based on the ideal environmental parameters, and import the standard operating parameters into the operating model to obtain the ideal performance coefficient of the hydraulic system;

[0097] The performance evaluation module is used to obtain the actual environmental parameters of the hydraulic system, calculate the equipment operation deviation coefficient based on the ideal environmental parameters, and preset the system operation warning threshold based on the equipment operation deviation coefficient;

[0098] The environmental analysis module is used to establish an environmental prediction model based on a convolutional neural network, import actual environmental parameters into the environmental prediction model to obtain predicted environmental parameters, and integrate multiple sets of predicted environmental change data within a preset prediction period to obtain an environmental deviation waveform. Based on the environmental deviation waveform, normal monitoring periods, peak monitoring periods, and key monitoring periods are delineated;

[0099] The intelligent early warning module is used to set corresponding monitoring frequency bands according to normal monitoring periods, peak monitoring periods and key monitoring periods, obtain equipment operation data sets to calculate the actual performance coefficient of the equipment, make early warning judgments based on the deviation value between the actual performance coefficient of the equipment and the ideal performance coefficient, and generate early warning reports.

[0100] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technical personnel in this field for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0101] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by those skilled in the art according to actual conditions.

[0102] In the two embodiments provided in this application, it should be understood that the disclosed devices and systems can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is merely a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not implemented. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interface, and the indirect coupling or communication connection of devices or modules may be electrical, mechanical or other forms.

[0103] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A fault diagnosis method for a hydraulic system, characterized in that: The following steps are involved: Step 1: Acquire the real-time equipment operating parameters of the hydraulic system through the sensor group, and perform signal amplification, filtering, and precise analog-to-digital conversion on the real-time equipment operating parameters to obtain an equipment operating data set; Step 2: Obtain ideal environmental parameters and standard operating parameters for the hydraulic system, establish an operating model for the hydraulic system based on the ideal environmental parameters, and import the standard operating parameters into the operating model to obtain an ideal performance coefficient of the hydraulic system; Step 3: Obtain the actual environmental parameters of the hydraulic system, calculate the equipment operation deviation coefficient based on the ideal environmental parameters, and preset the system operation warning threshold based on the equipment operation deviation coefficient; Step 4: Establish an environmental prediction model based on a convolutional neural network, import the actual environmental parameters into the environmental prediction model to obtain predicted environmental parameters, and integrate multiple sets of predicted environmental change data within a preset prediction period to obtain an environmental deviation waveform. Based on the environmental deviation waveform, normal monitoring periods, peak monitoring periods, and key monitoring periods are delineated; Step 5. Set the corresponding monitoring frequency bands according to the normal monitoring period, peak monitoring period and key monitoring period, obtain the equipment operation data set to calculate the actual performance coefficient of the equipment, make early warning judgments based on the deviation value between the actual performance coefficient of the equipment and the ideal performance coefficient, and generate an early warning report.

2. A fault diagnosis method for a hydraulic system according to claim 1, characterized in that: The sensor group includes a pressure sensor, a temperature sensor, a flow sensor, a vibration sensor and an oil quality sensor, wherein: Pressure sensors are used to monitor the pressure of various components in hydraulic systems; The temperature sensor is used to monitor the temperature of the hydraulic oil; Flow sensors are used to detect fluid flow in hydraulic systems; Vibration sensors are used to monitor the vibration of hydraulic pumps, motors, valves and core components in hydraulic systems; Oil quality sensors are used to detect the contamination level and viscosity changes of hydraulic oil.

3. A fault diagnosis method for a hydraulic system according to claim 1, characterized in that: The specific process of obtaining the ideal performance coefficient of the hydraulic system is as follows: S101. Acquire ideal environmental parameters and standard operating parameters for the hydraulic system. The ideal environmental parameters include ideal ambient temperature data, ideal ambient humidity data, and maximum ambient vibration data. The standard operating parameters include flow data, pressure data, and power data of the power source, flow data and flow direction of the directional valve, working pressure data of the pressure valve, flow data of the flow valve, speed of the actuator, and oil transmission path. S102. The specific process of establishing the power source model based on mechanical principles is as follows: The hydraulic pump model established based on mechanics principles is expressed as follows: , where Qp is the theoretical flow data, N is the theoretical speed data of the power source output, Vd is the theoretical displacement data of the hydraulic pump in the power source, and ηp is the actual output efficiency of the hydraulic pump; The hydraulic cylinder model established based on mechanics principles is expressed as follows: , where F is the theoretical thrust data of the hydraulic cylinder, P is the theoretical pressure data of the hydraulic oil, and A is the piston area of ​​the cylinder; S103. Based on the flow-pressure characteristic curve of the hydraulic pump, the relationship between the output flow and pressure data of the hydraulic pump is represented, and the dynamic equation of the hydraulic pump is obtained as follows: , where P(t) is the dynamic function of real-time pressure data, Q(t) is the real-time flow data, and θ is the load parameter; S104. Based on the flow control equation and the pressure control equation, a pressure-flow relationship model in the hydraulic system is obtained, which is expressed as follows: , where P0 is the initial pressure data in the hydraulic system, and Vtotal is the total volume data of the hydraulic system; S105. Input the ideal environmental parameters into the simulation software to construct a basic environmental model. Dynamically simulate the above models using the simulation software. Simultaneously, import the standard operating parameters into the operating model to obtain simulated oil viscosity data μr, simulated pressure change data Pr, simulated oil flow data Qr of the hydraulic system, and simulated motion speed data Vr of the actuator. S106. After normalizing and de-dimensionalizing the data, calculate the ideal performance coefficient Wk of the hydraulic system according to the following equation: , where e1, e2, e3 and e4 are preset weight coefficients, and the ideal performance coefficient Wk is used to reflect the performance state of the hydraulic system under ideal conditions.

4. A fault diagnosis method for a hydraulic system according to claim 1, characterized in that: The specific process of presetting the system operation warning threshold according to the equipment operation deviation coefficient is as follows: S201, obtaining actual environmental parameters of the hydraulic system, wherein the actual environmental parameters include actual environmental temperature data Tj, actual environmental humidity data RHj, and actual maximum vibration data Hj, and the ideal environmental parameters include ideal environmental temperature data Ti, ideal environmental humidity data RHi, and maximum environmental vibration data Hi; S202. After normalizing and de-dimensionalizing the data, calculate the equipment operation deviation coefficient Yk according to the following formula: , where m = 1, 2, 3, ..., n, α, β, γ are all preset weight coefficients, and the equipment operation deviation coefficient is used to reflect the degree of deviation between the operating state of the hydraulic system in the actual environment and the operating state in the ideal environment; S203. Obtain a preset warning judgment interval (Pmin, Pmax). If the equipment operation deviation coefficient is less than or equal to Pmin, the system operation warning thresholds include the oil viscosity risk threshold μ1, the pressure change risk threshold P1, the oil flow risk threshold Q1, and the actuator movement speed risk threshold V1. If the equipment operation deviation coefficient is less than Pmin or greater than Pmax, the system operation warning thresholds include the oil viscosity risk threshold μ2, the pressure change risk threshold P2, the oil flow risk threshold Q2, and the actuator movement speed risk threshold V2; If the equipment operation deviation coefficient is greater than or equal to Pmax, the system operation warning thresholds include the oil viscosity risk threshold μ3, the pressure change risk threshold P3, the oil flow risk threshold Q3, and the actuator movement speed risk threshold V3.

5. A fault diagnosis method for a hydraulic system according to claim 1, characterized in that: The specific process of demarcating normal monitoring periods, peak monitoring periods, and key monitoring periods based on the environmental deviation waveform is as follows: S301. Acquire historical environmental change data of the actual environment in which the hydraulic equipment is located, wherein the historical environmental change data includes historical environmental temperature data, historical environmental humidity data, and historical environmental vibration data; establish an environmental change graph based on a time axis; integrate the environmental change graph as a training sample; and split the training sample into a training set and a test set in a ratio of 8:2; S302: Build an environment prediction model based on a convolutional neural network, download the weight file and load it onto the corresponding network to initialize the migration network parameters; S303, modify the last fully connected layer of the network, keep the input unchanged, set the output to the predicted environment data, initialize the weights of the last layer, use the gradient descent algorithm for learning, and use fixed step size decay to optimize the training parameters, retrain the entire network, and obtain the environment prediction model; S304: During the training process, small batches of training samples are randomly extracted from the training set without duplication. The extraction of all training samples constitutes one training cycle. The training is completed after a certain number of iterations to obtain an environment prediction model. S305. Establish a time axis with a preset prediction period, delineate multiple time nodes on the time axis, import the actual environmental parameters into the environmental prediction model to obtain predicted environmental parameters, and mark multiple groups of predicted environmental parameters on the time axis according to the corresponding time nodes to obtain an environmental deviation waveform diagram, and delineate the normal monitoring period, peak monitoring period and key monitoring period on the environmental deviation waveform diagram according to the preset deviation amplitude A1, deviation amplitude A2 and deviation amplitude A3.

6. A fault diagnosis method for a hydraulic system according to claim 4, characterized in that: The specific process of generating an early warning report is as follows: S401, obtaining a device operation data set, wherein the device operation data set includes actual oil viscosity data μd, actual pressure change data Pd, actual oil flow data Qd, and actual motion speed data Vd of the actuator; S402. Calculate the actual performance coefficient Yd of the equipment according to the formula in S202 above, and calculate the deviation value ΔY between the actual performance coefficient of the equipment and the ideal performance coefficient: ; S403: If the deviation value ΔY is greater than or equal to a preset deviation judgment threshold, a warning report is generated, where the warning report includes a warning signal and a device operation data set.

7. An intelligent early warning device for a hydraulic system, applying the fault diagnosis method for a hydraulic system according to any one of claims 1 to 6, characterized in that: It includes data acquisition module, performance simulation module, performance evaluation module, environment analysis module and intelligent early warning module, among which: The data acquisition module is used to obtain the real-time equipment operating parameters of the hydraulic system through the sensor group, and perform signal amplification, filtering and accurate analog-to-digital conversion on the real-time equipment operating parameters to obtain the equipment operation data set; The performance simulation module is used to obtain the ideal environmental parameters and standard operating parameters of the hydraulic system, establish an operating model of the hydraulic system based on the ideal environmental parameters, and import the standard operating parameters into the operating model to obtain the ideal performance coefficient of the hydraulic system; The performance evaluation module is used to obtain the actual environmental parameters of the hydraulic system, calculate the equipment operation deviation coefficient based on the ideal environmental parameters, and preset the system operation warning threshold based on the equipment operation deviation coefficient; The environmental analysis module is used to establish an environmental prediction model based on a convolutional neural network, import actual environmental parameters into the environmental prediction model to obtain predicted environmental parameters, and integrate multiple sets of predicted environmental change data within a preset prediction period to obtain an environmental deviation waveform. Based on the environmental deviation waveform, normal monitoring periods, peak monitoring periods, and key monitoring periods are delineated; The intelligent early warning module is used to set corresponding monitoring frequency bands according to normal monitoring periods, peak monitoring periods and key monitoring periods, obtain equipment operation data sets to calculate the actual performance coefficient of the equipment, make early warning judgments based on the deviation value between the actual performance coefficient of the equipment and the ideal performance coefficient, and generate early warning reports.

Images