Hydraulic system unmanned monitoring method and system based on hybrid perception

Abstract

The invention provides a hydraulic system unmanned monitoring method and system based on hybrid perception. The method comprises the steps that attenuation coefficients and phase distortion characteristics are obtained based on captured reflected wave data processing; processing based on the obtained ultrasonic flow velocity distribution diagram to obtain a turbulence energy anomaly index; processing based on the oil parameter data to obtain an oil degradation index; inputting the attenuation coefficient, the phase distortion feature, the turbulence energy anomaly index and the oil degradation index into the constructed dynamic weight Bayesian network model for weight adjustment, and calculating the fault confidence through the dynamic weight Bayesian network model after weight adjustment. Comparing the fault confidence coefficient with a preset fault confidence coefficient threshold value to judge a fault type, determining a maintenance strategy of the fault type, and performing automatic maintenance on the hydraulic system based on the maintenance strategy; and adjusting the weight factor of the dynamic weight Bayesian network model to update the historical probability table based on the input data, the output data and the weight of the dynamic weight Bayesian network model.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent monitoring of hydraulic systems, and particularly relates to a method and system for unmanned monitoring of hydraulic systems based on hybrid perception. Background Art

[0002] As a core power transmission device in the industrial field, hydraulic systems play an irreplaceable role in fields such as construction machinery, metallurgical equipment, and aerospace. With the long-term use of hydraulic systems, various faults are likely to occur inside, such as oil circuit blockage and oil deterioration. Currently, the main detection method for hydraulic system faults is usually manual detection. In manual detection, through the analysis of the operation of the hydraulic system by the detection personnel and the observation of the oil, combined with their own experience, the type of fault in the hydraulic system is judged. Although this detection method can determine the type of fault in the hydraulic system, during the detection process, it requires the detection personnel to spend a lot of time checking and diagnosing step by step, resulting in low detection efficiency. At the same time, this detection method is carried out after the occurrence of hydraulic faults, and the detection method is single, unable to predict potential fault risks in advance, resulting in a long maintenance cycle of the equipment installed with the hydraulic system and affecting the use of the equipment installed with the hydraulic system. Summary of the Invention

[0003] In order to solve the problem that the existing hydraulic monitoring system has a single monitoring method, resulting in low efficiency and accuracy of hydraulic system fault monitoring, the present invention provides a method and system for unmanned monitoring of hydraulic systems based on hybrid perception.

[0004] To achieve the above object, the present invention provides the following technical solutions: The present invention proposes a method for unmanned monitoring of a hydraulic system based on hybrid perception, including the following steps: S1. Perform time-frequency decomposition on the reflected wave data captured by reflecting the pressure wave transmitted to the hydraulic system, and extract the attenuation coefficient and phase distortion characteristics; Analyze the ultrasonic velocity distribution map of the hydraulic system obtained and the standard flow map to obtain the turbulent energy anomaly index; Compare and analyze the obtained oil parameter data with the preset oil threshold to obtain the oil deterioration index; S2. Construct a Bayesian network model, configure the weight factors of each fault, and train a dynamic weight Bayesian network model based on historical operation data and historical probability tables; S3. Input the attenuation coefficient, the phase distortion characteristic, the turbulent energy anomaly index, and the oil deterioration index described in S1 into the dynamic weight Bayesian network model constructed in S2 for weight adjustment, and calculate the fault confidence through the dynamic weight Bayesian network model after weight adjustment; S4. Compare the fault confidence level in S3 with a preset fault confidence level threshold to determine the fault category, determine the maintenance strategy for the fault type, and automatically repair the hydraulic system based on the maintenance strategy. After the repair is completed, repeat S1; S5. Update the historical probability table by adjusting the weight factor of the dynamic weight Bayesian network model based on the input data, output data, and weights of the dynamic weight Bayesian network model in S3.

[0005] Preferably, in S1, perform time-frequency decomposition on the reflected wave data captured by reflecting the pressure wave transmitted into the hydraulic system, and extract the attenuation coefficient and phase distortion characteristics, including: Capture the reflected waveform of the pressure wave reflected in the hydraulic system to obtain reflected wave data; Convert the reflected wave data into analytical signal data to obtain the instantaneous phase of the reflected wave; Draw a curve of the change of phase over time through the instantaneous phase; Identify phase distortion points or phase jumps based on the change curve to obtain phase distortion characteristics; Perform Fourier transform on the reflected wave data to obtain the spectrum of the signal; Identify the main frequency components and reflection amplitudes in the spectrum; Calculate the attenuation coefficient based on the transmitted amplitude of the obtained pressure wave and the reflection amplitude.

[0006] Preferably, in S1, analyze based on the obtained ultrasonic flow velocity distribution map of the hydraulic system and the standard flow map, including: Obtain the flow velocity data and turbulence intensity data on multiple cross-sections of the hydraulic system; Draw a flow velocity distribution map based on the flow velocity data, the turbulence intensity data, and the positions of key nodes in the hydraulic system; Analyze the flow velocity distribution map and the standard flow map, mark the difference points, and compare the data of the difference points on the flow velocity distribution map and the standard flow map to obtain the flow velocity deviation, turbulence intensity deviation, and map similarity; Based on the flow velocity deviation, the turbulence intensity deviation, and the map similarity, and set standard weight coefficients, calculate the turbulence energy anomaly index.

[0007] Preferably, in S1, compare the obtained oil parameter data with a preset oil parameter threshold, including: Obtain oil parameter data, where the oil parameter data includes the oil viscosity value and the oil particle size value; Preset the oil viscosity threshold and the oil impurity threshold; Compare the viscosity value of the oil fluid with the preset oil fluid viscosity threshold, and calculate the deviation degree of the oil fluid viscosity; Compare the particle size value of the oil fluid with the oil fluid impurity threshold, and calculate the deviation degree of the oil fluid impurities; Calculate the oil fluid deterioration index based on the deviation degree of the oil fluid viscosity and the deviation degree of the oil fluid impurities.

[0008] Preferably, in S3, based on the attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, and the oil fluid deterioration index in S1, input them into the dynamic weight Bayesian network model constructed in S2 for weight adjustment, and calculate the fault confidence through the dynamic weight Bayesian network model after weight adjustment, including: Preprocess the attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, and the oil fluid deterioration index to obtain a normalized data set; Input the normalized data set into the dynamic weight Bayesian network model for dynamic weight adjustment; When the attenuation coefficient in the normalized data set exceeds the first critical value, increase the weight factor of the flow anomaly index in the dynamic weight Bayesian network model; Calculate the blockage confidence based on the attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, and the weight factor of the dynamic weight Bayesian network model after weight adjustment; When the particle size value of the oil fluid suddenly increases, increase the weight factor of the particle size value of the oil fluid when the dynamic weight Bayesian network model judges the oil circuit fault; Calculate the oil fluid deterioration confidence based on the turbulent energy anomaly index, the oil fluid deterioration index, and the weight factor of the dynamic weight Bayesian network model after weight adjustment.

[0009] Preferably, preprocess the attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, and the oil fluid deterioration index to obtain a normalized data set; Clean the attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, and the oil fluid deterioration index to remove noise and outliers; Perform normalization processing on the cleaned attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, and the oil fluid deterioration index so that the cleaned attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, and the oil fluid deterioration index fall within the same numerical range to obtain a normalized data set.

[0010] Preferably, in S4, based on the comparison between the fault confidence level in S3 and a preset fault confidence level threshold, the fault category is determined, and a maintenance strategy for the fault type is determined. Based on the maintenance strategy, an automatic inspection of the hydraulic system is performed, including: Preset a blockage confidence level threshold and an oil degradation threshold; Compare the blockage confidence level with the blockage confidence level threshold. If the blockage confidence level exceeds the blockage confidence level threshold, it is determined as a blockage fault, and an oil circuit flushing maintenance strategy is generated. The hydraulic system is automatically inspected through the oil circuit flushing maintenance strategy; Obtain the coordinate data corresponding to the blockage confidence level in the three-dimensional confidence space, determine the locally blocked oil circuit and component numbers in the hydraulic system through the coordinate data, and generate an inspection report through the component numbers and positions; Compare the oil degradation confidence level with the oil degradation threshold. If the oil degradation confidence level exceeds the oil degradation threshold, it is determined as an oil quality deterioration fault; Compare the oil degradation confidence level with a preset safety boundary threshold. When the oil degradation confidence level exceeds the preset safety boundary threshold, an oil circuit switching strategy is generated, and the hydraulic system automatically performs an oil circuit switch based on the oil circuit switching strategy.

[0011] The present invention proposes a hydraulic system unmanned monitoring system based on hybrid perception, and applies a hydraulic system unmanned monitoring method based on hybrid perception, which is characterized by including: An acquisition module, configured to: capture reflected wave data of pressure waves emitted to the hydraulic system, obtain an ultrasonic flow velocity distribution map of the hydraulic system, and obtain oil parameter data; An analysis module, configured to: Perform time-frequency decomposition based on the captured reflected wave data of pressure waves emitted to the hydraulic system, and extract the attenuation coefficient and phase distortion characteristics; Analyze based on the obtained ultrasonic flow velocity distribution map of the hydraulic system and a standard flow map to obtain a turbulent energy anomaly index; Compare the obtained oil parameter data with a preset oil threshold to obtain an oil degradation index; A model construction module, configured to: construct a Bayesian network model, configure weight factors for each fault, and train a dynamic weight Bayesian network model based on the obtained historical operation data and historical probability table; A response execution module, configured to: input the attenuation coefficient, the phase distortion feature, the turbulence energy anomaly index, and the oil degradation index into a constructed dynamic weight Bayesian network model for weight adjustment, and calculate a fault confidence level through the dynamic weight Bayesian network model after weight adjustment; A decision-making module, configured to: determine a fault category based on a comparison between the fault confidence level and a preset fault confidence level threshold, determine a maintenance strategy for the fault type, and automatically repair the hydraulic system based on the maintenance strategy; An optimization module, configured to: update a historical probability table by adjusting a weight factor of the dynamic weight Bayesian network model based on input data, output data, and weights of the dynamic weight Bayesian network model.

[0012] The present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable in the processor. When the processor executes the computer program, steps of an unmanned monitoring method for a hydraulic system based on hybrid sensing are implemented.

[0013] The present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, steps of an unmanned monitoring method for a hydraulic system based on hybrid sensing are implemented.

[0014] Compared with the prior art, the present invention has the following beneficial technical effects: The present invention provides an unmanned monitoring method for a hydraulic system based on hybrid sensing. By capturing reflected wave data of pressure wave reflection in the hydraulic system and performing time-frequency decomposition, the attenuation coefficient and the phase distortion feature can be accurately extracted. Combining the analysis of the ultrasonic velocity distribution map and the standard flow map, the turbulence energy anomaly index can be obtained. By comparing the acquired oil parameter data with a preset oil threshold, the oil degradation index can be obtained. Then, the above-mentioned multiple characteristic information is input into a constructed dynamic weight Bayesian network model for processing to obtain a fault confidence level, thereby accurately determining the fault type, improving the accuracy and reliability of fault identification. By comparing the fault confidence level with a preset threshold, a targeted maintenance strategy can be formulated to repair the hydraulic system in a timely and effective manner, thereby avoiding the expansion and deterioration of faults and reducing maintenance costs and downtime.

[0015] Furthermore, this method captures the reflection waveform of the pressure wave in the hydraulic system to obtain rich reflected wave data, converts the reflected wave data into analytic signal data, extracts the instantaneous phase of the reflected wave, and can accurately capture the propagation characteristics of the pressure wave in the hydraulic system. By plotting the curve of phase change over time, the phase distortion points or phase jumps can be visually identified. Performing Fourier transform on the reflected wave data to obtain the spectrum of the signal, and then identifying the main frequency components and reflection amplitude in the spectrum, which helps to deeply understand the frequency distribution and energy attenuation of the pressure wave in the hydraulic system. Calculating the attenuation coefficient based on the obtained pressure wave emission amplitude and reflection amplitude can accurately reflect the energy loss of the pressure wave during propagation, improving the efficiency and accuracy of fault monitoring, and also helping to detect and handle potential faults in a timely manner to ensure the safe and stable operation of the hydraulic system.

[0016] Even further, this method provides a powerful tool for visual analysis of the flow state of the hydraulic system by obtaining the flow velocity data and turbulence intensity data at multiple cross-sections of the hydraulic system and plotting the flow velocity distribution map. Comparing and analyzing the flow velocity distribution map with the standard flow map can visually mark the difference points and quantify the flow velocity deviation, turbulence intensity deviation, and map similarity. By setting the standard weight coefficient and comprehensively considering the flow velocity deviation, turbulence intensity deviation, and map similarity, the turbulence energy anomaly index is calculated. This index can accurately reflect the abnormal degree of turbulence energy in the hydraulic system, not only improving the accuracy and efficiency of fault monitoring of the hydraulic system, but also helping to optimize the design and operation of the hydraulic system, reducing the occurrence of faults, and improving the reliability and stability of the system.

[0017] Even further, this method can accurately evaluate the oil fluid state by obtaining key parameters such as the oil fluid viscosity value and oil fluid particle size value and comparing them with the preset oil fluid viscosity threshold and oil fluid impurity threshold. The calculated oil fluid viscosity deviation degree and oil fluid impurity deviation degree help to timely discover problems such as oil fluid deterioration and pollution, so as to take corresponding maintenance measures to avoid the expansion and deterioration of faults. By regularly monitoring the oil fluid parameters and calculating the oil fluid deterioration index, continuous tracking and evaluation of the oil fluid state of the hydraulic system can be achieved, improving the accuracy and efficiency of fault monitoring.

[0018] Furthermore, this method preprocesses the attenuation coefficient, phase distortion characteristics, turbulence energy anomaly index, and oil degradation index to obtain a normalized dataset, providing a unified data format for model input, improving the accuracy and efficiency of data processing. The constructed dynamic weight Bayesian network model can comprehensively consider various characteristic information. Through the dynamic weight adjustment mechanism, according to the specific numerical changes in the normalized dataset, the weight factors of each characteristic are flexibly adjusted. For example, when the attenuation coefficient exceeds the first critical value, the weight factor of the flow anomaly index is increased; when the oil particle size value suddenly increases, its weight factor is increased, so as to more accurately reflect the actual state of the hydraulic system. The confidence level and degradation index calculated based on the adjusted weight factors can more accurately evaluate the fault type and severity, providing a scientific basis for formulating targeted maintenance strategies, improving the accuracy and reliability of hydraulic system fault monitoring, helping to optimize maintenance decisions, reducing maintenance costs, and improving the operation efficiency and stability of the hydraulic system.

[0019] Furthermore, this system includes a collection module, an analysis module, a model construction module, a response execution module, an optimization module, and a decision module. The system synchronously emits low-frequency diagnostic signals with phase adaptation through the collection module, and combines ultrasonic flow velocity monitoring and embedded oil multi-spectrum analysis to achieve concurrent collection of pressure wave reflection signals, multi-section flow velocity distributions, and oil parameters. The analysis module adopts a third-order diagnostic verification mechanism, through reflection wave time-frequency analysis, flow velocity frequency-domain cross-correlation detection, and oil degradation threshold comparison. The model construction module constructs a dynamic weight Bayesian network model for data fusion to generate a three-dimensional fault confidence space. The response execution module automatically implements directional backwashing and redundant oil circuit switching based on the confidence level evaluation, improving the response rate and reducing the frequency of manual operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a schematic flow chart of a method for unmanned monitoring of a hydraulic system based on hybrid perception provided by the present invention; Figure 2 is a schematic diagram of an electronic device provided by the present invention; Figure 3 is a block diagram of a computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In the following, only some exemplary embodiments are briefly described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the spirit or scope of the present invention. Therefore, the drawings and the description are considered to be exemplary in nature rather than restrictive.

[0022] In addition, the terms "first" and "second" are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined.

[0023] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0024] The present invention provides a method and system for unmanned monitoring of a hydraulic system based on hybrid sensing, as Figure 1 shown, including the following steps: S1. Perform time-frequency decomposition on the reflected wave data captured by reflecting pressure waves transmitted into the hydraulic system, and extract the attenuation coefficient and phase distortion characteristics; Specifically, install a pressure wave generator and a reflected wave collector at key nodes of the hydraulic system, and use the hydraulic system condition sensing unit to analyze the current system load mode in real time. Dynamically adjust the transmission power and frequency of the pressure wave according to the working phase and pulsation frequency of the main pump; that is, when the system is in the high-pressure working period, the transmission power of the pressure wave automatically decays to less than 30% of the reference value; when high-frequency hydraulic pulsations are detected, the pressure wave frequency shifts to the harmonic blind area of the current main frequency; then activate the pressure wave generator to transmit pressure waves at key nodes, capture the reflected waveform through the reflected wave collector, and obtain the reflected wave data; Convert the reflected wave data into analytical signal data through Hilbert transform to obtain the instantaneous phase of the reflected wave, draw the curve of the phase change over time through the instantaneous phase, identify the phase distortion points or phase jumps based on the change curve to obtain the phase distortion characteristics; perform Fourier transform on the reflected wave data to obtain the spectrum of the signal, identify the main frequency components and reflection amplitude in the spectrum, and calculate the attenuation coefficient based on the transmission amplitude and reflection amplitude of the pressure wave.

[0025] Analyze based on the obtained ultrasonic velocity distribution map and standard flow map of the hydraulic system to obtain the turbulent energy anomaly index; Specifically, obtain the flow velocity data and turbulent intensity data on multiple cross-sections of the hydraulic system through ultrasonic sensors, draw the velocity distribution map based on the flow velocity data, turbulent intensity data, and the positions of key nodes in the hydraulic system, analyze the velocity distribution map and the standard flow map, mark the difference points, compare the data of the difference points on the velocity distribution map and the standard flow map to obtain the flow velocity deviation, turbulent intensity deviation, and map similarity, and calculate the turbulent energy anomaly index based on the flow velocity deviation, turbulent intensity deviation, and map similarity, and set the standard weight coefficient.

[0026] Based on the comparison and analysis of the obtained oil fluid parameter data with the preset oil fluid threshold values, an oil fluid deterioration index is obtained; Specifically, obtain the oil fluid parameter data, namely the oil fluid viscosity value and the oil fluid particle size value, the preset oil fluid viscosity threshold value and the oil fluid impurity threshold value, compare the oil fluid viscosity value with the preset oil fluid viscosity threshold value, calculate the oil fluid viscosity deviation degree, compare the oil fluid particle size value with the oil fluid impurity threshold value, and calculate the oil fluid impurity deviation degree; among them, the larger the deviation degree, the more serious the deviation of the oil fluid state from the normal state; The specific calculation process of the deviation degree is: deviation degree = (actual value / threshold - 1) × 100%.

[0027] Calculate the oil fluid deterioration index based on the oil fluid viscosity deviation degree and the oil fluid impurity deviation degree. Exemplarily, set the calculation weights of the oil fluid viscosity deviation degree and the oil fluid impurity deviation degree, and calculate the oil fluid deterioration index through the calculation weights of the oil fluid viscosity deviation degree, the calculation weights of the oil fluid impurity deviation degree, the oil fluid viscosity deviation degree and the oil fluid impurity deviation degree.

[0028] S2. Construct a Bayesian network model, configure the weight factors of each fault, and train a dynamic weight Bayesian network model based on the obtained historical operation data and historical probability table; Specifically, construct the dynamic weight Bayesian network model; define the attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index and the oil fluid deterioration index as input nodes, define the fault confidence as the output node, and configure the initial weight factors of each fault in the dynamic weight Bayesian network model; Obtain the historical operation parameters and historical fault probabilities in the hydraulic system, determine the initial probability relationship based on the historical operation parameters and historical fault probabilities in the hydraulic system, input the historical operation parameters, the initial probability relationship and the historical fault probabilities into the network model, introduce the Bayesian inference algorithm for iterative training, and train the dynamic weight Bayesian network model; S3. Input the attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index and the oil fluid deterioration index described in S1 into the dynamic weight Bayesian network model constructed in S2 for weight adjustment, and calculate the fault confidence through the dynamic weight Bayesian network model after weight adjustment; Specifically, preprocess the attenuation coefficient, phase distortion characteristics, turbulence energy anomaly index, and oil degradation index to obtain a normalized data set. Exemplarily, clean the attenuation coefficient, phase distortion characteristics, turbulence energy anomaly index, and oil degradation index to remove noise and outliers, and then normalize the cleaned attenuation coefficient, phase distortion characteristics, turbulence energy anomaly index, and oil degradation index so that the cleaned attenuation coefficient, phase distortion characteristics, turbulence energy anomaly index, and oil degradation index fall within the same numerical range to obtain a normalized data set.

[0029] Input the normalized data set into the dynamic weight Bayesian network model for dynamic weight adjustment. When the attenuation coefficient exceeds the first critical value, increase the weight factor of the flow anomaly index in the dynamic weight Bayesian network model. When the oil particle size value suddenly increases, activate the oil circuit wear priority diagnosis mode and increase the weight factor of the oil particle size value in the dynamic weight Bayesian network model when judging oil circuit faults. Based on the attenuation coefficient, phase distortion characteristics, turbulence energy anomaly index, oil degradation index, and the adjusted weight factors, input them into the dynamic weight Bayesian network model to calculate the fault confidence levels of each fault, that is, obtain the blockage confidence level and the oil degradation confidence level; among them, the blockage confidence level is calculated by the dynamic weight Bayesian network model through the attenuation coefficient, phase distortion characteristics, and turbulence energy anomaly index; the oil degradation confidence level is calculated by the dynamic weight Bayesian network model through the turbulence energy anomaly index and the oil degradation index.

[0030] S4. Based on the comparison between the fault confidence level in S3 and the preset fault confidence level threshold, determine the fault category, determine the maintenance strategy for the fault type, automatically repair the hydraulic system based on the maintenance strategy, and repeat S1; Preset the blockage confidence level threshold and the oil degradation threshold; Compare the blockage confidence level with the blockage confidence level threshold. If the blockage confidence level exceeds the blockage confidence level threshold, determine it as a blockage fault, generate an oil circuit flushing maintenance strategy, and repair the hydraulic system through the oil circuit flushing maintenance strategy; Calculate the blockage joint probability based on the blockage confidence level. Based on the position distribution of the key nodes in the hydraulic system, construct a three-dimensional node model space, and map the blockage joint probability to the corresponding points in the three-dimensional node model space to obtain a three-dimensional confidence level space.

[0031] Meanwhile, obtain the coordinate data corresponding to the blockage confidence in the three-dimensional confidence space, determine the blocked oil circuit and component number in the hydraulic system through the coordinate data, and generate a detection report based on the component number and location; when the blockage confidence is less than the second blockage confidence threshold, obtain the oil circuit pressure data in the hydraulic system, compare the oil circuit pressure data with the standard oil circuit pressure data, calculate the difference value, and if the difference value is within the deviation range, it is determined that the maintenance is completed; if the difference value exceeds the deviation range, execute the oil circuit flushing maintenance strategy to repair the backflush until the difference value is within the deviation range, where the preset second blockage confidence threshold range is 0.6 - 0.7; if the blockage confidence does not exceed the first blockage confidence threshold, it is determined that the oil circuit is normal.

[0032] Compare the oil deterioration confidence with the oil deterioration threshold. If the oil deterioration confidence exceeds the oil deterioration threshold, it is determined as an oil quality deterioration fault. When the oil deterioration confidence exceeds the preset safety boundary threshold, generate an oil circuit switching strategy, and the hydraulic system executes an oil circuit switch based on the oil circuit switching strategy to clean the oil and complete the cleaning and improvement of the oil; if the oil deterioration confidence does not exceed the oil deterioration threshold, it is determined that the oil quality is normal.

[0033] Compare the oil deterioration confidence with the preset safety boundary threshold. If...

[0034] S5. Update the historical probability table by adjusting the weight factor of the dynamic weighted Bayesian network model based on the input data, output data, and weights in the dynamic weighted Bayesian network model in S3.

[0035] Update the historical probability table by using the attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, the oil deterioration index, and adjusting the weight factor of the dynamic weighted Bayesian network model; specifically, extract the input node data, output node data, and the weight factor of the dynamically weighted Bayesian network model after weight adjustment of the dynamic weighted Bayesian network model, that is, the input data is the attenuation coefficient, phase distortion feature, turbulent energy anomaly index, and oil deterioration index, and the output data is the fault confidence. Generate the current conditional probability table through the attenuation coefficient, phase distortion feature, turbulent energy anomaly index, oil deterioration index, fault confidence, and the weight factor of the dynamically weighted Bayesian network model after weight adjustment. Compare the data in the current conditional probability table with the data in the historical conditional probability table, remove duplicate data, fuse them into a data table, and sort the data corresponding to each fault type based on the size of the weight factor to update the historical conditional probability table. The historical conditional probability table is updated each time the detection is completed.

[0036] The above method is further explained and illustrated through specific embodiments below; In a certain construction machinery hydraulic circuit; Install pressure wave excitation sensors with phase synchronization function at three locations: the outlet of the hydraulic pump, in front of the control valve group, and at the inlet of the actuator. The ultrasonic flow meters are fixed on the surface of the main oil pipe in a cross arrangement; When the load mode of the mechanical hydraulic circuit is obtained as the high-pressure working period, the transmission power of the pressure wave automatically decays to less than 30% of the reference value; when high-frequency hydraulic pulsations are detected, the pressure wave frequency shifts to the harmonic blind area of the current main frequency; activate the pressure wave generator to emit pressure waves, capture the reflected waveform through the reflected wave collector, and obtain the reflected wave data; Perform time-frequency decomposition on the reflected wave data captured by the reflected pressure wave transmitted to the hydraulic system, and extract the attenuation coefficient and phase distortion characteristics; analyze based on the obtained ultrasonic flow velocity distribution map of the hydraulic system and the standard flow map to obtain the abnormal index of turbulent energy; compare the obtained oil parameter data with the preset oil threshold to obtain the oil deterioration index; Input the attenuation coefficient, phase distortion characteristics, abnormal index of turbulent energy, and oil deterioration index into the constructed dynamic weight Bayesian network model for processing, and obtain a confidence level of 85% for blockage within 5 cm of the oil path, which is determined as local blockage; since the confidence level of 85% is greater than 0.6, generate an oil path flushing and maintenance strategy to repair a certain construction machinery hydraulic circuit.

[0037] The present invention proposes a hydraulic system unmanned monitoring system based on hybrid perception, which is used to implement the above-mentioned hydraulic system unmanned monitoring method based on hybrid perception, including an acquisition module, an analysis module, a model construction module, a response execution module, an optimization module, and a decision module: Among them, the acquisition module is configured to: capture the reflected wave data of the pressure wave reflected by the transmitted hydraulic system, obtain the ultrasonic flow velocity distribution map of the hydraulic system, and obtain the oil parameter data; The analysis module is configured to: Perform time-frequency decomposition on the reflected wave data captured by the reflected pressure wave transmitted to the hydraulic system, and extract the attenuation coefficient and phase distortion characteristics; Analyze based on the obtained ultrasonic flow velocity distribution map of the hydraulic system and the standard flow map to obtain the abnormal index of turbulent energy; Compare the obtained oil parameter data with the preset oil threshold to obtain the oil deterioration index; The model construction module is configured to: construct a Bayesian network model, configure the weight factors of each fault, and train to obtain a dynamic weight Bayesian network model based on the obtained historical operation data and historical probability table; A response execution module, configured to: input the attenuation coefficient, the phase distortion feature, the turbulence energy anomaly index, and the oil degradation index into a constructed dynamic weight Bayesian network model for weight adjustment, and calculate a fault confidence level through the dynamic weight Bayesian network model after weight adjustment; A decision-making module, configured to: compare the fault confidence level with a preset fault confidence level threshold to determine a fault category, determine a maintenance strategy for the fault type, and automatically repair the hydraulic system based on the maintenance strategy; An optimization module, configured to: update the historical probability table by adjusting the weight factor of the dynamic weight Bayesian network model based on the input data, output data, and weights of the dynamic weight Bayesian network model.

[0038] In another embodiment of the present invention, a terminal device is provided. The terminal device includes a processor and a memory. The memory is used to store a computer program. The computer program includes program instructions. The processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of a method for unmanned monitoring of a hydraulic system based on hybrid perception, including: Perform time-frequency decomposition on the reflected wave data captured by emitting pressure waves into the hydraulic system, and extract the attenuation coefficient and phase distortion characteristics; analyze the ultrasonic velocity distribution map of the hydraulic system and the standard flow map to obtain the turbulent energy anomaly index; compare and analyze the obtained oil parameter data with the preset oil threshold to obtain the oil deterioration index; construct a Bayesian network model, configure the weight factors for each fault, and train a dynamic weight Bayesian network model based on historical operation data and historical probability tables; input the attenuation coefficient, the phase distortion characteristics, the turbulent energy anomaly index, and the oil deterioration index described above into the dynamic weight Bayesian network model constructed above for weight adjustment, and calculate the fault confidence through the dynamic weight Bayesian network model after weight adjustment; determine the fault category by comparing the fault confidence in the above with the preset fault confidence threshold, determine the maintenance strategy for the fault type, automatically repair the hydraulic system based on the maintenance strategy, and update the historical probability table based on the input data, output data, and weight adjustment of the weight factor of the dynamic weight Bayesian network model in the above.

[0039] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in the terminal device for storing programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and, of course, the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space that stores the operating system of the terminal. And, one or more instructions suitable for being loaded and executed by the processor are stored in this storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory (Non-Volatile Memory), such as at least one disk memory.

[0040] One or more instructions stored in the computer-readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the method for unmanned monitoring of a hydraulic system based on hybrid perception in the above embodiment; one or more instructions in the computer-readable storage medium are loaded and executed by the processor to perform the following steps: Perform time-frequency decomposition on the reflected wave data captured by emitting pressure waves into the hydraulic system, and extract the attenuation coefficient and phase distortion characteristics; analyze the ultrasonic flow velocity distribution map of the hydraulic system and the standard flow pattern map to obtain the turbulent energy anomaly index; compare and analyze the obtained oil parameter data with the preset oil threshold to obtain the oil deterioration index; construct a Bayesian network model, configure the weight factors of each fault, and train a dynamic weight Bayesian network model based on historical operation data and historical probability tables; input the attenuation coefficient, the phase distortion characteristics, the turbulent energy anomaly index, and the oil deterioration index described above into the dynamic weight Bayesian network model constructed above for weight adjustment, and calculate the fault confidence through the dynamic weight Bayesian network model after weight adjustment; compare the fault confidence in the above with the preset fault confidence threshold to determine the fault category, determine the maintenance strategy for the fault type, automatically repair the hydraulic system based on the maintenance strategy, and update the historical probability table based on the input data, output data, and weight adjustment of the weight factor of the dynamic weight Bayesian network model in the above.

[0041] Please refer to Figure 2 The terminal device is a computer device. The computer device 60 in this embodiment includes: a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61. When the computer program 63 is executed by the processor 61, it implements the fluid composition calculation method in the reservoir stimulation wellbore in the embodiment. To avoid repetition, it will not be elaborated here one by one. Alternatively, when the computer program 63 is executed by the processor 61, it implements the functions of each model / unit in the fluid composition calculation system of the reservoir stimulation wellbore in the embodiment. To avoid repetition, it will not be elaborated here one by one.

[0042] The computer device 60 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device 60 may include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art can understand that Figure 2 is only an example of the computer device 60, and does not constitute a limitation on the computer device 60. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, the computer device may also include input / output devices, network access devices, buses, etc.

[0043] The so-called processor 61 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, central processors, graphics processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, quantum computing-based data processing logic units, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0044] The memory 62 may be an internal storage unit of the computer device 60, such as the hard disk or memory of the computer device 60. The memory 62 may also be an external storage device of the computer device 60, such as a plug-in hard disk equipped on the computer device 60, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc.

[0045] Furthermore, the memory 62 may also include both the internal storage unit of the computer device 60 and the external storage device. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 may also be used to temporarily store data that has been output or is to be output.

[0046] In each of the embodiments provided in the present application, any reference to a memory, a database, or other media may include at least one of non-volatile and volatile memories. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0047] In each of the embodiments provided in the present application, the database involved may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., without limitation. In each of the embodiments provided in the present application, the processor involved may be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without limitation.

[0048] Please refer to Figure 3 , the terminal device is a chip. The chip 600 of this embodiment includes a processor 622, the number of which may be one or more, and a memory 632 for storing computer programs executable by the processor 622. The computer programs stored in the memory 632 may include one or more modules each corresponding to a set of instructions. In addition, the processor 622 may be configured to execute the computer program to perform the above-mentioned generalizable general monocular absolute depth map estimation method.

[0049] In addition, the chip 600 may further include a power supply component 626 and a communication component 650. The power supply component 626 may be configured to perform power management of the chip 600, and the communication component 650 may be configured to implement communication of the chip 600, for example, wired or wireless communication. In addition, the chip 600 may further include an input / output interface 658. The chip 600 may operate based on an operating system stored in the memory 632.

[0050] The foregoing has shown and described the basic principles, main features and advantages of the present invention. For a person skilled in the art, it is obvious that the present invention is not limited to the details of the above-mentioned exemplary embodiments, and without departing from the spirit or basic features of the present invention, the present invention can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claims concerned.

[0051] In addition, it should be understood that although this specification is described in terms of embodiments, not every embodiment only contains an independent technical solution. This narrative manner of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of the present invention, and the protection scope of the present invention cannot be limited thereby. Any modification made on the basis of the technical solution according to the technical idea proposed by the present invention falls within the protection scope of the claims of the present invention.

Claims

1. A method for unmanned monitoring of a hydraulic system based on hybrid perception, characterized in that, Including the following steps: S1. Perform time-frequency decomposition on the reflected wave data captured by reflecting the pressure wave transmitted into the hydraulic system, and extract the attenuation coefficient and phase distortion characteristics; Based on the ultrasonic velocity distribution map and the standard flow map of the hydraulic system obtained, analyze to obtain the turbulent energy anomaly index; Based on the obtained oil parameter data and the preset oil parameter threshold, conduct a comparative analysis to obtain the oil deterioration index; S2. Construct a Bayesian network model, configure the weight factors of each fault, and train to obtain a dynamic weight Bayesian network model based on historical operation data and historical probability tables; S3. Input the attenuation coefficient, the phase distortion characteristics, the turbulent energy anomaly index, and the oil deterioration index described in S1 into the dynamic weight Bayesian network model constructed in S2 for weight adjustment, and calculate the fault confidence through the dynamic weight Bayesian network model after weight adjustment; S4. Based on the comparison between the fault confidence in S3 and the preset fault confidence threshold, determine the fault category, determine the maintenance strategy for the fault type, automatically repair the hydraulic system based on the maintenance strategy, and repeat S1; S5. Update the historical probability table based on the input data, output data, and weight adjustment of the weight factors of the dynamic weight Bayesian network model in S3.

2. The method for unmanned monitoring of a hydraulic system based on hybrid perception according to claim 1, characterized in that, In S1, performing time-frequency decomposition on the reflected wave data captured by reflecting the pressure wave transmitted into the hydraulic system and extracting the attenuation coefficient and phase distortion characteristics includes: Capture the reflected waveform of the pressure wave reflected by the hydraulic system to obtain the reflected wave data; Convert the reflected wave data into analytic signal data to obtain the instantaneous phase of the reflected wave; Draw the curve of the change of phase with time through the instantaneous phase; Based on the change curve, identify the phase distortion points or phase jumps to obtain the phase distortion characteristics; Perform Fourier transform on the reflected wave data to obtain the spectrum of the signal; Identify the main frequency components and reflection amplitudes in the spectrum; Calculate the attenuation coefficient based on the emission amplitude of the obtained pressure wave and the reflection amplitude.

3. A method for unmanned monitoring of a hydraulic system based on hybrid perception according to claim 1, characterized in that, In S1, the analysis based on the ultrasonic velocity distribution map and the standard flow map of the hydraulic system obtained includes: Obtain the velocity data and turbulent intensity data on multiple cross-sections of the hydraulic system; Based on the velocity data, the turbulent intensity data, and the positions of the key nodes in the hydraulic system, draw the velocity distribution map; Analyze the velocity distribution map and the standard flow map, mark the difference points, and compare the data of the difference points on the velocity distribution map and the standard flow map to obtain the velocity deviation, turbulent intensity deviation, and map similarity; Based on the velocity deviation, the turbulent intensity deviation, and the map similarity, and set the standard weight coefficient, calculate the turbulent energy anomaly index.

4. A method for unmanned monitoring of a hydraulic system based on hybrid perception according to claim 1, characterized in that, In S1, the comparison based on the obtained oil parameter data and the preset oil parameter threshold includes: Obtain the oil parameter data, where the oil parameter data includes the oil viscosity value and the oil particle size value; Preset the oil viscosity threshold and the oil impurity threshold; Compare the viscosity value of the oil fluid with the preset oil fluid viscosity threshold, and calculate the deviation degree of the oil fluid viscosity; Compare the particle size value of the oil fluid with the oil fluid impurity threshold, and calculate the deviation degree of the oil fluid impurities; Calculate the oil fluid deterioration index based on the deviation degree of the oil fluid viscosity and the deviation degree of the oil fluid impurities; 5. A method for unmanned monitoring of a hydraulic system based on hybrid perception according to claim 1, characterized in that, In step S3, based on the attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, and the oil fluid deterioration index in step S1, input them into the dynamic weight Bayesian network model constructed in step S2 for weight adjustment, and calculate the fault confidence through the dynamic weight Bayesian network model after weight adjustment, including: Preprocess the attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, and the oil fluid deterioration index to obtain a normalized data set; Input the normalized data set into the dynamic weight Bayesian network model for dynamic weight adjustment; When the attenuation coefficient in the normalized data set exceeds the first critical value, increase the weight factor of the flow anomaly index in the dynamic weight Bayesian network model; Calculate the blockage confidence based on the attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, and the weight factor of the dynamic weight Bayesian network model after weight adjustment; When the particle size value of the oil fluid suddenly increases, increase the weight factor of the particle size value of the oil fluid when the dynamic weight Bayesian network model judges the oil circuit fault; Calculate the oil fluid deterioration confidence based on the turbulent energy anomaly index, the oil fluid deterioration index, and the weight factor of the dynamic weight Bayesian network model after weight adjustment; 6. A method for unmanned monitoring of a hydraulic system based on hybrid perception according to claim 5, characterized in that, Preprocess the attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, and the oil fluid deterioration index to obtain a normalized data set; Clean the attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, and the oil fluid deterioration index to remove noise and outliers; Perform normalization processing on the cleaned attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, and the oil fluid deterioration index so that the cleaned attenuation coefficient, the phase distortion feature, the turbulent energy anomaly index, and the oil fluid deterioration index fall within the same numerical range to obtain a normalized data set; 7. A method for unmanned monitoring of a hydraulic system based on hybrid perception according to claim 1, characterized in that In step S4, based on the comparison between the fault confidence in step S3 and the preset fault confidence threshold, judge the fault category, determine the maintenance strategy for the fault type, and automatically repair the hydraulic system based on the maintenance strategy, including: Preset the blockage confidence threshold and the oil fluid deterioration threshold; Compare the blockage confidence with the blockage confidence threshold. If the blockage confidence exceeds the blockage confidence threshold, determine it as a blockage fault, generate an oil circuit flushing maintenance strategy, and automatically repair the hydraulic system through the oil circuit flushing maintenance strategy; Obtain the coordinate data corresponding to the blockage confidence in the three-dimensional confidence space, determine the oil circuit and component numbers with local blockage in the hydraulic system through the coordinate data, and generate a detection report through the component numbers and positions; Compare the confidence level of oil degradation with the oil degradation threshold. If the confidence level of oil degradation exceeds the oil degradation threshold, it is determined as an oil quality failure. Compare the confidence level of oil degradation with a preset safety boundary threshold. When the confidence level of oil degradation exceeds the preset safety boundary threshold, generate an oil circuit switching strategy, and the hydraulic system automatically performs oil circuit switching based on the oil circuit switching strategy.

8. A hydraulic system unmanned monitoring system based on hybrid perception, applying the unmanned monitoring method for a hydraulic system based on hybrid perception according to any one of claims 1 to 7, characterized in that, Comprising: An acquisition module, configured to: capture reflected wave data of pressure wave reflections transmitted into the hydraulic system, obtain an ultrasonic flow velocity distribution map of the hydraulic system, and obtain oil parameter data. An analysis module, configured to: Perform time-frequency decomposition based on the captured reflected wave data of pressure wave reflections transmitted into the hydraulic system, and extract the attenuation coefficient and phase distortion characteristics. Analyze based on the obtained ultrasonic flow velocity distribution map of the hydraulic system and a standard flow pattern map to obtain a turbulent energy anomaly index. Compare the obtained oil parameter data with a preset oil threshold to obtain an oil degradation index. A model construction module, configured to: construct a Bayesian network model, configure weight factors for each fault, and train a dynamic weight Bayesian network model based on the obtained historical operation data and historical probability table. A response execution module, configured to: input the attenuation coefficient, the phase distortion characteristics, the turbulent energy anomaly index, and the oil degradation index into the constructed dynamic weight Bayesian network model for weight adjustment, and calculate the fault confidence level through the dynamic weight Bayesian network model after weight adjustment. A decision module, configured to: determine the fault category based on the comparison of the fault confidence level with a preset fault confidence threshold, determine the maintenance strategy for the fault type, and automatically repair the hydraulic system based on the maintenance strategy. An optimization module, configured to: update the historical probability table by adjusting the weight factors of the dynamic weight Bayesian network model based on the input data, output data, and weights of the dynamic weight Bayesian network model.

9. An electronic device, characterized in that, Comprising a memory, a processor, and a computer program stored in the memory and executable in the processor. When the processor executes the computer program, the steps of a method for unmanned monitoring of a hydraulic system based on hybrid perception according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a method for unmanned monitoring of a hydraulic system based on hybrid perception according to any one of claims 1 to 7 are implemented.

Images