Method, system and equipment for monitoring faults of hydraulic system of digging and anchoring all-in-one machine in real time

Abstract

The invention relates to the related technical field of hydraulic monitoring, in particular to a real-time monitoring method, system and equipment for faults of a hydraulic system of a digging and anchoring all-in-one machine, and the method comprises the following steps: carrying out frequency domain analysis to obtain effective fault features; drawing up an initial fault instance; and analyzing valve port coordination action characteristics, performing parameter correction in combination with the initial fault instance, and performing adaptive adjustment according to an industry safety standard to obtain a working condition adaptive fault monitoring instance. The technical problem that dynamic changes under different load working conditions cannot be adapted due to the fact that the difference of valve port coordination action characteristics under different load working conditions is not fully considered is solved, effective fault characteristics are extracted, early weak faults are sensitively captured, the timeliness of fault recognition is improved, and meanwhile the fault recognition efficiency is improved. According to the technical scheme, the cooperative action characteristics of the two-way balance valve and the proportional overflow valve are combined, targeted monitoring on abnormal actions of the valve group is enhanced, and the technical effect that a fault monitoring instance can be dynamically matched with different operation conditions through load working condition adaptive adjustment and parameter iterative optimization is achieved.

Description

Technical Field

[0001] This invention relates to the field of hydraulic monitoring technology, specifically to a method, system, and equipment for real-time monitoring of hydraulic system faults in an integrated tunneling and anchoring machine. Background Technology

[0002] As the core equipment for tunneling and support in coal mine roadways, the hydraulic system of the integrated tunneling and anchoring machine undertakes the functions of driving cutting, traveling, and anchoring. The stability of the system is directly related to tunneling efficiency, operational safety, and equipment life. In complex underground environments, hydraulic systems often experience mechanical wear, oil contamination, and pressure instability due to factors such as high load, dust pollution, and frequent start-stop. If fault monitoring and early warning are not carried out in a timely manner, it may lead to equipment shutdown, roadway construction interruption, or even safety accidents. However, in the current fault monitoring process of the hydraulic system of the integrated tunneling and anchoring machine, the differences in the coordinated action characteristics of valve ports under different load conditions are not fully considered. Fixed parameters are used for fault judgment, resulting in a significant increase in false alarm rate under high load. In addition, the detection flow of fault types such as mechanical wear and hydraulic contamination is independent of each other and lacks coupled analysis, making it impossible to form a systematic fault diagnosis scheme and failing to meet the monitoring needs of complex underground environments.

[0003] In summary, the existing technology has the technical problem of not fully considering the differences in the coordinated action characteristics of valve ports under different load conditions, and is unable to adapt to the dynamic changes under different load conditions. Summary of the Invention

[0004] This application provides a method, system, and equipment for real-time monitoring of hydraulic system faults in an integrated tunneling and anchoring machine, aiming to solve the technical problem in the prior art that it does not fully consider the differences in valve port coordinated action characteristics under different load conditions and cannot adapt to dynamic changes under different load conditions.

[0005] In view of the above problems, the technical solution to achieve the present application is as follows: In a first aspect, this application provides a real-time monitoring method for hydraulic system faults in a roadheader / anchor operator. The method includes: performing multi-scale frequency domain analysis on hydraulic signals to obtain effective fault characteristics; based on the effective fault characteristics, proposing initial fault instances for the roadheader / anchor operator's hydraulic system, the initial fault instances including mechanical wear detection flow, hydraulic contamination detection flow, and system instability detection flow; analyzing the valve port coordination action characteristics of the hydraulic solenoid valve assembly based on the bidirectional balance valve opening sequence and the proportional relief valve opening sequence, the valve port coordination action characteristics including synchronous response action characteristics and differential pressure compensation action characteristics; under different load conditions, based on the valve port coordination action characteristics, and according to the load pressure fluctuation amplitude and valve port action response delay, combining the initial fault instances to perform parameter correction, and adapting the method according to the industry safety standards of the roadheader / anchor operator, obtaining a condition-adaptive fault monitoring instance.

[0006] Preferably, the decomposition level and dynamic threshold corresponding to the multi-scale frequency domain analysis are configured; wherein, the dynamic threshold needs to reflect the statistical distribution law of the hydraulic signal.

[0007] Preferably, the effective fault features include pressure pulsation frequency, temperature change rate, and flow fluctuation coefficient; wavelet packet decomposition is performed on the pressure pulsation frequency to extract characteristic frequency components; when the energy proportion of any frequency band exceeds the abnormal energy threshold coefficient under the frequency band energy concentration criterion, an abnormal pulsation source marker is added, wherein the abnormal energy threshold coefficient is defined as the ratio of the energy value of the corresponding frequency band to the total energy value of the entire frequency band.

[0008] Preferably, a hydraulic solenoid valve assembly is connected, and a bidirectional balance valve opening sequence and a proportional relief valve opening sequence are set according to the initial fault instance; wherein, the bidirectional balance valve opening sequence includes M first working condition adapted opening values, and the proportional relief valve opening sequence includes N second working condition adapted opening values.

[0009] Preferably, the following steps are taken: collecting the time-domain acceleration signal of the hydraulic pump housing under different load conditions, the particle size distribution data of metal abrasive particles in the oil, and the temperature field distribution of the housing surface; extracting the characteristic frequency peak value from the acceleration time-domain signal; marking the characteristic frequency peak value as a potential wear vibration feature when it exceeds P times the reference peak value (P>1); and coupling the potential wear vibration feature with the particle size distribution data of metal abrasive particles in the oil and the temperature field distribution of the housing surface. After triggering the mechanical wear fault reminder command, the data is associated with the wear type of the hydraulic pump bearing or plunger pair to obtain the mechanical wear detection flow.

[0010] Preferably, an online particle counter and a moisture sensor are installed at the hydraulic oil tank outlet, return port, and key valve group interfaces; the concentration of solid particles and the moisture content in the oil are simultaneously uploaded through the online particle counter and moisture sensor; based on the concentration of solid particles and the moisture content in the oil, combined with the oil viscosity, a contamination assessment is performed to determine the hydraulic contamination detection flow.

[0011] Preferably, the pressure fluctuation curve of the main oil circuit of the hydraulic system, the speed response curve of the actuator, and the current feedback signal of the proportional relief valve are acquired. The actuator includes a cylinder and a motor. The pressure fluctuation curve of the main oil circuit of the hydraulic system is analyzed in the time domain to determine the pressure fluctuation amplitude and frequency. The overshoot and settling time are extracted from the speed response curve of the actuator. The system instability detection flow is determined by combining the pressure fluctuation amplitude and frequency, the overshoot and settling time, and the fluctuation of the current feedback signal of the proportional relief valve.

[0012] Preferably, based on the valve port action response delay and combined with the potential wear and vibration characteristics, the opening adjustment rate of the bidirectional balancing valve and the opening adjustment rate of the proportional relief valve are compensated and adjusted; simultaneously, the correlation coefficient between the load pressure fluctuation amplitude and the opening sequence of the bidirectional balancing valve and the proportional relief valve is evaluated; based on the initial fault instance and combined with the correlation coefficient, the opening sequence of the bidirectional balancing valve and the opening sequence of the proportional relief valve are iteratively optimized until the valve port action response delay and the load pressure fluctuation amplitude within at least Q monitoring cycles meet the safety margin limit in the industry safety standard, and a compensation cycle is established, wherein Q≥3.

[0013] In a second aspect, this application provides a real-time monitoring system for hydraulic system faults in a roadheader / anchor operator. The system includes: a frequency domain analysis module for performing multi-scale frequency domain analysis on hydraulic signals to obtain effective fault characteristics; a fault instance formulation module for formulating initial fault instances for the roadheader / anchor operator's hydraulic system based on the effective fault characteristics, including mechanical wear detection flow, hydraulic contamination detection flow, and system instability detection flow; a feature analysis module for analyzing the valve port coordination action characteristics of the hydraulic solenoid valve assembly based on the bidirectional balance valve opening sequence and the proportional relief valve opening sequence, including synchronous response action characteristics and differential pressure compensation action characteristics; and a parameter correction module for performing parameter correction under different load conditions based on the valve port coordination action characteristics, the load pressure fluctuation amplitude, and the valve port action response delay, combined with the initial fault instances, and adapting the system according to the industry safety standards for roadheader / anchor operators to obtain condition-adaptive fault monitoring instances.

[0014] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method for real-time monitoring of hydraulic system faults in the integrated tunneling and anchoring machine.

[0015] In summary, one or more technical solutions provided in this application achieve the extraction of effective fault features, sensitive capture of early and weak faults, and improved timeliness of fault identification. At the same time, by combining the coordinated action features of the bidirectional balancing valve and the proportional relief valve, the targeted monitoring of abnormal valve group actions is enhanced. Through load condition adaptation and parameter iterative optimization, the fault monitoring instance can dynamically match the technical effect of different operating conditions. Attached Figure Description

[0016] Figure 1 This application provides a flowchart illustrating a method for real-time monitoring of hydraulic system faults in an integrated tunneling and anchoring machine.

[0017] Figure 2 This application provides a structural schematic diagram of a real-time monitoring system for hydraulic system faults in an integrated tunneling and anchoring machine.

[0018] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0019] Explanation of reference numerals in the attached diagram: Frequency domain analysis module M100, fault instance formulation module M200, feature analysis module M300, parameter correction module M400, bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 305. Detailed Implementation

[0020] Example 1: The present application will be described in detail below with reference to the accompanying drawings, as follows... Figure 1 As shown, this application provides a real-time monitoring method for hydraulic system faults in an integrated tunneling and anchoring machine, wherein the method includes: S1: Perform multi-scale frequency domain analysis on the hydraulic signal to obtain effective fault characteristics; S2: Based on the effective fault characteristics, propose initial fault instances for the hydraulic system of the tunneling and anchoring machine, including mechanical wear detection flow, hydraulic contamination detection flow, and system instability detection flow.

[0021] Specifically, hydraulic signals refer to signals collected by various sensors (such as pressure sensors, temperature sensors, and flow sensors) in the hydraulic system of a tunneling and anchoring machine, reflecting the operating status of the system. These signals characterize the changes in parameters such as pressure, temperature, and flow rate of the hydraulic system in the form of electrical or digital signals. Multi-scale frequency domain analysis refers to the decomposition and reconstruction of hydraulic signals at multiple frequency resolution scales, commonly achieved using wavelet packet decomposition (WPD) or multi-scale one-dimensional convolutional neural networks (MS-1D-CNN), which can simultaneously capture high-frequency transient impacts and low-frequency energy drift. Effective fault features refer to indicators that characterize mechanical wear, oil contamination, or system instability after being screened by energy concentration criteria, such as pressure pulsation frequency, temperature change rate, and flow fluctuation coefficient. Initial fault instances are specific models or data templates constructed based on effective fault features to preliminarily determine the types of faults that may occur in the hydraulic system. Among them, the mechanical wear detection flow refers to the detection process for the wear of mechanical components in the hydraulic system, the hydraulic contamination detection flow refers to the detection process for the degree of hydraulic oil contamination, and the system instability detection flow refers to the detection process for monitoring whether the pressure, flow rate, etc., of the hydraulic system are stable and whether there are abnormal fluctuations.

[0022] Multi-scale frequency domain analysis of hydraulic signals is performed, and the signals are decomposed using algorithms such as wavelet transform to obtain signal characteristics in different frequency bands. Comparative analysis of hydraulic signals under normal operation and fault conditions in the roadheader-anchor integrated machine's hydraulic system reveals significant differences in energy distribution between fault signals and normal signals in certain frequency bands. For example, when the energy proportion in a certain frequency band exceeds the abnormal energy threshold coefficient under the frequency band energy concentration criterion, an abnormal pulsation source can be identified. Based on these effective fault characteristics, the process of formulating initial fault instances involves associating these characteristics with specific fault types to construct corresponding detection flows. For instance, mechanical wear may cause the peak value of the acceleration time-domain signal characteristic frequency of the hydraulic pump housing to exceed 1.2 times the reference peak value (P=1.2), thereby triggering the mechanical wear detection flow. By constructing these three types of initial fault instances, early multi-dimensional monitoring of faults in the roadheader-anchor integrated machine's hydraulic system is possible, improving the timeliness and comprehensiveness of fault monitoring and providing a basic model for subsequent parameter correction and working condition adaptation.

[0023] S3: Based on the opening sequence of the bidirectional balance valve and the opening sequence of the proportional relief valve, analyze the valve port coordinated action characteristics of the hydraulic solenoid valve assembly. The valve port coordinated action characteristics include synchronous response action characteristics and differential pressure compensation action characteristics. S4: Under different load conditions, based on the valve port coordinated action characteristics, and according to the load pressure fluctuation amplitude and valve port action response delay, combine the initial fault instance to make parameter corrections, and make adaptation adjustments according to the industry safety standards of the tunneling and anchoring machine to obtain a working condition adapted fault monitoring instance.

[0024] Specifically, the bidirectional balancing valve opening sequence refers to the discrete sampled value sequence of the valve core displacement (or pilot pressure) of the bidirectional balancing valve changing with time within the monitoring period, denoted as {x_a}. i |i=1…U}, where, x_a i Let a represent the sampled value of the valve core displacement or pilot pressure of the bidirectional balancing valve at the i-th sampling time, where a i The parameters used to identify the bidirectional balancing valve are: 'i' is the index of the sampling time, ranging from 1 to U, corresponding to each discrete sampling point within the monitoring period; and U represents the total number of times the bidirectional balancing valve opening is sampled within the entire monitoring period, i.e., the number of sampled values ​​in the sequence. The proportional relief valve opening sequence is the sampling sequence of the proportional relief valve control current or valve opening within the same period {y_b}. j |j=1…V}, where y_b jThis represents the sampled value of the control current or valve opening of the proportional relief valve at the j-th sampling time. b is used to identify the parameters related to the proportional relief valve. j is the index of the sampling time, ranging from 1 to V, corresponding to each discrete sampling point within the same monitoring period. V represents the total number of times the proportional relief valve opening is sampled within the entire monitoring period, i.e., the number of sampled values ​​contained in the sequence.

[0025] The valve port coordination characteristic refers to the temporal and functional coordination of the opening changes of the two-way balance valve and the proportional relief valve during the operation of the hydraulic system. The synchronous response characteristic refers to the simultaneous reception and rapid response of the two-way balance valve and the proportional relief valve when the hydraulic system issues a control signal, ensuring that the movement of the hydraulic cylinder is consistent with the control signal and avoiding system shocks or movement deviations caused by asynchronous valve responses. The differential pressure compensation characteristic refers to the proportional relief valve automatically adjusting its opening through its built-in differential pressure compensator during operation to maintain a constant differential pressure across the valve port, thereby ensuring stable hydraulic cylinder movement speed unaffected by load changes. The load pressure fluctuation amplitude refers to the peak-to-peak value of the main oil circuit, and the valve port response delay is defined as the time required for the actual displacement of the valve port to reach the commanded amplitude. Through parameter correction and industry safety standard adaptation adjustments, the thresholds and weights of the initial fault instances are iteratively updated, ultimately outputting condition-adaptive fault monitoring instances that can be directly deployed under different tunneling conditions.

[0026] Analyzing the valve orifice coordination characteristics based on the opening sequence of the bidirectional balance valve and the proportional relief valve is a crucial step. Specifically, precise control and adjustment of the opening sequences of the bidirectional balance valve and the proportional relief valve are essential. For instance, during different operating stages of the roadheader-anchor machine, such as cutting, traveling, or anchoring, the hydraulic system load will change significantly. By controlling the opening sequences of the bidirectional balance valve and the proportional relief valve, the coordination characteristics of their valve orifices can be matched with the actual working conditions. By analyzing and optimizing these coordination characteristics, the stability and reliability of the roadheader-anchor machine's hydraulic system can be effectively improved, the probability of failure can be reduced, and strong support can be provided for the efficient tunneling and support of coal mine roadways.

[0027] Furthermore, by performing multi-scale frequency domain analysis based on hydraulic signals to obtain effective fault characteristics, the method of this application includes: Configure the number of decomposition layers and dynamic thresholds corresponding to the multi-scale frequency domain analysis; wherein the dynamic thresholds need to reflect the statistical distribution law of the hydraulic signal.

[0028] Specifically, in this step, multi-scale frequency domain analysis refers to using wavelet packet decomposition (WPD) to perform layer-by-layer bi-band decomposition of the hydraulic pressure, flow, and temperature signals. The number of decomposition layers refers to the number of different frequency scales into which the hydraulic signal is decomposed in multi-scale frequency domain analysis. Each layer corresponds to a different frequency band. The more decomposition layers, the richer the signal details can be captured. The number of decomposition layers refers to the depth L of the wavelet packet tree, which determines the minimum bandwidth Δf = fs / 2^(L + 1), where fs is the sampling rate. The dynamic threshold is a set of judgment criteria that are automatically adjusted according to the statistical distribution of the hydraulic signal. It is used to distinguish between normal signals and fault signals. It can reflect the characteristic change law of the hydraulic signal under different operating conditions, making fault monitoring more adaptable and accurate. Furthermore, the dynamic threshold is not a fixed constant. It is an energy proportion threshold adaptively calculated based on the statistical distribution of the data in the real-time sliding window, such as the mean μ, standard deviation σ, kurtosis κ. Commonly, it is μ + kσ or a 95% confidence upper limit based on kernel density estimation to eliminate threshold mismatch caused by operating condition drift.

[0029] The configuration of the decomposition levels and dynamic thresholds for multi-scale frequency domain analysis is explained in detail below. Based on the actual working characteristics and common fault features of the roadheader's hydraulic system, the number of decomposition levels for multi-scale frequency domain analysis is determined, generally set to 3-5 levels to achieve a balance between computational complexity and signal detail capture. For example, for the hydraulic signals of a roadheader, a decomposition level of 4 levels can effectively distinguish the characteristic frequency components of normal signals from fault signals, achieving a fault identification accuracy of over 90%. The determination of the dynamic threshold is based on statistical analysis of the hydraulic signals. During normal system operation, a large number of hydraulic signal samples are collected, and their mean, standard deviation, and other statistical parameters are calculated. Based on these parameters, an initial threshold is set according to certain statistical laws (such as the 3σ principle of normal distribution). When the characteristic value of the hydraulic signal exceeds this dynamic threshold, a possible fault characteristic is identified. By reasonably configuring the decomposition levels and dynamic thresholds, effective fault characteristics can be extracted more accurately from complex hydraulic signals, providing a reliable basis for subsequent fault diagnosis, improving the timeliness and accuracy of fault monitoring, reducing false alarm and false negative rates, and thus better ensuring the stable operation of the roadheader's hydraulic system.

[0030] Furthermore, the method of this application includes: The effective fault features include pressure pulsation frequency, temperature change rate, and flow fluctuation coefficient; wavelet packet decomposition is performed on the pressure pulsation frequency to extract characteristic frequency components; when the energy proportion of any frequency band exceeds the abnormal energy threshold coefficient under the frequency band energy concentration criterion, an abnormal pulsation source is added; the abnormal energy threshold coefficient is defined as the ratio of the energy value of the corresponding frequency band to the total energy value of the entire frequency band.

[0031] Specifically, pressure pulsation frequency refers to the frequency at which pressure changes over time in a hydraulic system, reflecting the fluctuation characteristics of pressure; temperature change rate indicates the amplitude of hydraulic oil temperature change per unit time, and is a key indicator for measuring the thermal balance of the system; flow fluctuation coefficient describes the stability of hydraulic oil flow, with a smaller value indicating a more stable flow; frequency band energy ratio refers to the proportion of energy in a specific frequency band to the total energy of the entire signal; and abnormal energy threshold coefficient is a preset criterion used to identify the presence of abnormal pulsation sources, and the abnormal energy threshold coefficient is equal to E. j / E total E j That is, the percentage of energy in the j-th frequency band relative to the total energy of the entire frequency band; E total The frequency band energy concentration criterion is a statistical threshold rule: when the energy proportion of a certain frequency band exceeds the threshold set by the criterion (such as 3%), it is judged as abnormal; the abnormal pulsation source marker is a Boolean flag bit written by the system in the data stream, which is used for the immediate triggering of subsequent fault detection streams; the characteristic frequency component refers to the narrowband signal component that is directly corresponding to physical faults such as mechanical wear, cavitation or valve core oscillation after wavelet packet decomposition.

[0032] Wavelet packet decomposition is performed on the pressure pulsation frequency. Specifically, the pressure signal of the hydraulic system is collected, and then the wavelet packet decomposition algorithm is used to decompose it into different frequency bands. The characteristic frequency components of each band are extracted. For example, in the test of a certain roadheader, wavelet packet decomposition revealed that when mechanical wear faults occur in the hydraulic system, the energy proportion of the pressure pulsation frequency in the 100Hz-200Hz band increases significantly, exceeding the abnormal energy threshold coefficient during normal operation. At this time, the system automatically adds an abnormal pulsation source marker, indicating the possible mechanical wear fault, accurately capturing early weak fault characteristics, and improving the timeliness and accuracy of fault identification. By monitoring effective fault characteristics such as temperature change rate and flow fluctuation coefficient, the operating status of the hydraulic system can be comprehensively evaluated, providing a reliable basis for subsequent fault diagnosis and handling, effectively reducing the risk of equipment failure, and ensuring the stable operation and safety of the roadheader.

[0033] Furthermore, by combining initial failure instances to correct parameters, the method of this application includes: Connect the hydraulic solenoid valve assembly, and based on the initial fault instance, set the bidirectional balance valve opening sequence and the proportional relief valve opening sequence; wherein, the bidirectional balance valve opening sequence includes M first working condition adapted opening values, and the proportional relief valve opening sequence includes N second working condition adapted opening values.

[0034] Specifically, the hydraulic solenoid valve assembly is a key control component in the hydraulic system of the tunneling and anchoring machine, used to regulate the pressure, flow, and direction of hydraulic oil to achieve precise control of the actuator; the two-way balance valve balances the pressure on both sides of the hydraulic cylinder by adjusting its opening degree, ensuring the stable movement of the hydraulic cylinder under different loads. Its opening sequence refers to the change law of the opening degree of the two-way balance valve with time or control signal under different working conditions, with each opening value corresponding to specific load conditions and motion requirements; the proportional relief valve is a valve that can accurately adjust the relief pressure according to the input electrical signal. Its opening sequence also refers to the change law of the opening degree of the proportional relief valve with time or control signal under different working conditions, maintaining the stability of system pressure by adjusting the opening degree.

[0035] The operating condition adaptation opening value refers to the pre-set opening values ​​of the bidirectional balance valve and proportional relief valve that enable the hydraulic system to achieve optimal performance based on different operating conditions of the tunneling and anchoring machine (such as cutting, traveling, anchoring, etc.). These opening values ​​are determined through a large number of experiments and data analysis to ensure the stable operation of the hydraulic system under various complex operating conditions. Connecting the hydraulic solenoid valve assembly refers to establishing a closed-loop data link between the bidirectional balance valve, proportional relief valve and the onboard controller through a CAN bus or analog channel, so that the opening command, feedback current and diagnostic information can be communicated in real time. The bidirectional balance valve opening sequence is the M discrete valve core displacement percentages (0%–100%) output by the controller to maintain load balance under the current operating condition. Similarly, the proportional relief valve opening sequence is the N valve port opening percentages used to limit the maximum pressure of the system. The two sequences together constitute the input of the valve port coordinated action characteristics, which are used for the next step of synchronous response and differential pressure compensation analysis.

[0036] Based on initial fault examples, the opening sequence of the bidirectional balance valve and proportional relief valve is set. Specifically, the hydraulic solenoid valve assembly is connected to the hydraulic system and then to the controller. This ensures that the controller can monitor the system's operating status in real time. Based on the monitoring data and fault characteristics from the initial fault examples, corresponding opening adjustment strategies are formulated. For example, when the roadheader is performing cutting operations, the load is large and changes frequently. The system needs to be set with a larger bidirectional balance valve opening value and an appropriate proportional relief valve opening value to ensure that the hydraulic cylinder can stably push the cutting head and that the system pressure is not too high. This ensures the stable operation of the hydraulic system under different load conditions, provides accurate basic data for subsequent fault monitoring, and also improves the overall operating efficiency and safety of the roadheader.

[0037] Furthermore, the initial fault instances include mechanical wear detection streams, hydraulic contamination detection streams, and system instability detection streams. The method of this application includes: The system collects the time-domain acceleration signal of the hydraulic pump housing under different load conditions, the particle size distribution data of metal abrasive particles in the oil, and the temperature field distribution of the housing surface. It extracts the characteristic frequency peak from the acceleration time-domain signal. When the characteristic frequency peak exceeds P times the reference peak, it is marked as a potential wear vibration feature (P > 1). Based on the particle size distribution data of metal abrasive particles in the oil and the temperature field distribution of the housing surface, it couples the potential wear vibration features with the data. After triggering a mechanical wear fault warning command, it is associated with the wear type of the hydraulic pump bearing or plunger pair to obtain the mechanical wear detection flow.

[0038] Specifically, the acceleration time-domain signal refers to the signal of the vibration acceleration of the hydraulic pump housing under different load conditions as a function of time, reflecting the motion state and vibration characteristics of the internal mechanical components of the pump. Specifically, the vibration acceleration waveform corresponding to the acceleration time-domain signal is continuously recorded by a triaxial MEMS accelerometer arranged radially, axially, and tangentially on the surface of the hydraulic pump housing at a sampling frequency of 10kHz. The particle size distribution data of metal abrasive particles in the oil refers to the distribution of different particle sizes of metal abrasive particles in the oil measured by oil analysis instruments, characterizing the degree and type of mechanical wear. It is obtained by an online laser particle size analyzer or an inductive metal abrasive sensor, and the number density of ferromagnetic / non-ferromagnetic particles in the range of 0–150µm is statistically analyzed.

[0039] The surface temperature field distribution of the hydraulic pump casing refers to the spatial distribution of the surface temperature of the hydraulic pump casing, reflecting the internal heat load and heat transfer status of the pump. Specifically, the surface temperature field distribution of the casing is acquired by a patch thermocouple array (spatial resolution 20mm×20mm) or an infrared thermal imager to capture friction hot spots. The characteristic frequency peak value is the amplitude of the pump shaft rotation frequency (BPF), gear meshing frequency (GMF), and their harmonics in the spectrum obtained by FFT of the above acceleration signal. The potential wear vibration characteristics refer to the vibration characteristics caused by mechanical wear when the characteristic frequency peak value exceeds the normal reference peak value by a certain multiple (P times, P>1). Coupling refers to mapping the three heterogeneous characteristics of vibration, abrasive particles, and temperature to the same decision space for joint probabilistic inference. The mechanical wear fault warning instruction is the warning signal issued by the system when the monitoring data shows that there is a potential mechanical wear fault. The wear type of the hydraulic pump bearing or plunger pair refers to the specific fault form of the bearing or plunger pair components inside the hydraulic pump due to mechanical wear, such as pitting, scratches, and wear.

[0040] The system collects the time-domain acceleration signal of the hydraulic pump housing under different load conditions, the particle size distribution data of metal abrasive particles in the oil, and the temperature field distribution of the housing surface. Specifically, during high-load cutting operations of the tunneling and anchoring machine, the acceleration time-domain signal is collected by an acceleration sensor installed on the hydraulic pump housing. At the same time, the particle size distribution of metal abrasive particles in the oil is measured using an oil analysis instrument, and the temperature field distribution of the housing surface is obtained using an infrared thermal imager. The collected acceleration time-domain signal is analyzed in the frequency domain to extract the characteristic frequency peak. For example, under normal operating conditions, the reference peak frequency of the hydraulic pump is f0, and the amplitude is A0. When the characteristic frequency peak exceeds P times the reference peak (e.g., P=1.5), that is, the amplitude reaches 1.5A0, it is marked as a potential wear vibration characteristic.

[0041] The particle size distribution data of metal abrasive particles in the hydraulic fluid (e.g., a 20% increase in the concentration of abrasive particles larger than 10 μm) and the temperature field distribution on the shell surface (e.g., a local temperature increase of 15°C) are coupled with potential wear vibration characteristics for analysis. If an increase in metal abrasive particle concentration, a local temperature increase, and potential wear vibration characteristics occur simultaneously, a mechanical wear fault warning command is triggered. Based on the coupling analysis results, the specific wear type of the hydraulic pump bearing or plunger pair is correlated, such as pitting wear of the bearing or scratch wear of the plunger pair, thus forming a mechanical wear detection flow. In the above steps, through the fusion analysis of multi-source data, early and accurate diagnosis of mechanical wear faults is achieved, providing detailed information for subsequent fault handling, effectively improving the reliability and safety of the hydraulic system of the tunneling and anchoring machine, and reducing equipment downtime caused by mechanical wear faults.

[0042] Furthermore, the initial fault instances include mechanical wear detection streams, hydraulic contamination detection streams, and system instability detection streams. The method of this application includes: Online particle counters and moisture sensors are installed at the hydraulic oil tank outlet, return port, and key valve group interfaces. The concentration of solid particles and moisture content in the oil are simultaneously uploaded through the online particle counters and moisture sensors. Based on the concentration of solid particles and moisture content in the oil, combined with the oil viscosity, a contamination assessment is performed to determine the hydraulic contamination detection flow.

[0043] Specifically, online particle counters are sensors that monitor the concentration of solid particles in oil in real time. They detect the number and size distribution of particles in the oil using principles such as laser scattering or impedance and output the particle size distribution according to ISO 4406 code. Moisture sensors are used to monitor the moisture content in oil in real time. They are usually based on capacitive or oscillatory principles and can accurately measure the moisture concentration in oil, with results expressed in ppm or %RH. Solid particle concentration refers to the number of solid particles in a unit volume of oil, usually expressed as particles / 100mL or mg / 100mL, reflecting the concentration of solid particles in the oil. The content of impurities; water content refers to the mass percentage or volume percentage of water in the oil, reflecting the degree of water content in the oil; oil viscosity is a measure of the internal friction force of the oil when it flows, usually expressed as dynamic viscosity (unit: Pa·s) or kinematic viscosity (unit: mm² / s), which affects the fluidity and lubrication performance of the oil. Oil viscosity is continuously measured using an online vibrating string viscometer or a differential pressure viscometer; contamination assessment maps solid particle concentration, water content and viscosity to the same contamination index model, generating trigger thresholds and health scores for hydraulic contamination detection flow in real time.

[0044] Online particle counters and moisture sensors are installed at the oil outlet, return port, and key valve assembly interfaces of the hydraulic oil tank. Specifically, in the hydraulic system of the tunneling and anchoring machine, online particle counters and moisture sensors are installed at the oil tank outlet, return port, and interfaces of the main valve assembly and actuators, respectively. These sensors can monitor the concentration of solid particles and moisture content in the oil in real time and synchronously upload the data to the monitoring system. For example, the concentration of solid particles in the oil should be less than 1000 particles / 100mL, and the moisture content should be less than 0.1%. When the monitoring data shows that the concentration of solid particles exceeds 1500 particles / 100mL or the moisture content exceeds 0.15%, the system determines that the oil contamination level exceeds the standard. At this time, combined with the change in oil viscosity (e.g., a 15% increase in viscosity), a comprehensive contamination assessment can be performed to more accurately determine the contamination status of the hydraulic system and thus determine the hydraulic contamination detection flow. In the above steps, by monitoring the oil contamination status in real time, contamination problems in the hydraulic system can be detected in a timely manner, providing a basis for subsequent fault diagnosis and maintenance, helping to extend the service life of the hydraulic system and improve the reliability and efficiency of the system.

[0045] Furthermore, the initial fault instances include mechanical wear detection streams, hydraulic contamination detection streams, and system instability detection streams. The method of this application includes: The pressure fluctuation curve of the main oil circuit of the hydraulic system, the speed response curve of the actuator, and the current feedback signal of the proportional relief valve are acquired. The actuator includes a cylinder and a motor. Time-domain analysis is performed on the pressure fluctuation curve of the main oil circuit of the hydraulic system to determine the pressure fluctuation amplitude and frequency. Overshoot and settling time are extracted from the speed response curve of the actuator. The system instability detection flow is determined by combining the pressure fluctuation amplitude and frequency, overshoot and settling time with the fluctuation of the current feedback signal of the proportional relief valve.

[0046] Specifically, the pressure fluctuation curve refers to the curve showing the pressure change over time in the main oil circuit of a hydraulic system, reflecting the dynamic characteristics of pressure changes. For example, the continuous pressure waveform obtained by a 0–40MPa piezoresistive pressure sensor sampled at 2kHz between the main pump outlet and the main valve P port of a roadheader is the pressure fluctuation curve of the main oil circuit of the hydraulic system. The speed response curve of the actuator refers to the curve showing the speed change over time of the actuator (such as a cylinder or motor) in the hydraulic system, reflecting the response characteristics of the actuator to the control signal. The current feedback signal of the proportional relief valve refers to the closed-loop sampling value of the current of the proportional electromagnet coil, reflecting the actual position of the valve core. The overshoot is defined as the percentage of the difference between the peak speed and the steady-state speed to the steady-state speed, reflecting the overshoot characteristics of the system. The settling time is the time required for the speed of the actuator to reach and stabilize near the target speed from the initial state, reflecting the response speed and stability of the system. The current feedback signal is the current signal flowing through the coil of the proportional relief valve when it is working, and its fluctuation reflects the stability of the valve's working state.

[0047] The pressure fluctuation curve of the main oil circuit of the hydraulic system, the speed response curve of the actuator, and the current feedback signal of the proportional relief valve are obtained. Specifically, the pressure fluctuation curve is collected by a pressure sensor installed on the main oil circuit, the speed response curve is collected by a speed sensor installed on the cylinder and motor, and the current feedback signal of the proportional relief valve is collected by a current sensor. Time-domain analysis of the pressure fluctuation curve can determine the amplitude and frequency of the pressure fluctuation. For example, under normal operating conditions, the pressure fluctuation amplitude should be less than 1 MPa and the fluctuation frequency should be less than 10 Hz. When the pressure fluctuation amplitude exceeds 1.5 MPa or the fluctuation frequency is higher than 15 Hz, it indicates that there is a pressure instability problem in the system.

[0048] By extracting the overshoot and settling time from the speed response curve, it can be compared that under normal operating conditions, the cylinder speed overshoot should be less than 10% and the settling time should be less than 2 seconds. When the overshoot exceeds 15% or the settling time exceeds 3 seconds, it indicates a decrease in the response performance of the actuator. Combining the fluctuation of the current feedback signal of the proportional relief valve (a current fluctuation exceeding 0.5A is considered an abnormal fluctuation), it is possible to further determine whether there is instability in the system. Through the above steps, the system instability detection flow is determined, and the unstable state of the hydraulic system is detected in a timely manner, providing a basis for subsequent fault diagnosis and handling, thereby improving the stability and reliability of the hydraulic system of the tunneling and anchoring machine and reducing equipment failures and downtime caused by system instability.

[0049] Furthermore, based on the load pressure fluctuation amplitude and valve orifice response delay, and combined with initial fault examples, parameter corrections are performed. The method of this application includes: Based on the valve action response delay and the potential wear and vibration characteristics, the opening adjustment rate of the bidirectional balancing valve and the proportional relief valve are compensated and adjusted. Simultaneously, the correlation coefficient between the load pressure fluctuation amplitude and the opening sequence of the bidirectional balancing valve and the proportional relief valve is evaluated. Based on the initial fault instance and the correlation coefficient, the opening sequence of the bidirectional balancing valve and the proportional relief valve is iteratively optimized until the valve action response delay and load pressure fluctuation amplitude within at least Q monitoring cycles meet the safety margin limits in industry safety standards, establishing a compensation loop where Q ≥ 3.

[0050] Specifically, valve port action response delay refers to the time difference required for the hydraulic solenoid valve assembly to actually start acting after receiving a control signal, reflecting the valve's response speed; compensation adjustment refers to adjusting the valve opening adjustment rate according to the monitored delay to reduce the impact of the delay on system performance; the opening adjustment rate of the bidirectional balancing valve and the opening adjustment rate of the proportional relief valve refer to the percentage change in valve core stroke that the two valves can achieve per unit time; the correlation coefficient refers to the degree of correlation between the load pressure fluctuation amplitude and the opening sequence of the bidirectional balancing valve and the opening sequence of the proportional relief valve. By calculating the correlation coefficient, the quantitative relationship between pressure fluctuation and valve opening can be understood; iterative optimization refers to adjusting the opening sequence of the bidirectional balancing valve and the proportional relief valve multiple times based on the initial fault instance and the correlation coefficient to achieve the best monitoring effect; the compensation cycle is an iterative closed loop: each complete process of data acquisition → correlation analysis → parameter correction → performance verification is called one monitoring cycle. If the industry safety margin is met for Q (≥3) consecutive cycles, the cycle converges and the final sequence is solidified.

[0051] The opening adjustment rate of the bidirectional balance valve and the proportional relief valve is compensated and adjusted based on the valve orifice action response delay and potential wear and vibration characteristics. Specifically, the valve orifice action response delay data is obtained through a monitoring system, and the causes of the delay are analyzed in conjunction with potential wear and vibration characteristics, such as wear of mechanical parts or contamination of hydraulic oil. Based on the analysis results, the opening adjustment rate of the bidirectional balance valve and the proportional relief valve is compensated and adjusted. For example, if the valve orifice action response delay time is detected to increase by 0.2 seconds and there are obvious wear and vibration characteristics, then the impact of the delay can be reduced by increasing the opening adjustment rate.

[0052] Meanwhile, by monitoring the load pressure fluctuation amplitude, correlation analysis is used to calculate the correlation coefficient between the load pressure fluctuation amplitude and the opening sequence of the bidirectional balance valve and the proportional relief valve. If the correlation coefficient is 0.8, it indicates a strong positive correlation between pressure fluctuation and valve opening. Based on the initial fault instance and combined with the correlation coefficient, the opening sequence of the bidirectional balance valve and the proportional relief valve is iteratively optimized. Furthermore, within at least three monitoring cycles, the opening sequence is continuously adjusted so that the valve action response delay and load pressure fluctuation amplitude gradually meet the safety margin limits in industry safety standards. This effectively improves the stability and reliability of the hydraulic system, reduces the risk of failure caused by valve delay and pressure fluctuation, and provides a guarantee for the normal operation of the tunneling and anchoring machine.

[0053] In summary, the beneficial effects of the embodiments of this application are: By employing multi-scale frequency domain analysis based on hydraulic signals, effective fault characteristics are obtained. Based on these characteristics, initial fault instances of the roadheader-anchor integrated machine's hydraulic system are proposed, including mechanical wear detection flow, hydraulic contamination detection flow, and system instability detection flow. Based on the opening sequence of the bidirectional balance valve and the opening sequence of the proportional relief valve, the valve port coordination action characteristics of the hydraulic solenoid valve assembly are analyzed, including synchronous response action characteristics and differential pressure compensation action characteristics. Under different load conditions, based on the valve port coordination action characteristics and considering the load pressure fluctuation amplitude and valve port action response delay, parameters are corrected in conjunction with the initial fault instances, and adapted according to industry safety standards for roadheader-anchor integrated machines, resulting in condition-adaptive fault monitoring instances. This application provides a real-time monitoring method, system, and equipment for faults in the hydraulic system of a roadheader-anchor integrated machine. It achieves the extraction of effective fault features, sensitive capture of early and weak faults, and improves the timeliness of fault identification. At the same time, by combining the coordinated action features of bidirectional balancing valves and proportional relief valves, it enhances the targeted monitoring of abnormal valve group actions. Through load condition adaptation and parameter iterative optimization, it enables the fault monitoring instance to dynamically match the technical effects of different operating conditions.

[0054] Example 2, based on the same inventive concept as the real-time monitoring method for hydraulic system faults of the integrated tunneling and anchoring machine in the foregoing examples, such as... Figure 2 As shown in the embodiment of this application, a real-time monitoring system for hydraulic system faults in a tunneling and anchoring machine is provided, wherein the system includes: Frequency domain analysis module M100: Performs multi-scale frequency domain analysis based on hydraulic signals to obtain effective fault characteristics.

[0055] Fault Instance Proposal Module M200: Based on the effective fault characteristics, propose initial fault instances for the hydraulic system of the tunneling and anchoring machine. The initial fault instances include mechanical wear detection flow, hydraulic contamination detection flow, and system instability detection flow.

[0056] Feature Analysis Module M300: Based on the bidirectional balance valve opening sequence and the proportional relief valve opening sequence, analyzes the valve port coordinated action characteristics of the hydraulic solenoid valve assembly. The valve port coordinated action characteristics include synchronous response action characteristics and differential pressure compensation action characteristics.

[0057] Parameter correction module M400: Under different load conditions, based on the valve port coordinated action characteristics, and according to the load pressure fluctuation amplitude and valve port action response delay, combined with the initial fault instance, the parameters are corrected, and adapted according to the industry safety standards of the tunneling and anchoring machine to obtain a working condition adapted fault monitoring instance.

[0058] Furthermore, the frequency domain analysis module M100 is used to perform the following method: Configure the number of decomposition layers and dynamic thresholds corresponding to the multi-scale frequency domain analysis; wherein the dynamic thresholds need to reflect the statistical distribution law of the hydraulic signal.

[0059] Furthermore, the frequency domain analysis module M100 is also used to perform the following methods: The effective fault features include pressure pulsation frequency, temperature change rate, and flow fluctuation coefficient; wavelet packet decomposition is performed on the pressure pulsation frequency to extract characteristic frequency components; when the energy proportion of any frequency band exceeds the abnormal energy threshold coefficient under the frequency band energy concentration criterion, an abnormal pulsation source is added; the abnormal energy threshold coefficient is defined as the ratio of the energy value of the corresponding frequency band to the total energy value of the entire frequency band.

[0060] Furthermore, the parameter correction module M400 is used to perform the following method: Connect the hydraulic solenoid valve assembly, and based on the initial fault instance, set the bidirectional balance valve opening sequence and the proportional relief valve opening sequence; wherein, the bidirectional balance valve opening sequence includes M first working condition adapted opening values, and the proportional relief valve opening sequence includes N second working condition adapted opening values.

[0061] Furthermore, the fault instance proposing module M200 is used to execute the following method: The system collects the time-domain acceleration signal of the hydraulic pump housing under different load conditions, the particle size distribution data of metal abrasive particles in the oil, and the temperature field distribution of the housing surface. It extracts the characteristic frequency peak from the acceleration time-domain signal. When the characteristic frequency peak exceeds P times the reference peak, it is marked as a potential wear vibration feature (P > 1). Based on the particle size distribution data of metal abrasive particles in the oil and the temperature field distribution of the housing surface, it couples the potential wear vibration features with the data. After triggering a mechanical wear fault warning command, it is associated with the wear type of the hydraulic pump bearing or plunger pair to obtain the mechanical wear detection flow.

[0062] Furthermore, the fault instance proposing module M200 is also used to perform the following method: Online particle counters and moisture sensors are installed at the hydraulic oil tank outlet, return port, and key valve group interfaces. The concentration of solid particles and moisture content in the oil are simultaneously uploaded through the online particle counters and moisture sensors. Based on the concentration of solid particles and moisture content in the oil, combined with the oil viscosity, a contamination assessment is performed to determine the hydraulic contamination detection flow.

[0063] Furthermore, the fault instance proposing module M200 is also used to perform the following method: The pressure fluctuation curve of the main oil circuit of the hydraulic system, the speed response curve of the actuator, and the current feedback signal of the proportional relief valve are acquired. The actuator includes a cylinder and a motor. Time-domain analysis is performed on the pressure fluctuation curve of the main oil circuit of the hydraulic system to determine the pressure fluctuation amplitude and frequency. Overshoot and settling time are extracted from the speed response curve of the actuator. The system instability detection flow is determined by combining the pressure fluctuation amplitude and frequency, overshoot and settling time with the fluctuation of the current feedback signal of the proportional relief valve.

[0064] Furthermore, the parameter correction module M400 is also used to perform the following method: Based on the valve action response delay and the potential wear and vibration characteristics, the opening adjustment rate of the bidirectional balancing valve and the proportional relief valve are compensated and adjusted. Simultaneously, the correlation coefficient between the load pressure fluctuation amplitude and the opening sequence of the bidirectional balancing valve and the proportional relief valve is evaluated. Based on the initial fault instance and the correlation coefficient, the opening sequence of the bidirectional balancing valve and the proportional relief valve is iteratively optimized until the valve action response delay and load pressure fluctuation amplitude within at least Q monitoring cycles meet the safety margin limits in industry safety standards, establishing a compensation loop where Q ≥ 3.

[0065] Example 3: Based on the same inventive concept as the real-time monitoring method for hydraulic system faults of the integrated tunneling and anchoring machine in Example 1, the present invention also provides an electronic device, including: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the method described in Example 1.

[0066] like Figure 3 As shown, the bus architecture is represented by bus 300. Bus 300 may include any number of interconnected buses and bridges, connecting various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 during operation.

[0067] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for real-time monitoring of hydraulic system faults in an integrated tunneling and anchoring machine, characterized in that, The method includes: Effective fault characteristics are obtained by performing multi-scale frequency domain analysis on hydraulic signals. Based on the aforementioned effective fault characteristics, initial fault instances of the hydraulic system of the tunneling and anchoring machine are proposed. The initial fault instances include mechanical wear detection flow, hydraulic contamination detection flow, and system instability detection flow. Based on the opening sequence of the bidirectional balance valve and the opening sequence of the proportional relief valve, the valve port coordinated action characteristics of the hydraulic solenoid valve assembly are analyzed. The valve port coordinated action characteristics include synchronous response action characteristics and differential pressure compensation action characteristics. Under different load conditions, based on the valve port coordinated action characteristics, and according to the load pressure fluctuation amplitude and valve port action response delay, the parameters are corrected in conjunction with the initial fault instance, and adapted and adjusted according to the industry safety standards of the tunneling and anchoring machine, to obtain a working condition adapted fault monitoring instance.

2. The real-time monitoring method for hydraulic system faults of the integrated tunneling and anchoring machine as described in claim 1, characterized in that, The method involves performing multi-scale frequency domain analysis on hydraulic signals to obtain effective fault characteristics. Configure the number of decomposition layers and dynamic thresholds for multi-scale frequency domain analysis; The dynamic threshold needs to reflect the statistical distribution pattern of the hydraulic signal.

3. The real-time monitoring method for hydraulic system faults of the integrated tunneling and anchoring machine as described in claim 2, characterized in that, The method includes: The effective fault characteristics include pressure pulsation frequency, temperature change rate, and flow fluctuation coefficient. Wavelet packet decomposition is performed on the pressure pulsation frequency to extract characteristic frequency components. When the energy proportion of any frequency band exceeds the abnormal energy threshold coefficient under the frequency band energy concentration criterion, an abnormal pulsation source is added. The abnormal energy threshold coefficient is defined as the ratio of the energy value of the corresponding frequency band to the total energy value of the entire frequency band.

4. The real-time monitoring method for hydraulic system faults of the integrated tunneling and anchoring machine as described in claim 1, characterized in that, The method for parameter correction based on initial fault instances includes: Connect the hydraulic solenoid valve assembly, and set the bidirectional balance valve opening sequence and the proportional relief valve opening sequence according to the initial fault example; The bidirectional balance valve opening sequence includes M first operating condition adapted opening values, and the proportional relief valve opening sequence includes N second operating condition adapted opening values.

5. The real-time monitoring method for hydraulic system faults of the integrated tunneling and anchoring machine as described in claim 4, characterized in that, The initial fault examples include mechanical wear detection streams, hydraulic contamination detection streams, and system instability detection streams; the method includes: The acceleration time-domain signal of the hydraulic pump housing under different load conditions, the particle size distribution data of metal abrasive particles in the oil, and the temperature field distribution on the housing surface were collected. The characteristic frequency peak is extracted from the acceleration time-domain signal. When the characteristic frequency peak exceeds the reference peak by P times, it is marked as a potential wear vibration feature, where P>1. Based on the particle size distribution data of metal abrasive particles in the oil and the temperature field distribution of the shell surface, and coupled with the potential wear vibration characteristics, after triggering the mechanical wear fault reminder command, it is associated with the wear type of the hydraulic pump bearing or plunger pair to obtain the mechanical wear detection flow.

6. The real-time monitoring method for hydraulic system faults of the integrated tunneling and anchoring machine as described in claim 4, characterized in that, The initial fault examples include mechanical wear detection streams, hydraulic contamination detection streams, and system instability detection streams; the method includes: Online particle counters and moisture sensors are installed at the hydraulic oil tank outlet, return port, and key valve group interfaces; The concentration of solid particles and the moisture content in the oil are simultaneously uploaded through the online particle counter and the moisture sensor. Based on the concentration of solid particles and water content in the oil, combined with the oil viscosity, a contamination assessment is performed to determine the hydraulic contamination detection flow.

7. The real-time monitoring method for hydraulic system faults of the integrated tunneling and anchoring machine as described in claim 5, characterized in that, The initial fault examples include mechanical wear detection streams, hydraulic contamination detection streams, and system instability detection streams; the method includes: The pressure fluctuation curve of the main oil circuit of the hydraulic system, the speed response curve of the actuator, and the current feedback signal of the proportional relief valve are obtained. The actuator includes a hydraulic cylinder and a motor. Time-domain analysis was performed on the pressure fluctuation curve of the main oil circuit of the hydraulic system to determine the pressure fluctuation amplitude and frequency. The overshoot and settling time are extracted from the speed response curve of the actuator. The system instability detection flow is determined by combining the pressure fluctuation amplitude and frequency, overshoot and settling time with the fluctuation of the current feedback signal from the proportional relief valve.

8. The real-time monitoring method for hydraulic system faults of the integrated tunneling and anchoring machine as described in claim 7, characterized in that, Based on the load pressure fluctuation amplitude and valve orifice response delay, and combined with initial fault examples, parameter correction is performed. The method includes: Based on the valve port action response delay and combined with the potential wear and vibration characteristics, the opening adjustment rate of the bidirectional balance valve and the opening adjustment rate of the proportional relief valve are compensated and adjusted. Simultaneously, the correlation coefficients with the opening sequence of the bidirectional balance valve and the opening sequence of the proportional relief valve are evaluated based on the load pressure fluctuation amplitude. Based on the initial fault instance and the correlation coefficient, the opening sequence of the bidirectional balance valve and the opening sequence of the proportional relief valve are iteratively optimized until the valve action response delay and load pressure fluctuation amplitude within at least Q monitoring cycles meet the safety margin limit in the industry safety standard, and a compensation loop is established, wherein Q≥3.

9. A real-time monitoring system for hydraulic system faults in an integrated tunneling and anchoring machine, characterized in that, The steps for implementing the real-time monitoring method for hydraulic system faults of the tunneling and anchoring machine according to any one of claims 1-8, wherein the system comprises: Frequency domain analysis module: Performs multi-scale frequency domain analysis based on hydraulic signals to obtain effective fault characteristics; Fault Instance Proposal Module: Based on the effective fault characteristics, propose initial fault instances for the hydraulic system of the tunneling and anchoring machine. The initial fault instances include mechanical wear detection flow, hydraulic contamination detection flow, and system instability detection flow. Feature Analysis Module: Based on the opening sequence of the bidirectional balance valve and the opening sequence of the proportional relief valve, the valve port coordinated action characteristics of the hydraulic solenoid valve assembly are analyzed. The valve port coordinated action characteristics include synchronous response action characteristics and differential pressure compensation action characteristics. Parameter correction module: Under different load conditions, based on the valve port coordinated action characteristics, and according to the load pressure fluctuation amplitude and valve port action response delay, combined with the initial fault instance, the parameters are corrected, and adapted according to the industry safety standards of the tunneling and anchoring machine to obtain a working condition adapted fault monitoring instance.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the real-time monitoring method for hydraulic system faults of the tunneling and anchoring machine as described in any one of claims 1-8.

Images