Wear detection method and system, terminal and storage medium

Abstract

The invention relates to a wear detection method and system, a terminal and a storage medium, and relates to the technical field of wear detection.The wear detection method comprises the steps that after a pretreatment device is controlled to conduct pretreatment on a wear detection device, the wear detection device is controlled to conduct detection on lubricating oil, and a wear detection signal is generated; inputting the wear detection signal into a time sequence feature extraction sub-module for feature extraction so as to generate a signal time sequence feature vector; analyzing the signal time sequence feature vector based on a random forest algorithm to generate a copper-containing abrasive particle analysis result; judging whether the copper-containing abrasive particle analysis result is a copper-containing abrasive particle result or a copper-free abrasive particle result; if the abrasive particles do not contain copper, continuously controlling the wear detection device to detect the lubricating oil so as to generate a wear detection signal for cyclic judgment; and if the result is that the abrasive particles contain copper, analyzing the signal time sequence feature vector to generate copper abrasive particle parameters. The method has the effect of improving the timeliness of wear detection.

Description

Technical Field

[0001] This application relates to the technical field of wear detection, and in particular to a wear detection method, system, terminal, and storage medium. Background Technology

[0002] Wear detection refers to a technical method that uses wear detection devices to capture wear signals generated by the wear of the copper bushing of a cone crusher during operation, in order to determine whether the wear is normal or abnormal and to ensure that the wear condition of the bushing can be reflected in a timely and accurate manner.

[0003] In related technologies, most focus is on the identification and analysis of ferromagnetic particles. This involves collecting samples of the lubricating oil after the cone crusher has been running for a certain period of time, then installing an inductive abrasive sensor in the lubrication system pipeline to detect the concentration and size distribution of ferromagnetic particles in the flowing oil in real time. Finally, the condition of the copper bushing is inferred from this correlation. Since the copper bushing itself is a non-ferromagnetic material, the copper abrasive particles it produces cannot be effectively detected by the inductive sensor. Therefore, when abnormally high wear signals appear on iron parts such as the main shaft or eccentric sleeve, it proves that the copper bushing of the cone crusher has worn out and failed, leading to direct friction between the iron parts.

[0004] Regarding the aforementioned technologies, when the wear detection device detects and correlates abnormally high wear signals on ferrous components to infer the condition of copper bushings, it fails to distinguish between copper abrasive particles and ferromagnetic particles, thus failing to capture the key signals of early wear of the bushings in a timely and accurate manner. This results in poor timeliness of wear detection, and there is still room for improvement. Summary of the Invention

[0005] To improve the timeliness of wear detection, this application provides a wear detection method, system, terminal, and storage medium.

[0006] Firstly, this application provides a wear detection method, which adopts the following technical solution: A wear detection method, comprising: After the preset pre-processing device performs pre-processing on the preset wear detection device, the pre-processed wear detection device is controlled to detect the lubricating oil in the preset cone crusher lubricating oil tank to generate a wear detection signal. The wear detection signal is input into a preset time-series feature extraction submodule for feature extraction to generate a signal time-series feature vector; The signal time-series feature vector is analyzed based on a pre-defined random forest algorithm to generate copper-containing abrasive particle analysis results. The analysis results of copper-containing abrasive particles are determined to be either the preset copper-containing abrasive particle result or the preset copper-free abrasive particle result. If the abrasive grains do not contain copper, the wear detection device continues to monitor the lubricating oil in the cone crusher's lubricating oil tank to generate wear detection signals for cyclic judgment. If the abrasive grains contain copper, then the signal timing feature vector is analyzed to generate copper abrasive grain parameters; The copper abrasive parameters are uploaded to a pre-set host computer for wear warning.

[0007] By adopting the above technical solution, the pre-processing device is first controlled to pre-process the wear detection device, and then the pre-processed wear detection device is controlled to detect the lubricating oil in the lubricating oil tank of the cone crusher to determine the wear detection signal. The wear detection signal is input into the time-series feature extraction submodule for feature extraction to determine the signal time-series feature vector. The signal time-series feature vector is analyzed according to the random forest algorithm to determine the copper-containing abrasive analysis result. When the copper-containing abrasive analysis result is determined to be the result of copper-containing abrasive, the signal time-series feature vector is analyzed to determine the copper abrasive parameters. Finally, the determined copper abrasive parameters are uploaded to the host computer for wear early warning, thereby timely and accurately capturing the key signal of early wear of the bushing and improving the timeliness of wear detection.

[0008] Optionally, the step of controlling the pre-treated wear detection device to detect the lubricating oil in the preset cone crusher lubricating oil tank to generate a wear detection signal includes: The wear detection device is controlled to detect the lubricating oil in the lubricating oil tank of the cone crusher to generate a basic detection signal; The preset LC resonant module is controlled to process the basic detection signal to generate an amplitude-enhancing signal; The preset preamplifier module is controlled to process the amplitude enhancement signal to generate an amplified detection signal; The preset low-pass filter module is controlled to process the amplified detection signal to generate a noise-reduced detection signal; The preset coherent demodulation module is controlled to process the noise reduction detection signal to generate a wear detection signal.

[0009] By adopting the above technical solution, the wear detection device is first controlled to detect the lubricating oil in the lubricating oil tank of the cone crusher to determine the basic detection signal. Then, the LC resonant module is controlled to process the basic detection signal to determine the amplitude enhancement signal. Next, the preamplifier module is controlled to process the amplitude enhancement signal to determine the amplified detection signal. Then, the low-pass filter module is controlled to process the amplified detection signal to determine the noise reduction detection signal. Finally, the coherent demodulation module is controlled to process the noise reduction detection signal to determine the wear detection signal, thereby improving the accuracy of the wear detection signal.

[0010] Optionally, the step of analyzing the signal timing feature vector to generate copper abrasive parameters includes: The signal time-series feature vector is analyzed based on a pre-defined deep residual network to generate confidence in the copper abrasive material. Determine whether the confidence level of the copper abrasive material meets the preset material confidence threshold requirements; If the conditions are met, the signal amplitude is determined based on the signal timing feature vector. The signal amplitude is substituted into a preset cubic polynomial relationship for calculation and counting to generate the copper abrasive diameter and the number of copper abrasive grains; If it does not meet the requirements, the signal timing feature vector will be analyzed according to the preset digital twin model to generate the copper abrasive diameter and the number of copper abrasive particles. The diameter and number of copper abrasive grains were analyzed to generate copper abrasive grain parameters.

[0011] By adopting the above technical solution, the confidence level of the copper abrasive material is determined by analyzing the signal time-series feature vector based on the deep residual network. When the confidence level of the copper abrasive material meets the material confidence threshold, the signal amplitude is determined based on the signal time-series feature vector. Then, the signal amplitude is substituted into a cubic polynomial relationship for calculation and counting to determine the diameter and number of copper abrasive particles. When the confidence level of the copper abrasive material does not meet the material confidence threshold, the diameter and number of copper abrasive particles are determined by analyzing the signal time-series feature vector based on the digital twin model. By analyzing the diameter and number of copper abrasive particles, the copper abrasive parameters are determined, thereby improving the accuracy of the copper abrasive parameters.

[0012] Optionally, the cubic polynomial relation is: , in, The signal amplitude, The coefficients are the fitting coefficients for the cubic term. The fitting coefficients are quadratic terms. The coefficients for the first-order term are the fitting coefficients. The fitting coefficients are constant terms. The diameter is the copper abrasive grain diameter.

[0013] By adopting the above technical solution, the diameter of copper abrasive grains is determined by calculating the signal amplitude, cubic fitting coefficient, quadratic fitting coefficient, linear fitting coefficient, and constant fitting coefficient, thereby improving the accuracy of the copper abrasive grain diameter.

[0014] Optionally, the step of analyzing the signal timing feature vector based on a preset digital twin model to generate the copper abrasive grain diameter and the number of copper abrasive grains includes: The digital twin model is controlled according to the preset abrasive particle combination parameters to simulate and generate aliased signal feature vectors. The temporal feature vectors of the signal and the feature vectors of the aliased signal are analyzed to generate signal feature similarity. Determine whether the signal feature similarity meets the requirements of the preset signal similarity threshold; If it does not meet the requirements, then the abrasive grain combination parameters will be removed. If the conditions are met, the diameter and number of copper abrasive grains are determined based on the abrasive grain combination parameters.

[0015] By adopting the above technical solution, the aliased signal feature vector is determined by simulating the digital twin model according to the abrasive combination parameters. The signal timing feature vector and the aliased signal feature vector are analyzed to determine the signal feature similarity. When the signal feature similarity does not meet the signal similarity threshold, the abrasive combination parameter is removed. When the signal feature similarity meets the signal similarity threshold, the copper abrasive diameter and the number of copper abrasives are determined according to the abrasive combination parameters, thereby improving the accuracy of the copper abrasive diameter and the number of copper abrasives.

[0016] Optionally, the steps of analyzing the diameter and number of copper abrasive grains to generate copper abrasive grain parameters include: Calculate the sum of the diameters of the copper abrasive grains to generate the total diameter of the copper abrasive grains; Calculate the quotient of the total diameter of the copper abrasive grains and the preset reference abrasive grain diameter to generate the corrected number of copper abrasive grains; Calculate the quotient of the corrected number of copper abrasive particles to the preset lubricating oil volume to generate the copper abrasive particle concentration; Copper abrasive grain diameter, number of copper abrasive grains, and copper abrasive grain concentration are correlated to generate copper abrasive grain parameters.

[0017] By adopting the above technical solution, the total diameter of copper abrasive grains is calculated by summing the diameters of the copper abrasive grains. Then, the corrected number of copper abrasive grains is calculated based on the total diameter of copper abrasive grains and the reference abrasive grain diameter. The copper abrasive grain concentration is then calculated based on the corrected number of copper abrasive grains and the lubricating oil volume. Finally, the copper abrasive grain parameters are determined by correlating the copper abrasive grain diameter, the number of copper abrasive grains, and the copper abrasive grain concentration, thus ensuring the accuracy of the copper abrasive grain parameters.

[0018] Optionally, the steps for uploading copper abrasive parameters to a pre-set host computer for wear warning include: Determine the copper abrasive concentration based on the copper abrasive parameters; Collect the reference concentration of copper abrasive particles; Calculate the difference between the copper abrasive concentration and the copper abrasive reference concentration to generate the concentration change. Calculate the quotient of the concentration change to the copper abrasive reference concentration to generate the concentration growth rate; Determine whether the concentration growth rate is greater than the preset concentration growth rate threshold; If so, a wear warning will be issued; If not, continue uploading the copper abrasive parameters to the host computer for repeated judgments.

[0019] By adopting the above technical solution, the concentration change is obtained by calculating the copper abrasive concentration and the copper abrasive reference concentration. The concentration growth rate is obtained by calculating the concentration change and the copper abrasive reference concentration. When the concentration growth rate is greater than the concentration growth rate threshold, wear warning is issued, thereby improving the timeliness of wear detection.

[0020] Secondly, this application provides a wear detection system, which adopts the following technical solution: A wear detection system, comprising: The acquisition module is used to acquire the reference concentration of copper abrasive particles; A memory for storing a program for a wear detection method as described in any of the preceding claims; The processor and the program in the memory can be loaded and executed by the processor to implement a wear detection method as described in any of the above.

[0021] By adopting the above technical solution, the control processor loads and executes a program for a wear detection method stored in the memory. First, the preprocessing device is controlled to preprocess the wear detection device. Then, the preprocessed wear detection device is controlled to detect the lubricating oil in the lubricating oil tank of the cone crusher to determine the wear detection signal. The wear detection signal is input into the time-series feature extraction submodule for feature extraction to determine the signal time-series feature vector. The signal time-series feature vector is analyzed according to the random forest algorithm to determine the copper-containing abrasive analysis result. When the copper-containing abrasive analysis result is determined to be a copper-containing abrasive result, the signal time-series feature vector is analyzed to determine the copper abrasive parameters. Finally, the determined copper abrasive parameters are uploaded to the host computer for wear early warning, thereby timely and accurately capturing the key signal of early wear of the bushing and improving the timeliness of wear detection.

[0022] Thirdly, this application provides a smart terminal, which adopts the following technical solution: A smart terminal includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in any of the preceding claims.

[0023] By adopting the above technical solution, the processor loads and executes a computer program for a wear detection method stored in the memory through the operation of the intelligent terminal. First, the preprocessing device is controlled to preprocess the wear detection device, and then the preprocessed wear detection device is controlled to detect the lubricating oil in the lubricating oil tank of the cone crusher to determine the wear detection signal. The wear detection signal is input into the time-series feature extraction submodule for feature extraction to determine the signal time-series feature vector. The signal time-series feature vector is analyzed according to the random forest algorithm to determine the copper-containing abrasive analysis result. When the copper-containing abrasive analysis result is determined to be a copper-containing abrasive result, the signal time-series feature vector is analyzed to determine the copper abrasive parameters. Finally, the determined copper abrasive parameters are uploaded to the host computer for wear early warning, thereby timely and accurately capturing the key signal of early wear of the bushing and improving the timeliness of wear detection.

[0024] Fourthly, this application provides a computer storage medium capable of storing corresponding programs, which facilitates improving the timeliness of wear detection, and adopts the following technical solution: A computer-readable storage medium storing a computer program that can be loaded by a processor and executed by any of the wear detection methods described above.

[0025] By adopting the above technical solution, a computer program for a wear detection method is stored in a computer-readable storage medium. The processor loads and executes the computer program in the storage medium. First, the preprocessing device is controlled to preprocess the wear detection device. Then, the preprocessed wear detection device is controlled to detect the lubricating oil in the lubricating oil tank of the cone crusher to determine the wear detection signal. The wear detection signal is input into the time-series feature extraction submodule for feature extraction to determine the signal time-series feature vector. The signal time-series feature vector is analyzed according to the random forest algorithm to determine the copper-containing abrasive analysis result. When the copper-containing abrasive analysis result is determined to be a copper-containing abrasive result, the signal time-series feature vector is analyzed to determine the copper abrasive parameters. Finally, the determined copper abrasive parameters are uploaded to the host computer for wear early warning, thereby timely and accurately capturing the key signal of early wear of the bushing and improving the timeliness of wear detection.

[0026] In summary, this application includes at least one of the following beneficial technical effects: 1. By first controlling the preprocessing device to preprocess the wear detection device, and then controlling the preprocessed wear detection device to detect the lubricating oil in the lubricating oil tank of the cone crusher to determine the wear detection signal, the wear detection signal is input into the time-series feature extraction submodule for feature extraction to determine the signal time-series feature vector. The signal time-series feature vector is analyzed according to the random forest algorithm to determine the copper-containing abrasive analysis result. When the copper-containing abrasive analysis result is determined to be the result of copper-containing abrasive, the signal time-series feature vector is analyzed to determine the copper abrasive parameters. Finally, the determined copper abrasive parameters are uploaded to the host computer for wear early warning, thereby timely and accurately capturing the key signal of early wear of the bushing and improving the timeliness of wear detection. 2. The basic detection signal is determined by first controlling the wear detection device to detect the lubricating oil in the lubricating oil tank of the cone crusher. Then, the LC resonant module is controlled to process the basic detection signal to determine the amplitude enhancement signal. Next, the preamplifier module is controlled to process the amplitude enhancement signal to determine the amplified detection signal. Then, the low-pass filter module is controlled to process the amplified detection signal to determine the noise reduction detection signal. Finally, the coherent demodulation module is controlled to process the noise reduction detection signal to determine the wear detection signal, thereby improving the accuracy of the wear detection signal. 3. The confidence level of the copper abrasive material is determined by analyzing the signal time-series feature vector based on a deep residual network. When the confidence level of the copper abrasive material meets the material confidence threshold, the signal amplitude is determined based on the signal time-series feature vector. The signal amplitude is then substituted into a cubic polynomial relationship for calculation and counting to determine the diameter and number of copper abrasive particles. When the confidence level of the copper abrasive material does not meet the material confidence threshold, the diameter and number of copper abrasive particles are determined by analyzing the signal time-series feature vector based on a digital twin model. By analyzing the diameter and number of copper abrasive particles, the copper abrasive parameters are determined, thereby improving the accuracy of the copper abrasive parameters. Attached Figure Description

[0027] Figure 1 This is a flowchart of a wear detection method according to an embodiment of this application.

[0028] Figure 2 This is a flowchart illustrating how a wear detection device, after preprocessing, detects the lubricating oil in a pre-set cone crusher lubricating oil tank to generate a wear detection signal, as described in this embodiment.

[0029] Figure 3 This is a flowchart illustrating the analysis of signal timing feature vectors to generate copper abrasive parameters in this embodiment of the application.

[0030] Figure 4 This embodiment of the application is a flowchart that analyzes the signal timing feature vector according to a preset digital twin model to generate the diameter and number of copper abrasive grains.

[0031] Figure 5 This is a flowchart illustrating the analysis of the diameter and number of copper abrasive grains in this embodiment of the application to generate copper abrasive grain parameters.

[0032] Figure 6 This is a flowchart in this embodiment of the application showing how copper abrasive parameters are uploaded to a preset host computer for wear warning. Detailed Implementation

[0033] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figures 1 to 6 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0034] This application discloses a wear detection method, in which a cone crusher lubricating oil tank delivery pipeline is sequentially connected to a data acquisition device, a preprocessing device, and a wear detection device. The specific operation steps are as follows: First, the preprocessing device preprocesses the wear detection device. Then, the preprocessed wear detection device detects the lubricating oil in the cone crusher lubricating oil tank to determine the wear detection signal. The wear detection signal is input into a time-series feature extraction submodule for feature extraction to determine the signal time-series feature vector. The signal time-series feature vector is analyzed using a random forest algorithm to determine the copper-containing abrasive particle analysis result. When the copper-containing abrasive particle analysis result is determined to be copper-containing, the signal time-series feature vector is analyzed to determine the copper abrasive particle parameters. Finally, the determined copper abrasive particle parameters are uploaded to a host computer for wear warning.

[0035] Reference Figure 1 This application discloses a wear detection method, including the following steps: Step S100: Control the preset pre-processing device to pre-process the preset wear detection device, and then control the pre-processed wear detection device to detect the lubricating oil in the preset cone crusher lubricating oil tank to generate a wear detection signal.

[0036] The pretreatment device is the core functional component that optimizes the signal stability and sensor operation of the wear detection device. It is a general term for equipment integrating an oil purification module, a flow rate control module, and a self-calibration unit. The oil purification module is based on gradient aperture sieving and interception, permanent magnet magnetic field adsorption, and fluid shearing and replacement principles. It uses multi-layered filter elements to trap large mechanical impurities and colloids, high-energy-product permanent magnets to separate ferromagnetic abrasive particles, and high-speed oil flow to shear and remove contaminants deposited in the pipeline, thus purifying the lubricating oil and flow path. The flow rate control module is based on the momentum and heat transfer speed measurement principles of flow sensors and the PID closed-loop feedback regulation principle. Based on the principle of pressure equalization and pulsation elimination using an elastic diaphragm, the system collects flow velocity signals in real time and compares them with preset values. It then adjusts the servo pump speed and proportional valve opening to compensate for fluctuations and eliminate pressure pulsation, stabilizing the oil flow at a standard layer velocity. The self-calibration unit, based on the principles of standard excitation response comparison, DC bias differential correction, and amplitude sensitivity mapping, detects the on / off state and gain status of the sensing link by injecting standard calibration signals. It also collects the baseline deviation of the non-abrasive oil and compensates for zero drift in reverse. By fine-tuning the resonance and amplification parameters, it restores the detection sensitivity and completes the full-dimensional self-calibration of the core sensing components of the wear detection device, ensuring the stability of the signal before detection.

[0037] The wear detection device refers to the core functional component that realizes the online sensing, feature extraction and intelligent recognition of metal abrasive particles in the lubrication system of a cone crusher. It is the general term for equipment integrating a sampling pipeline, an oil sample microfluidic detection channel, an inductance detection unit, an excitation signal source, a signal processing circuit, a data processing and recognition unit, and a data communication unit. The sampling pipeline uses a rubber hose to ensure that it does not affect the magnetic field distribution. It is used to extract the lubricating oil to be detected from the lubricating oil tank of the cone crusher, ensuring that the oil fluid moves in laminar flow and there is no aggregation of abrasive particles caused by turbulence, meeting the requirements of full-flow online monitoring. The oil sample microfluidic detection channel is composed of non-metallic and non-magnetic materials, and a circular microchannel with an inner diameter in the range of 0.1 - 1 mm is etched by microfabrication methods. The inductance detection unit adopts a three-winding radial magnetic induction structure, including two symmetrically arranged excitation coils and an induction coil in the middle, which is sleeved outside the pipeline of the detected microfluidic detection channel, and is used to sense the magnetic field disturbance caused by the eddy current effect when copper abrasive particles pass through and output corresponding electrical signals. The excitation signal source is used to provide AC excitation signal data with specific frequencies and amplitudes. The data processing and recognition unit synchronously performs size inversion and material classification. The signal processing circuit includes an LC resonance module, a preamplification module, a low-pass filtering module and a coherent demodulation module, which are used to amplify, filter, denoise and demodulate weak induction signals, and extract parameters related to the characteristics of copper abrasive particles. The LC resonance module is composed of an induction coil and an external capacitor in series, and improves the signal-to-noise ratio of copper abrasive particle signals through resonance characteristics. The preamplification module uses a low-noise operational amplifier with adjustable gain as needed, which can receive weak signals and amplify them. The low-pass filtering module uses a dedicated filtering device with adjustable cut-off frequency to filter out high-frequency interference components in the signal. The coherent demodulation module is based on a demodulation chip and performs demodulation processing with the excitation signal as a reference, outputs a signal reflecting the characteristics of copper abrasive particles, and suppresses irrelevant noise and processes this signal. The data processing and recognition unit integrates an intelligent diagnosis module to convert the baseband signal into a digital signal. The data recognition unit pre-stores a signal feature library of copper abrasive particles and ferromagnetic abrasive particles, and deploys an attention mechanism LSTM network and a multi-level diagnosis model. By analyzing signal polarity, amplitude, pulse width, phase and timing characteristics, it distinguishes copper abrasive particles from ferromagnetic abrasive particles, processes multi-abrasive particle overlapping signals, and realizes the size estimation and counting of copper abrasive particles. The data communication unit outputs structured wear parameters to form data linkage with the upper computer.

[0038] The lubricating oil in the lubricating oil tank of the cone crusher refers to the industrial lubricating oil containing abrasive particles that is specifically used to lubricate and clean the key moving parts of the cone crusher and is stored in the closed lubricating oil tank supporting the equipment. A representative oil sample flow is extracted from the operating lubrication system as the transmission carrier of wear particles for online wear detection.

[0039] Wear detection signal refers to an electrical signal output by a wear detection device that indicates the presence and physical characteristics of wear particles in the lubricating oil. It is obtained through an inductive detection unit within the wear detection device and provides data support for subsequently obtaining the signal's timing feature vector. Specific methods are described in [reference needed]. Figure 2 The steps.

[0040] Step S101: Input the wear detection signal into the preset time-series feature extraction submodule for feature extraction to generate a signal time-series feature vector.

[0041] The temporal feature extraction submodule is a functional subunit in the data processing and recognition unit that is dedicated to mining the temporal, amplitude, and waveform variation patterns from digital wear detection signals. It uses an attention mechanism LSTM network to focus on key segments of the signal. This module takes the wear detection signal sequence as input and can extract the temporal feature vector of the signal.

[0042] The signal timing feature vector is a one-dimensional quantized array that indicates the timing pattern of wear detection signals. Each vector element corresponds to a timing, amplitude, or waveform feature. The vector as a whole completely shows the timing differences between copper wear particles, iron wear particles, and noise signals. It is obtained through the output of the timing feature extraction submodule and can be directly input into a random forest or deep residual network to complete classification and regression calculations, providing data support for subsequent analysis results of copper wear particles.

[0043] Step S102: Analyze the signal time-series feature vector based on the preset random forest algorithm to generate copper-containing abrasive particle analysis results.

[0044] The Random Forest algorithm is a machine learning algorithm that performs anomaly screening and binary classification on signal time-series feature vectors. It integrates multiple independent decision trees, random sample sampling, random feature selection, and majority voting decision-making mechanism into an ensemble learning model. The algorithm takes a 128-dimensional signal time-series feature vector as input and connects to the front-end time-series feature extraction submodule and the back-end deep residual network recognition module. As the core algorithm for pre-screening copper abrasive signal segments, it distinguishes between suspected copper abrasive signals and non-copper abrasive signals through parallel reasoning and voting of multiple decision trees.

[0045] The copper-containing abrasive particle analysis result refers to the structured judgment result indicating whether the signal to be analyzed contains effective features of copper abrasive particles. The signal time series feature vector is input into a trained and solidified random forest model. The model completes the classification of copper abrasive particle signals by independent discrimination and majority voting by multiple decision trees, combined with feature importance screening. This result serves as the key judgment basis for whether a signal is a suspected abnormal signal containing copper abrasive particles.

[0046] Step S103: Determine whether the copper-containing abrasive analysis result is the preset copper-containing abrasive result or the preset copper-free abrasive result.

[0047] Among them, the result of copper-containing abrasive particles refers to the conclusion of the wear detection device that the current abrasive event originates from the wear of copper or copper alloy components.

[0048] The result that the abrasive grains do not contain copper refers to the conclusion reached by the wear detection device that the current abrasive event does not originate from the wear of copper or copper alloy components.

[0049] By determining whether the analysis results of copper-containing abrasive particles are copper-containing or copper-free, it can be determined whether the copper bushing of the cone crusher is abnormally worn, and further determine whether an early wear warning is needed.

[0050] Step S1031: If the result is that the abrasive grains do not contain copper, then continue to control the wear detection device to detect the lubricating oil in the lubricating oil tank of the cone crusher, so as to generate a wear detection signal for cyclic judgment.

[0051] If the abrasive grains do not contain copper, it indicates that the copper bushing has not experienced abnormal wear. Therefore, it is necessary to continue to control the wear detection device to detect the lubricating oil in the lubricating oil tank of the cone crusher, and then make cyclic judgments based on the wear detection signals to monitor the wear of the copper bushing in real time.

[0052] Step S1032: If the result is that the abrasive grains contain copper, then analyze the signal timing feature vector to generate copper abrasive grain parameters.

[0053] If the abrasive grains contain copper, it indicates abnormal wear of the copper bushing. Therefore, it is necessary to analyze the signal timing feature vector to determine the copper abrasive grain parameters. Specific methods are described in [reference needed]. Figure 3 The steps.

[0054] Copper abrasive parameters refer to a set of quantifiable wear state indicators, including copper abrasive diameter, number of copper abrasive particles, and copper abrasive particle concentration, generated by analyzing the signal time-series feature vector, assuming the abrasive material is confirmed to be copper. These parameters are obtained through analysis of the signal time-series feature vector and provide data support for subsequent wear warning.

[0055] Step S104: Upload the copper abrasive parameters to the preset host computer for wear warning.

[0056] In this context, the host computer refers to the data aggregation, analysis, and human-computer interaction platform located at the top of the control level in an industrial monitoring system. It can transform the uploaded copper abrasive parameters into visualized and intelligent early warning commands.

[0057] After determining the copper abrasive parameters, wear warnings are generated by uploading these parameters to a host computer. For specific methods, please refer to [link / reference needed]. Figure 6 The steps.

[0058] Reference Figure 2 The steps for controlling the pre-treated wear detection device to detect the lubricating oil in the preset cone crusher lubricating oil tank to generate a wear detection signal include: Step S200: Control the wear detection device to detect the lubricating oil in the lubricating oil tank of the cone crusher to generate a basic detection signal.

[0059] Among them, the basic detection signal refers to the original or primary processed analog or digital electrical signal directly output by the wear detection device when the lubricating oil flows through its sensitive area. It is obtained by controlling the inductive detection unit in the wear detection device to detect the lubricating oil in the lubricating oil tank of the cone crusher, and provides data support for obtaining the amplitude enhancement signal in the future.

[0060] Step S201: Control the preset LC resonant module to process the basic detection signal to generate an amplitude enhancement signal.

[0061] The LC resonant module is a functional module consisting of an induction coil and an external capacitor connected in series. It improves the signal-to-noise ratio of the copper abrasive signal through its resonant characteristics. It is part of the signal processing circuit in the wear detection device and can increase the signal amplitude by 3-5 times.

[0062] The amplitude enhancement signal refers to the signal with a higher signal-to-noise ratio output after frequency selection and amplification by the LC resonant module. It is obtained by controlling the LC resonant module to process the basic detection signal, providing data support for obtaining the amplified detection signal in the future.

[0063] Step S202: Control the preset preamplifier module to process the amplitude enhancement signal to generate an amplified detection signal.

[0064] Among them, the preamplifier module refers to a functional module that uses a low-noise operational amplifier with adjustable gain, capable of receiving weak signals and amplifying them to a processable range. It is located between the LC resonant module and the low-pass filter module and is part of the signal processing circuit in the wear detection device.

[0065] The amplified detection signal refers to the gain waveform signal that retains the peak-valley polarity, waveform timing and amplitude ratio of the original induction signal. It is obtained by controlling the preamplifier module to process the amplitude-enhanced signal, which provides support for obtaining the noise-reduced detection signal in the future.

[0066] Step S203: Control the preset low-pass filter module to process the amplified detection signal to generate a noise-reduced detection signal.

[0067] The low-pass filter module is a functional module located between the preamplifier module and the coherent demodulation module in the signal processing circuit. This module uses dedicated filtering devices with an adjustable cutoff frequency to filter out high-frequency interference components in the signal.

[0068] The noise reduction detection signal refers to the pure mid-range processed signal that retains the original pulse timing, polarity, and amplitude ratio of copper and iron abrasive grains, while eliminating high-frequency interference and distortion. It is obtained by processing the amplified detection signal through the control of the low-pass filter module, providing a high signal-to-noise ratio signal input for subsequent coherent demodulation.

[0069] Step S204: Control the preset coherent demodulation module to process the noise reduction detection signal to generate a wear detection signal.

[0070] The coherent demodulation module is a functional module located after the low-pass filter module and before the data processing unit in the signal processing circuit. This module demodulates the noise reduction detection signal with the excitation signal as a reference, outputs a wear detection signal that reflects the characteristics of copper abrasive particles, and suppresses irrelevant noise.

[0071] The wear detection signal is consistent with the wear detection signal in step S100, and the noise reduction detection signal is processed and determined by the coherent demodulation module.

[0072] Reference Figure 3 The steps for analyzing the signal timing feature vector to generate copper abrasive parameters include: Step S300: Analyze the signal time-series feature vector based on the preset deep residual network to generate the confidence score of copper abrasive material.

[0073] Among them, the deep residual network refers to the deep neural network model in the multi-level diagnostic sub-module of the data processing and identification unit, which undertakes random forest anomaly screening, and is used for high-precision copper abrasive material determination and feature fitting. This model uses the residual structure to learn the deep correlation of high-dimensional time-series features, and can classify time-series features and perform material identification and size estimation.

[0074] The confidence level of copper abrasive material refers to the probability value that the current signal time-series feature vector belongs to the copper abrasive feature category. It is obtained by classifying the time-series features through forward inference using a deep residual network, and provides a basis for subsequent judgment on whether it meets the requirements of the material confidence level threshold.

[0075] Step S301: Determine whether the confidence level of the copper abrasive material meets the requirements of the preset material confidence level threshold.

[0076] Among them, the material confidence threshold refers to the preset critical probability value used to determine whether the material confidence of the copper abrasive output by the deep residual network reaches the reliable identification standard. It is a judgment standard used to determine whether there are multiple copper abrasives. The requirement of the material confidence threshold is that the material confidence of the copper abrasive is not less than the material confidence threshold.

[0077] By determining whether the confidence level of the copper abrasive material is not less than the material confidence threshold, it is possible to determine whether there is a multi-particle aliasing signal.

[0078] Step S3011: If the condition is met, the signal amplitude is determined based on the signal timing feature vector.

[0079] If the confidence level of the copper abrasive material is not less than the material confidence threshold, it indicates that it is a single copper abrasive grain. Since the data processing and identification unit of the wear detection device only generates a unique, non-overlapping, and waveform-complete single magnetic field disturbance, the corresponding generated signal timing feature vector has completely preserved the signal amplitude corresponding to the disturbance. Therefore, the signal amplitude can be directly determined based on the signal timing feature vector.

[0080] The signal amplitude refers to the absolute value of the maximum voltage extreme value extracted from the wear detection baseband signal and the corresponding digital signal sequence, which indicates the intensity of the magnetic field disturbance caused by the abrasive grains. It is obtained by quantitative analysis of the signal time sequence feature vector, providing data support for obtaining the diameter of the copper abrasive grains.

[0081] Step S30111: Substitute the signal amplitude into the preset cubic polynomial relationship for calculation and counting to generate the copper abrasive diameter and the number of copper abrasive grains.

[0082] The cubic polynomial relationship refers to a third-order polynomial mathematical model preset within the data processing and recognition unit, describing the quantitative mapping between the amplitude of the copper abrasive grain signal and the diameter of the copper abrasive grain. This model was obtained through experimental calibration using the eddy current effect detected by inductance and the magnetic field response characteristics of the coil. It provides the core mathematical basis for the device to achieve quantitative calculations of the diameter and number of copper abrasive grains. The expression for the cubic polynomial relationship is: .

[0083] in, The signal amplitude, The coefficients are cubic fitting coefficients, reflecting the sensitivity of signal amplitude to abrasive particle volume, and are obtained through experimental calibration. The coefficients for the quadratic term reflect the secondary influence of the abrasive surface area or eddy current effect, and are obtained through experimental calibration. The coefficients are the first-order fitting coefficients, reflecting the first-order response of the abrasive grains along their length to magnetic field disturbance. They are obtained through experimental calibration. The constant term is the fitting coefficient, and the intercept term in the model represents the baseline voltage without abrasive particles, obtained through experimental calibration. The diameter is the copper abrasive grain diameter.

[0084] The diameter of copper abrasive grains refers to a quantitative physical parameter that indicates the equivalent spherical particle size of copper abrasive grains passing through the detection area. It is calculated by substituting the signal amplitude into a cubic polynomial relationship, providing data support for subsequent determination of copper abrasive grain parameters.

[0085] The number of copper abrasive particles refers to the number of copper abrasive particles flowing per unit time or per unit oil sample. It is obtained by counting the cumulative number of independent copper abrasive particle signal pulses that meet the requirements within the detection time window, and provides data support for subsequent determination of copper abrasive particle parameters.

[0086] Step S3012: If it does not meet the requirements, the signal timing feature vector is analyzed according to the preset digital twin model to generate the copper abrasive diameter and the number of copper abrasive particles.

[0087] In this step, the copper abrasive diameter and number of copper abrasive grains are consistent with those in step S30111. The abrasive grain combination parameters are first input into a digital twin model to simulate and obtain the aliasing signal feature vector. Then, the aliasing signal feature vector is matched with the measured vector. The copper abrasive grain diameter in the combination parameters of the aliasing signal feature vector and the measured vector is directly extracted as the copper abrasive grain diameter. The number of copper abrasive grains in the combination is counted to obtain the number of copper abrasive grains, thereby ensuring the accuracy of the copper abrasive grain diameter and the number of copper abrasive grains.

[0088] A digital twin model is a high-fidelity virtual simulation system that integrates physical mechanisms and data-driven approaches. It accurately reproduces the coupling process of copper abrasive particles, electromagnetic sensors, and oil flow through mathematical modeling. Based on the finite element dynamics equations, it effectively distinguishes between single abrasive particle and multi-abrasive particle signals.

[0089] If the confidence level of the copper abrasive material is less than the material confidence threshold, it indicates that multiple abrasive grains are passing through the wear detection device simultaneously, causing signal aliasing. Therefore, it is necessary to analyze the signal time-series feature vector based on the digital twin model to determine the diameter and number of copper abrasive grains, thereby improving the timeliness and accuracy of wear warning. Specific methods are described in [reference needed]. Figure 4 The steps.

[0090] Step S302: Analyze the diameter and number of copper abrasive grains to generate copper abrasive grain parameters.

[0091] After determining the diameter and number of copper abrasive grains, the parameters of the copper abrasive grains are determined by analyzing the determined diameter and number of copper abrasive grains. The specific method is described in [reference needed]. Figure 5 The steps.

[0092] Reference Figure 4 The steps for analyzing the signal timing feature vector based on a pre-defined digital twin model to generate the copper abrasive grain diameter and number of copper abrasive grains include: Step S400: Control the digital twin model to perform simulation according to the preset abrasive particle combination parameters to generate aliasing signal feature vectors.

[0093] Among them, the abrasive grain combination parameters refer to the set of input parameters, which indicate the material type, diameter, number and spatial state of multiple abrasive grains passing through the detection area simultaneously when the digital twin model simulates aliased signals. By first extracting features such as peak and valley number, amplitude distortion and pulse broadening from the time-series feature vector of low-confidence signals, the initial candidate values ​​of material, grain size and number are obtained by inversion. Then, the gradient parameters of the same interval are matched based on the offline working condition library to obtain the feature vector of the aliased signal, which provides data support for obtaining the feature vector of the aliased signal.

[0094] The aliasing signal feature vector refers to the time-series feature quantization array of the same dimension as the measured signal, extracted from the superimposed waveform generated by multiple abrasive particles passing through the sensing area simultaneously. It is obtained by simulation output based on the abrasive particle combination parameters through a digital twin model, providing data support for subsequent acquisition of signal feature similarity.

[0095] Step S401: Analyze the signal timing feature vector and the aliased signal feature vector to generate signal feature similarity.

[0096] Signal feature similarity refers to the normalized value used in the data processing and recognition unit to quantify the consistency of feature distribution and waveform feature matching degree between the measured signal time-series feature vector and the digital twin simulated aliased signal feature vector. By using the cosine similarity algorithm to perform vector space quantization analysis on the two sets of feature vectors of the same dimension, the corresponding dimension dot product of the signal time-series feature vector and the aliased signal feature vector is first summed, and then the L2 norm of the two vectors is calculated separately. The dot product result is divided by the product of the L2 norms of the two vectors to obtain the signal similarity threshold. This provides a basis for subsequent judgment on whether the signal similarity threshold is met.

[0097] Step S402: Determine whether the signal feature similarity meets the requirements of the preset signal similarity threshold.

[0098] Among them, the signal similarity threshold refers to the critical quantization value preset in the data processing and recognition unit, which is used to determine the effectiveness of matching between the time-series feature vector of the measured signal and the feature vector of the digital twin simulation aliased signal. It is obtained through experimental calibration and serves as the basis for subsequent judgment on whether the signal feature similarity is not less than the signal similarity threshold. The requirement of the signal similarity threshold is that the signal feature similarity is not less than the signal similarity threshold.

[0099] By determining whether the signal feature similarity is not less than the signal similarity threshold, it can be further determined whether there are truly multiple abrasive grains mixed together, and whether it is necessary to determine the diameter and number of copper abrasive grains based on the abrasive grain combination parameters.

[0100] Step S4021: If it does not meet the requirements, then the abrasive combination parameters are discarded.

[0101] If the signal feature similarity is less than the signal similarity threshold, it indicates that the combination of abrasive parameters used is far from the actual abrasive parameters, so the combination of abrasive parameters needs to be removed.

[0102] Step S4022: If the conditions are met, determine the diameter and number of copper abrasive grains based on the abrasive grain combination parameters.

[0103] If the signal feature similarity is not less than the signal similarity threshold, it indicates that the combination of abrasive parameters used is highly similar to the actual abrasive parameters. Therefore, it is necessary to further analyze the copper abrasive diameter and the number of copper abrasives to determine the copper abrasive parameters.

[0104] Reference Figure 5 The steps for analyzing the diameter and number of copper abrasive grains to generate copper abrasive grain parameters include: Step S500: Calculate the sum of the copper abrasive grain diameters to generate the total copper abrasive grain diameter.

[0105] The total diameter of copper abrasive grains refers to a comprehensive quantitative indicator that represents the total wear of copper components in a cone crusher within a unit testing cycle. It is determined by arithmetic summation of the diameters of all validly identified individual copper abrasive grains, providing data support for obtaining the corrected number of copper abrasive grains in the future.

[0106] Step S501: Calculate the quotient of the total diameter of the copper abrasive grains and the preset reference abrasive grain diameter to generate the corrected number of copper abrasive grains.

[0107] The reference abrasive diameter refers to a preset standard diameter value that represents the size of a typical wear unit. It is calibrated experimentally to provide data support for subsequent calculations of the corrected number of copper abrasive grains.

[0108] The corrected number of copper abrasive grains refers to converting the multiple copper abrasive grains decoupled from a single aliasing event into an equivalent number of standard-sized particles based on their total volume. This is obtained by calculating the quotient of the total diameter of the copper abrasive grains and the diameter of the reference abrasive grain, providing data support for subsequently obtaining the copper abrasive grain concentration.

[0109] Step S502: Calculate the quotient of the corrected number of copper abrasive grains and the preset lubricating oil volume to generate copper abrasive grain concentration.

[0110] Among them, the lubricating oil volume refers to the quantitative value of the lubricating oil sample volume involved in the wear test, which is obtained through experimental calibration and provides data support for the subsequent calculation of copper abrasive concentration.

[0111] Copper abrasive concentration refers to the standardized density index of the number of corrected copper abrasive particles contained in a unit volume of lubricating oil. It is obtained by calculating the quotient of the number of corrected copper abrasive particles and the volume of lubricating oil, providing data support for obtaining copper abrasive parameters in the future.

[0112] Step S503: Associate the copper abrasive diameter, the number of copper abrasive grains, and the copper abrasive concentration to generate copper abrasive parameters.

[0113] The copper abrasive parameters are consistent with those in step S302. The copper abrasive parameters are determined by associating the set of copper abrasive diameter, number of copper abrasive particles, and copper abrasive concentration after determining the copper abrasive diameter, number of copper abrasive particles, and copper abrasive concentration.

[0114] Reference Figure 6 The steps for uploading copper abrasive parameters to a pre-set host computer for wear warning include: Step S600: Determine the copper abrasive concentration based on the copper abrasive parameters.

[0115] In this step, the copper abrasive concentration is the same as that in step S502, which is obtained by looking up the corresponding copper abrasive parameters, thereby improving the accuracy of the wear detection signal.

[0116] Step S601: Collect the reference concentration of copper abrasive particles.

[0117] Among them, the copper abrasive reference concentration refers to the concentration detected in the previous cycle, which is obtained by the wear detection device and provides data support for obtaining the concentration change in the future.

[0118] Step S602: Calculate the difference between the copper abrasive concentration and the copper abrasive reference concentration to generate the concentration change.

[0119] The concentration change refers to the rise or fall of the copper abrasive wear concentration, which is obtained by calculating the difference between the copper abrasive concentration and the copper abrasive reference concentration, providing data support for obtaining the concentration growth rate in the future.

[0120] Step S603: Calculate the quotient of the concentration change and the copper abrasive reference concentration to generate the concentration growth rate.

[0121] The concentration growth rate refers to the relative change rate of the number and concentration of copper abrasive particles within the monitoring period. It is obtained by calculating the quotient of the concentration change and the reference concentration of copper abrasive particles, and provides a basis for subsequent judgment on whether it exceeds the concentration growth rate threshold.

[0122] Step S604: Determine whether the concentration growth rate is greater than the preset concentration growth rate threshold.

[0123] The concentration growth rate threshold is a preset critical value used to determine whether the concentration growth of copper abrasive particles is abnormal. When the measured concentration growth rate exceeds this threshold, the system determines that the equipment is in an accelerated wear state and triggers a corresponding level of warning or maintenance command.

[0124] After determining the concentration growth rate, it is determined whether a wear warning is needed by judging whether the concentration growth rate is greater than the concentration growth rate threshold.

[0125] Step S6041: If so, then perform a wear warning.

[0126] If the concentration growth rate is greater than the concentration growth rate threshold, it indicates that the device is experiencing abnormal wear, so wear warning is required.

[0127] Step S6042: If not, continue to upload the copper abrasive parameters to the host computer for cyclic judgment.

[0128] If the concentration growth rate is not greater than the concentration growth rate threshold, it indicates that the device has not experienced abnormal wear. Therefore, it is necessary to continue uploading the copper abrasive parameters to the host computer for cyclical judgment.

[0129] Based on the same inventive concept, embodiments of this application provide a wear detection system, including: The acquisition module is used to acquire the reference concentration of copper abrasive particles; A memory used to store a program for a wear detection method; The processor can load and execute programs in memory to implement a wear detection method.

[0130] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0131] This application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as a wear detection method.

[0132] Computer storage media include, for example, USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media that can store program code.

[0133] Based on the same inventive concept, embodiments of this application provide a smart terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as a wear detection method.

[0134] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0135] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A wear detection method, characterized in that, include: After the preset pre-processing device performs pre-processing on the preset wear detection device, the pre-processed wear detection device is controlled to detect the lubricating oil in the preset cone crusher lubricating oil tank to generate a wear detection signal. The wear detection signal is input into a preset time-series feature extraction submodule for feature extraction to generate a signal time-series feature vector; The signal time-series feature vector is analyzed based on a pre-defined random forest algorithm to generate copper-containing abrasive particle analysis results. The analysis results of copper-containing abrasive particles are determined to be either the preset copper-containing abrasive particle result or the preset copper-free abrasive particle result. If the abrasive grains do not contain copper, the wear detection device continues to monitor the lubricating oil in the cone crusher's lubricating oil tank to generate wear detection signals for cyclic judgment. If the abrasive grains contain copper, then the signal timing feature vector is analyzed to generate copper abrasive grain parameters; The copper abrasive parameters are uploaded to a pre-set host computer for wear warning.

2. The wear detection method according to claim 1, characterized in that, The steps for controlling the pre-treated wear detection device to detect the lubricating oil in the preset cone crusher lubricating oil tank to generate a wear detection signal include: The wear detection device is controlled to detect the lubricating oil in the lubricating oil tank of the cone crusher to generate a basic detection signal; The preset LC resonant module is controlled to process the basic detection signal to generate an amplitude-enhancing signal; The preset preamplifier module is controlled to process the amplitude enhancement signal to generate an amplified detection signal; The preset low-pass filter module is controlled to process the amplified detection signal to generate a noise-reduced detection signal; The preset coherent demodulation module is controlled to process the noise reduction detection signal to generate a wear detection signal.

3. The wear detection method according to claim 1, characterized in that, The steps for analyzing the signal timing feature vector to generate copper abrasive parameters include: The signal time-series feature vector is analyzed based on a pre-defined deep residual network to generate confidence in the copper abrasive material. Determine whether the confidence level of the copper abrasive material meets the preset material confidence threshold requirements; If the conditions are met, the signal amplitude is determined based on the signal timing feature vector. The signal amplitude is substituted into a preset cubic polynomial relationship for calculation and counting to generate the copper abrasive diameter and the number of copper abrasive grains; If it does not meet the requirements, the signal timing feature vector will be analyzed according to the preset digital twin model to generate the copper abrasive diameter and the number of copper abrasive particles. The diameter and number of copper abrasive grains were analyzed to generate copper abrasive grain parameters.

4. The wear detection method according to claim 3, characterized in that, The relation of the cubic polynomial is: ， in, The signal amplitude, The coefficients are the fitting coefficients for the cubic term. The fitting coefficients are quadratic terms. The coefficients for the first-order term are the fitting coefficients. The fitting coefficients are constant terms. The diameter is the copper abrasive grain diameter.

5. The wear detection method according to claim 3, characterized in that, The steps for analyzing the signal timing feature vector based on a pre-defined digital twin model to generate the copper abrasive grain diameter and the number of copper abrasive grains include: The digital twin model is controlled according to the preset abrasive particle combination parameters to simulate and generate aliased signal feature vectors. The temporal feature vectors of the signal and the feature vectors of the aliased signal are analyzed to generate signal feature similarity. Determine whether the signal feature similarity meets the requirements of the preset signal similarity threshold; If it does not meet the requirements, then the abrasive grain combination parameters will be removed. If the conditions are met, the diameter and number of copper abrasive grains are determined based on the abrasive grain combination parameters.

6. The wear detection method according to claim 3, characterized in that, The steps for analyzing the diameter and number of copper abrasive grains to generate copper abrasive grain parameters include: Calculate the sum of the diameters of the copper abrasive grains to generate the total diameter of the copper abrasive grains; Calculate the quotient of the total diameter of the copper abrasive grains and the preset reference abrasive grain diameter to generate the corrected number of copper abrasive grains; Calculate the quotient of the corrected number of copper abrasive particles to the preset lubricating oil volume to generate the copper abrasive particle concentration; Copper abrasive grain diameter, number of copper abrasive grains, and copper abrasive grain concentration are correlated to generate copper abrasive grain parameters.

7. The wear detection method according to claim 1, characterized in that, The steps for uploading copper abrasive parameters to a pre-set host computer for wear warning include: Determine the copper abrasive concentration based on the copper abrasive parameters; Collect the reference concentration of copper abrasive particles; Calculate the difference between the copper abrasive concentration and the copper abrasive reference concentration to generate the concentration change. Calculate the quotient of the concentration change to the copper abrasive reference concentration to generate the concentration growth rate; Determine whether the concentration growth rate is greater than the preset concentration growth rate threshold; If so, a wear warning will be issued; If not, continue uploading the copper abrasive parameters to the host computer for repeated judgments.

8. A wear detection system, characterized in that, include: The acquisition module is used to acquire the reference concentration of copper abrasive particles; A memory for storing a program of a wear detection method as described in any one of claims 1 to 7; The processor and the program in the memory can be loaded and executed by the processor to implement the wear detection method as described in any one of claims 1 to 7.

9. A smart terminal, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program is stored and can be loaded by a processor and executed as described in any one of claims 1 to 7.

Images