Intelligent fault diagnosis method and system in intelligent manufacturing process of mining equipment

Abstract

The invention relates to the technical field of component testing, and discloses an intelligent fault diagnosis method and system in the intelligent manufacturing process of mining equipment, and the method comprises the steps: collecting the operation state information of the mining equipment, which is collected in real time through a multi-source sensor; aligning the vibration signal and the acoustic emission signal through a timestamp, and then carrying out space coordinate registration to obtain a three-dimensional working condition map; performing feature decoupling on the operation state information based on an equipment dynamic model to obtain a fault sensitive feature set; inputting the fault sensitive feature set into a multi-layer decision network to output a fault diagnosis result and a confidence score; constructing a fault causal graph based on pre-acquired design parameters and manufacturing process parameters, and designing a correction scheme for the abnormal process parameters based on the abnormal process parameters of which the traceability confidence score is lower than a set threshold value in the fault causal graph; fusing the correction scheme, the fault diagnosis result and the three-dimensional working condition map, and constructing a visual diagnosis report; according to the invention, the intelligent fault diagnosis effect can be improved.

Description

Technical Field

[0001] The present invention relates to the field of component testing technology, and in particular to an intelligent fault diagnosis method and system in the intelligent manufacturing process of mining equipment. Background Art

[0002] In the field of intelligent manufacturing for mining equipment, fault diagnosis relies on sensors collecting exogenous data for analysis. While existing technologies can achieve basic data collection and feature extraction, they suffer from significant deficiencies in multimodal data fusion. Due to the inaccurate time synchronization of different data types, such as vibration and acoustic emission signals, and the lack of an effective spatial coordinate alignment mechanism, the constructed equipment operating condition models struggle to accurately reflect the actual operating state. This, in turn, results in incomplete decoupling of fault characteristics, and a large amount of redundant information interferes with the diagnostic process, slowing down fault diagnosis and failing to meet the real-time requirements of intelligent manufacturing.

[0003] Traditional fault diagnosis algorithms are often based on single physical models or shallow neural networks, and their ability to capture the nonlinear characteristics of complex dynamic systems is limited. For example, analyzing the frequency components of a vibration signal solely through Fourier transforms makes it difficult to effectively separate multi-source fault characteristics such as gear meshing impact and bearing wear. Rule-based diagnostic systems are unable to dynamically learn the implicit correlation between parameter changes and fault modes during equipment operation, resulting in low diagnostic accuracy. Furthermore, existing methods lack the ability to deeply trace the causal relationship between manufacturing process parameters and faults, making it impossible to optimize diagnostic logic across the entire design, assembly, and processing process, further limiting the overall effectiveness of intelligent fault diagnosis. Summary of the Invention

[0004] The present invention provides an intelligent fault diagnosis method in the intelligent manufacturing process of mining equipment, the main purpose of which is to solve the problem of poor intelligent fault diagnosis effect in the intelligent manufacturing process of mining equipment.

[0005] To achieve the above objectives, the present invention provides an intelligent fault diagnosis method for intelligent manufacturing of mining equipment, comprising:

[0006] S1. Collecting vibration signals, acoustic emission signals and thermal imaging data of mining equipment in real time through multi-source sensors as the operating status information of the mining equipment;

[0007] S2. After aligning the vibration signal and the acoustic emission signal by time stamp, perform spatial coordinate registration to obtain a three-dimensional operating state map of the mining equipment;

[0008] S3. Decoupling the characteristics of the operating status information under physical constraints based on the equipment dynamics model to obtain a fault-sensitive feature set of the mining equipment;

[0009] S4. Input the fault-sensitive feature set into a multi-layer decision network and output the fault diagnosis results and confidence scores;

[0010] S5. Constructing a fault cause-effect diagram for the mining equipment based on the pre-acquired design parameters and manufacturing process parameters, and designing a correction plan including process constraints for abnormal process parameters of the mining equipment whose traceability confidence scores in the fault cause-effect diagram are below a set threshold;

[0011] S6. Integrate the correction plan, the fault diagnosis result and the three-dimensional working condition map to construct a visual diagnosis report.

[0012] In a preferred embodiment, the collecting of vibration signals, acoustic emission signals and thermal imaging data of mining equipment collected in real time by multi-source sensors as operating status information of the mining equipment includes:

[0013] Deploy a vibration acceleration sensor on the axial mounting surface of a bearing seat of mining equipment to obtain a vibration signal of the mining equipment under full load conditions;

[0014] Arrange acoustic emission sensors in a circular array on the surface of the gearbox housing to obtain acoustic emission signals of the mining equipment;

[0015] An infrared thermal imager is installed in the radial observation area of ​​the equipment friction area, and is driven by a stepper motor to realize dynamic tracking and focusing of the thermal imaging data of the mining equipment;

[0016] The vibration signal, the acoustic emission signal and the thermal imaging data are collected as the operating status information of the mining equipment.

[0017] In a preferred embodiment, after aligning the vibration signal and the acoustic emission signal by time stamp, performing spatial coordinate registration to obtain a three-dimensional working condition map of the mining equipment includes:

[0018] Using the clock-synchronized vibration acceleration sensor and the acoustic emission sensor to collect information from the mining equipment, when the delay of the information collection exceeds a signal segment of a set threshold, using sliding window interpolation to compensate for the timing deviation of the collected information to obtain the vibration signal and acoustic emission signal of the mining equipment;

[0019] Aligning the vibration signal and the acoustic emission signal through a timestamp to obtain a vibration signal and an acoustic emission signal of the same frequency of the mining equipment;

[0020] A three-dimensional spatial framework is constructed based on spatial coordinates, and the vibration signal and acoustic emission signal of the same frequency and the thermal imaging data are arranged in the three-dimensional spatial framework according to spatial position and time sequence to obtain a three-dimensional working condition map of the mining equipment.

[0021] In a preferred embodiment, the feature decoupling of the operating state information under physical constraints based on the equipment dynamics model to obtain the fault-sensitive feature set of the mining equipment includes:

[0022] Establishing an equipment dynamics equation for the mining equipment based on the structural characteristics, operating principles, and correlation between physical parameters of the mining equipment;

[0023] Based on the equipment dynamics equation, the vibration signal is decomposed into a time domain impact component related to the gear meshing torque and a centrifugal force modulation component related to bearing wear;

[0024] The amplitude spectrum of the acoustic emission signal is extracted through Morlet wavelet transform to identify the gear tooth breakage impact frequency and its harmonic components, and then correlated with the equipment load rate change curve to obtain the harmonic components of the mining equipment;

[0025] generating heat flux density distribution data per unit area of ​​the mining equipment according to the temperature gradient distribution collected by the infrared thermal imager;

[0026] The time domain impact component, centrifugal force modulation component, harmonic component and unit area heat flux density distribution data are collected to form the fault sensitive feature set of the mining equipment.

[0027] In a preferred embodiment, generating the unit area heat flux density distribution data of the mining equipment according to the temperature gradient distribution collected by the infrared thermal imager includes:

[0028] collecting temperature distribution data of the friction contact area of ​​the mining equipment by the infrared thermal imager to generate a real-time temperature gradient distribution map of the friction contact area;

[0029] The rotational speed, load pressure, and lubricant flow parameters of the rotor in the mining equipment are used as boundary conditions for temperature field modeling. The temperature gradient distribution map is mapped to the friction contact area according to Fourier's law of heat conduction to obtain a three-dimensional transient temperature field model of the friction contact area.

[0030] Multiplying the friction force and the relative displacement in the three-dimensional transient temperature field model to obtain the friction heat generation power of the friction contact area;

[0031] The frictional heat power is distributed to the friction contact area, and combined with the meshing of the three-dimensional transient temperature field model, unit area heat flux density distribution data of the mining equipment is generated.

[0032] In a preferred embodiment, inputting the fault-sensitive feature set into a multi-layer decision network and outputting a fault diagnosis result and a confidence score includes:

[0033] Using a gated recurrent layer to perform a temporal dependency analysis on the fault-sensitive feature set, and outputting a hidden Markov chain state transition probability of the mining equipment operating state;

[0034] The energy distribution characteristics of the vibration signal in the gear meshing line direction are captured by a convolutional neural network to generate a two-dimensional spatial correlation map of the mining equipment;

[0035] The hidden Markov chain state transition probability and the two-dimensional spatial association graph are aggregated to output the fault diagnosis result and confidence score of the mining equipment.

[0036] In a preferred embodiment, the constructing of the fault cause-effect graph of the mining equipment based on the pre-acquired design parameters and manufacturing process parameters includes:

[0037] Performing Bayesian estimation on the depth of cut, tool feed rate, and spindle torque among the pre-acquired design parameters and manufacturing process parameters to obtain a conditional probability distribution of the mining equipment under different states, filling the conditional probability distribution into network parameters, and establishing a Bayesian network model;

[0038] Performing a hierarchical aggregation strategy on the process parameters and fault labels in the pre-acquired design parameters and manufacturing process parameters to obtain a process-fault matrix of the mining equipment;

[0039] Markov chain Monte Carlo sampling is performed on a Bayesian network model set as a normal distribution and different types of faults in the process-fault matrix to obtain a fault causal diagram of the mining equipment.

[0040] In a preferred embodiment, the abnormal process parameters of the mining equipment whose traceability confidence score in the fault causal graph is lower than a set threshold are used to design a correction scheme containing process constraints for the abnormal process parameters, including:

[0041] If the fault cause-effect diagram shows a strong correlation between cutting depth and excessive vibration, adjust the tool feed rate and add lubrication compensation conditions;

[0042] If there is causal feedback between the centrifugal force modal parameters and the bearing temperature, the assembly tolerance verification instruction is triggered;

[0043] When the heat loss rate is abnormal, the geometric matching degree of the friction pair is verified by finite element simulation.

[0044] In a preferred embodiment, the design of a correction scheme including process constraints for the abnormal process parameters includes:

[0045] modifying a path parameter of the tool based on a maximum allowable cutting force limit of the mining equipment;

[0046] Setting a tolerance threshold for the assembly clearance of the mining equipment according to the accuracy grade requirement of the gearbox in the mining equipment;

[0047] The critical temperature rise value of the bearing of the mining equipment is defined in combination with the heat treatment characteristics of the material of the mining equipment.

[0048] In a preferred embodiment, the integration of the correction scheme, the fault diagnosis result and the three-dimensional operating condition map to construct a visual diagnosis report includes:

[0049] After mapping the axial vibration amplitude of the three-dimensional operating condition map to a chromatographic gradient, the spectral characteristic lines in the fault diagnosis results are superimposed on the corresponding area of ​​the thermal imaging map, and the impact path of abnormal process parameters on equipment performance is marked with dynamic vector arrows to obtain a visual diagnostic report of the mining equipment.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] 1. The present invention significantly improves the speed of fault diagnosis through the spatiotemporal alignment and feature decoupling technology of multi-source data. Vibration signals and acoustic emission signals are synchronized using timestamps, and timing deviations are compensated through sliding window interpolation. A three-dimensional working condition map is constructed in combination with spatial coordinate registration to achieve precise spatiotemporal alignment of multimodal data. At the same time, based on the equipment dynamics model, the operating status information is decoupled under physical constraints to form a high-dimensional, low-redundancy fault-sensitive feature set. This structured feature representation can be directly input into a multi-layer decision network, avoiding the complex feature engineering process in traditional methods. Combined with the parallel processing mechanism of the gated recurrent layer and the convolutional neural network, the diagnostic response time is greatly shortened to meet the real-time requirements of intelligent manufacturing of mining equipment.

[0052] 2. The present invention achieves dual-precision optimization through the collaborative mechanism of multi-layer decision-making networks and fault causal graphs. The multi-layer decision-making network analyzes the temporal dependency through the gated recurrent layer to generate the hidden Markov chain state transition probability, and uses the convolutional neural network to capture the spatial energy distribution characteristics of the vibration signal. After the two are aggregated, the fault diagnosis results containing the confidence score are output, which effectively improves the recognition accuracy of multi-source faults under complex working conditions. In addition, based on the Bayesian network model and process-fault matrix constructed based on the design parameters and manufacturing process parameters, the fault causal graph is generated through Markov chain Monte Carlo sampling, which can probabilistically model the relationship between process parameters such as cutting depth and tool feed rate and faults, trace the root cause of the fault from the dimension of the entire manufacturing process, and dynamically correct the diagnostic logic, forming a closed-loop optimization link of "data acquisition-feature decoupling-intelligent diagnosis-process traceability", significantly reducing the false alarm rate and missed diagnosis rate, and achieving a systematic improvement in diagnostic accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A schematic flow chart of an intelligent fault diagnosis method for intelligent manufacturing of mining equipment provided by one embodiment of the present invention;

[0054] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0056] The embodiment of the present application provides an intelligent fault diagnosis method in the intelligent manufacturing process of mining equipment. The execution subject of the intelligent fault diagnosis method in the intelligent manufacturing process of mining equipment includes but is not limited to at least one of the electronic devices such as the server and the terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the intelligent fault diagnosis method in the intelligent manufacturing process of mining equipment can be executed by software or hardware installed in the terminal device or the server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0057] Reference Figure 1FIG. 1 is a flow chart of an intelligent fault diagnosis method for intelligent manufacturing of mining equipment according to an embodiment of the present invention. In this embodiment, the intelligent fault diagnosis method for intelligent manufacturing of mining equipment includes:

[0058] S1. Collecting vibration signals, acoustic emission signals and thermal imaging data of mining equipment in real time through multi-source sensors as the operating status information of the mining equipment;

[0059] In an embodiment of the present invention, the collecting of vibration signals, acoustic emission signals, and thermal imaging data of mining equipment collected in real time by multi-source sensors as operating status information of the mining equipment includes:

[0060] Deploy a vibration acceleration sensor on the axial mounting surface of a bearing seat of mining equipment to obtain a vibration signal of the mining equipment under full load conditions;

[0061] Arrange acoustic emission sensors in a circular array on the surface of the gearbox housing to obtain acoustic emission signals of the mining equipment;

[0062] An infrared thermal imager is installed in the radial observation area of ​​the equipment friction area, and is driven by a stepper motor to realize dynamic tracking and focusing of the thermal imaging data of the mining equipment;

[0063] The vibration signal, the acoustic emission signal and the thermal imaging data are collected as the operating status information of the mining equipment.

[0064] Specifically, the vibration acceleration sensor is firmly installed in the designated position on the axial mounting surface of the bearing seat of the mining equipment using suitable mounting tools, such as high-strength bolts and nuts.

[0065] Furthermore, after installation, ensure that the sensor fits tightly against the axial mounting surface of the bearing seat without any looseness or gap.

[0066] Furthermore, when the mining equipment is operating at full load, the vibration acceleration sensor starts working and senses the vibration generated by the bearing seat during operation through the built-in sensitive element.

[0067] Furthermore, these sensitive elements can convert the physical quantity of vibration into electrical signals, which are then amplified, filtered, and processed by the signal conditioning circuit inside the sensor to ultimately output vibration signals that can be used for analysis.

[0068] Furthermore, on the surface of the gearbox housing, according to the layout requirements of the annular array form, a dedicated sensor mounting adhesive is used to evenly stick multiple acoustic emission sensors on the housing surface to form an annular array.

[0069] Furthermore, the installation position and angle of each sensor are precisely measured and calibrated to ensure that the acoustic emission signals generated during gearbox operation can be fully and accurately collected.

[0070] Furthermore, when mining equipment is running, mechanical activities such as gear meshing and friction inside the gearbox will generate elastic waves, namely acoustic emission signals.

[0071] Furthermore, these acoustic emission signals propagate in the gearbox housing, and the sensors arranged in a ring array can capture these signals and convert them into electrical signals, which are then output as acoustic emission signals after preliminary processing by the signal processing module.

[0072] Furthermore, in the friction area of ​​the mining equipment, a radial observation area is determined, and the infrared thermal imager is installed on a suitable bracket near the area.

[0073] Furthermore, by connecting the stepper motor and the control system of the infrared thermal imager, a tracking and focusing program is set.

[0074] Furthermore, when mining equipment is in operation, the friction area will generate different temperature distributions due to frictional heat. The infrared thermal imager uses an infrared detector to receive infrared rays radiated by objects in the area and converts them into electrical signals.

[0075] Furthermore, the electrical signal is converted and enhanced by an image processing algorithm to form thermal imaging data.

[0076] Furthermore, the stepper motor precisely controls the movement and focus of the infrared thermal imager's lens based on preset programs and feedback from thermal imaging data, enabling dynamic tracking and focusing of thermal imaging data in the friction area of ​​mining equipment.

[0077] Furthermore, during the operation of mining equipment, the vibration signals collected by the vibration accelerometer, the acoustic emission signals collected by the annular array sensor, and the thermal imaging data collected by the infrared thermal imager are transmitted to the data collection center through their respective transmission lines, such as dedicated data cables or wireless transmission modules.

[0078] Furthermore, in the data collection center, data acquisition cards and data processing software are used to integrate and store these different types of signals and data, ultimately forming complete mining equipment operating status information for subsequent equipment status analysis and fault diagnosis.

[0079] In general, vibration signals can directly reflect the dynamic load and wear status of mechanical components, acoustic emission signals can capture transient impact events such as gear tooth breakage and crack propagation, and thermal imaging data can reveal hidden faults such as abnormal heating of contact pairs.

[0080] In general, the three types of signals cover the typical failure modes of mining equipment from the dimensions of mechanical response, energy release, and thermal conduction characteristics, forming a multi-physical field coupled fault characterization system to avoid the one-sidedness of single signal diagnosis.

[0081] In general, the directional deployment of vibration acceleration sensors, the circular array layout of acoustic emission sensors, and the dynamic focusing of the friction area of ​​infrared thermal imagers are all designed for key and vulnerable parts of the equipment to ensure a strong correlation between the collected data and fault characteristics.

[0082] In general, the mechanism of collecting vibration signals and dynamically tracking thermal imaging data under full-load conditions can cover the extreme working conditions of the equipment during actual operation, improve the adaptability of the data to complex working conditions, and provide a more representative sample set for subsequent fault feature decoupling and diagnostic model training.

[0083] S2. After aligning the vibration signal and the acoustic emission signal by time stamp, perform spatial coordinate registration to obtain a three-dimensional operating state map of the mining equipment;

[0084] In an embodiment of the present invention, after aligning the vibration signal and the acoustic emission signal by time stamp, performing spatial coordinate registration to obtain a three-dimensional working condition map of the mining equipment includes:

[0085] Using the clock-synchronized vibration acceleration sensor and the acoustic emission sensor to collect information from the mining equipment, when the delay of the information collection exceeds a signal segment of a set threshold, using sliding window interpolation to compensate for the timing deviation of the collected information to obtain the vibration signal and acoustic emission signal of the mining equipment;

[0086] Aligning the vibration signal and the acoustic emission signal through a timestamp to obtain a vibration signal and an acoustic emission signal of the same frequency of the mining equipment;

[0087] A three-dimensional spatial framework is constructed based on spatial coordinates, and the vibration signal and acoustic emission signal of the same frequency and the thermal imaging data are arranged in the three-dimensional spatial framework according to spatial position and time sequence to obtain a three-dimensional working condition map of the mining equipment.

[0088] Specifically, the vibration acceleration sensor and the acoustic emission sensor are precisely synchronized using clock synchronization technology.

[0089] Furthermore, during the operation of the mining equipment, the two sensors simultaneously start collecting information from the equipment.

[0090] Furthermore, once it is detected that the signal segment delay of the information collection exceeds a preset threshold, the sliding window interpolation method is started.

[0091] Furthermore, a specific operation is to define a window of a fixed size with the delayed signal segment as the center, and use the adjacent normal signals collected in the window as reference data.

[0092] Furthermore, by calculating the changing trends and numerical relationships of these reference data, reasonable intermediate values ​​are inserted in the delayed signal segment to compensate for the timing deviation, thereby obtaining accurate mining equipment vibration signals and acoustic emission signals.

[0093] Furthermore, the vibration signal and acoustic emission signal after timing deviation compensation are processed using time stamp technology.

[0094] Furthermore, during the signal acquisition process, the system automatically adds a corresponding timestamp to each set of vibration signals and acoustic emission signals, which accurately records the specific moment of signal acquisition.

[0095] Furthermore, based on the time information provided by the timestamp, the two sets of signals are compared and adjusted one by one, and the vibration signals and acoustic emission signals at the same time point are matched and aligned to ensure that the vibration signals and acoustic emission signals are completely synchronized in the time dimension, thereby obtaining vibration signals and acoustic emission signals with the same frequency of the mining equipment.

[0096] Furthermore, based on the actual spatial coordinates of each component of the mining equipment, a three-dimensional space framework is constructed using professional three-dimensional modeling software.

[0097] Furthermore, within this framework, each spatial coordinate corresponds to the actual location of the device. The co-frequency vibration signals, acoustic emission signals, and thermal imaging data collected by the infrared camera obtained in the previous steps are accurately mapped to the corresponding positions in the three-dimensional spatial framework according to their corresponding spatial locations of the device.

[0098] Furthermore, according to the time sequence of data collection, these data are arranged in sequence in a three-dimensional spatial framework, and finally a three-dimensional working condition map is constructed that can comprehensively and intuitively reflect the operating status of mining equipment.

[0099] In general, data is collected by clock-synchronized sensors, and timing deviations are compensated by sliding window interpolation to ensure that vibration signals and acoustic emission signals are strictly aligned in the time dimension, thus solving the timing misalignment problem caused by sampling frequency differences and transmission delays in traditional multi-source data.

[0100] In general, the signals after frequency alignment can accurately map the mechanical response and energy release characteristics of the device at the same moment, avoiding misjudgment of fault characteristics caused by time mismatch, and providing a reliable time reference for subsequent feature decoupling and fault location.

[0101] In general, a three-dimensional framework is built based on spatial coordinates, and the aligned vibration / acoustic emission signals and thermal imaging data are structured and deployed according to spatial position and time sequence to form a three-dimensional working condition map that includes "time-space-physical characteristics".

[0102] In general, the atlas can intuitively present the state evolution process of each component of the equipment in three-dimensional space. Combined with the temperature field distribution of thermal imaging data, it can realize the three-dimensional mapping of faults from "time domain-frequency domain" analysis to "time-space domain-energy domain", significantly improving the accuracy and visualization of early fault location, and providing multi-dimensional input basis for subsequent feature decoupling based on dynamic models and multi-layer decision network diagnosis.

[0103] S3. Decoupling the characteristics of the operating status information under physical constraints based on the equipment dynamics model to obtain a fault-sensitive feature set of the mining equipment;

[0104] In an embodiment of the present invention, the feature decoupling of the operating state information under physical constraints based on the equipment dynamics model to obtain the fault-sensitive feature set of the mining equipment includes:

[0105] Establishing an equipment dynamics equation for the mining equipment based on the structural characteristics, operating principles, and correlation between physical parameters of the mining equipment;

[0106] Based on the equipment dynamics equation, the vibration signal is decomposed into a time domain impact component related to the gear meshing torque and a centrifugal force modulation component related to bearing wear;

[0107] The amplitude spectrum of the acoustic emission signal is extracted through Morlet wavelet transform to identify the gear tooth breakage impact frequency and its harmonic components, and then correlated with the equipment load rate change curve to obtain the harmonic components of the mining equipment;

[0108] generating heat flux density distribution data per unit area of ​​the mining equipment according to the temperature gradient distribution collected by the infrared thermal imager;

[0109] The time domain impact component, centrifugal force modulation component, harmonic component and unit area heat flux density distribution data are collected to form the fault sensitive feature set of the mining equipment.

[0110] The generating of the heat flux density distribution data per unit area of ​​the mining equipment according to the temperature gradient distribution collected by the infrared thermal imager includes:

[0111] collecting temperature distribution data of the friction contact area of ​​the mining equipment by the infrared thermal imager to generate a real-time temperature gradient distribution map of the friction contact area;

[0112] The rotational speed, load pressure, and lubricant flow parameters of the rotor in the mining equipment are used as boundary conditions for temperature field modeling. The temperature gradient distribution map is mapped to the friction contact area according to Fourier's law of heat conduction to obtain a three-dimensional transient temperature field model of the friction contact area.

[0113] Multiplying the friction force and the relative displacement in the three-dimensional transient temperature field model to obtain the friction heat generation power of the friction contact area;

[0114] The frictional heat power is distributed to the friction contact area, and combined with the meshing of the three-dimensional transient temperature field model, unit area heat flux density distribution data of the mining equipment is generated.

[0115] Specifically, the components of mining equipment are mapped in detail, their shapes and sizes are recorded, and the connection methods between components, such as bolt connections and welding, are observed.

[0116] Furthermore, we need to gain an in-depth understanding of the motion trajectory of each component during equipment operation, such as the rotation of gears and bearings, clarify the force transmission and interaction relationship between components, analyze how mass affects motion inertia, how stiffness determines the degree of component deformation, and how damping consumes motion energy.

[0117] Furthermore, by applying the principles of system dynamics, the equipment is regarded as consisting of multiple interrelated subsystems, and a mechanical analysis is performed on each subsystem. Factors such as force, motion, and mass are considered to construct an equipment dynamics equation that can fully describe the operating status of mining equipment.

[0118] Furthermore, the vibration signal is input into the signal analysis software and the signal decomposition algorithm is used.

[0119] Furthermore, the algorithm first divides the vibration signal into multiple small segments in chronological order. For each small segment, it analyzes the waveform changes in the signal based on the gear meshing and bearing motion laws reflected by the equipment dynamics equation.

[0120] Furthermore, when sudden and dramatic waveform fluctuations are found in the signal, similar to the shape of an impact, and the pattern of their occurrence is consistent with the gear meshing period, this part of the signal is extracted and determined as the time domain impact component related to the gear meshing torque; if there is a periodic waveform modulation phenomenon in the signal, and its frequency is related to the bearing rotation frequency, this part of the signal is separated as the centrifugal force modulation component related to bearing wear.

[0121] Furthermore, the acoustic emission signal is introduced into a signal processing system that supports Morlet wavelet transform. The Morlet wavelet transform algorithm first selects a suitable Morlet wavelet function, which is a waveform with specific frequency and time characteristics.

[0122] Furthermore, the Morlet wavelet function is slid on the acoustic emission signal from the starting position at a certain time interval. At each position, a value is obtained by calculating the similarity between the Morlet wavelet function and the acoustic emission signal at the corresponding position.

[0123] Furthermore, as the Morlet wavelet function slides over the entire acoustic emission signal, these values ​​constitute the amplitude spectrum of the acoustic emission signal.

[0124] Furthermore, the amplitude spectrum was analyzed to find the part with a higher peak and a specific frequency pattern, which was determined to be the gear tooth breakage impact frequency and its harmonic components. These frequency components were then compared with the load rate change curve recorded during equipment operation to find the correlation between the two, thereby obtaining the harmonic components of the mining equipment.

[0125] Furthermore, the temperature gradient distribution image captured by the infrared thermal imager is opened using image processing software.

[0126] Furthermore, the device surface is first divided into a plurality of regular unit area regions in the image, just like dividing a map into grids.

[0127] Furthermore, according to the physical relationship between temperature and heat flux, that is, temperature change will cause heat flow, the greater the temperature difference, the greater the heat flux.

[0128] Furthermore, the average temperature in each unit area is calculated and compared with the temperature of the adjacent area. Based on the temperature difference and the area, the heat flux density of each unit area is calculated, and finally the unit area heat flux density distribution data of the mining equipment is generated.

[0129] Furthermore, the time domain impact component and centrifugal force modulation component decomposed from the vibration signal, the harmonic component extracted from the acoustic emission signal, and the unit area heat flux density distribution data generated based on the infrared thermal imager data are uniformly transmitted to the data processing center through the data transmission line.

[0130] Furthermore, in the data processing center, data integration software is used to organize and convert these different types of data according to unified format requirements, remove duplicate and invalid data, and combine valid data to form a fault-sensitive feature set that can accurately reflect the potential faults of mining equipment for subsequent equipment fault diagnosis and analysis.

[0131] Specifically, an infrared thermal imager is used to monitor the friction contact area of ​​mining equipment in real time. The infrared radiation radiated by objects in the area is received by the infrared detector. After signal processing and image processing algorithms, the infrared radiation of different intensities is converted into corresponding temperature values. A real-time temperature gradient distribution map of the friction contact area is generated according to the spatial position distribution, which intuitively presents the temperature high and low and change trends of the area.

[0132] Furthermore, the rotational speed of the rotor in the mining equipment is determined, and the number of revolutions per minute of the rotor is measured and recorded in real time through a speed sensor; the load pressure is obtained, and a pressure sensor is installed at the load application location to measure and record the pressure acting on the equipment; the lubricant flow parameters are counted, and a flow metering device is installed in the lubricant delivery pipeline to calculate the volume of lubricant flowing through the pipeline per unit time.

[0133] Furthermore, these three parameters are used as boundary conditions for temperature field modeling. At the same time, based on Fourier's law of heat conduction, which states that the heat conduction rate is proportional to the temperature gradient and the direction is opposite to the temperature gradient, the temperature data in the real-time temperature gradient distribution map are mapped point by point to the three-dimensional spatial position of the friction contact area according to the heat conduction direction and rate, and a three-dimensional transient temperature field model of the friction contact area is constructed. This model reflects the temperature distribution at different times and positions.

[0134] Furthermore, in the three-dimensional transient temperature field model, the friction force data and relative displacement data of the friction contact area are extracted.

[0135] Furthermore, the friction force data is measured by a force sensor installed near the friction pair, reflecting the force that hinders the relative motion between the friction surfaces; the relative displacement data is obtained by measuring the relative movement distance between the friction pairs through a displacement sensor.

[0136] Furthermore, these two data are multiplied, that is, the friction force value is multiplied by the relative displacement value, and the result is the friction heat generation power of the friction contact area, which represents the amount of heat generated per unit time during the friction process.

[0137] Furthermore, the calculated frictional heat generation power is distributed to different positions in the friction contact area according to the actual contact conditions and heat conduction characteristics of each part of the friction contact area.

[0138] Furthermore, the three-dimensional transient temperature field model is first meshed to divide the friction contact area into multiple fine mesh cells, each of which represents a tiny unit area.

[0139] Furthermore, based on the friction force, relative displacement and heat conduction capacity of each grid unit, the thermal power to be allocated to the grid unit is calculated. The thermal power is then divided by the area of ​​the grid unit to obtain the heat flux density per unit area. Finally, the unit area heat flux density distribution data of the mining equipment is generated, which clearly shows the size and distribution pattern of the heat flux density per unit area in the friction contact area.

[0140] In general, a dynamic equation is established based on the structural characteristics and operating principles of mining equipment, and the vibration signal is decomposed into a time-domain impact component and a centrifugal force modulation component. The physical characteristics directly related to the specific failure mode are separated from the mixed signal, avoiding the feature ambiguity problem caused by the aliasing of multiple source signals in traditional frequency domain analysis.

[0141] In general, the harmonic components of the acoustic emission signal are extracted through Morlet wavelet transform, and combined with the unit area heat flux density distribution generated by thermal imaging data, a multi-physical fault-sensitive feature set covering mechanics, acoustics, and thermals is formed. This significantly reduces the data dimension while retaining the core fault information, thereby improving the input quality of subsequent diagnostic models.

[0142] In general, the feature decoupling process is closely based on the device dynamics principles, so that each feature component corresponds to a clear physical meaning.

[0143] In general, this feature engineering method based on prior knowledge not only improves the causal relationship between features and failure modes, but also provides a traceable physical mechanism explanation for the diagnostic results, avoiding the "black box" problem of deep learning models, making it easier for engineers to quickly locate the root cause of the fault and formulate targeted maintenance strategies.

[0144] S4. Input the fault-sensitive feature set into a multi-layer decision network and output the fault diagnosis results and confidence scores;

[0145] In an embodiment of the present invention, inputting the fault-sensitive feature set into a multi-layer decision network and outputting a fault diagnosis result and a confidence score includes:

[0146] Using a gated recurrent layer to perform a temporal dependency analysis on the fault-sensitive feature set, and outputting a hidden Markov chain state transition probability of the mining equipment operating state;

[0147] The energy distribution characteristics of the vibration signal in the gear meshing line direction are captured by a convolutional neural network to generate a two-dimensional spatial correlation map of the mining equipment;

[0148] The hidden Markov chain state transition probability and the two-dimensional spatial association graph are aggregated to output the fault diagnosis result and confidence score of the mining equipment.

[0149] Specifically, the previously obtained mining equipment fault sensitive feature set is input into the gated recurrent layer model in chronological order.

[0150] Furthermore, the gated recurrent layer contains two control units: an update gate and a reset gate. The update gate determines how much of the state information at the previous moment is retained to the current moment, while the reset gate determines the degree of forgetting of the state information at the previous moment.

[0151] Furthermore, when processing the fault-sensitive feature set data at each moment, the gated recurrent layer calculates the hidden state at the current moment based on the calculation results of the update gate and the reset gate, combined with the current input data and the state at the previous moment.

[0152] Furthermore, as all moment data processing is completed, the gated recurrent layer calculates the hidden Markov chain state transition probability of the mining equipment operating state based on the final hidden state sequence, that is, the probability of transitioning from one operating state to another.

[0153] Furthermore, the processed vibration signal is input into the convolutional neural network.

[0154] Furthermore, the convolutional neural network consists of multiple convolutional layers, pooling layers, and fully connected layers. In the convolutional layers, multiple convolution kernels of different sizes and weights are designed and slid across the vibration signal data at a set step size to extract features from the vibration signal data along the gear meshing line.

[0155] Furthermore, each convolution kernel performs a convolution operation with the data in the corresponding area, that is, the corresponding elements are multiplied and then summed to obtain the eigenvalue of the area.

[0156] Furthermore, after processing through multiple convolutional layers, the energy distribution characteristics of the vibration signal at different levels in the direction of the gear meshing line are extracted.

[0157] Furthermore, a pooling layer performs dimensionality reduction on the features, retaining key features while reducing the amount of data. Finally, a fully connected layer integrates the extracted features to generate a two-dimensional spatial correlation map of mining equipment that reflects the energy distribution characteristics of the vibration signal along the gear mesh line.

[0158] Furthermore, the hidden Markov chain state transition probabilities calculated by the gated recurrent layer and the two-dimensional spatial correlation map generated by the convolutional neural network are input into the data aggregation module. In the data aggregation module, the data formats of the hidden Markov chain state transition probabilities and the two-dimensional spatial correlation map are first converted to a unified format for compatible processing.

[0159] Furthermore, a weighted fusion method is adopted to combine the data of the two according to pre-set weights.

[0160] Furthermore, the merged data is processed by a classifier, which determines the current fault state of the mining equipment based on the trained classification model and rules and outputs the fault diagnosis results.

[0161] Furthermore, based on the decision information and data features in the classification process, the confidence score of the fault diagnosis result is calculated to indicate the reliability of the diagnosis result.

[0162] In general, the gated recurrent layer is used to perform temporal dependency analysis on the fault-sensitive feature set, generate the hidden Markov chain state transition probability, and capture the dynamic evolution of the equipment operating status over time; at the same time, the convolutional neural network is used to extract the energy distribution characteristics of the vibration signal in the direction of the gear meshing line, generate a two-dimensional spatial correlation diagram, and characterize the fault propagation mode of the spatial position of the mechanical component.

[0163] In general, the two network structures process temporal features and spatial features in parallel, realizing cross-dimensional feature aggregation of "time series-spatial distribution", avoiding the limitations of a single network in representing complex working conditions, significantly improving the model's generalized diagnostic capabilities for multiple types of faults such as non-stationary vibrations and sudden impacts, and shortening the time link from feature analysis to the output of diagnostic results.

[0164] In general, the multi-layer decision network outputs not only the fault type but also the confidence score, providing a quantitative credibility indicator for the diagnosis result.

[0165] For example, when the vibration signal's time-domain impact component and acoustic emission harmonic components simultaneously trigger a gear tooth breakage warning, the model can use confidence scoring to determine the reliability of the diagnostic result, effectively filtering out false alarms caused by interference factors such as sensor noise and operating condition fluctuations. This diagnostic mechanism with probabilistic output not only meets the real-time requirements of intelligent manufacturing, but also improves the reliability of diagnostic results through data-driven statistical learning, providing a more reliable decision-making basis for subsequent fault causal tracing and process correction.

[0166] S5. Constructing a fault cause-effect diagram for the mining equipment based on the pre-acquired design parameters and manufacturing process parameters, and designing a correction plan including process constraints for abnormal process parameters of the mining equipment whose traceability confidence scores in the fault cause-effect diagram are below a set threshold;

[0167] In an embodiment of the present invention, constructing a fault cause-effect graph of the mining equipment based on pre-acquired design parameters and manufacturing process parameters includes:

[0168] Performing Bayesian estimation on the depth of cut, tool feed rate, and spindle torque among the pre-acquired design parameters and manufacturing process parameters to obtain a conditional probability distribution of the mining equipment under different states, filling the conditional probability distribution into network parameters, and establishing a Bayesian network model;

[0169] Performing a hierarchical aggregation strategy on the process parameters and fault labels in the pre-acquired design parameters and manufacturing process parameters to obtain a process-fault matrix of the mining equipment;

[0170] Markov chain Monte Carlo sampling is performed on a Bayesian network model set as a normal distribution and different types of faults in the process-fault matrix to obtain a fault causal diagram of the mining equipment.

[0171] The abnormal process parameters of the mining equipment whose traceability confidence score in the fault causal graph is lower than a set threshold are used to design a correction plan containing process constraints for the abnormal process parameters, including:

[0172] If the fault cause-effect diagram shows a strong correlation between cutting depth and excessive vibration, adjust the tool feed rate and add lubrication compensation conditions;

[0173] If there is causal feedback between the centrifugal force modal parameters and the bearing temperature, the assembly tolerance verification instruction is triggered;

[0174] When the heat loss rate is abnormal, the geometric matching degree of the friction pair is verified by finite element simulation.

[0175] The correction scheme for designing the abnormal process parameters including the process constraint conditions includes:

[0176] modifying a path parameter of the tool based on a maximum allowable cutting force limit of the mining equipment;

[0177] Setting a tolerance threshold for the assembly clearance of the mining equipment according to the accuracy grade requirement of the gearbox in the mining equipment;

[0178] The critical temperature rise value of the bearing of the mining equipment is defined in combination with the heat treatment characteristics of the material of the mining equipment.

[0179] Specifically, the pre-acquired design parameters and manufacturing process parameters of the mining equipment are first collected, and the manufacturing process parameters are separated therefrom.

[0180] Furthermore, these process parameters and corresponding fault labels are divided according to a certain hierarchical relationship. For example, the first level of classification is carried out according to the major process categories, such as casting process, processing process, assembly process, etc., and then the second level of classification is carried out according to the specific process steps or process indicators under each major category, and so on.

[0181] Furthermore, the process parameters and fault labels within each level are aggregated, and the process parameters and fault labels with associated relationships are combined together. Through this hierarchical aggregation strategy, a mining equipment process-fault matrix is ​​finally constructed that can clearly show the correspondence between process parameters and faults.

[0182] Furthermore, the Markov chain Monte Carlo sampling method is adopted for the Bayesian network model set as normal distribution and different types of faults in the process-fault matrix.

[0183] Furthermore, the initial state of the sampling is determined, and this initial state can be based on certain prior knowledge or a random setting.

[0184] Furthermore, starting from the initial state, the next state is generated according to the current state according to the rules of the Markov chain. During the generation process, each state is evaluated and screened based on the probability distribution set by the Bayesian network model and the relationship between faults and process parameters in the process-fault matrix.

[0185] Furthermore, for each new state generated, its probability of acceptance is calculated. If the acceptance probability meets certain conditions, the state is retained as part of the sampling result; otherwise, it is discarded. By repeating this process, a large number of sampled states are generated. Based on these sampled states, the causal relationship between different process parameters and faults is analyzed and organized, ultimately creating a fault causal diagram that can intuitively demonstrate the causal relationship of mining equipment failures.

[0186] Specifically, when the fault cause-effect diagram shows a strong correlation between cutting depth and excessive vibration, adjustment measures are taken immediately.

[0187] Furthermore, the current tool feed rate is determined first, and based on experience and actual processing conditions, the tool feed rate is gradually reduced to reduce the amount of tool penetration into the workpiece during each cutting.

[0188] Furthermore, lubrication compensation conditions are added. In the cutting contact area between the tool and the workpiece, a special lubrication device is used to increase the supply amount and frequency of lubricant, improve the lubrication condition during the cutting process, reduce cutting resistance and friction, and thus reduce the problem of excessive vibration caused by cutting depth.

[0189] Furthermore, if a causal feedback loop is detected between the centrifugal force modal parameters and the bearing temperature, an assembly tolerance verification instruction is immediately triggered. Professional assembly personnel are assigned to use high-precision measuring tools such as micrometers and dial indicators to measure the dimensions of bearing assembly-related components in mining equipment.

[0190] Furthermore, the actual dimensions measured are compared one by one with the standard dimensions required by the design to check whether the dimensional deviation of each component is within the specified tolerance range.

[0191] Furthermore, components that are out of tolerance are reprocessed or replaced to ensure that the assembly tolerances of all components meet the requirements and eliminate the causal feedback between abnormal centrifugal force modal parameters and increased bearing temperature caused by assembly problems.

[0192] Furthermore, once an abnormal heat loss rate is detected, finite element simulation technology is immediately used to verify the geometric matching of the friction pair.

[0193] Furthermore, 3D modeling software is first used to accurately construct a 3D model of the friction pair according to the actual size and shape of the friction pair of the mining equipment.

[0194] Furthermore, the constructed three-dimensional model is imported into the finite element analysis software, and the friction pair is meshed and divided into multiple small mesh units.

[0195] Furthermore, according to the actual working conditions, the boundary conditions of the simulation are set, including the movement mode and force conditions of the friction pair.

[0196] Furthermore, a finite element simulation program is run in the software to simulate the stress, deformation and heat transfer of the friction pair during operation. By analyzing the simulation results, it is determined whether the geometric shapes of the friction pair are well matched and the geometric shape problems that lead to abnormal heat loss rate are found.

[0197] Furthermore, the tool path parameters are modified based on the maximum allowable cutting force limit of the mining equipment.

[0198] Furthermore, the maximum allowable cutting force value specified by the mining equipment is obtained, and the current tool path data is imported using specialized tool path planning software.

[0199] Furthermore, the software performs force analysis on each cutting point on the tool path and calculates the cutting force at each point under the current path.

[0200] Furthermore, for the point where the calculated cutting force exceeds the maximum allowable cutting force, the software automatically adjusts the tool path at that point, such as changing the tool's cutting angle, increasing the number of cuts, etc., and replans the tool's motion trajectory to ensure that the tool's cutting force does not exceed the maximum allowable cutting force limit throughout the entire cutting process.

[0201] Furthermore, according to the accuracy level requirement of the gearbox in the mining equipment, a tolerance threshold of the assembly clearance of the mining equipment is set.

[0202] Furthermore, the technical documentation of the mining equipment is reviewed to determine the required accuracy grade standard for the gearbox. Based on the requirements for assembly clearance in this accuracy grade standard, the appropriate assembly clearance tolerance range is determined.

[0203] Furthermore, during the actual assembly process, a gap measuring tool, such as a feeler gauge, is used to measure the assembly gaps between the various components of the mining equipment.

[0204] Furthermore, when the measured value exceeds a preset assembly clearance tolerance threshold, the assembly position of the component is adjusted or the relevant component is replaced so that the assembly clearance meets the gearbox accuracy grade requirement.

[0205] Furthermore, in combination with the material heat treatment characteristics of the mining equipment, the critical value of the bearing temperature rise of the mining equipment is limited.

[0206] Furthermore, detailed heat treatment data on the materials used in mining equipment bearings should be collected to understand the changes in the material's physical properties at different temperatures, such as hardness and strength. Through experiments or by referring to data provided by the material supplier, the maximum temperature the material can withstand under normal operating conditions should be determined.

[0207] Furthermore, this temperature value is set as the bearing temperature rise threshold. During the operation of mining equipment, temperature sensors are used to monitor the bearing temperature in real time. Once the bearing temperature approaches or reaches this threshold, cooling measures are immediately implemented, such as increasing the power of the cooling device, to ensure that the bearing temperature does not exceed the specified temperature rise threshold.

[0208] In general, a Bayesian network model and process-fault matrix are constructed based on the design parameters and manufacturing process parameters, and a fault causal diagram is generated through Markov chain Monte Carlo sampling, and the relationship between process parameters and failure modes is probabilistically modeled.

[0209] In general, this traceability method that combines data-driven and physical models breaks through the limitations of traditional diagnosis that only targets operating data. It can trace the root cause of the fault from the dimensions of the entire design, processing, and assembly process, and realize reverse tracking of "equipment failure-process parameter abnormality", solving the problem of disconnection between fault diagnosis and manufacturing process in existing technologies, and improving the depth and systematicness of diagnostic results.

[0210] In general, for abnormal process parameters with low traceability confidence in the fault causal diagram, a correction plan is designed in combination with process constraints:

[0211] In general, the tool path parameters should be corrected based on the maximum allowable cutting force limit of the equipment to avoid blind adjustments that may cause mechanical overload;

[0212] In general, the assembly clearance tolerance threshold is set according to the gearbox accuracy grade to ensure that the revised assembly process meets the design standards;

[0213] In general, the critical value of bearing temperature rise is limited in combination with the heat treatment characteristics of the material to prevent secondary failures caused by thermal deformation.

[0214] In general, this mechanism maps the diagnostic results directly to process parameter optimization. Through the closed loop of "probabilistic modeling-threshold triggering-constraint correction", it achieves an upgrade from fault handling to preventive optimization of the manufacturing process. It not only eliminates current fault hazards, but also reduces the probability of recurrence of similar faults through dynamic tuning of process parameters, forming a synergistic effect of fault diagnosis and process improvement in the intelligent manufacturing process, and significantly improving the reliability and production efficiency of the equipment throughout its life cycle.

[0215] S6. Integrate the correction plan, the fault diagnosis result and the three-dimensional working condition map to construct a visual diagnosis report.

[0216] In an embodiment of the present invention, the integration of the correction scheme, the fault diagnosis result and the three-dimensional operating condition map to construct a visual diagnosis report includes:

[0217] After mapping the axial vibration amplitude of the three-dimensional operating condition map to a chromatographic gradient, the spectral characteristic lines in the fault diagnosis results are superimposed on the corresponding area of ​​the thermal imaging map, and the impact path of abnormal process parameters on equipment performance is marked with dynamic vector arrows to obtain a visual diagnostic report of the mining equipment.

[0218] Specifically, the three-dimensional working condition map of the mining equipment is processed to extract the axial vibration amplitude data.

[0219] Furthermore, a set of fixed mapping rules is established to correspond axial vibration amplitudes of different sizes to chromatographic gradients of different colors.

[0220] For example, set lower axial vibration amplitudes to correspond to cool colors, and higher axial vibration amplitudes to correspond to warm colors. According to this rule, the axial vibration amplitudes at each position in the three-dimensional working condition map are converted into corresponding colors to form a visualization effect with a chromatographic gradient.

[0221] Furthermore, the spectral characteristic line data is obtained from the fault diagnosis results. The previously generated thermal image is found and, based on the device location information corresponding to the spectral characteristic lines, these spectral characteristic lines are accurately superimposed on the corresponding areas of the thermal image.

[0222] Furthermore, during the overlay process, it is ensured that the position, shape, and direction of the spectrum characteristic lines match the actual structure and position of the equipment in the thermal image, so that the two can be clearly integrated for easy observation and analysis.

[0223] Furthermore, for the abnormal process parameters that have been identified, the specific path of their impact on the performance of mining equipment is analyzed.

[0224] Furthermore, the starting point and end point of each abnormal process parameter affecting equipment performance, as well as the specific route of transmitting the impact in the equipment structure, are determined.

[0225] Furthermore, a dynamic vector arrow is drawn on the visualization graph using drawing software. The starting point of the arrow is the location where the abnormal process parameter occurs, the direction of the arrow is along the route of image transmission, and the end point of the arrow is the location where the equipment performance is affected.

[0226] Furthermore, in this way, the impact path of abnormal process parameters on equipment performance can be intuitively marked.

[0227] Furthermore, the thermal imaging images with chromatographic gradients, superimposed spectrum characteristic lines, and annotated dynamic vector arrows after the above processing are integrated, and necessary elements such as legends, text descriptions, and titles are added to form a complete visual diagnosis report of mining equipment. This report can display the operating status, fault characteristics, and the impact of abnormal process parameters of mining equipment in an intuitive and vivid way.

[0228] In general, the axial vibration amplitude of the three-dimensional operating condition map is mapped to a chromatographic gradient, and the spectral characteristics in the fault diagnosis results are superimposed on the corresponding area of ​​the thermal imaging map to achieve the spatiotemporal correlation display of "vibration energy distribution-temperature field anomaly-fault frequency characteristics".

[0229] For example, by superimposing high-frequency vibration spectrum lines at the same position in the high-temperature area of ​​the thermal image, the overheating and abnormal vibration coupling failure of the friction pair caused by insufficient lubrication can be quickly located, avoiding the information fragmentation problem in traditional single chart analysis, and greatly shortening the time cost for engineers from data interpretation to fault location.

[0230] In general, the impact path of abnormal process parameters on equipment performance is marked by dynamic vector arrows, transforming the abstract fault causal relationship into an intuitive physical link display.

[0231] In general, combined with the process constraints in the correction plan, the visual diagnostic report can simultaneously present the complete logical chain of "fault phenomenon-process traceability-correction strategy".

[0232] For example, arrows are used in the three-dimensional working condition map to dynamically demonstrate the downward trend of the vibration amplitude after the assembly gap is corrected, providing operators with an integrated decision-making interface that combines diagnostic results, traceability basis and improvement plans, thereby improving the transparency and collaborative efficiency of fault handling in the intelligent manufacturing process, and providing traceable historical data reference for subsequent process optimization.

[0233] In the several embodiments provided by the present invention, it should be understood that the disclosed methods can be implemented in other ways.

[0234] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0235] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method and technology of using digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to achieve optimal results.

[0236] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent fault diagnosis method in the intelligent manufacturing process of mining equipment, characterized in that: The method comprises: S1. Collecting vibration signals, acoustic emission signals and thermal imaging data of mining equipment in real time through multi-source sensors as the operating status information of the mining equipment; S2. After aligning the vibration signal and the acoustic emission signal by time stamp, perform spatial coordinate registration to obtain a three-dimensional operating state map of the mining equipment; S3. Decoupling the characteristics of the operating status information under physical constraints based on the equipment dynamics model to obtain a fault-sensitive feature set of the mining equipment; S4. Input the fault-sensitive feature set into a multi-layer decision network and output the fault diagnosis results and confidence scores; S5. Constructing a fault cause-effect diagram for the mining equipment based on the pre-acquired design parameters and manufacturing process parameters, and designing a correction plan including process constraints for abnormal process parameters of the mining equipment whose traceability confidence scores in the fault cause-effect diagram are below a set threshold; S6. Integrate the correction plan, the fault diagnosis result and the three-dimensional working condition map to construct a visual diagnosis report.

2. The intelligent fault diagnosis method in the intelligent manufacturing process of mining equipment according to claim 1, characterized in that: The collecting of vibration signals, acoustic emission signals and thermal imaging data of mining equipment in real time through multi-source sensors as operating status information of the mining equipment includes: Deploy a vibration acceleration sensor on the axial mounting surface of a bearing seat of mining equipment to obtain a vibration signal of the mining equipment under full load conditions; Arrange acoustic emission sensors in a circular array on the surface of the gearbox housing to obtain acoustic emission signals of the mining equipment; An infrared thermal imager is installed in the radial observation area of ​​the equipment friction area, and is driven by a stepper motor to realize dynamic tracking and focusing of the thermal imaging data of the mining equipment; The vibration signal, the acoustic emission signal and the thermal imaging data are collected as the operating status information of the mining equipment.

3. The intelligent fault diagnosis method in the intelligent manufacturing process of mining equipment according to claim 2, characterized in that: After aligning the vibration signal and the acoustic emission signal by time stamp, spatial coordinate registration is performed to obtain a three-dimensional working condition map of the mining equipment, including: Using the clock-synchronized vibration acceleration sensor and the acoustic emission sensor to collect information from the mining equipment, when the delay of the information collection exceeds a signal segment of a set threshold, using sliding window interpolation to compensate for the timing deviation of the collected information to obtain the vibration signal and acoustic emission signal of the mining equipment; Aligning the vibration signal and the acoustic emission signal through a timestamp to obtain a vibration signal and an acoustic emission signal of the same frequency of the mining equipment; A three-dimensional spatial framework is constructed based on spatial coordinates, and the vibration signal and acoustic emission signal of the same frequency and the thermal imaging data are arranged in the three-dimensional spatial framework according to spatial position and time sequence to obtain a three-dimensional working condition map of the mining equipment.

4. The intelligent fault diagnosis method in the intelligent manufacturing process of mining equipment according to claim 2, characterized in that: The feature decoupling of the operating state information under physical constraints based on the equipment dynamics model to obtain the fault-sensitive feature set of the mining equipment includes: Establishing an equipment dynamics equation for the mining equipment based on the structural characteristics, operating principles, and correlation between physical parameters of the mining equipment; Based on the equipment dynamics equation, the vibration signal is decomposed into a time domain impact component related to the gear meshing torque and a centrifugal force modulation component related to bearing wear; The amplitude spectrum of the acoustic emission signal is extracted through Morlet wavelet transform to identify the gear tooth breakage impact frequency and its harmonic components, and then correlated with the equipment load rate change curve to obtain the harmonic components of the mining equipment; generating heat flux density distribution data per unit area of ​​the mining equipment according to the temperature gradient distribution collected by the infrared thermal imager; The time domain impact component, centrifugal force modulation component, harmonic component and unit area heat flux density distribution data are collected to form the fault sensitive feature set of the mining equipment.

5. The intelligent fault diagnosis method in the intelligent manufacturing process of mining equipment according to claim 4, characterized in that: The generating of the heat flux density distribution data per unit area of ​​the mining equipment according to the temperature gradient distribution collected by the infrared thermal imager includes: collecting temperature distribution data of the friction contact area of ​​the mining equipment by the infrared thermal imager to generate a real-time temperature gradient distribution map of the friction contact area; The rotational speed, load pressure, and lubricant flow parameters of the rotor in the mining equipment are used as boundary conditions for temperature field modeling. The temperature gradient distribution map is mapped to the friction contact area according to Fourier's law of heat conduction to obtain a three-dimensional transient temperature field model of the friction contact area. Multiplying the friction force and the relative displacement in the three-dimensional transient temperature field model to obtain the friction heat generation power of the friction contact area; The frictional heat power is distributed to the friction contact area, and combined with the meshing of the three-dimensional transient temperature field model, unit area heat flux density distribution data of the mining equipment is generated.

6. The intelligent fault diagnosis method in the intelligent manufacturing process of mining equipment according to claim 1, characterized in that: The step of inputting the fault-sensitive feature set into a multi-layer decision network and outputting a fault diagnosis result and a confidence score includes: Using a gated recurrent layer to perform a temporal dependency analysis on the fault-sensitive feature set, and outputting a hidden Markov chain state transition probability of the mining equipment operating state; The energy distribution characteristics of the vibration signal in the gear meshing line direction are captured by a convolutional neural network to generate a two-dimensional spatial correlation map of the mining equipment; The hidden Markov chain state transition probability and the two-dimensional spatial association graph are aggregated to output the fault diagnosis result and confidence score of the mining equipment.

7. The intelligent fault diagnosis method in the intelligent manufacturing process of mining equipment according to claim 1, characterized in that: The constructing of a fault cause-effect graph of the mining equipment based on pre-acquired design parameters and manufacturing process parameters includes: Performing Bayesian estimation on the depth of cut, tool feed rate, and spindle torque among the pre-acquired design parameters and manufacturing process parameters to obtain a conditional probability distribution of the mining equipment under different states, filling the conditional probability distribution into network parameters, and establishing a Bayesian network model; Performing a hierarchical aggregation strategy on the process parameters and fault labels in the pre-acquired design parameters and manufacturing process parameters to obtain a process-fault matrix of the mining equipment; Markov chain Monte Carlo sampling is performed on a Bayesian network model set as a normal distribution and different types of faults in the process-fault matrix to obtain a fault causal diagram of the mining equipment.

8. The intelligent fault diagnosis method in the intelligent manufacturing process of mining equipment according to claim 1, characterized in that: The abnormal process parameters of the mining equipment whose traceability confidence score in the fault causal graph is lower than a set threshold are used to design a correction plan containing process constraints for the abnormal process parameters, including: If the fault cause-effect diagram shows a strong correlation between cutting depth and excessive vibration, adjust the tool feed rate and add lubrication compensation conditions; If there is causal feedback between the centrifugal force modal parameters and the bearing temperature, the assembly tolerance verification instruction is triggered; When the heat loss rate is abnormal, the geometric matching degree of the friction pair is verified by finite element simulation.

9. The intelligent fault diagnosis method in the intelligent manufacturing process of mining equipment according to claim 8, characterized in that: The correction scheme for designing the abnormal process parameters including the process constraint conditions includes: modifying a path parameter of the tool based on a maximum allowable cutting force limit of the mining equipment; Setting a tolerance threshold for the assembly clearance of the mining equipment according to the accuracy grade requirement of the gearbox in the mining equipment; The critical temperature rise value of the bearing of the mining equipment is defined in combination with the heat treatment characteristics of the material of the mining equipment.

10. The intelligent fault diagnosis method in the intelligent manufacturing process of mining equipment according to claim 1, characterized in that: The integration of the correction scheme, the fault diagnosis result and the three-dimensional operating condition map to construct a visual diagnosis report includes: After mapping the axial vibration amplitude of the three-dimensional operating condition map to a chromatographic gradient, the spectral characteristic lines in the fault diagnosis results are superimposed on the corresponding area of ​​the thermal imaging map, and the impact path of abnormal process parameters on equipment performance is marked with dynamic vector arrows to obtain a visual diagnostic report of the mining equipment.

Images