Linear guide rail fault diagnosis method and system based on deep learning

Abstract

The invention relates to the technical field of linear guide rail operation and maintenance management, in particular to a linear guide rail fault diagnosis method and system based on deep learning, which can improve the stability and the production efficiency of equipment and reduce the maintenance cost. The method comprises the following steps: acquiring first running state data of a target linear guide rail and second running state data of at least one associated linear guide rail; inputting the first operation state data into a preset guide rail fault evaluation model to obtain a first fault evaluation result; respectively inputting the at least one group of second operation state data into a guide rail fault evaluation model to obtain at least one group of second fault evaluation results; and considering the homologous fault influence, correcting the first fault evaluation result according to the at least one group of second fault evaluation results, and obtaining a target linear guide rail fault diagnosis result.

Description

Technical Field

[0001] The present invention relates to the technical field of linear guide rail operation and maintenance management, and in particular to a linear guide rail fault diagnosis method and system based on deep learning. Background Art

[0002] In linear guide systems, fault diagnosis is a key link in ensuring the stable operation of mechanical equipment and maintaining production efficiency. As precision mechanical components, linear guides are widely used in various automation equipment, such as CNC machine tools, industrial robots, etc. Due to their long-term load, friction and vibration, linear guides are prone to a variety of faults, which not only affect the accuracy and stability of the equipment, but may also cause equipment downtime and production losses.

[0003] Existing linear guide fault diagnosis methods are mostly performed on single devices or components, ignoring the interrelationships and fault propagation characteristics between devices in actual industrial scenarios. In particular, in linear guide systems, adjacent linear guides are often in similar operating environments and working conditions. The failure of one guide may have a homologous fault effect on its adjacent guides. This homologous fault effect increases the complexity of fault diagnosis, making it difficult for traditional methods to accurately determine the true source and extent of the fault. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a linear guide rail fault diagnosis method and system based on deep learning, which can improve the stability and production efficiency of equipment and reduce maintenance costs.

[0005] In a first aspect, the present invention provides a linear guide rail fault diagnosis method based on deep learning, the method comprising: Acquire first operating status data of a target linear guide rail and second operating status data of at least one associated linear guide rail; Inputting the first operating state data into a preset guide rail fault assessment model to obtain a first fault assessment result; Inputting at least one set of the second operating status data into the guide rail fault assessment model to obtain at least one set of second fault assessment results; Taking into account the influence of homologous faults, the first fault assessment result is corrected according to at least one set of the second fault assessment results to obtain a target linear guide rail fault diagnosis result.

[0006] Furthermore, the associated linear guide is a linear guide of the same type as the target linear guide and located adjacently.

[0007] Furthermore, the method for collecting operation status data includes: Installing a variety of sensors on the linear guide rail and adjacent linear guide rails to monitor their operating status in real time; the sensors include temperature sensors, acceleration sensors, vibration sensors and noise sensors; Set the frequency of data collection; According to the data collection frequency, the data is collected in real time through the sensor installed on the linear guide; Preprocess the collected sensor data; The preprocessed sensor data is stored in a preset database.

[0008] Furthermore, the first fault assessment result includes a ball wear fault probability value, a guide rail corrosion fault probability value, a slider deformation fault probability value, and a slider end cover detachment fault probability value.

[0009] Furthermore, the method for constructing the guide rail fault assessment model includes: Collect historical linear guide operation status data and pre-process the collected data; A deep learning model is selected as the basic architecture of the guide rail fault assessment model; the deep learning model includes a recurrent neural network and a convolutional neural network; The preprocessed historical linear guide running status data is divided into a training set, a validation set and a test set; Use the training set to train the model and adjust the model parameters; Use the validation set data to validate the model and adjust the model parameters and structure based on the validation results; Use the test set data to evaluate the model; Deploy the trained model to the production environment, receive real-time data streams from sensors, and perform online fault assessment.

[0010] Furthermore, a mathematical calculation formula for correcting the first fault assessment result according to at least one set of the second fault assessment results is: Among them, P c represents the corrected failure probability value; P t represents the original target rail failure probability value; α is an adjustment coefficient between 0 and 1, which is used to balance the proportion of the original evaluation and the impact of the same source fault; n represents the number of associated rails; w i represents the weight of the i-th associated rail; P ai Represents the failure probability value of the i-th associated rail.

[0011] Furthermore, the target linear guide rail fault diagnosis result includes a corrected fault probability value, fault type confirmation, fault severity assessment, homologous fault impact analysis and maintenance recommendations.

[0012] On the other hand, the present application also provides a linear guide rail fault diagnosis system based on deep learning, the system comprising: A data acquisition module, for acquiring first operating status data of a target linear guide rail and second operating status data of at least one associated linear guide rail; A guide rail fault assessment module, inputting the first operating state data into a preset guide rail fault assessment model to obtain a first fault assessment result; Associating the guide rail fault assessment module, inputting at least one set of the second operating state data into the guide rail fault assessment model respectively, and obtaining at least one set of second fault assessment results; The fault diagnosis module considers the influence of the same-source faults and corrects the first fault assessment result according to at least one set of the second fault assessment results to obtain a target linear guide fault diagnosis result.

[0013] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0014] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0015] Compared with the prior art, the present invention has the following beneficial effects: the method not only evaluates the state of a single linear guide rail, but also analyzes the mutual influence between adjacent guide rails; by acquiring and processing the running state data of at least one associated linear guide rail, the influence of homologous faults can be more accurately identified, thereby improving the diagnostic accuracy; by comprehensively analyzing the data of the target guide rail and the associated guide rails, and correcting the fault assessment results by considering the influence of homologous faults, the location, type and severity of the fault can be more accurately determined, thereby reducing the possibility of misdiagnosis or missed diagnosis; Accurate fault diagnosis helps plan maintenance activities in advance, making maintenance work more predictable and targeted, reducing unexpected downtime, lowering maintenance costs, and improving production efficiency; The deep learning model can handle complex nonlinear relationships and is suitable for different types of fault pattern recognition. It can maintain good performance even under complex operating conditions such as long-term load, friction and vibration. As more operating status data is accumulated, the preset guide rail fault assessment model can self-optimize through continuous learning and training, improving its diagnostic accuracy and reliability over time. The entire diagnostic process from data collection to the generation of final fault diagnosis results is automated, which greatly reduces the need for manual intervention, improves the system's response speed and work efficiency, and also reduces the risk of human error; The detailed fault diagnosis results provided by the method can be directly used to guide operation and maintenance personnel to make correct maintenance decisions, ensuring the stable operation and efficient production of mechanical equipment; through accurate fault diagnosis, enterprises can avoid unnecessary comprehensive inspections and excessive maintenance, saving human and material resources, while improving the availability and service life of equipment; In summary, the above-mentioned linear guide fault diagnosis method based on deep learning overcomes the shortcomings of traditional fault diagnosis methods, can improve the stability and production efficiency of equipment, and reduce maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of the present invention; Figure 2 is a flow chart of a method for constructing a guide rail fault assessment model; Figure 3 This is a block diagram of a linear guide fault diagnosis system based on deep learning; Figure 4 are sample configuration diagrams under four different operating conditions. DETAILED DESCRIPTION

[0017] In the description of this application, those skilled in the art should know that this application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, this application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, this application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0018] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0019] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0020] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0021] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0022] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0023] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0024] The present application is described below in conjunction with the drawings in the present application.

[0025] Embodiment 1: Figure 1 to Figure 2 As shown, the linear guide rail fault diagnosis method based on deep learning of the present invention specifically includes the following steps: S1, obtaining first operating status data of a target linear guide rail and second operating status data of at least one associated linear guide rail; The associated linear guide is a linear guide of the same type as the target linear guide and adjacent in position; the first operating status data and the second operating status data have the same data content, and both include at least one of temperature data, acceleration data, vibration data and noise data; The method for collecting operation status data includes: A variety of sensors are installed on the linear guide rail and adjacent linear guide rails to monitor their operating status in real time; the sensors include temperature sensors, acceleration sensors, vibration sensors and noise sensors; Temperature sensors are used to monitor temperature changes in the linear guide and the surrounding environment. Abnormal temperature rise is a sign of wear and insufficient lubrication. Accelerometers can detect sudden movements or shocks caused by friction or mechanical problems; Vibration sensors are used to record the vibration patterns generated by equipment during operation, which helps to identify mechanical defects or imbalances; Noise sensors can capture abnormal sounds caused by faults, such as abnormal friction or impact between metals; Set the data collection frequency to monitor the changes in the long-term operating status of the linear guide; According to the data collection frequency, the sensor installed on the linear guide rail collects data in real time to ensure the timeliness and accuracy of the data; Preprocess the collected sensor data to ensure data quality and usability; this includes data cleaning, data format conversion, and data normalization steps; The pre-processed sensor data is stored in a preset database for subsequent analysis and processing; in order to ensure the security and reliability of the data, data backup and recovery measures are taken for the stored data through the database.

[0026] In this step, by acquiring the first operating status data and the second operating status data of the target linear guide and at least one of its associated linear guides, comprehensive monitoring of the linear guide system is achieved, which can fully reflect the operating status of the linear guide and help to discover potential problems in a timely manner; due to the introduction of associated linear guides, this step can locate the problem more accurately; when an abnormal situation occurs in the target linear guide, by comparing its data with the data of the associated linear guide, it can be more quickly determined whether it is a local problem or a systemic problem, so as to take targeted maintenance measures; by installing multiple sensors on the linear guide and the adjacent linear guides, and setting the data acquisition frequency, real-time monitoring of the operating status of the linear guide is achieved. Monitoring; helps to detect abnormal situations in time and issue early warnings to avoid further expansion of faults and ensure stable operation of equipment; pre-processes the collected sensor data to ensure the quality and availability of the data; at the same time, stores the pre-processed data in a preset database to provide reliable data support for subsequent analysis and processing; through data backup and recovery measures, it further ensures the security and reliability of the data; through the implementation of this step, potential problems of linear guides can be discovered and handled in time, thereby avoiding extended downtime and increased maintenance costs caused by faults; at the same time, through real-time monitoring and data analysis, it can also optimize maintenance plans, improve maintenance efficiency, and reduce overall maintenance costs.

[0027] S2. Inputting the first operating state data into a preset guide rail fault assessment model to obtain a first fault assessment result; The first fault assessment result includes a ball wear fault probability value, a guide rail corrosion fault probability value, a slider deformation fault probability value, and a slider end cover falling off fault probability value; The ball wear failure probability value is used to assess the possibility of excessive wear of the ball; The guide rail corrosion failure probability value is used to determine the probability of whether there is corrosion on the guide rail surface; The slider deformation failure probability value is used to detect whether the slider has abnormal deformation; The slider end cover falling off failure probability value is used to predict whether the slider end cover has the risk of loosening or falling off; The method for constructing the guide rail fault assessment model comprises: Collect historical linear guide operation status data, including temperature data, acceleration data, vibration data, and noise data; Preprocess the collected data, including data cleaning, data format conversion and data normalization steps, to ensure data quality and consistency; Perform feature extraction on the pre-processed historical linear guide operation status data to extract features that can reflect the linear guide fault; A deep learning model is selected as the basic architecture of the guide rail fault assessment model; the deep learning model includes a recurrent neural network and a convolutional neural network; Design the input layer, hidden layer, and output layer of the model; the input layer is used to receive preprocessed data, the hidden layer is used for feature extraction and pattern recognition, and the output layer is used to output fault assessment results; in the hidden layer, design multiple convolutional layers, pooling layers, fully connected layers and other structures to extract deeper features; The preprocessed historical linear guide running status data is divided into a training set, a validation set and a test set; the training set is used for model training, the validation set is used for model verification and adjustment, and the test set is used to evaluate the performance of the model; Use the training set to train the model, and adjust the model parameters through the back propagation algorithm to minimize the error between the model's prediction results and the actual fault type; during the training process, use the optimization algorithm to accelerate the training process and improve the convergence of the model; optimize the performance of the model by adjusting the model's hyperparameters; Use the validation set data to validate the model, and adjust the model parameters and structure based on the validation results; repeat the training and optimization process until the model achieves optimal performance on the validation set; Use the test set data to evaluate the model and calculate the model's accuracy, recall rate, F1 score and other indicators; by comparing the evaluation results of different models, select the model with the best performance as the final guide rail fault assessment model; Deploy the trained model to the production environment, receive real-time data streams from sensors, and perform online fault assessment.

[0028] In this step, by constructing a guide rail fault assessment model based on deep learning, we can make full use of the historical linear guide rail operating status data. The comprehensive processing and analysis of information enables the model to more accurately predict fault types such as ball wear, guide rail corrosion, slider deformation, and slider end cover shedding, thereby improving the accuracy of fault prediction; the fault probability value output by the model provides clear fault warning information for operation and maintenance personnel; it helps operation and maintenance personnel to take measures in advance to prevent the occurrence of faults, or to discover and deal with faults in the early stages, thereby avoiding equipment downtime and production losses caused by the expansion of faults; online fault assessment based on the model enables operation and maintenance personnel to understand the operating status of the linear guide rail in real time, The frequency and intensity of manual inspections are reduced. At the same time, the model can automatically identify the type of fault, reducing the time for operation and maintenance personnel to determine the cause of the fault and improving the operation and maintenance efficiency. In addition, by preventing the occurrence of faults, the maintenance costs and production interruption costs caused by faults are reduced. Through the introduction of deep learning models, intelligent monitoring and fault prediction of the operating status of linear guides are realized, providing strong support for the construction of an intelligent operation and maintenance management system. This step realizes intelligent monitoring and fault prediction of the operating status of linear guides by constructing a guide fault assessment model based on deep learning, improves the accuracy of fault prediction, operation and maintenance efficiency, and intelligence level, and reduces operation and maintenance costs and production interruption risks.

[0029] S3, inputting at least one set of the second operating state data into the guide rail fault assessment model respectively to obtain at least one set of second fault assessment results; the second fault assessment results include ball wear failure probability value, guide rail corrosion failure probability value, slider deformation failure probability value and slider end cover falling failure probability value; Preprocessing the second operating state data, including data cleaning, data format conversion and data normalization; The pre-processed second operating state data is input into a preset guide rail fault assessment model; the model can automatically extract features from the data and make probability predictions on the fault type; The model outputs at least one set of second fault assessment results, each set of results corresponding to an associated linear guide rail; the results include ball wear failure probability values, guide rail corrosion failure probability values, slider deformation failure probability values, and slider end cover detachment failure probability values; the probability value reflects the possibility of the associated linear guide rail having the corresponding fault type; The output fault assessment results are recorded and stored in the database for subsequent analysis and comparison.

[0030] In this step, by collecting and preprocessing the second operating status data of at least one group of associated linear guides, the operating conditions of these guides can be fully obtained; the quality and consistency of the data are ensured through preprocessing steps such as data cleaning, format conversion and normalization, providing a reliable basis for subsequent analysis; the preprocessed data is input into a preset guide rail fault assessment model, which is built based on deep learning and can automatically extract key features from complex data and perform probability prediction of fault types, greatly improving the efficiency and accuracy of fault diagnosis; the second fault assessment result output by the model intuitively reflects the possibility of the corresponding fault type occurring in the associated linear guide, providing clear fault warning information for operation and maintenance personnel; the operation and maintenance personnel can compare the fault assessment results of the target linear guide and the associated linear guide, analyze the propagation and impact of the same-source fault, and thus more accurately determine the true source and extent of the fault; based on detailed fault probability assessment and same-source fault impact analysis, the operation and maintenance personnel can formulate more scientific and reasonable maintenance plans and fault handling strategies; this helps to reduce equipment downtime caused by faults, improve production efficiency and equipment utilization, and reduce operation and maintenance costs.

[0031] S4, considering the influence of the same-origin fault, correcting the first fault assessment result according to at least one set of the second fault assessment results to obtain a target linear guide rail fault diagnosis result; Analyze the second fault assessment results of the associated linear guides, and identify whether there are similar fault modes by comparing the fault probability value distribution and fault type proportion of each associated guide. If multiple associated guides show high probability values ​​for the same or similar fault types, it indicates the influence of the same fault. Correcting a first fault assessment result of the target linear guide rail according to the identified homologous fault mode; If it is determined that there is a homologous fault, and the fault probability value of the associated guide rail is higher than the corresponding fault probability value of the target guide rail, then consider appropriately increasing the fault probability value of the target guide rail to reflect the additional risk brought by the homologous fault; On the contrary, if the failure probability value of the associated rail is low, and this low probability value is caused by the same source factors, then the actual failure condition of the target rail should be carefully evaluated; During the calibration process, different weights are assigned to the fault assessment results of different associated rails; the weights are assigned based on factors such as the physical distance between the associated rail and the target rail, the similarity of the operating environment, and the difference in working conditions; By using the weighted average method, the fault probability value and corresponding weight of each associated guide rail are combined to correct the fault assessment result of the target guide rail; The mathematical calculation formula for correcting the first fault assessment result according to at least one set of the second fault assessment results is: Among them, P crepresents the corrected failure probability value; P t represents the original target rail failure probability value; α is an adjustment coefficient between 0 and 1, which is used to balance the proportion of the original evaluation and the impact of the same source fault; n represents the number of associated rails; w i represents the weight of the i-th associated rail; P ai represents the failure probability value of the i-th associated rail; The target linear guide fault diagnosis results include: Corrected fault probability value: For each fault type, the corrected fault probability value gives the probability of the target linear guide failing on that fault type; this probability value has taken into account the impact of homologous faults and is therefore more accurate than the original first fault assessment result; Fault type confirmation: Based on the corrected fault probability value, the type of fault that is about to occur in the target linear guide can be determined; this helps operation and maintenance managers to quickly locate the fault point and take corresponding maintenance measures; Fault severity assessment: Combined with historical data and experience, it can make a preliminary assessment of the severity of the fault; it helps operation and maintenance managers understand the specific impact of the fault on equipment operation and production efficiency; Analysis of the impact of homologous faults: During the calibration process, by comparing the fault probability values ​​of the target linear guide and the associated linear guide, the impact of homologous faults on the target guide can be analyzed; this helps operation and maintenance managers understand the propagation characteristics of faults and the mutual impact between adjacent equipment, providing a basis for formulating preventive measures; Maintenance recommendations: Based on the fault diagnosis results, operation and maintenance managers can develop targeted maintenance plans and recommendations.

[0032] In this step, by comprehensively correlating the fault assessment results of the linear guide rail, the influence of the same-source fault on the target guide rail fault probability value can be identified and corrected, thereby more accurately reflecting the actual fault situation of the target guide rail; this helps to improve the accuracy and reliability of fault diagnosis; after considering the influence of the same-source fault, potential faults can be predicted and identified earlier, providing operation and maintenance managers with sufficient time to carry out maintenance and repair work, avoiding the expansion of faults or causing equipment downtime; accurate fault diagnosis results provide operation and maintenance managers with a scientific decision-making basis, which helps to optimize operation and maintenance strategies and resource allocation, reduce operation and maintenance costs, and improve production efficiency; by timely correcting and predicting faults, this step helps to improve the stability and reliability of the entire linear guide system and reduce production interruptions and losses caused by faults; the correction formula and weight distribution method in this step have certain flexibility and scalability, and can be adjusted and optimized according to the actual industrial scenario and the characteristics of the linear guide system to meet different fault diagnosis needs; this step can significantly improve the accuracy of fault diagnosis, prediction ability and operation and maintenance management efficiency, and provide a strong guarantee for the stable operation and production efficiency of the linear guide system.

[0033] Embodiment 2: Figure 3 As shown, the linear guide rail fault diagnosis system based on deep learning of the present invention specifically includes the following modules: A data acquisition module, for acquiring first operating status data of a target linear guide rail and second operating status data of at least one associated linear guide rail; A guide rail fault assessment module, inputting the first operating state data into a preset guide rail fault assessment model to obtain a first fault assessment result; Associating the guide rail fault assessment module, inputting at least one set of the second operating state data into the guide rail fault assessment model respectively, and obtaining at least one set of second fault assessment results; The fault diagnosis module considers the influence of the same-source faults and corrects the first fault assessment result according to at least one set of the second fault assessment results to obtain a target linear guide fault diagnosis result.

[0034] The system not only focuses on the operating status of the target linear guide, but also simultaneously collects and analyzes the data of the linear guides associated with the target linear guide, which helps to capture the impact of homologous faults and improve the accuracy of fault diagnosis; By introducing the impact analysis of homologous faults, the fault diagnosis module can more accurately determine the source and extent of the fault, avoiding misdiagnosis or missed diagnosis due to ignoring the correlation between devices; accurate fault diagnosis results can help operation and maintenance personnel plan maintenance activities in advance, reduce unexpected downtime, reduce production losses, and optimize the allocation of maintenance resources; The deep learning model can handle nonlinear and complex input-output relationships and is suitable for different types of fault pattern recognition. As more operating status data is collected and analyzed, the guide rail fault assessment model can optimize itself through continuous learning and training, thereby improving the accuracy and reliability of fault diagnosis over time. The entire process from data collection to the generation of fault diagnosis results is automated, reducing the need for manual intervention, improving the system's response speed and work efficiency, while reducing the risk of human error; providing intuitive and detailed fault diagnosis information for operation and maintenance managers, helping them make more informed maintenance decisions and ensure stable operation and efficient production of mechanical equipment; By integrating deep learning technology and understanding the interactions between linear guides, the system provides a more intelligent, accurate and efficient fault diagnosis solution, which helps to improve equipment stability and production efficiency and reduce maintenance costs.

[0035] Embodiment 3: Figure 4 As shown, taking the acquisition of acceleration data of the target linear guide as an example, the steps for diagnosing the fault of the target linear guide include: The sampling frequency of the acceleration data is set, and three sets of data are collected at different speeds and loads for eight seconds respectively; in order to simulate the actual operating environment of the linear guide and the state when a fault occurs, in this embodiment, each fault type is tested under four different working conditions; Determine the number of sampling points for each sensor and put the data collected by the sensor into two channels; the vibration data collected by the acceleration sensor often contains a lot of noise, and direct use will reduce the fault recognition rate of the model, so the collected data needs to be preprocessed; decomposing the signal into modes of different frequency bands can effectively separate the noise and useful information in the signal; when decomposing the vibration data, it is necessary to determine the number of modes and penalty parameters. If the number of modes is set too large, it will lead to over-decomposition and modal aliasing; if it is set too small, it will cause under-decomposition and loss of feature information; The training set, validation set, and test set are divided according to the fault category, and the converted data are normalized; the converted data are divided into data sets according to the fault category, with a division ratio of 8:1:1; the training set is used for iterative training of the model, the test set is used to evaluate the change of model accuracy during the training process, and the validation set is used to evaluate the generalization effect of the model; The data in the training set is input into the model for training, and the model parameters are determined by the validation set and the test set; the model includes a multi-channel extraction module, a feature screening module and a fault classification module; The number of modes and penalty parameters are optimized, and the original data is processed. Since the obtained modal functions contain different amounts of information and noise, they need to be selected; when the modal function contains more fault feature information, the stronger the sparsity of the signal, the smaller the envelope entropy, and vice versa, the larger the envelope entropy. Therefore, the minimum envelope entropy is used as the standard for screening the modal function, and the three screened modal components are input into the model for training; the convolution layer extracts the feature information, the pooling layer reduces the size of the feature map and reduces the number of calculated parameters, and the residual connection can alleviate the gradient vanishing and explosion problems during gradient back propagation, and can speed up the training speed and improve the model performance; finally, the feature information is flattened and input through the fully connected layer, and the fault classification label is output; The trained model is used to carry out fault diagnosis tests under different working conditions.

[0036] The various variations and specific embodiments of the deep learning-based linear guide fault diagnosis method in the aforementioned embodiment 1 are also applicable to the deep learning-based linear guide fault diagnosis system in this embodiment. Through the aforementioned detailed description of the deep learning-based linear guide fault diagnosis method, those skilled in the art can clearly understand the implementation method of the deep learning-based linear guide fault diagnosis system in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0037] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0038] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A linear guide rail fault diagnosis method based on deep learning, characterized in that: The method comprises: Acquire first operating status data of a target linear guide rail and second operating status data of at least one associated linear guide rail; Inputting the first operating state data into a preset guide rail fault assessment model to obtain a first fault assessment result; Inputting at least one set of the second operating status data into the guide rail fault assessment model to obtain at least one set of second fault assessment results; Taking into account the influence of homologous faults, the first fault assessment result is corrected according to at least one set of the second fault assessment results to obtain a target linear guide rail fault diagnosis result.

2. The linear guide rail fault diagnosis method based on deep learning according to claim 1, characterized in that: The associated linear guide is a linear guide that is of the same type as the target linear guide and is located adjacent to the target linear guide.

3. The linear guide rail fault diagnosis method based on deep learning according to claim 1, characterized in that: The method for collecting operation status data includes: Installing a variety of sensors on the linear guide rail and adjacent linear guide rails to monitor their operating status in real time; the sensors include temperature sensors, acceleration sensors, vibration sensors and noise sensors; Set the frequency of data collection; According to the data collection frequency, the data is collected in real time through the sensor installed on the linear guide; Preprocess the collected sensor data; The preprocessed sensor data is stored in a preset database.

4. The linear guide rail fault diagnosis method based on deep learning according to claim 1, characterized in that: The first fault assessment result includes a ball wear fault probability value, a guide rail corrosion fault probability value, a slider deformation fault probability value, and a slider end cover falling off fault probability value.

5. The linear guide rail fault diagnosis method based on deep learning according to claim 1, characterized in that: The method for constructing the guide rail fault assessment model comprises: Collect historical linear guide operation status data and pre-process the collected data; A deep learning model is selected as the basic architecture of the guide rail fault assessment model; the deep learning model includes a recurrent neural network and a convolutional neural network; The preprocessed historical linear guide running status data is divided into a training set, a validation set and a test set; Use the training set to train the model and adjust the model parameters; Use the validation set data to validate the model and adjust the model parameters and structure based on the validation results; Use the test set data to evaluate the model; Deploy the trained model to the production environment, receive real-time data streams from sensors, and perform online fault assessment.

6. The linear guide rail fault diagnosis method based on deep learning according to claim 1, characterized in that: The mathematical calculation formula for correcting the first fault assessment result according to at least one set of the second fault assessment results is: Among them, P c represents the corrected failure probability value; P t represents the original target rail failure probability value; α is an adjustment coefficient between 0 and 1, which is used to balance the proportion of the original evaluation and the impact of the same source fault; n represents the number of associated rails; w i represents the weight of the i-th associated rail; P ai Represents the failure probability value of the i-th associated rail.

7. The linear guide rail fault diagnosis method based on deep learning according to claim 1, characterized in that: The target linear guide rail fault diagnosis result includes a corrected fault probability value, fault type confirmation, fault severity assessment, homologous fault impact analysis and maintenance recommendations.

8. A linear guide fault diagnosis system based on deep learning, characterized in that: The system comprises: A data acquisition module, for acquiring first operating status data of a target linear guide rail and second operating status data of at least one associated linear guide rail; A guide rail fault assessment module, inputting the first operating state data into a preset guide rail fault assessment model to obtain a first fault assessment result; Associating the guide rail fault assessment module, inputting at least one set of the second operating state data into the guide rail fault assessment model respectively, and obtaining at least one set of second fault assessment results; The fault diagnosis module considers the influence of the same-source faults and corrects the first fault assessment result according to at least one set of the second fault assessment results to obtain a target linear guide fault diagnosis result.

9. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 7 are implemented.

Images