Double-spindle operation detection method, system and equipment of vertical machining center and medium
By preprocessing and model comparison and analysis of the operating status data of the dual-spindle machining center, a fault risk prediction report is generated, and the problem of untimely fault monitoring in traditional methods is solved, real-time fault detection and equipment optimization are achieved, and processing quality is improved and efficiency.
Patent Information
- Application Number
- CN202411416432.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-11
- Publication Date
- 2024-11-29
AI Technical Summary
Traditional dual-spindle machining centers cannot realize real-time fault monitoring, and the hidden fault recognition capabilities are limited, resulting in untimely fault discovery, which affects processing quality and efficiency.
By obtaining the operating status data of the dual spindles for pre-processing, and inputting it into the pre-trained fault detection model for comparison and analysis, a fault risk prediction report is generated, and operating parameters are adjusted to optimize the equipment status.
Real-time fault detection and prediction are realized, extending the service life of the equipment, improving production efficiency and processing quality.
Smart Images

Figure CN119036191A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of motor control, and in particular to a dual-spindle operation detection method, system, equipment and medium for a vertical machining center. Background Art
[0002] At present, in the field of vertical machining centers, the dual-spindle design can significantly improve machining efficiency, but this is accompanied by an increase in the complexity of the spindle's operating status, which puts higher requirements on the detection and prevention of spindle faults. Traditional dual-spindle machining centers usually rely on operators to regularly check and judge by experience to identify spindle faults, or use simple sensors for preliminary monitoring.
[0003] The above-mentioned existing technical solutions have the following defects: the traditional method cannot achieve real-time monitoring, and has limited ability to identify hidden faults, resulting in untimely fault discovery, affecting processing quality and efficiency, so there is room for improvement. Summary of the invention
[0004] In order to improve the machining quality of a machining center, the present application provides a dual-spindle operation detection method, system, equipment and medium for a vertical machining center.
[0005] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A dual-spindle operation detection method for a vertical machining center, the dual-spindle operation detection method for the vertical machining center comprising: Acquiring running status data of the dual spindles, and preprocessing the running status data of the dual spindles to obtain preprocessed running status data; Inputting the preprocessed operating status data into a pre-trained fault detection model for comparison and analysis to obtain a comparison and analysis result; According to the comparison and analysis results, the operating status of the dual spindles is evaluated in real time to obtain an evaluation result, and a fault risk prediction report is generated according to the evaluation result; According to the fault risk prediction report, parameter adjustment data of the dual spindles are generated, and the operating parameters of the dual spindles are adjusted according to the parameter adjustment data.
[0006] By adopting the above technical solution, by obtaining the operating status data of the dual spindles and preprocessing the operating status data of the dual spindles, noise can be removed and data quality can be optimized, thereby improving the accuracy of fault detection; by inputting the preprocessed operating status data into a pre-trained fault detection model for comparison and analysis, potential faults can be discovered quickly and accurately, thereby reducing the risk of faults; by conducting real-time evaluation of the operating status of the dual spindles based on the comparison and analysis results, the health status of the equipment can be continuously monitored, thereby generating a fault risk prediction report in a timely manner and improving the foresight of equipment management; by generating parameter adjustment data based on the fault risk prediction report and adjusting the operating parameters of the dual spindles, the equipment parameters can be optimized according to the actual operating conditions, thereby extending the service life of the equipment and improving production efficiency.
[0007] In a preferred example, the present application may be further configured as follows: the acquisition of the running status data of the dual spindles and preprocessing of the running status data of the spindles to obtain the preprocessed running status data include: Acquiring the operating status data of the dual spindles through a sensor group, wherein the sensor group includes a temperature sensor, a vibration sensor, a pressure sensor and a rotation speed sensor; Performing multi-stage filtering and denoising processing and data normalization processing on the operating status data of the dual spindles to obtain preliminarily processed data; Key characteristic parameters are extracted from the preliminarily processed data to obtain the pre-processed operating status data, wherein the key characteristic parameters include temperature change rate, vibration spectrum characteristics, pressure fluctuation range and rotation speed change rate.
[0008] By adopting the above technical solution, a group of sensors are used to collect the operating status data of the dual spindles. The sensor group includes temperature sensors, vibration sensors, pressure sensors and speed sensors. These sensors provide comprehensive data, which is helpful to understand the real-time operating status of the dual spindles; a multi-level filtering algorithm is applied to the collected raw data. The filtering process helps to remove random noise in the data, making subsequent data analysis more accurate, and the filtered processed data is normalized to scale it to a small, specified range. Normalization ensures the comparability between different sensor data and facilitates subsequent feature extraction and model training; by extracting key feature parameters from the initially processed data, these parameters can represent the operating status and potential problems of the dual spindles, providing rich and refined information for subsequent fault detection and prediction.
[0009] In a preferred example, the present application may be further configured as follows: before inputting the preprocessed operation status data into a pre-trained fault detection model for comparison and analysis to obtain a comparison and analysis result, the dual-spindle operation detection method of the vertical machining center further includes: Acquire historical spindle operation data and fault sample data, and preprocess and annotate the historical spindle operation data and the fault sample data to obtain a training set; A fault detection model is constructed based on a long short-term memory network, the fault detection model is optimized by regularization technology to obtain an optimized fault detection model, and the optimized fault detection model is offline trained using the training set to obtain the pre-trained fault detection model.
[0010] By adopting the above technical solution, by acquiring historical spindle operation data and fault sample data and performing labeling processing, a high-quality training set can be constructed, thereby improving the learning ability of the fault detection model; by using the fault detection model constructed by the long short-term memory network, the model's processing ability for time series data can be improved, thereby more accurately predicting equipment failures; by optimizing the model through regularization technology, overfitting can be avoided and the generalization ability of the model under different working conditions can be improved.
[0011] In a preferred example, the present application can be further configured as follows: the pre-processed running status data is input into a pre-trained fault detection model for comparison and analysis, and the comparison and analysis results obtained include: Comparing the preprocessed operating status data with corresponding data in the pre-trained fault detection model to obtain a data comparison result; When the data comparison result is that the data is deviated, the preprocessed running status data and the corresponding data in the pre-trained fault detection model are subjected to deviation calculation to identify abnormal data; Classifying the abnormal data to obtain a fault type and a corresponding severity, and generating a fault possibility score according to the fault type and the corresponding severity; The fault type, the severity corresponding to the fault type and the fault possibility score are integrated to obtain the comparison and analysis result.
[0012] By adopting the above technical solution, by comparing and analyzing the pre-processed operating status data with the pre-trained fault detection model, abnormal data in the operating status can be quickly identified, thereby improving the accuracy of fault detection; by classifying the abnormal data and generating a fault possibility score, the severity of the fault can be better evaluated, thereby providing a reliable basis for decision-making; by integrating the fault type, severity and fault possibility score into the comparison analysis result, a comprehensive fault analysis report can be generated, thereby improving the accuracy and comprehensiveness of equipment management.
[0013] In a preferred example, the present application may be further configured as follows: performing a real-time evaluation on the operating status of the dual spindles according to the comparison and analysis results to obtain an evaluation result, and generating a fault risk prediction report according to the evaluation result includes: Based on the comparison and analysis results, the operating status of the dual spindles is evaluated in real time to obtain the evaluation results, which include the change trend data of the current temperature, vibration, pressure and rotation speed of the dual spindles; The assessment result is analyzed to obtain the risk level of the dual-spindle failure, and based on the assessment result and the risk level, the failure risk prediction report is generated, wherein the failure risk prediction report includes the risk level, occurrence time and confidence score of each type of potential failure.
[0014] By adopting the above technical solutions, the temperature, vibration, pressure and speed change trends of the dual spindles can be evaluated in real time, so as to continuously monitor the operating status of the equipment and promptly discover potential risks; by generating a fault risk prediction report, a scientific basis can be provided for equipment maintenance, thereby optimizing maintenance plans and reducing downtime.
[0015] In a preferred example, the present application can be further configured as follows: the dual-spindle operation detection method of the vertical machining center also includes: When a dual-spindle fault or potential fault is detected, a multi-level alarm message is triggered, wherein the multi-level alarm message includes an audible and visual alarm and a text message notification; Analyze the mode and trend of the dual-spindle failure based on the historical spindle operation data, and generate a failure statistics report; Maintenance suggestion information is generated according to the fault statistics report, and the fault statistics report and maintenance suggestion information are transmitted to the user end.
[0016] By adopting the above technical solution, by triggering multi-level alarm messages when a fault or potential fault is detected, relevant personnel can be notified in time to handle equipment abnormalities, thereby reducing losses caused by the fault; by analyzing historical spindle operation data to generate fault statistical reports, the long-term operation status of the equipment can be better understood, thereby providing data support for equipment maintenance and improvement; by generating maintenance recommendation information based on the fault statistical report and transmitting it to the user end, the equipment management process can be optimized, thereby improving equipment reliability and production efficiency.
[0017] The second object of the invention is achieved by the following technical solutions: A dual-spindle operation detection system for a vertical machining center, the dual-spindle operation detection system for the vertical machining center comprising: An operation data acquisition module is used to acquire the operation status data of the dual spindles and preprocess the operation status data of the dual spindles to obtain the preprocessed operation status data; A model analysis module is used to input the pre-processed operating status data into a pre-trained fault detection model for comparison and analysis to obtain a comparison and analysis result; An evaluation module, used to evaluate the operating status of the dual spindles in real time according to the comparison and analysis results, obtain evaluation results, and generate a fault risk prediction report according to the evaluation results; An adjustment module is used to generate parameter adjustment data of the dual spindles according to the fault risk prediction report, and adjust the operating parameters of the dual spindles according to the parameter adjustment data.
[0018] By adopting the above technical solution, by obtaining the operating status data of the dual spindles and preprocessing the operating status data of the dual spindles, noise can be removed and data quality can be optimized, thereby improving the accuracy of fault detection; by inputting the preprocessed operating status data into a pre-trained fault detection model for comparison and analysis, potential faults can be discovered quickly and accurately, thereby reducing the risk of faults; by conducting real-time evaluation of the operating status of the dual spindles based on the comparison and analysis results, the health status of the equipment can be continuously monitored, thereby generating a fault risk prediction report in a timely manner and improving the foresight of equipment management; by generating parameter adjustment data based on the fault risk prediction report and adjusting the operating parameters of the dual spindles, the equipment parameters can be optimized according to the actual operating conditions, thereby extending the service life of the equipment and improving production efficiency. The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the dual-spindle operation detection method of the vertical machining center are implemented.
[0019] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the dual-spindle operation detection method of the vertical machining center are implemented.
[0020] In summary, the present application includes at least one of the following beneficial technical effects: 1. By obtaining the running status data of the dual spindles and preprocessing the running status data of the dual spindles, noise can be removed and data quality can be optimized, thereby improving the accuracy of fault detection; by inputting the preprocessed running status data into the pre-trained fault detection model for comparison and analysis, potential faults can be discovered quickly and accurately, thereby reducing the risk of faults; 2. By conducting real-time evaluation of the operating status of the dual spindles based on the comparison and analysis results, the health status of the equipment can be continuously monitored, so that a fault risk prediction report can be generated in a timely manner to improve the foresight of equipment management; by generating parameter adjustment data based on the fault risk prediction report and adjusting the operating parameters of the dual spindles, the equipment parameters can be optimized according to the actual operating conditions, thereby extending the service life of the equipment and improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] Figure 1 is a flow chart of a dual-spindle operation detection method for a vertical machining center in one embodiment of the present application; Figure 2 This is a flowchart for implementing step S10 in a dual-spindle operation detection method for a vertical machining center in one embodiment of the present application; Figure 3 This is a flowchart for implementing step S20 in a dual-spindle operation detection method for a vertical machining center in one embodiment of the present application; Figure 4 This is a flowchart for implementing step S30 in a dual-spindle operation detection method for a vertical machining center in one embodiment of the present application; Figure 5 This is a flowchart for implementing step S40 in a dual-spindle operation detection method for a vertical machining center in one embodiment of the present application; Figure 6 This is a flowchart for implementing step S50 in a dual-spindle operation detection method for a vertical machining center in one embodiment of the present application; Figure 7 This is a principle block diagram of a dual-spindle operation detection system for a vertical machining center in one embodiment of the present application; Figure 8 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION
[0022] The present application is further described in detail below in conjunction with the accompanying drawings.
[0023] In one embodiment, if Figure 1 As shown, the present application discloses a dual-spindle operation detection method for a vertical machining center, which specifically includes the following steps: S10: Acquire the running status data of the dual spindles, and pre-process the running status data of the dual spindles to obtain the pre-processed running status data.
[0024] Specifically, the operating status data of the dual spindles are collected by sensors installed on them. These data include parameters such as temperature, vibration, load, and speed, providing real-time information for analyzing the operating status of the dual spindles. The collected raw data are processed, such as denoising, normalization, and filtering, to improve the data quality, and finally the preprocessed operating status data is obtained. The preprocessed data is more accurate and reliable, providing high-quality input for subsequent analysis and model training.
[0025] S20: Input the preprocessed operating status data into a pre-trained fault detection model for comparison and analysis to obtain a comparison and analysis result.
[0026] Specifically, the preprocessed data is input into a fault detection model based on machine learning for comparison and analysis. For example, a convolutional neural network (CNN) and a support vector machine (SVM) are used to build a fault detection model. The model compares the input data with known fault modes to determine whether a fault exists. The final model outputs the comparison and analysis results. The obtained comparison and analysis results provide a judgment on whether the operating status of the dual spindles is normal.
[0027] S30: According to the comparison and analysis results, the operating status of the dual spindles is evaluated in real time to obtain an evaluation result, and a fault risk prediction report is generated according to the evaluation result.
[0028] Specifically, first, various sensors are used to collect data from the dual-spindle system in real time. These data may include vibration, temperature, sound, current, voltage and other multi-source data. According to the analysis results of the model, the system evaluates the operating status of the dual spindles in real time. According to the monitored real-time operating data of the dual spindles, the health status of the dual spindles is evaluated, such as performance degradation evaluation, reliability evaluation, etc., and finally the evaluation results are obtained. The system generates a fault risk prediction report based on the evaluation results. The report may include fault type, risk level, recommended maintenance measures, etc., which is helpful for equipment maintenance and management.
[0029] S40: Generate parameter adjustment data of the dual spindles according to the fault risk prediction report, and adjust the operating parameters of the dual spindles according to the parameter adjustment data.
[0030] Specifically, the system generates parameter adjustment data based on the fault risk prediction report. These data provide guidance on how to adjust the operating parameters of the dual spindles to avoid faults. Based on the parameter adjustment data, the system automatically adjusts the operating parameters of the dual spindles, such as temperature, vibration, load, speed and other parameters. The adjusted dual spindle parameters help reduce the failure risk of the machining center and improve production efficiency and safety.
[0031] By adopting the above technical solution, by obtaining the operating status data of the dual spindles and preprocessing the operating status data of the dual spindles, noise can be removed and data quality can be optimized, thereby improving the accuracy of fault detection; by inputting the preprocessed operating status data into a pre-trained fault detection model for comparison and analysis, potential faults can be discovered quickly and accurately, thereby reducing the risk of faults; by conducting real-time evaluation of the operating status of the dual spindles based on the comparison and analysis results, the health status of the equipment can be continuously monitored, thereby generating a fault risk prediction report in a timely manner and improving the foresight of equipment management; by generating parameter adjustment data based on the fault risk prediction report and adjusting the operating parameters of the dual spindles, the equipment parameters can be optimized according to the actual operating conditions, thereby extending the service life of the equipment and improving production efficiency.
[0032] In one embodiment, if Figure 2 As shown, in step S10, the running status data of the dual spindles is obtained, and the running status data of the dual spindles is preprocessed to obtain the preprocessed running status data, which specifically includes: S11: Acquire the operating status data of the dual spindles through a sensor group, where the sensor group includes a temperature sensor, a vibration sensor, a pressure sensor, and a rotation speed sensor.
[0033] Specifically, a group of sensors are used to collect the operating status data of the dual spindles. The temperature of the dual spindles is measured by a temperature sensor to monitor whether there is overheating or abnormal temperature changes. The vibration of the dual spindles is detected by a vibration sensor. The working pressure of the dual spindles is monitored by a pressure sensor to ensure that they operate within a safe and effective pressure range. The rotation speed of the dual spindles is recorded by a speed sensor to evaluate their operating efficiency and performance, providing comprehensive data for subsequent analysis and calculation, which helps to understand the real-time operating status of the dual spindles.
[0034] S12: Perform multi-level filtering and denoising processing and data normalization processing on the operating status data of the dual spindles to obtain preliminary processed data.
[0035] Specifically, a multi-stage filtering algorithm, such as a low-pass filter, a high-pass filter, or a band-pass filter, is applied to the collected raw sensor data to remove noise and interference. The processed data is normalized to scale it to a small, specified range, such as 0 to 1 or -1 to 1. The filtering process helps to remove random noise in the data, making subsequent data analysis more accurate. Normalization ensures the comparability between different sensor data, facilitating subsequent feature extraction and model training.
[0036] S13: extracting key characteristic parameters from the preliminarily processed data to obtain pre-processed operating status data, wherein the key characteristic parameters include temperature change rate, vibration spectrum characteristics, pressure fluctuation range and rotation speed change rate.
[0037] Specifically, key characteristic parameters are extracted from the preliminarily processed data through statistical methods. These parameters can represent the operating status and potential problems of the dual spindles. The key characteristic parameters include temperature change rate, vibration spectrum characteristics, pressure fluctuation range and speed change rate. The extracted key characteristic parameters are integrated into a preprocessed operating status data set, which provides rich and refined information for subsequent fault detection and prediction.
[0038] In one embodiment, if Figure 3 As shown, before step S20, that is, before the preprocessed operation status data is input into the pre-trained fault detection model for comparison and analysis to obtain the comparison and analysis results, the dual-spindle operation detection method of the vertical machining center also includes: S201: Obtain historical spindle operation data and fault sample data, and preprocess and label the historical spindle operation data and fault sample data to obtain a training set.
[0039] Specifically, historical data of the spindle during normal operation and when failures occur are collected. These data may include parameters measured by various sensors, such as temperature, vibration, sound, pressure, etc. The collected data are preprocessed by cleaning, formatting, standardization and other preprocessing operations, and labeled. The labeling includes classifying the data as "normal" or "fault", as well as the type and severity of the fault. The preprocessed and labeled data are organized into a training set, which will be used to train the machine learning model.
[0040] S202: Based on the fault detection model constructed by the long short-term memory network, the fault detection model is optimized by regularization technology to obtain an optimized fault detection model, and the optimized fault detection model is offline trained using a training set to obtain a pre-trained fault detection model.
[0041] Specifically, first, we need to build a neural network model based on LSTM. The LSTM model consists of an input layer, one or more LSTM layers, and an output layer. The LSTM layer contains a forget gate, an input gate, a cell state, and an output gate. These structures help the model capture long-term dependencies in time series data. In order to optimize the fault detection model, regularization techniques can be used to prevent the model from overfitting. Common regularization techniques include L1 regularization, L2 regularization, and Dropout. L1 regularization promotes the sparsity of model weights by adding the L1 norm of weights to the loss function; L2 regularization limits the growth of model weights by adding the L2 norm of weights; Dropout randomly "discards" a part of neurons during training to reduce the complex co-adaptation relationship between them. The optimized fault detection model is trained offline using the training set, the training data is input into the model, and the weights of the model are updated through the back propagation algorithm. After the training is completed, the model is evaluated using the validation set or the test set to ensure that it can accurately detect faults. Once the model training is completed and the evaluation results are satisfactory, the model can be saved for future use in fault detection, and a pre-trained fault detection model is finally obtained.
[0042] In one embodiment, if Figure 4 As shown, in step S20, the pre-processed operating status data is input into a pre-trained fault detection model for comparison and analysis to obtain a comparison and analysis result, which specifically includes: S21: Compare the preprocessed operating status data with the corresponding data in the pre-trained fault detection model to obtain a data comparison result.
[0043] Specifically, the preprocessed operating status data is compared with the data in the pre-trained fault detection model, such as temperature, vibration, etc. Through comparison, it can be preliminarily determined whether the current operating status is consistent with the normal status or known fault status recorded in the model, and the data comparison result is finally output.
[0044] S22: When the data comparison result shows that the data is deviated, the preprocessed operating status data is subjected to deviation calculation with the corresponding data in the pre-trained fault detection model to identify the abnormal data.
[0045] Specifically, if the comparison results show that there is a deviation in the data, that is, the current operating state does not match the normal state or fault state in the model, a detailed deviation calculation is performed on the deviated data to determine the specific differences in the data and identify abnormal data. Through the deviation calculation, it is possible to identify which parameters are abnormal, providing a basis for subsequent fault type and severity analysis.
[0046] S23: Classify the abnormal data to obtain the fault type and the corresponding severity, and generate a fault possibility score according to the fault type and the corresponding severity.
[0047] Specifically, the identified abnormal data is classified to determine the possible fault types, such as bearing failure, motor overheating, etc. This is done by analyzing the characteristic strength of the abnormal data, the development speed of the fault mode, or the similarity with other known serious faults, and evaluating the severity of the fault. Based on the fault type and severity, a fault probability score is generated, which reflects the risk of failure, such as a score from 1 to 10.
[0048] S24: Integrate the data of the fault type, the severity corresponding to the fault type, and the fault possibility score to obtain a comparison analysis result.
[0049] Specifically, the fault type, severity and fault probability score are integrated to form the final comparative analysis result, which provides a comprehensive fault diagnosis report, including the nature, severity and possible consequences of the fault, providing a basis for maintenance and repair decisions.
[0050] In one embodiment, if Figure 5 As shown, in step S30, the operating status of the dual spindles is evaluated in real time according to the comparison and analysis results to obtain the evaluation results, and a fault risk prediction report is generated according to the evaluation results, specifically including: S31: Based on the comparison and analysis results, the operating status of the dual spindles is evaluated in real time to obtain evaluation results, which include the change trend data of the current temperature, vibration, pressure and rotation speed of the dual spindles.
[0051] Specifically, the current operating status of the dual spindles is evaluated in real time using the comparative analysis results obtained from the fault detection model. The evaluation provides a performance snapshot of the dual spindles at a specific moment, including change trend data for key parameters such as temperature, vibration, pressure, and speed. It lists the current performance indicators and change trends of the dual spindles in detail, which helps to understand whether the equipment is operating normally or whether there are signs of performance degradation.
[0052] S32: Analyze the assessment results to obtain the risk level of the dual-spindle failure, and generate a failure risk prediction report based on the assessment results and the risk level. The failure risk prediction report includes the risk level, occurrence time and confidence score of each potential failure.
[0053] Specifically, the real-time assessment results are deeply analyzed to determine the failure risk level of the dual spindles. According to the analysis results, the failure risk of the dual spindles is assigned a level, such as low, medium, and high risk. Based on the assessment results and risk level, a detailed failure risk prediction report is generated. The report provides detailed information about potential failures, including listing all identified potential failures and assigning a risk level, possible occurrence time, and confidence score to each failure. This information helps the maintenance team develop preventive maintenance plans, reduce unexpected downtime, and optimize the allocation of maintenance resources.
[0054] In one embodiment, if Figure 6 As shown, the dual-spindle operation detection method of the vertical machining center also includes: S50: When a dual-spindle fault or potential fault is detected, a multi-level alarm message is triggered, and the multi-level alarm message includes an audible and visual alarm and a text message notification.
[0055] Specifically, when the system detects a fault or potential fault in the dual spindles, it automatically triggers an alarm message to immediately attract the operator's attention through sound and visual signals, such as flashing lights, as well as sending text messages to responsible personnel, ensuring that the fault information can be quickly conveyed to relevant personnel so that timely measures can be taken.
[0056] S60: Analyze the patterns and trends of dual-spindle failures based on historical spindle operation data and generate a failure statistics report.
[0057] Specifically, the system collects and analyzes the historical operating data of the dual spindles to identify the patterns and trends of fault occurrence. By analyzing the historical data, the regularity of faults can be discovered, such as frequent faults at specific times and under specific conditions. Based on the results of the historical data analysis, the system generates a detailed fault statistics report. The fault statistics report provides the maintenance team with statistical data on the frequency, type and severity of faults, which helps to understand the operating status of the equipment.
[0058] S70: Generate maintenance suggestion information according to the fault statistics report, and transmit the fault statistics report and the maintenance suggestion information to the user end.
[0059] Specifically, based on the fault statistics report, the system generates maintenance recommendation information, which may include preventive maintenance measures, inspection cycle adjustment or component replacement, and sends the fault statistics report and maintenance recommendation information to the user end through appropriate communication methods, such as computers and mobile devices. After receiving this information, the user end can conduct more in-depth analysis, formulate maintenance plans, or share information with the maintenance team to coordinate maintenance activities.
[0060] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0061] In one embodiment, a dual-spindle operation detection system for a vertical machining center is provided, and the dual-spindle operation detection system for the vertical machining center corresponds one-to-one to the dual-spindle operation detection method for the vertical machining center in the above embodiment. Figure 7 As shown, the dual-spindle operation detection system of the vertical machining center includes an operation data acquisition module, a model analysis module, an evaluation module and an adjustment module. The detailed description of each functional module is as follows: The operation data acquisition module is used to acquire the operation status data of the dual spindles and pre-process the operation status data of the dual spindles to obtain the pre-processed operation status data; The model analysis module is used to input the pre-processed operating status data into the pre-trained fault detection model for comparison and analysis to obtain the comparison and analysis results; An evaluation module is used to evaluate the operating status of the dual spindles in real time according to the comparison and analysis results, obtain the evaluation results, and generate a fault risk prediction report according to the evaluation results; The adjustment module is used to generate parameter adjustment data of the dual spindles according to the fault risk prediction report, and adjust the operating parameters of the dual spindles according to the parameter adjustment data.
[0062] Optionally, the dual-spindle operation detection system of the vertical machining center also includes: An alarm module is used to trigger a multi-level alarm message when a dual-spindle fault or potential fault is detected. The multi-level alarm message includes an audible and visual alarm and a text message notification; Generate a report module to analyze the patterns and trends of dual-spindle failures based on historical spindle operation data and generate failure statistics reports; The maintenance suggestion generation module is used to generate maintenance suggestion information according to the fault statistics report, and transmit the fault statistics report and maintenance suggestion information to the user end.
[0063] A historical data acquisition module is used to acquire historical spindle operation data and fault sample data, and pre-process and annotate the historical spindle operation data and fault sample data to obtain a training set; The model training module is used for the fault detection model built based on the long short-term memory network. The fault detection model is optimized by regularization technology to obtain the optimized fault detection model, and the optimized fault detection model is trained offline using the training set to obtain a pre-trained fault detection model.
[0064] Optionally, the module for obtaining operation data includes: The sensor detection submodule is used to obtain the running status data of the dual spindles through a sensor group, the sensor group includes a temperature sensor, a vibration sensor, a pressure sensor and a speed sensor; The denoising submodule is used to perform multi-level filtering denoising and data normalization on the running status data of the dual spindles to obtain the preliminarily processed data; The feature extraction submodule is used to extract key feature parameters from the preliminarily processed data to obtain the preprocessed operating status data. The key feature parameters include temperature change rate, vibration spectrum characteristics, pressure fluctuation range and speed change rate.
[0065] Optionally, the model analysis module includes: The comparison submodule is used to compare the preprocessed operating status data with the corresponding data in the pre-trained fault detection model to obtain the data comparison result; The deviation calculation submodule is used to calculate the deviation between the pre-processed running status data and the corresponding data in the pre-trained fault detection model when the data comparison result shows that the data is biased, and identify the abnormal data; The scoring submodule is used to classify abnormal data, obtain the fault type and the corresponding severity, and generate a fault probability score based on the fault type and the corresponding severity; The integration submodule is used to integrate the fault type, the severity corresponding to the fault type and the fault possibility score to obtain the comparison and analysis results.
[0066] Optional assessment modules include: The state evaluation submodule is used to evaluate the operating state of the dual spindles in real time based on the comparison and analysis results to obtain evaluation results, which include the change trend data of the current temperature, vibration, pressure and speed of the dual spindles; The report generation submodule is used to analyze the evaluation results, obtain the risk level of dual-spindle failures, and generate a fault risk prediction report based on the evaluation results and risk level. The fault risk prediction report includes the risk level, occurrence time and confidence score of various potential failures.
[0067] For the specific definition of the dual-spindle operation detection system of the vertical machining center, please refer to the definition of the dual-spindle operation detection method of the vertical machining center mentioned above, which will not be repeated here. Each module in the dual-spindle operation detection system of the vertical machining center can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0068] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a dual-spindle operation detection method for a vertical machining center is implemented.
[0069] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented: Acquire the running status data of the dual spindles, and pre-process the running status data of the dual spindles to obtain the pre-processed running status data; The pre-processed operating status data is input into a pre-trained fault detection model for comparison and analysis to obtain the comparison and analysis results; According to the comparison and analysis results, the operating status of the dual spindles is evaluated in real time to obtain the evaluation results, and a fault risk prediction report is generated based on the evaluation results; According to the fault risk prediction report, parameter adjustment data of the dual spindles are generated, and the operating parameters of the dual spindles are adjusted according to the parameter adjustment data.
[0070] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Acquire the running status data of the dual spindles, and pre-process the running status data of the dual spindles to obtain the pre-processed running status data; The pre-processed operating status data is input into a pre-trained fault detection model for comparison and analysis to obtain the comparison and analysis results; According to the comparison and analysis results, the operating status of the dual spindles is evaluated in real time to obtain the evaluation results, and a fault risk prediction report is generated based on the evaluation results; According to the fault risk prediction report, parameter adjustment data of the dual spindles are generated, and the operating parameters of the dual spindles are adjusted according to the parameter adjustment data.
[0071] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0072] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.
[0073] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A dual-spindle operation detection method for a vertical machining center, characterized in that: The dual-spindle operation detection method of the vertical machining center comprises: Acquiring running status data of the dual spindles, and preprocessing the running status data of the dual spindles to obtain preprocessed running status data; Inputting the preprocessed operating status data into a pre-trained fault detection model for comparison and analysis to obtain a comparison and analysis result; According to the comparison and analysis results, the operating status of the dual spindles is evaluated in real time to obtain an evaluation result, and a fault risk prediction report is generated according to the evaluation result; According to the fault risk prediction report, parameter adjustment data of the dual spindles are generated, and the operating parameters of the dual spindles are adjusted according to the parameter adjustment data.
2. The dual-spindle operation detection method of a vertical machining center according to claim 1 is characterized in that: The step of acquiring the running status data of the dual spindles and preprocessing the running status data of the spindles to obtain the preprocessed running status data includes: Acquiring the operating status data of the dual spindles through a sensor group, wherein the sensor group includes a temperature sensor, a vibration sensor, a pressure sensor and a rotation speed sensor; Performing multi-stage filtering and denoising processing and data normalization processing on the operating status data of the dual spindles to obtain preliminarily processed data; Key characteristic parameters are extracted from the preliminarily processed data to obtain the pre-processed operating status data, wherein the key characteristic parameters include temperature change rate, vibration spectrum characteristics, pressure fluctuation range and rotation speed change rate.
3. The dual-spindle operation detection method of a vertical machining center according to claim 1 is characterized in that: Before inputting the preprocessed operation status data into a pre-trained fault detection model for comparison and analysis to obtain a comparison and analysis result, the dual-spindle operation detection method for a vertical machining center further includes: Acquire historical spindle operation data and fault sample data, and preprocess and annotate the historical spindle operation data and the fault sample data to obtain a training set; A fault detection model is constructed based on a long short-term memory network, the fault detection model is optimized by regularization technology to obtain an optimized fault detection model, and the optimized fault detection model is offline trained using the training set to obtain the pre-trained fault detection model.
4. The dual-spindle operation detection method of a vertical machining center according to claim 1, characterized in that: The pre-processed running status data is input into a pre-trained fault detection model for comparison and analysis, and the comparison and analysis results obtained include: Comparing the preprocessed operating status data with corresponding data in the pre-trained fault detection model to obtain a data comparison result; When the data comparison result is that the data is deviated, the preprocessed running status data and the corresponding data in the pre-trained fault detection model are subjected to deviation calculation to identify abnormal data; Classifying the abnormal data to obtain a fault type and a corresponding severity, and generating a fault possibility score according to the fault type and the corresponding severity; The fault type, the severity corresponding to the fault type and the fault possibility score are integrated to obtain the comparison and analysis result.
5. The dual-spindle operation detection method of a vertical machining center according to claim 1, characterized in that: According to the comparison and analysis results, the operating status of the dual spindles is evaluated in real time to obtain an evaluation result, and a fault risk prediction report is generated according to the evaluation result, including: Based on the comparison and analysis results, the operating status of the dual spindles is evaluated in real time to obtain the evaluation results, which include the change trend data of the current temperature, vibration, pressure and rotation speed of the dual spindles; The assessment result is analyzed to obtain the risk level of the dual-spindle failure, and based on the assessment result and the risk level, the failure risk prediction report is generated, wherein the failure risk prediction report includes the risk level, occurrence time and confidence score of each type of potential failure.
6. The dual-spindle operation detection method of a vertical machining center according to claim 1, characterized in that: The dual-spindle operation detection method of the vertical machining center also includes: When a dual-spindle fault or potential fault is detected, a multi-level alarm message is triggered, wherein the multi-level alarm message includes an audible and visual alarm and a text message notification; Analyze the mode and trend of the dual-spindle failure based on the historical spindle operation data, and generate a failure statistics report; Maintenance suggestion information is generated according to the fault statistics report, and the fault statistics report and maintenance suggestion information are transmitted to the user end.
7. A dual-spindle operation detection system for a vertical machining center, characterized in that: The dual-spindle operation detection system of the vertical machining center includes: An operation data acquisition module is used to acquire the operation status data of the dual spindles and preprocess the operation status data of the dual spindles to obtain the preprocessed operation status data; A model analysis module is used to input the pre-processed operating status data into a pre-trained fault detection model for comparison and analysis to obtain a comparison and analysis result; An evaluation module, used to evaluate the operating status of the dual spindles in real time according to the comparison and analysis results, obtain evaluation results, and generate a fault risk prediction report according to the evaluation results; An adjustment module is used to generate parameter adjustment data of the dual spindles according to the fault risk prediction report, and adjust the operating parameters of the dual spindles according to the parameter adjustment data.
8. The dual-spindle operation detection system for a vertical machining center according to claim 7, characterized in that: An alarm module, used for triggering a multi-level alarm message when a dual-spindle fault or potential fault is detected, wherein the multi-level alarm message includes an audible and visual alarm and a text message notification; A report generation module is used to analyze the mode and trend of the dual-spindle failure based on the historical spindle operation data and generate a failure statistics report; The maintenance suggestion generating module is used to generate maintenance suggestion information according to the fault statistical report, and transmit the fault statistical report and maintenance suggestion information to the user end.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the dual-spindle operation detection method for a vertical machining center as described in any one of claims 1 to 6 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the dual-spindle operation detection method for a vertical machining center as claimed in any one of claims 1 to 6 are implemented.
Citation Information
Patent Citations
Fatigue factor recessive anomaly detection and fault diagnosis method based on LSTM
CN111353482A
Numerical control machine tool control system fault diagnosis method based on Petri network
CN117111589A
CAE-based numerical control machine tool processing dynamic performance monitoring method and system
CN117555287A
Method and system for monitoring health state of transformer of power station
CN117630758A
Numerical control machine tool control method and system based on Internet of Things
CN118377268A
Cited By
A plastic part strength detection method and system
CN119742016A
