Method and system for predicting reliability life of low-power frequency conversion system

Abstract

The invention discloses a reliability life prediction method and system of a low-power frequency conversion system. The method relates to the technical field of life prediction data processing, and comprises the following steps: collecting and processing reliability life prediction data of a numerical control machine tool; analyzing numerical control machine tool reliability life prediction data; and comprehensively analyzing, optimizing and adjusting. According to the method, the numerical control machine tool reliability life prediction data is collected and processed, the numerical control machine tool reliability life prediction data is analyzed, the numerical control machine tool life prediction data quality reliability evaluation index and the numerical control machine tool life prediction signal quality evaluation index are obtained, and the numerical control machine tool life prediction accuracy is comprehensively analyzed, optimized and adjusted. The accuracy of the reliability life prediction method of the low-power frequency conversion is improved, and the problem that the accuracy of the reliability life prediction method of the low-power frequency conversion is insufficient in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of life prediction data processing, and in particular to a reliability life prediction method and system for a low-power frequency conversion system. Background Art

[0002] As a key equipment in the field of industrial automation control, low-power frequency conversion systems are widely used in various types of production machinery, such as fans, water pumps, conveyor belts, etc. The working status of these devices is directly related to the stability and efficiency of the entire production line. Therefore, improving the reliability and life prediction ability of the frequency conversion system is an inevitable choice to meet the development needs of industrial automation.

[0003] The existing reliability life prediction system of small power variable frequency system realizes the fields of condition monitoring, maintenance decision and spare parts ordering through the life prediction method based on degradation data; through the data-driven reliability assessment and life prediction method based on covariates, it is suitable for the situation where it is difficult to obtain the physical model of the failure mechanism of complex and high reliability equipment. By using the system degradation data and system operating environment monitoring data obtained by automatic monitoring technology and sensor technology, the covariate-based method can be applied to the reliability assessment model, which is divided into fixed covariate model, time-varying covariate model and random covariate model.

[0004] For example, the invention patent application with publication number: CN119047402A discloses a method, system, storage medium and product for predicting the life of an inverter IGBT module, including: S1: obtaining the rated power of the inverter, and presetting the carrier frequency, maximum frequency, acceleration time, deceleration time and load type of the inverter; S2: importing the temperature difference life curve diagram, IGBT module power consumption table and Tcyc data corresponding to the IGBT module according to the rated power; S3: updating the Tcyc data according to the load type; S4: comparing the Tcyc data with the preset early warning cycle to determine whether to execute the early warning program; S5: calculating the temperature change value △Th of the radiator; S6: calculating the real-time power consumption Pi2 using a linear equation; S7: calculating the wafer junction temperature Tj of the IGBT module; S8: querying the temperature difference life curve diagram according to the total change temperature difference △Tall to determine whether to send an early warning message; thereby achieving a more intuitive response to the temperature difference change of the wafer junction temperature in applications with rapid load changes.

[0005] For example, the IGBT power module life prediction method and device disclosed in the invention patent announcement with the announcement number CN116579189B includes: in the IGBT power module life prediction method, the life Nf of the IGBT power module to be tested is calculated according to Tj(max), Tj(min), and △Rths. Wherein, Tj(max) and Tj(min) correspond to the maximum junction temperature of the IGBT chip and the minimum junction temperature of the IGBT chip in the IGBT module to be tested within a power cycle period, respectively; thermal resistance deviation △Rths=(Rths,v-Rths) / Rths; Rths,v is the thermal resistance of the chip solder layer of the IGBT power module to be tested, and Rths is the thermal resistance of the chip solder layer of the ideal IGBT power module, and the chip solder layer of the ideal IGBT power module is a chip solder layer without initial voids.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems: When this method is applied in CNC machine tool scenarios, there is a problem of insufficient accuracy in the reliability life prediction assessment of small-power frequency conversion systems. The high-frequency generator in the CNC machine tool will generate strong electromagnetic waves, resulting in inaccurate collected data. At the same time, temperature changes will accelerate the aging of capacitors and resistors, causing capacitor and resistor component parameter drift. There is a problem of insufficient accuracy in the reliability life prediction method of small-power frequency conversion. Summary of the invention

[0007] The embodiments of the present application solve the problem of insufficient accuracy of the reliability life prediction method of small power frequency conversion in the prior art by providing a reliability life prediction method and system for a small power frequency conversion system, thereby improving the accuracy of the reliability life prediction method of small power frequency conversion.

[0008] The embodiment of the present application provides a reliability life prediction method for a low-power frequency conversion system, comprising the following steps: collecting and processing reliability life prediction data of CNC machine tools; analyzing the reliability life prediction data of CNC machine tools to obtain a quality reliability evaluation index of the CNC machine tool life prediction data and a quality evaluation index of the CNC machine tool life prediction signal; comprehensively analyzing to obtain an accuracy evaluation index of the CNC machine tool life prediction data; comparing and analyzing the quality reliability evaluation index of the CNC machine tool life prediction data with a first threshold of the quality reliability evaluation index of the CNC machine tool life prediction data, and optimizing the quality reliability method of the CNC machine tool life prediction data; comparing and analyzing the quality evaluation index of the CNC machine tool life prediction signal with a second threshold of the quality evaluation index of the CNC machine tool life prediction signal, and optimizing and adjusting the quality method of the CNC machine tool life prediction signal; comparing and analyzing the accuracy evaluation index of the CNC machine tool life prediction data with a comprehensive threshold of the accuracy evaluation index of the CNC machine tool life prediction data, and optimizing and adjusting the accuracy method of the CNC machine tool life prediction.

[0009] Furthermore, the specific steps of collecting and processing the reliability life prediction data of CNC machine tools are: collecting the original data of the reliability life prediction of CNC machine tools through sensor equipment; cleaning and denoising the original data of the reliability life prediction of CNC machine tools to obtain the reliability life prediction data of CNC machine tools, and the reliability life prediction data of CNC machine tools includes the quality reliability data of the life prediction data of CNC machine tools and the quality data of the life prediction signal of CNC machine tools.

[0010] Furthermore, the specific steps of obtaining the CNC machine tool life prediction data quality reliability evaluation index are: obtaining the electromagnetic wave intensity of the preset CNC machine tool life prediction data quality reliability time detection point through the electromagnetic interference detector; obtaining the vibration amplitude of the preset CNC machine tool life prediction data quality reliability time detection point through the vibration sensor; obtaining the maximum temperature of the CNC machine tool in the preset CNC machine tool life prediction data quality reliability time detection section through the thermocouple; obtaining the minimum temperature of the CNC machine tool in the preset CNC machine tool life prediction data quality reliability time detection section through the thermocouple; when the machine tool is not working, measuring the output value of the sensor as the reference zero point, obtaining the CNC machine tool life prediction data drift rate of the preset CNC machine tool life prediction data quality reliability time detection point through the high-precision sensor, and taking the difference between the reference zero point and the data drift rate as the zero point drift rate; and obtaining the life prediction data of the CNC machine tool at the preset CNC machine tool life prediction data quality reliability time detection point through the dynamic signal analysis. The phase peak of the CNC machine life prediction signal of the preset CNC machine life prediction data quality reliability time detection section is obtained by the analyzer; the phase trough of the CNC machine life prediction signal of the preset CNC machine life prediction data quality reliability time detection section is obtained by the dynamic signal analyzer; the CNC machine life prediction data acquisition frequency of the preset CNC machine life prediction data quality reliability time detection point is obtained by the data acquisition card; the CNC machine life prediction data quality reliability data includes electromagnetic wave intensity, vibration amplitude, maximum temperature of the CNC machine tool, minimum temperature of the CNC machine tool, zero drift rate of CNC machine life prediction data, phase peak of the CNC machine tool life prediction signal, phase trough of the CNC machine tool life prediction signal and CNC machine life prediction data acquisition frequency; the CNC machine life prediction data quality reliability evaluation index is obtained according to the CNC machine life prediction data quality reliability data analysis.

[0011] Furthermore, the specific steps of obtaining the CNC machine tool life prediction signal quality evaluation index are: obtaining the electromagnetic wave intensity of the preset CNC machine tool life prediction signal quality time detection point through an electromagnetic field intensity meter; obtaining the vibration amplitude of the preset CNC machine tool life prediction signal quality time detection point through a vibration sensor; obtaining the maximum temperature of the CNC machine tool in the preset CNC machine tool life prediction signal quality time detection section through an infrared temperature sensor; obtaining the minimum temperature of the CNC machine tool in the preset CNC machine tool life prediction signal quality time detection section through an infrared temperature sensor; obtaining the phase peak of the CNC machine tool life prediction signal in the preset CNC machine tool life prediction signal quality time detection section through a dynamic signal analyzer; obtaining the phase trough of the CNC machine tool life prediction signal in the preset CNC machine tool life prediction signal quality time detection section through a dynamic signal analyzer; obtaining the CNC machine tool life prediction signal phase peak in the preset CNC machine tool life prediction signal quality time detection section through a dynamic signal analyzer; obtaining the CNC machine tool life prediction signal phase peak in the preset CNC machine tool life prediction signal quality time detection section through a power meter The life prediction signal power of the CNC machine tool is obtained by a power meter; the life prediction output signal power of the CNC machine tool at a preset CNC machine tool life prediction signal quality time detection point is obtained by a power meter; the background noise power at a preset CNC machine tool life prediction signal quality time detection point is obtained by a spectrum analyzer; the life prediction data transmission response time of the CNC machine tool in a preset CNC machine tool life prediction signal quality time detection section is obtained by a network analyzer; the life prediction signal quality data of the CNC machine tool includes electromagnetic wave intensity, vibration amplitude, maximum temperature of the CNC machine tool, minimum temperature of the CNC machine tool, phase peak of the CNC machine tool life prediction signal, phase trough of the CNC machine tool life prediction signal, life prediction input signal power of the CNC machine tool, life prediction output signal power of the CNC machine tool, background noise power and life prediction data transmission response time of the CNC machine tool; the life prediction signal quality evaluation index of the CNC machine tool is obtained according to the analysis of the life prediction signal quality data of the CNC machine tool.

[0012] Furthermore, the specific steps of the comprehensive analysis to obtain the CNC machine tool life prediction data accuracy evaluation index are: obtaining the CNC machine tool life prediction data drift of the preset CNC machine tool life prediction accuracy time detection segment through the edge computing device; obtaining the CNC machine tool life prediction data accuracy evaluation index through comprehensive analysis of the CNC machine tool life prediction data quality reliability evaluation index, the CNC machine tool life prediction signal quality evaluation index and the CNC machine tool life prediction data drift.

[0013] Furthermore, the specific steps of the method for optimizing the quality reliability of CNC machine tool life prediction data are as follows: if the quality reliability evaluation index of the CNC machine tool life prediction data is greater than or equal to the first threshold value of the quality reliability evaluation index of the CNC machine tool life prediction data, there is no need to optimize the quality reliability of the CNC machine tool life prediction data; if the quality reliability evaluation index of the CNC machine tool life prediction data is lower than the first threshold value of the quality reliability evaluation index of the CNC machine tool life prediction data, then the difference between the quality reliability evaluation index of the CNC machine tool life prediction data and the first threshold value of the quality reliability evaluation index of the CNC machine tool life prediction data is used to match the corresponding adjustment plan in the reliability life prediction database.

[0014] Furthermore, the specific steps of the method for optimizing and adjusting the quality of the CNC machine tool life prediction signal are as follows: if the CNC machine tool life prediction signal quality evaluation index is lower than or equal to the second threshold value of the CNC machine tool life prediction signal quality evaluation index, there is no need to optimize and adjust the CNC machine tool life prediction signal quality; if the CNC machine tool life prediction signal quality evaluation index is greater than the second threshold value of the CNC machine tool life prediction signal quality evaluation index, then the difference between the CNC machine tool life prediction signal quality evaluation index and the second threshold value of the CNC machine tool life prediction signal quality evaluation index is used to match the corresponding adjustment plan in the reliability life prediction database.

[0015] Furthermore, the specific steps of the method for optimizing and adjusting the accuracy of CNC machine tool life prediction are: extracting the comprehensive threshold of the CNC machine tool life prediction data accuracy assessment index in the reliability life prediction database, and comparing the CNC machine tool life prediction data accuracy assessment index with the comprehensive threshold of the CNC machine tool life prediction data accuracy assessment index; if the CNC machine tool life prediction data accuracy assessment index is greater than or equal to the comprehensive threshold of the CNC machine tool life prediction data accuracy assessment index, there is no need to optimize and adjust the CNC machine tool life prediction accuracy.

[0016] Furthermore, the method for optimizing and adjusting the accuracy of CNC machine tool life prediction also includes: if the CNC machine tool life prediction data accuracy assessment index is lower than the CNC machine tool life prediction data accuracy assessment index comprehensive threshold, then matching the corresponding adjustment plan in the reliability life prediction database through the difference between the CNC machine tool life prediction data accuracy assessment index and the CNC machine tool life prediction data accuracy assessment index comprehensive threshold.

[0017] The embodiment of the present application provides a reliability life prediction system for a low-power frequency conversion system, including a module for collecting CNC machine tool reliability life prediction data, a CNC machine tool reliability life prediction data analysis module, a comprehensive analysis module, and a module for optimizing and adjusting the accuracy of CNC machine tool life prediction: a module for collecting CNC machine tool reliability life prediction data: used to collect and process CNC machine tool reliability life prediction data; a CNC machine tool reliability life prediction data analysis module: used to analyze CNC machine tool reliability life prediction data, obtain CNC machine tool life prediction data quality reliability evaluation index and obtain CNC machine tool life prediction signal quality evaluation index; a comprehensive analysis module: used to comprehensively analyze and obtain CNC machine tool life prediction accuracy Life prediction data accuracy evaluation index; Optimize and adjust the CNC machine tool life prediction accuracy module: used to compare and analyze the CNC machine tool life prediction data quality reliability evaluation index with the first threshold of the CNC machine tool life prediction data quality reliability evaluation index, and optimize the CNC machine tool life prediction data quality reliability method; compare and analyze the CNC machine tool life prediction signal quality evaluation index with the second threshold of the CNC machine tool life prediction signal quality evaluation index, and optimize the CNC machine tool life prediction signal quality method; compare and analyze the CNC machine tool life prediction data accuracy evaluation index with the CNC machine tool life prediction data accuracy evaluation index comprehensive threshold, and optimize the CNC machine tool life prediction accuracy method.

[0018] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By collecting and processing the reliability life prediction data of CNC machine tools, analyzing the reliability life prediction data of CNC machine tools, obtaining the reliability evaluation index of the life prediction data quality of CNC machine tools and the quality evaluation index of the life prediction signal of CNC machine tools, comprehensively analyzing and optimizing the accuracy method of CNC machine tool life prediction, the accuracy of the reliability life prediction method of small-power frequency conversion is improved, and the problem of insufficient accuracy of the reliability life prediction method of small-power frequency conversion in the prior art is solved.

[0019] 2. By analyzing the reliability life prediction data of CNC machine tools, we can obtain the CNC machine tool life prediction data quality reliability evaluation index and the CNC machine tool life prediction signal quality evaluation index. By predicting potential failures, we can take measures in advance to prevent accidents, determine which machine tools need more attention and maintenance, and reasonably allocate maintenance resources and budgets.

[0020] 3. Through comprehensive analysis and optimization of the CNC machine tool life prediction accuracy method, the remaining service life of the CNC machine tool can be predicted more accurately, the prediction error can be reduced, potential faults can be identified more effectively, and maintenance can be performed in time, thereby reducing the machine tool failure rate and extending the service life of the machine tool. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1A flow chart of a reliability life prediction method for a low-power frequency conversion system provided in an embodiment of the present application; Figure 2 A schematic diagram of an index function for evaluating the accuracy of CNC machine tool life prediction data provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a reliability life prediction system for a low-power frequency conversion system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The embodiments of the present application solve the problem of insufficient accuracy of the reliability life prediction method of small power frequency conversion in the prior art by providing a reliability life prediction method and system for a small power frequency conversion system. The reliability life prediction data of CNC machine tools are collected and processed, and the reliability life prediction data of CNC machine tools are analyzed to obtain a reliability evaluation index of the life prediction data quality of CNC machine tools and a quality evaluation index of the life prediction signal of CNC machine tools. The accuracy method of CNC machine tool life prediction is comprehensively analyzed and optimized, thereby improving the accuracy of the reliability life prediction method of small power frequency conversion.

[0023] The technical solution in the embodiment of the present application is to solve the above-mentioned problem that the reliability life prediction method of low-power frequency conversion is not accurate enough. The overall idea is as follows: By collecting and processing the reliability life prediction data of CNC machine tools, analyzing the reliability life prediction data of CNC machine tools, obtaining the reliability evaluation index of the CNC machine tool life prediction data quality and the CNC machine tool life prediction signal quality evaluation index, comprehensively analyzing and optimizing the CNC machine tool life prediction accuracy method, the accuracy of the reliability life prediction method of small power frequency conversion is improved.

[0024] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0025] like Figure 1As shown, it is a flow chart of the reliability life prediction method of the low-power frequency conversion system provided in the embodiment of the present application. The method is applied to the reliability life prediction system of the low-power frequency conversion system. The method includes the following steps: collecting and processing the reliability life prediction data of the CNC machine tool; analyzing the reliability life prediction data of the CNC machine tool to obtain the quality reliability evaluation index of the CNC machine tool life prediction data and the quality evaluation index of the CNC machine tool life prediction signal; comprehensively analyzing to obtain the accuracy evaluation index of the CNC machine tool life prediction data; comparing and analyzing the quality reliability evaluation index of the CNC machine tool life prediction data with the first threshold of the quality reliability evaluation index of the CNC machine tool life prediction data, and optimizing the quality reliability method of the CNC machine tool life prediction data; comparing and analyzing the quality evaluation index of the CNC machine tool life prediction signal with the second threshold of the quality evaluation index of the CNC machine tool life prediction signal, and optimizing and adjusting the quality method of the CNC machine tool life prediction signal; comparing and analyzing the accuracy evaluation index of the CNC machine tool life prediction data with the comprehensive threshold of the accuracy evaluation index of the CNC machine tool life prediction data, and optimizing and adjusting the accuracy method of the CNC machine tool life prediction.

[0026] In this embodiment, various types of high-precision sensors, such as accelerometers, temperature sensors, pressure sensors, etc., are installed to collect real-time data of the CNC machine tool during operation. The CNC machine tool operation data includes collecting historical maintenance, repair and component replacement records of the machine tool from maintenance logs and repair reports, recording the operating conditions of the machine tool, etc., removing obvious erroneous data and irrelevant information in the real-time data during the operation of the CNC machine tool, filling or deleting missing data points, removing outliers, identifying and processing outliers in the data, converting the data into a unified format and scale for easy analysis, and extracting features that are helpful in predicting machine tool performance degradation from the collected data, such as average vibration amplitude, temperature change rate, motor load change, etc.

[0027] Furthermore, the specific steps of collecting and processing the reliability life prediction data of CNC machine tools are as follows: collecting the original data of the reliability life prediction of CNC machine tools through sensor equipment; cleaning and denoising the original data of the reliability life prediction of CNC machine tools to obtain the reliability life prediction data of CNC machine tools, wherein the reliability life prediction data of CNC machine tools includes the quality reliability data of the life prediction data of CNC machine tools and the quality data of the life prediction signal of CNC machine tools.

[0028] Furthermore, the specific steps for obtaining the CNC machine tool life prediction data quality reliability evaluation index are as follows: obtaining the electromagnetic wave intensity of the preset CNC machine tool life prediction data quality reliability time detection point through an electromagnetic interference detector; obtaining the vibration amplitude of the preset CNC machine tool life prediction data quality reliability time detection point through a vibration sensor; obtaining the maximum temperature of the CNC machine tool in the preset CNC machine tool life prediction data quality reliability time detection section through a thermocouple; obtaining the minimum temperature of the CNC machine tool in the preset CNC machine tool life prediction data quality reliability time detection section through a thermocouple; when the machine tool is not working, measuring the output value of the sensor as the reference zero point, obtaining the CNC machine tool life prediction data drift rate of the preset CNC machine tool life prediction data quality reliability time detection point through a high-precision sensor, and taking the difference between the reference zero point and the data drift rate as the zero point drift rate; through dynamic signal analysis The instrument obtains the phase peak of the CNC machine tool life prediction signal in the preset CNC machine tool life prediction data quality reliability time detection section; the dynamic signal analyzer obtains the phase trough of the CNC machine tool life prediction signal in the preset CNC machine tool life prediction data quality reliability time detection section; the data acquisition card obtains the CNC machine tool life prediction data acquisition frequency at the preset CNC machine tool life prediction data quality reliability time detection point; the CNC machine tool life prediction data quality reliability data includes electromagnetic wave intensity, vibration amplitude, CNC machine tool maximum temperature, CNC machine tool minimum temperature, CNC machine tool life prediction data zero point drift rate, CNC machine tool life prediction signal phase peak, CNC machine tool life prediction signal phase trough and CNC machine tool life prediction data acquisition frequency; according to the CNC machine tool life prediction data quality reliability data analysis, the CNC machine tool life prediction data quality reliability evaluation index is obtained.

[0029] In this embodiment, the specific method for analyzing and obtaining the reliability evaluation index of the CNC machine tool life prediction data quality is as follows: ; ; ; ; ; ; ; The preset CNC machine tool life prediction data quality reliability time detection points are numbered in sequence. Indicates The number of the CNC machine tool life prediction data quality reliability time detection point under the CNC machine tool life prediction data quality reliability detection section, , Indicates the total number of time inspection points for the quality reliability of CNC machine tool life prediction data.

[0030] Divide the preset CNC machine tool life prediction data quality reliability time into CNC machine tool life prediction data quality reliability detection segments of the same length, Indicates the number of the reliability detection section of the CNC machine tool life prediction data quality. , Indicates the total number of quality reliability detection segments of CNC machine tool life prediction data.

[0031] Indicates The reliability evaluation index of CNC machine tool life prediction data quality at the reliability time detection point of CNC machine tool life prediction data quality.

[0032] Indicates The electromagnetic wave intensity correction coefficient at the reliability time detection point of the CNC machine tool life prediction data quality.

[0033] Indicates The vibration amplitude correction coefficient at the time detection point of the quality reliability of CNC machine tool life prediction data.

[0034] Indicates The temperature fluctuation coefficient of the CNC machine tool life prediction data quality reliability detection stage.

[0035] It represents the zero-point drift rate threshold of the CNC machine tool life prediction data, which is the preset zero-point drift rate threshold of the CNC machine tool life prediction data obtained from the reliability life prediction database, and can be the average value of the zero-point drift rate of the CNC machine tool life prediction data at the quality reliability time detection point of the CNC machine tool life prediction data preset from the historical database.

[0036] Indicates The zero point drift rate of CNC machine tool life prediction data under the quality reliability time detection point of CNC machine tool life prediction data.

[0037] It represents the standard value of the frequency of data collection for the life prediction of CNC machine tools, which is the preset standard value of the frequency of data collection for the life prediction of CNC machine tools obtained from the reliability life prediction database, and can be the average value of the frequency of data collection for the life prediction of CNC machine tools at the preset reliability time detection point of the life prediction data of CNC machine tools from the historical database.

[0038] Indicates The frequency of CNC machine tool life prediction data collection under the CNC machine tool life prediction data quality reliability time detection point.

[0039] Indicates The phase distortion coefficient of the CNC machine tool life prediction signal under the CNC machine tool life prediction data quality reliability detection stage.

[0040] Indicates The electromagnetic wave intensity at the time detection point of the quality reliability of CNC machine tool life prediction data.

[0041] It represents the standard value of electromagnetic wave intensity, which is the preset standard value of electromagnetic wave intensity obtained from the reliability life prediction database, and can be the average value of electromagnetic wave intensity at the quality reliability time detection point of CNC machine tool life prediction data preset in the historical database.

[0042] Indicates The vibration amplitude at the time detection point of the CNC machine tool life prediction data quality reliability.

[0043] It represents the standard value of vibration amplitude, which is the preset standard value of vibration amplitude obtained from the reliability life prediction database, and can be the average value of vibration amplitude at the quality reliability time detection point of CNC machine tool life prediction data preset in the historical database.

[0044] Indicates The maximum temperature of the CNC machine tool under the quality reliability detection stage of the CNC machine tool life prediction data.

[0045] Indicates The minimum temperature of CNC machine tools under the quality reliability detection stage of CNC machine tool life prediction data.

[0046] It represents the standard value of the temperature fluctuation range of the CNC machine tool, which is the preset standard value of the temperature fluctuation range of the CNC machine tool obtained from the reliability life prediction database, and can be the average value of the temperature fluctuation range of the CNC machine tool under the quality reliability time detection section of the CNC machine tool life prediction data preset in the historical database.

[0047] Indicates The phase peak of the CNC machine tool life prediction signal under the CNC machine tool life prediction data quality reliability detection section.

[0048] Indicates The phase trough of the CNC machine tool life prediction signal under the CNC machine tool life prediction data quality reliability detection section.

[0049] It represents the standard value of the phase offset of the CNC machine tool life prediction signal, which is the preset standard value of the phase offset of the CNC machine tool life prediction signal obtained from the reliability life prediction database, and can be the average value of the phase offset of the CNC machine tool life prediction signal under the quality reliability time detection section of the CNC machine tool life prediction data preset in the historical database.

[0050] The temperature fluctuation coefficient influence weighting factor is a preset value obtained from the reliability life prediction database.

[0051] It is the weight factor affecting the zero drift rate of the preset CNC machine tool life prediction data obtained from the reliability life prediction database.

[0052] The frequency of collecting preset CNC machine tool life prediction data obtained from the reliability life prediction database affects the weight factor.

[0053] It is the influence weight factor of the phase distortion coefficient of the preset CNC machine tool life prediction signal obtained from the reliability life prediction database.

[0054] is the preset electromagnetic wave intensity correction factor obtained from the reliability life prediction database.

[0055] is the preset vibration amplitude correction factor obtained from the reliability life prediction database.

[0056] The preset numerical temperature fluctuation coefficient influence weight factor, the preset CNC machine life prediction data zero drift rate influence weight factor, the preset CNC machine life prediction data acquisition frequency influence weight factor and the preset CNC machine life prediction signal phase distortion coefficient influence weight factor respectively represent the numerical value of the influence of the numerical temperature fluctuation coefficient, the CNC machine life prediction data zero drift rate, the CNC machine life prediction data acquisition frequency and the CNC machine life prediction signal phase distortion coefficient on the CNC machine life prediction data quality reliability evaluation index, and represent the proportion of the numerical temperature fluctuation coefficient, the CNC machine life prediction data zero drift rate, the CNC machine life prediction data acquisition frequency and the CNC machine life prediction signal phase distortion coefficient in the influence on the CNC machine life prediction data quality reliability evaluation index.

[0057] The preset numerical temperature fluctuation coefficient influence weight factor, the preset numerical control machine tool life prediction data zero drift rate influence weight factor, the preset numerical control machine tool life prediction data acquisition frequency influence weight factor and the preset numerical control machine tool life prediction signal phase distortion coefficient influence weight factor are obtained through mapping relationships. For example, the numerical temperature fluctuation coefficient, the numerical control machine tool life prediction data zero drift rate, the numerical control machine tool life prediction data acquisition frequency and the numerical control machine tool life prediction signal phase distortion coefficient in the historical data are used to establish the relationship between the numerical temperature fluctuation coefficient, the numerical control machine tool life prediction data zero drift rate, the numerical control machine tool life prediction data acquisition frequency and the numerical control machine tool life prediction signal phase distortion coefficient and the data transmission speed. , a mapping set of CNC machine life prediction data acquisition frequency and CNC machine life prediction signal phase distortion coefficient and their corresponding weights, by inputting real-time digital temperature fluctuation coefficient, CNC machine life prediction data zero drift rate, CNC machine life prediction data acquisition frequency and CNC machine life prediction signal phase distortion coefficient, the corresponding preset digital temperature fluctuation coefficient influence weight factor, preset CNC machine life prediction data zero drift rate influence weight factor, preset CNC machine life prediction data acquisition frequency influence weight factor and preset CNC machine life prediction signal phase distortion coefficient influence weight factor in the mapping set are obtained.

[0058] The preset electromagnetic wave intensity correction factor and the preset vibration amplitude correction factor respectively represent the numerical values ​​of the influence of the electromagnetic wave intensity and the vibration amplitude on the quality reliability evaluation index of the CNC machine tool life prediction data, and represent the proportion of the electromagnetic wave intensity and the vibration amplitude in the influence of the quality reliability evaluation index of the CNC machine tool life prediction data.

[0059] The preset electromagnetic wave intensity correction factor and the preset vibration amplitude correction factor are obtained through mapping relationships. For example, a mapping set of electromagnetic wave intensity and vibration amplitude and their corresponding weights is established respectively through the relationship between the electromagnetic wave intensity and vibration amplitude in the historical data and the data delay. The corresponding preset electromagnetic wave intensity correction factor and preset vibration amplitude correction factor in the mapping set are obtained by inputting the real-time electromagnetic wave intensity and vibration amplitude.

[0060] The increase in electromagnetic wave intensity, caused by electrical faults or electromagnetic interference, affects the normal operation of the motor, thereby leading to an increase in vibration amplitude; the increase in electromagnetic wave intensity leads to overheating of electronic components, and the square of the difference between the maximum temperature of the CNC machine tool and the minimum temperature of the CNC machine tool becomes larger; the increase in vibration amplitude leads to increased friction between mechanical components, which in turn leads to an increase in temperature, and the square of the difference between the maximum temperature of the CNC machine tool and the minimum temperature of the CNC machine tool becomes larger; the increase in vibration amplitude leads to an increase in the rate of change of the sensor output signal when there is no input change, and an increase in the zero-point drift rate of the CNC machine tool life prediction data; the change in vibration amplitude will affect the phase of the signal, and the larger the vibration amplitude, the larger the square of the difference between the phase peak of the CNC machine tool life prediction signal and the phase trough of the CNC machine tool life prediction signal; the greater the frequency of CNC machine tool life prediction data acquisition, the smaller the zero-point drift rate of the CNC machine tool life prediction data.

[0061] The larger the square of the difference between the electromagnetic wave intensity and the standard value of the electromagnetic wave intensity, the greater the electromagnetic interference, which reduces the accuracy of data acquisition. The square of the difference between the electromagnetic wave intensity and the standard value of the electromagnetic wave intensity is negatively correlated with the reliability evaluation index of the life prediction data quality of the CNC machine tool, and the smaller the reliability evaluation index of the life prediction data quality of the CNC machine tool is. The larger the square of the difference between the vibration amplitude and the standard value of the vibration amplitude, the greater the abnormality of the machine tool, which reduces the data quality. The square of the difference between the vibration amplitude and the standard value of the vibration amplitude is negatively correlated with the reliability evaluation index of the life prediction data quality of the CNC machine tool, and the smaller the reliability evaluation index of the life prediction data quality of the CNC machine tool is. The larger the square of the difference between the maximum temperature of the CNC machine tool and the minimum temperature of the CNC machine tool, the greater the performance degradation or failure of the machine tool, thereby reducing the data quality. The square of the difference between the maximum temperature of the CNC machine tool and the minimum temperature of the CNC machine tool is negatively correlated with the reliability evaluation index of the life prediction data quality of the CNC machine tool, and the smaller the reliability evaluation index of the life prediction data quality of the CNC machine tool is. The larger the zero drift rate of the life prediction data of the CNC machine tool is, the greater the The lower the accuracy of the sensor reading, the negative correlation exists between the zero drift rate of the CNC machine life prediction data and the quality reliability evaluation index of the CNC machine life prediction data, and the smaller the quality reliability evaluation index of the CNC machine life prediction data; the larger the square of the difference between the phase peak of the CNC machine life prediction signal and the phase trough of the CNC machine life prediction signal, the worse the signal quality, the negative correlation exists between the square of the difference between the phase peak of the CNC machine life prediction signal and the phase trough of the CNC machine life prediction signal and the quality reliability evaluation index of the CNC machine life prediction data, and the smaller the quality reliability evaluation index of the CNC machine life prediction data; the larger the absolute value of the difference between the acquisition frequency of the CNC machine life prediction data and the acquisition frequency of the CNC machine life prediction data, the missing or redundant data points will be caused, thereby reducing the quality of the overall data, the absolute value of the difference between the acquisition frequency of the CNC machine life prediction data and the acquisition frequency of the CNC machine life prediction data is negatively correlated with the quality reliability evaluation index of the CNC machine life prediction data, and the smaller the quality reliability evaluation index of the CNC machine life prediction data is.

[0062] Furthermore, the specific steps for obtaining the CNC machine tool life prediction signal quality evaluation index are as follows: obtaining the electromagnetic wave intensity at a preset CNC machine tool life prediction signal quality time detection point through an electromagnetic field intensity meter; obtaining the vibration amplitude at a preset CNC machine tool life prediction signal quality time detection point through a vibration sensor; obtaining the maximum temperature of the CNC machine tool in the preset CNC machine tool life prediction signal quality time detection section through an infrared temperature sensor; obtaining the minimum temperature of the CNC machine tool in the preset CNC machine tool life prediction signal quality time detection section through an infrared temperature sensor; obtaining the phase peak of the CNC machine tool life prediction signal in the preset CNC machine tool life prediction signal quality time detection section through a dynamic signal analyzer; obtaining the phase trough of the CNC machine tool life prediction signal in the preset CNC machine tool life prediction signal quality time detection section through a dynamic signal analyzer; obtaining the CNC machine tool phase peak of the CNC machine tool life prediction signal in the preset CNC machine tool life prediction signal quality time detection section through a power meter Life prediction input signal power; obtaining the CNC machine life prediction output signal power at a preset CNC machine life prediction signal quality time detection point through a power meter; obtaining the background noise power at a preset CNC machine life prediction signal quality time detection point through a spectrum analyzer; obtaining the CNC machine life prediction data transmission response time of a preset CNC machine life prediction signal quality time detection section through a network analyzer; the CNC machine life prediction signal quality data includes electromagnetic wave intensity, vibration amplitude, CNC machine maximum temperature, CNC machine minimum temperature, CNC machine life prediction signal phase peak, CNC machine life prediction signal phase trough, CNC machine life prediction input signal power, CNC machine life prediction output signal power, background noise power and CNC machine life prediction data transmission response time; and obtaining a CNC machine life prediction signal quality evaluation index based on the CNC machine life prediction signal quality data analysis.

[0063] In this embodiment, the specific method of analyzing and obtaining the quality evaluation index of the CNC machine tool life prediction signal is as follows: ; ; ; ; ; ; ; ; The preset CNC machine tool life prediction signal quality time detection points are numbered in sequence. Indicates The number of the CNC machine tool life prediction signal quality time detection point under the CNC machine tool life prediction signal quality detection section, , Indicates the total number of signal quality time detection points for CNC machine tool life prediction.

[0064] Divide the preset CNC machine tool life prediction signal quality time into CNC machine tool life prediction signal quality detection segments of the same length, Indicates the number of the quality detection section of the CNC machine tool life prediction signal. , Indicates the total number of signal quality detection segments for CNC machine tool life prediction.

[0065] Indicates The quality evaluation index of the CNC machine tool life prediction signal at each CNC machine tool life prediction signal quality time detection point.

[0066] Indicates The electromagnetic wave intensity influence coefficient of the signal quality time detection point for CNC machine tool life prediction.

[0067] Indicates The vibration amplitude influence coefficient of the signal quality time detection point for CNC machine tool life prediction.

[0068] Indicates The temperature fluctuation influence coefficient of the signal quality detection section for CNC machine tool life prediction.

[0069] Indicates The phase distortion coefficient of the CNC machine tool life prediction signal under the CNC machine tool life prediction signal quality detection section.

[0070] Indicates The attenuation coefficient of the CNC machine tool life prediction signal at the quality time detection point of the CNC machine tool life prediction signal.

[0071] Indicates The background noise power at the quality time detection point of the CNC machine tool life prediction signal.

[0072] It represents the background noise power threshold, which is the preset background noise power threshold obtained from the reliability life prediction database, and can be the average background noise power at the quality time detection point of the CNC machine tool life prediction signal preset in the historical database.

[0073] Indicates The data transmission response time of CNC machine tool life prediction in the CNC machine tool life prediction signal quality detection stage.

[0074] It represents the standard value of the data transmission response time for the life prediction of CNC machine tools, which is the preset standard value of the data transmission response time for the life prediction of CNC machine tools obtained from the reliability life prediction database, and can be the average value of the data transmission response time for the life prediction of CNC machine tools under the preset CNC machine tool life prediction signal quality time detection section from the historical database.

[0075] Indicates The electromagnetic wave intensity at the time detection point of the CNC machine tool life prediction signal quality.

[0076] It represents the standard value of electromagnetic wave intensity, which is the preset standard value of electromagnetic wave intensity obtained from the reliability life prediction database, and can be the average value of electromagnetic wave intensity at the preset CNC machine tool life prediction signal quality time detection point from the historical database.

[0077] Indicates The vibration amplitude at the time detection point of the CNC machine tool life prediction signal quality.

[0078] It represents the standard value of vibration amplitude, which is the preset standard value of vibration amplitude obtained from the reliability life prediction database, and can be the average value of vibration amplitude at the preset CNC machine tool life prediction signal quality time detection point from the historical database.

[0079] Indicates The maximum temperature of the CNC machine tool under the quality detection section of the CNC machine tool life prediction signal.

[0080] Indicates The minimum temperature of the CNC machine tool under the quality detection section of the CNC machine tool life prediction signal.

[0081] It represents the standard value of the temperature fluctuation range of the CNC machine tool, which is the preset standard value of the temperature fluctuation range of the CNC machine tool obtained from the reliability life prediction database, and can be the average value of the temperature fluctuation range of the CNC machine tool under the quality time detection section of the CNC machine tool life prediction signal preset from the historical database.

[0082] Indicates The phase peak of the CNC machine tool life prediction signal under the quality detection section of the CNC machine tool life prediction signal.

[0083] Indicates The phase trough of the CNC machine tool life prediction signal under the quality detection section of the CNC machine tool life prediction signal.

[0084] It represents the standard value of the phase offset of the CNC machine tool life prediction signal, which is the preset standard value of the phase offset of the CNC machine tool life prediction signal obtained from the reliability life prediction database, and can be the average value of the phase offset of the CNC machine tool life prediction signal under the quality time detection section of the CNC machine tool life prediction signal preset from the historical database.

[0085] Indicates The power of the CNC machine tool life prediction input signal at the CNC machine tool life prediction signal quality time detection point.

[0086] It represents the standard value of the CNC machine tool life prediction input signal power, which is the preset CNC machine tool life prediction input signal power standard value obtained from the reliability life prediction database, and can be the average value of the CNC machine tool life prediction input signal power at the preset CNC machine tool life prediction signal quality time detection point from the historical database.

[0087] Indicates The output signal power of the CNC machine tool life prediction signal at the CNC machine tool life prediction signal quality time detection point.

[0088] It represents the standard value of the output signal power of the CNC machine tool life prediction, which is the preset standard value of the output signal power of the CNC machine tool life prediction obtained from the reliability life prediction database, and can be the average value of the output signal power of the CNC machine tool life prediction at the preset CNC machine tool life prediction signal quality time detection point from the historical database.

[0089] It is the influence weight factor of the phase distortion coefficient of the preset CNC machine tool life prediction signal obtained from the reliability life prediction database.

[0090] It is the weight factor affecting the attenuation coefficient of the preset CNC machine tool life prediction signal obtained from the reliability life prediction database.

[0091] is the preset background noise power impact weight factor obtained from the reliability life prediction database.

[0092] The weight factor affecting the transmission response time of the preset CNC machine tool life prediction data obtained from the reliability life prediction database.

[0093] is the preset electromagnetic wave intensity influencing factor obtained from the reliability life prediction database.

[0094] is the preset vibration amplitude influence factor obtained from the reliability life prediction database.

[0095] is the preset temperature fluctuation impact factor obtained from the reliability life prediction database.

[0096] The preset CNC machine life prediction signal phase distortion coefficient influence weight factor, the preset CNC machine life prediction signal attenuation coefficient influence weight factor, the preset background noise power influence weight factor and the preset CNC machine life prediction data transmission response time influence weight factor respectively represent the numerical values ​​of the influence of the CNC machine life prediction signal phase distortion coefficient, the CNC machine life prediction signal attenuation coefficient, the background noise power and the CNC machine life prediction data transmission response time on the CNC machine life prediction signal quality evaluation index, and represent the proportion of the CNC machine life prediction signal phase distortion coefficient, the CNC machine life prediction signal attenuation coefficient, the background noise power and the CNC machine life prediction data transmission response time in the influence on the CNC machine life prediction signal quality evaluation index.

[0097] The preset weight factor affecting the phase distortion coefficient of the CNC machine tool life prediction signal, the preset weight factor affecting the attenuation coefficient of the CNC machine tool life prediction signal, the preset weight factor affecting the background noise power and the preset weight factor affecting the data transmission response time of the CNC machine tool life prediction are obtained through mapping relationships. For example, a mapping set of the phase distortion coefficient of the CNC machine tool life prediction signal, the attenuation coefficient of the CNC machine tool life prediction signal, the background noise power and the data transmission response time of the CNC machine tool life prediction in the historical data and the relationship between the data acquisition frequency and the data acquisition frequency is established respectively. The preset weight factor affecting the phase distortion coefficient of the CNC machine tool life prediction signal, the preset weight factor affecting the attenuation coefficient of the CNC machine tool life prediction signal, the preset weight factor affecting the background noise power and the preset weight factor affecting the data transmission response time of the CNC machine tool life prediction are obtained by inputting the real-time phase distortion coefficient of the CNC machine tool life prediction signal, the attenuation coefficient of the CNC machine tool life prediction signal, the background noise power and the data transmission response time of the CNC machine tool life prediction.

[0098] The preset electromagnetic wave intensity influence factor, the preset vibration amplitude influence factor and the preset temperature fluctuation influence factor respectively represent the numerical values ​​of the influence of the electromagnetic wave intensity, the vibration amplitude and the temperature fluctuation on the quality evaluation index of the CNC machine tool life prediction signal, and represent the proportion of the electromagnetic wave intensity, the vibration amplitude and the temperature fluctuation in the influence on the quality evaluation index of the CNC machine tool life prediction signal.

[0099] The preset electromagnetic wave intensity influencing factor, the preset vibration amplitude influencing factor and the preset temperature fluctuation influencing factor are obtained through mapping relationships. For example, a mapping set of electromagnetic wave intensity, vibration amplitude and temperature fluctuation and their corresponding weights is established respectively through the relationship between the electromagnetic wave intensity, vibration amplitude and temperature fluctuation and the signal strength in the historical data. The corresponding preset electromagnetic wave intensity influencing factor, preset vibration amplitude influencing factor and preset temperature fluctuation influencing factor in the mapping set are obtained by inputting the real-time electromagnetic wave intensity, vibration amplitude and temperature fluctuation.

[0100] As the intensity of electromagnetic waves increases, the short circuit of the motor coil generates a stronger electromagnetic field and causes vibration, resulting in increased mechanical vibration; temperature changes affect the size and shape of mechanical parts, which in turn affects the vibration characteristics. The larger the square of the difference between the maximum temperature of the CNC machine tool and the minimum temperature of the CNC machine tool, the poor bearing lubrication and increased friction will increase the vibration amplitude; the larger the square of the difference between the phase peak of the CNC machine tool life prediction signal and the phase trough of the CNC machine tool life prediction signal, which is related to the power change of the signal, and produces greater resistance at a specific operating frequency, resulting in a decrease in the power of the CNC machine tool life prediction output signal; the greater the background noise power, the more it will interfere with data transmission, resulting in signal distortion or errors, requiring additional error detection and correction, thereby increasing the data transmission response time of the CNC machine tool life prediction; the input signal power of the CNC machine tool life prediction reflects the efficiency of the machine tool. The larger the input signal power of the CNC machine tool life prediction, the lower the output signal power of the CNC machine tool life prediction, indicating that there is energy loss inside the machine tool due to component wear or failure.

[0101] The larger the square of the difference between the electromagnetic wave intensity and the standard value of the electromagnetic wave intensity, the greater the electromagnetic interference, which reduces the signal quality. The square of the difference between the electromagnetic wave intensity and the standard value of the electromagnetic wave intensity is positively correlated with the quality evaluation index of the CNC machine tool life prediction signal, and the larger the quality evaluation index of the CNC machine tool life prediction signal; the larger the square of the difference between the vibration amplitude and the standard value of the vibration amplitude, the greater the machine tool fault, and the larger the quality evaluation index of the CNC machine tool life prediction signal; the square of the difference between the vibration amplitude and the standard value of the vibration amplitude is positively correlated with the quality evaluation index of the CNC machine tool life prediction signal, and the larger the quality evaluation index of the CNC machine tool life prediction signal; the larger the square of the difference between the maximum temperature of the CNC machine tool and the minimum temperature of the CNC machine tool, the greater the machine tool overheating. Causes signal distortion or sensor performance degradation, the square of the difference between the maximum temperature of the CNC machine tool and the minimum temperature of the CNC machine tool is positively correlated with the quality evaluation index of the CNC machine tool life prediction signal, and the larger the CNC machine tool life prediction signal quality evaluation index; the larger the square of the difference between the phase peak of the CNC machine tool life prediction signal and the phase trough of the CNC machine tool life prediction signal, the more unstable the signal quality, the square of the difference between the phase peak of the CNC machine tool life prediction signal and the phase trough of the CNC machine tool life prediction signal is positively correlated with the quality evaluation index of the CNC machine tool life prediction signal, and the larger the CNC machine tool life prediction signal quality evaluation index; the square of the difference between the power of the CNC machine tool life prediction input signal and the standard value of the power of the CNC machine tool life prediction input signal The larger the square, the worse the signal quality. There is a positive correlation between the square of the difference between the input signal power of the CNC machine tool life prediction and the standard value of the input signal power of the CNC machine tool life prediction and the square of the phase trough difference of the CNC machine tool life prediction signal and the CNC machine tool life prediction signal quality evaluation index. The larger the CNC machine tool life prediction signal quality evaluation index is; the larger the square of the difference between the output signal power of the CNC machine tool life prediction and the standard value of the output signal power of the CNC machine tool life prediction, the worse the signal quality is. There is a positive correlation between the square of the difference between the output signal power of the CNC machine tool life prediction and the standard value of the output signal power of the CNC machine tool life prediction and the square of the phase trough difference of the CNC machine tool life prediction signal and the CNC machine tool life prediction signal quality evaluation index. The larger the quality evaluation index of the CNC machine tool life prediction signal is; the larger the background noise power is, the more affected the signal quality is, and the noise interferes with the clarity of the signal. There is a positive correlation between the background noise power and the quality evaluation index of the CNC machine tool life prediction signal, and the larger the quality evaluation index of the CNC machine tool life prediction signal is; the larger the absolute value of the difference between the data transmission response time of the CNC machine tool life prediction and the standard value of the data transmission response time of the CNC machine tool life prediction is, it indicates that there is a delay in data transmission, and the absolute value of the difference between the data transmission response time of the CNC machine tool life prediction and the standard value of the data transmission response time of the CNC machine tool life prediction is positively correlated with the quality evaluation index of the CNC machine tool life prediction signal, and the larger the quality evaluation index of the CNC machine tool life prediction signal is.

[0102] Furthermore, the specific steps of comprehensively analyzing and obtaining the CNC machine tool life prediction data accuracy evaluation index are as follows: obtaining the CNC machine tool life prediction data drift of the preset CNC machine tool life prediction accuracy time detection segment through the edge computing device; and obtaining the CNC machine tool life prediction data accuracy evaluation index through comprehensive analysis of the CNC machine tool life prediction data quality reliability evaluation index, the CNC machine tool life prediction signal quality evaluation index and the CNC machine tool life prediction data drift.

[0103] In this embodiment, the specific method of obtaining the accuracy evaluation index of the CNC machine tool life prediction data by analysis is as follows: ; ; Divide the preset CNC machine tool life prediction data accuracy time into CNC machine tool life prediction data accuracy time detection segments of the same length, Indicates the number of the time detection segment for the accuracy of the CNC machine tool life prediction data. , Indicates the total number of time detection segments for the accuracy of CNC machine tool life prediction data.

[0104] Represents the accuracy evaluation index of CNC machine tool life prediction data.

[0105] Indicates The reliability evaluation index of CNC machine tool life prediction data quality at the reliability time detection point of CNC machine tool life prediction data quality.

[0106] Indicates The quality evaluation index of the CNC machine tool life prediction signal at each CNC machine tool life prediction signal quality time detection point.

[0107] Indicates The drift amount of the CNC machine tool life prediction data under the CNC machine tool life prediction data accuracy time detection period is the absolute value of the deviation difference between the CNC machine tool life prediction data under the preset CNC machine tool life prediction accuracy time detection period and the CNC machine tool life prediction original data.

[0108] It represents the standard value of the drift of the CNC machine tool life prediction data, which is the preset standard value of the CNC machine tool life prediction data drift obtained from the reliability life prediction database, and can be the average value of the CNC machine tool life prediction data drift under the preset CNC machine tool life prediction accuracy time detection period from the historical database.

[0109] It is the weight factor affecting the quality reliability evaluation index of the preset CNC machine tool life prediction data obtained from the reliability life prediction database.

[0110] It is the influencing weight factor of the quality evaluation index of the preset CNC machine tool life prediction signal obtained from the reliability life prediction database.

[0111] It is the weight factor affecting the drift of the preset CNC machine tool life prediction data obtained from the reliability life prediction database.

[0112] The preset weight factor affecting the quality and reliability evaluation index of the CNC machine tool life prediction data, the preset weight factor affecting the quality and reliability evaluation index of the CNC machine tool life prediction signal and the preset weight factor affecting the drift amount of the CNC machine tool life prediction data are obtained through mapping relationships. For example, a mapping set of the quality and reliability evaluation index of the CNC machine tool life prediction data, the quality and reliability evaluation index of the CNC machine tool life prediction signal and the drift amount of the CNC machine tool life prediction data and their corresponding weights is established respectively through the relationship between the quality and reliability evaluation index of the CNC machine tool life prediction data, the quality and reliability evaluation index of the CNC machine tool life prediction signal and the drift amount of the CNC machine tool life prediction data in the historical data and the data update frequency. The preset weight factor affecting the quality and reliability evaluation index of the CNC machine tool life prediction data, the weight factor affecting the quality and reliability evaluation index of the CNC machine tool life prediction signal and the weight factor affecting the drift amount of the CNC machine tool life prediction data corresponding to the mapping set are obtained by inputting the real-time quality and reliability evaluation index of the CNC machine tool life prediction data, the quality and reliability evaluation index of the CNC machine tool life prediction signal and the drift amount of the CNC machine tool life prediction data.

[0113] Table 1 is an example table of the accuracy evaluation index of CNC machine tool life prediction data. The example parameters in Table 1 only take the parameters under one CNC machine tool life prediction accuracy detection point for example. The weight factor Set to 0.4, weight factor Set to 0.3, weight factor Set to 0.3, The standard value of the data drift for CNC machine tool life prediction is 2, as shown in Table 1.

[0114] Table 1 Example table of CNC machine tool life prediction data accuracy evaluation index

[0115] The reliability evaluation index of the data quality for predicting the life of CNC machine tools is an indicator of the overall quality of the data set used to predict the life of CNC machine tools. It depends on the result of the signal quality evaluation. The larger the reliability evaluation index of the data quality for predicting the life of CNC machine tools, the smaller the signal quality evaluation index of the life of CNC machine tools; the signal quality evaluation index of the life of CNC machine tools is the basis of data quality. The drift of the data for predicting the life of CNC machine tools affects the stability of the signal for predicting the life of CNC machine tools. The more the data drift of the life of CNC machine tools, the larger the signal quality evaluation index of the life of CNC machine tools; the drift of the data for predicting the life of CNC machine tools refers to the change in the statistical characteristics of the data distribution over time. During the operation of the CNC machine tools, data drift leads to inaccurate prediction of the life of CNC machine tools. The more the data drift of the life of CNC machine tools, the smaller the reliability evaluation index of the data quality for predicting the life of CNC machine tools.

[0116] It can be seen from Table 1 that the higher the quality reliability evaluation index of CNC machine tool life prediction data, the more accurate, complete and consistent the data used for prediction is, which reflects the status of CNC machine tools, thereby improving the accuracy of life prediction. There is a positive correlation between the quality reliability evaluation index of CNC machine tool life prediction data and the accuracy evaluation index of CNC machine tool life prediction data. The larger the accuracy evaluation index of CNC machine tool life prediction data, the higher the reliability evaluation index. The quality evaluation index of CNC machine tool life prediction signal measures the quality of a single signal such as a sensor signal. The larger the quality evaluation index of CNC machine tool life prediction signal, the more unstable the CNC machine tool life prediction signal is. The greater the noise, the negative correlation between the CNC machine tool life prediction signal quality evaluation index and the CNC machine tool life prediction data accuracy evaluation index, and the smaller the CNC machine tool life prediction data accuracy evaluation index; the greater the absolute value of the CNC machine tool life prediction data drift and the CNC machine tool life prediction data drift difference, the data characteristics have changed over time, resulting in a decrease in prediction accuracy, the absolute value of the CNC machine tool life prediction data drift and the CNC machine tool life prediction data drift difference is negatively correlated with the CNC machine tool life prediction data accuracy evaluation index, and the smaller the CNC machine tool life prediction data accuracy evaluation index is.

[0117] like Figure 2 As shown, it is a schematic diagram of the CNC machine tool life prediction data accuracy evaluation exponential function provided in the embodiment of the present application; x is the positive semi-axis of the horizontal coordinate, y is the positive semi-axis of the vertical coordinate, and the weight factor Set to 0.4, weight factor Set to 0.3, weight factor Set to 0.3, The standard value of the data drift for CNC machine tool life prediction is 2.

[0118] Curve a indicates that if the quality evaluation index of the CNC machine tool life prediction signal is set to a fixed value of 1, the drift of the CNC machine tool life prediction data is set to a fixed value of 1, the quality reliability evaluation index of the CNC machine tool life prediction data is x, and the accuracy evaluation index of the CNC machine tool life prediction data is y, the accuracy evaluation index of the CNC machine tool life prediction data increases with the increase of the quality reliability evaluation index of the CNC machine tool life prediction data.

[0119] Furthermore, the specific steps of the method for optimizing the quality reliability of CNC machine tool life prediction data are as follows: if the quality reliability evaluation index of the CNC machine tool life prediction data is greater than or equal to the first threshold value of the quality reliability evaluation index of the CNC machine tool life prediction data, there is no need to optimize the quality reliability of the CNC machine tool life prediction data; if the quality reliability evaluation index of the CNC machine tool life prediction data is lower than the first threshold value of the quality reliability evaluation index of the CNC machine tool life prediction data, then the difference between the quality reliability evaluation index of the CNC machine tool life prediction data and the first threshold value of the quality reliability evaluation index of the CNC machine tool life prediction data is used to match the corresponding adjustment plan in the reliability life prediction database.

[0120] In this embodiment, assuming that the reliability evaluation index of the quality of the life prediction data of a CNC machine tool is 3, the first threshold value of the reliability evaluation index of the quality of the life prediction data of a CNC machine tool obtained from the reliability life prediction database is 4, and the corresponding difference is -1, then the adjustment scheme corresponding to the difference between the reliability evaluation index of the quality of the life prediction data of a CNC machine tool and the first threshold value of the reliability evaluation index of the quality of the life prediction data of a CNC machine tool obtained from the reliability life prediction database is -1 is as follows: by using a phase-stable signal processing technology, for example, a phase-locked loop (PLL) technology is used to stabilize the phase of the signal, the phase-locked loop can track the phase change of the input signal, and automatically adjust the frequency of the local oscillator to keep the phase synchronized with the input signal; By optimizing the signal transmission path, for example, identifying and replacing aging or degraded cables and connectors in the signal transmission path, using high-quality, low-loss cables to reduce signal attenuation and phase distortion, and considering using optical fiber instead of copper wire for long-distance transmission, because optical fiber transmission has lower signal distortion and higher anti-interference ability; by adjusting the standard value of signal phase offset, for example, after the system has been running for a period of time, the phase offset increases due to temperature rise, and a compensation value can be preset in the signal processing algorithm to correct this offset. For every increase of 10 degrees Celsius, the phase offset increases by 0.5 degrees, and the corresponding compensation formula is preset in the software; through the above optimization steps, the reliability evaluation index of the quality of CNC machine tool life prediction data can be improved.

[0121] Furthermore, the specific steps of the method for optimizing and adjusting the quality of the CNC machine tool life prediction signal are as follows: if the CNC machine tool life prediction signal quality evaluation index is lower than or equal to the second threshold value of the CNC machine tool life prediction signal quality evaluation index, there is no need to optimize and adjust the CNC machine tool life prediction signal quality; if the CNC machine tool life prediction signal quality evaluation index is greater than the second threshold value of the CNC machine tool life prediction signal quality evaluation index, then the difference between the CNC machine tool life prediction signal quality evaluation index and the second threshold value of the CNC machine tool life prediction signal quality evaluation index is used to match the corresponding adjustment plan in the reliability life prediction database.

[0122] In this embodiment, assuming that the quality evaluation index of the CNC machine tool life prediction signal is 6, the second threshold of the CNC machine tool life prediction signal quality evaluation index obtained from the reliability life prediction database is 3, and the corresponding difference is 3, then the adjustment scheme corresponding to the difference between the CNC machine tool life prediction signal quality evaluation index and the second threshold of the CNC machine tool life prediction signal quality evaluation index obtained from the reliability life prediction database is 3 is as follows: by implementing signal filtering technology, a low-pass filter is used to suppress high-frequency interference. For example, a low-pass filter with a cutoff frequency of 1000Hz is connected to the signal acquisition system to filter out high-frequency interference above 1000Hz. Frequency noise; Isolate interference signals by using isolation transformers or optical isolators, use optical isolators for signal isolation, for example, add an optical isolator in the signal transmission line to convert electrical signals into optical signals, and then convert optical signals into electrical signals, thereby effectively isolating electromagnetic interference; compensate for signal attenuation by adding signal amplifiers or repeaters, for example, install a signal amplifier in the middle of the signal transmission line to amplify the attenuated signal to an appropriate size, and ensure that the signal quality meets the evaluation requirements; Through the above optimization steps, the signal quality evaluation index of CNC machine tool life prediction can be reduced.

[0123] Furthermore, the specific steps of optimizing and adjusting the accuracy of CNC machine tool life prediction are as follows: extracting the comprehensive threshold of the CNC machine tool life prediction data accuracy assessment index in the reliability life prediction database, and comparing the CNC machine tool life prediction data accuracy assessment index with the comprehensive threshold of the CNC machine tool life prediction data accuracy assessment index; if the CNC machine tool life prediction data accuracy assessment index is greater than or equal to the comprehensive threshold of the CNC machine tool life prediction data accuracy assessment index, there is no need to optimize and adjust the CNC machine tool life prediction accuracy.

[0124] Furthermore, the method for optimizing and adjusting the accuracy of CNC machine tool life prediction also includes: if the accuracy evaluation index of the CNC machine tool life prediction data is lower than the comprehensive threshold of the CNC machine tool life prediction data accuracy evaluation index, then matching the corresponding adjustment plan in the reliability life prediction database through the difference between the CNC machine tool life prediction data accuracy evaluation index and the comprehensive threshold of the CNC machine tool life prediction data accuracy evaluation index.

[0125] In this embodiment, assuming that the accuracy evaluation index of the CNC machine tool life prediction data is 4, the comprehensive threshold of the CNC machine tool life prediction data accuracy evaluation index obtained from the reliability life prediction database is 8, and the corresponding difference is -4, then the adjustment scheme corresponding to the difference between the CNC machine tool life prediction data accuracy evaluation index and the comprehensive threshold of the CNC machine tool life prediction data accuracy evaluation index obtained from the reliability life prediction database is -4 is as follows: by increasing the signal transmission power, increasing the signal-to-noise ratio, and increasing the signal transmission power, for example, adjusting the power setting of the sensor transmission unit, increasing the transmission power from 2mW to 4mW, thereby increasing Improve the received signal strength and increase the signal-to-noise ratio; use noise suppression technology, such as noise gates and filters. For example, add a bandpass filter with a noise gate in the signal processing unit. The filter is designed to only allow signals in a specific frequency range to pass through the normal operating frequency range of the machine tool. At the same time, the noise gate can automatically identify and suppress noise signals below the set threshold; by measuring signal attenuation, add amplifiers or adjust transmission lines as needed, measure signal attenuation and increase amplifiers or adjust transmission lines accordingly. For example, use a signal attenuation measuring instrument to detect the transmission line and find that the signal is attenuated by 50% after 400 meters of transmission. According to the measurement results, install a signal amplifier in the middle of the transmission line to amplify the signal to a degree sufficient to compensate for the attenuation; through the above optimization steps, the accuracy evaluation index of the CNC machine tool life prediction data can be improved.

[0126] Specifically, the information gain method is used to select the most important features for life prediction, PCA or other dimensionality reduction techniques are used to reduce the number of features while retaining most of the information, and a suitable prediction model, such as a support vector machine, is selected according to data characteristics and prediction targets. The model is trained using preset CNC machine tool operation data, wherein the preset CNC machine tool operation data includes feature data and corresponding remaining life data as a training set, wherein the feature data includes operating time, temperature change rate, etc., and the remaining life data includes the remaining service life of the machine tool, etc. The trained model is integrated into the monitoring system of the machine tool, and the input of the model is the CNC machine tool operation data, which reflects the operating conditions and performance status of the machine tool at a specific time point, and the output of the model is the corresponding remaining life data, i.e., the time during which the machine tool is expected to operate normally under the current feature data until repair or component replacement is required; the CNC machine tool operation data collected in real time is input into the model for prediction to obtain a predicted value of the remaining service life of the CNC machine tool, and when the predicted remaining service life of the CNC machine tool is not lower than a preset threshold, the system automatically issues an early warning to prompt maintenance.

[0127] like Figure 3 As shown, it is a structural schematic diagram of the reliability life prediction system of the low-power frequency conversion system provided in the embodiment of the present application. The reliability life prediction system of the low-power frequency conversion system provided in the embodiment of the present application includes: a module for collecting CNC machine tool reliability life prediction data, a CNC machine tool reliability life prediction data analysis module, a comprehensive analysis module and a module for optimizing and adjusting the accuracy of CNC machine tool life prediction: a module for collecting CNC machine tool reliability life prediction data: used for collecting and processing CNC machine tool reliability life prediction data; a CNC machine tool reliability life prediction data analysis module: used for analyzing CNC machine tool reliability life prediction data, obtaining a CNC machine tool life prediction data quality reliability evaluation index and obtaining a CNC machine tool life prediction signal quality evaluation index; ... Analysis module: used for comprehensive analysis to obtain the accuracy evaluation index of CNC machine tool life prediction data; optimization and adjustment of CNC machine tool life prediction accuracy module: used for comparing and analyzing the CNC machine tool life prediction data quality reliability evaluation index with the first threshold of the CNC machine tool life prediction data quality reliability evaluation index, and optimizing the CNC machine tool life prediction data quality reliability method; comparing and analyzing the CNC machine tool life prediction signal quality evaluation index with the second threshold of the CNC machine tool life prediction signal quality evaluation index, and optimizing and adjusting the CNC machine tool life prediction signal quality method; comparing and analyzing the CNC machine tool life prediction data accuracy evaluation index with the comprehensive threshold of the CNC machine tool life prediction data accuracy evaluation index, and optimizing and adjusting the CNC machine tool life prediction accuracy method.

[0128] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0129] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0130] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0131] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0132] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0133] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A reliability life prediction method for a low-power frequency conversion system, characterized in that: The following steps are involved: Collect and process CNC machine tool reliability life prediction data; Analyze the reliability life prediction data of CNC machine tools, obtain the quality reliability evaluation index of CNC machine tool life prediction data and obtain the quality evaluation index of CNC machine tool life prediction signal; Comprehensive analysis yields the CNC machine tool life prediction data accuracy evaluation index; Compare and analyze the reliability evaluation index of CNC machine tool life prediction data quality with the first threshold of CNC machine tool life prediction data quality reliability evaluation index, and optimize the reliability method of CNC machine tool life prediction data quality; Compare and analyze the CNC machine tool life prediction signal quality evaluation index with the second threshold of the CNC machine tool life prediction signal quality evaluation index, and optimize and adjust the CNC machine tool life prediction signal quality method; The accuracy evaluation index of CNC machine tool life prediction data is compared and analyzed with the comprehensive threshold of CNC machine tool life prediction data accuracy evaluation index, and the CNC machine tool life prediction accuracy method is optimized and adjusted.

2. The reliability life prediction method of a low-power frequency conversion system according to claim 1, characterized in that: The specific steps of collecting and processing the reliability life prediction data of CNC machine tools are as follows: Collect the original data of reliability life prediction of CNC machine tools through sensor equipment; The original data of reliability life prediction of CNC machine tools are cleaned and denoised to obtain reliability life prediction data of CNC machine tools, wherein the reliability life prediction data of CNC machine tools includes quality reliability data of life prediction data of CNC machine tools and quality data of life prediction signal of CNC machine tools.

3. The reliability life prediction method of a low-power frequency conversion system according to claim 1 is characterized in that: The specific steps of obtaining the quality reliability evaluation index of CNC machine tool life prediction data are as follows: The electromagnetic wave intensity at the preset CNC machine tool life prediction data quality reliability time detection point is obtained through the electromagnetic interference detector; The vibration amplitude of the preset CNC machine tool life prediction data quality reliability time detection point is obtained through the vibration sensor; The maximum temperature of the CNC machine tool in the preset CNC machine tool life prediction data quality reliability time detection period is obtained through the thermocouple; The minimum temperature of the CNC machine tool in the preset CNC machine tool life prediction data quality reliability time detection period is obtained through the thermocouple; When the machine tool is not working, the output value of the sensor is measured as the reference zero point, and the drift rate of the CNC machine tool life prediction data at the preset CNC machine tool life prediction data quality reliability time detection point is obtained through a high-precision sensor, and the difference between the reference zero point and the data drift rate is taken as the zero point drift rate; The phase peak of the CNC machine tool life prediction signal in the preset CNC machine tool life prediction data quality reliability time detection section is obtained by a dynamic signal analyzer; The phase trough of the CNC machine tool life prediction signal in the preset CNC machine tool life prediction data quality reliability time detection section is obtained by a dynamic signal analyzer; The CNC machine tool life prediction data collection frequency of the preset CNC machine tool life prediction data quality reliability time detection point is obtained through the data acquisition card; The quality reliability data of the CNC machine tool life prediction data includes electromagnetic wave intensity, vibration amplitude, maximum temperature of the CNC machine tool, minimum temperature of the CNC machine tool, zero drift rate of the CNC machine tool life prediction data, phase peak of the CNC machine tool life prediction signal, phase trough of the CNC machine tool life prediction signal and acquisition frequency of the CNC machine tool life prediction data; According to the reliability data analysis of CNC machine tool life prediction data quality, the reliability evaluation index of CNC machine tool life prediction data quality is obtained.

4. The reliability life prediction method of a low-power frequency conversion system according to claim 1, characterized in that: The specific steps of obtaining the quality evaluation index of the CNC machine tool life prediction signal are as follows: The electromagnetic wave intensity at the preset CNC machine tool life prediction signal quality time detection point is obtained by an electromagnetic field intensity meter; The vibration amplitude of the preset CNC machine tool life prediction signal quality time detection point is obtained through the vibration sensor; The maximum temperature of the CNC machine tool in the preset CNC machine tool life prediction signal quality time detection section is obtained by an infrared temperature sensor; The minimum temperature of the CNC machine tool in the preset CNC machine tool life prediction signal quality time detection section is obtained by an infrared temperature sensor; The phase peak of the CNC machine tool life prediction signal of the preset CNC machine tool life prediction signal quality time detection section is obtained by a dynamic signal analyzer; The phase trough of the CNC machine tool life prediction signal of the preset CNC machine tool life prediction signal quality time detection section is obtained by a dynamic signal analyzer; The power of the CNC machine tool life prediction input signal at a preset CNC machine tool life prediction signal quality time detection point is obtained by a power meter; The power of the output signal for predicting the life of a numerically controlled machine tool at a preset time detection point of the quality of the signal for predicting the life of a numerically controlled machine tool is obtained by a power meter; The background noise power of the preset CNC machine tool life prediction signal quality time detection point is obtained through a spectrum analyzer; The data transmission response time of the life prediction signal of the numerical control machine tool in the preset time detection section of the life prediction signal of the numerical control machine tool is obtained by a network analyzer; The CNC machine tool life prediction signal quality data includes electromagnetic wave intensity, vibration amplitude, CNC machine tool maximum temperature, CNC machine tool minimum temperature, CNC machine tool life prediction signal phase peak, CNC machine tool life prediction signal phase trough, CNC machine tool life prediction input signal power, CNC machine tool life prediction output signal power, background noise power and CNC machine tool life prediction data transmission response time; The quality evaluation index of CNC machine tool life prediction signal is obtained based on the quality data analysis of CNC machine tool life prediction signal.

5. The reliability life prediction method of a low-power frequency conversion system according to claim 1, characterized in that: The specific steps of obtaining the accuracy evaluation index of CNC machine tool life prediction data through comprehensive analysis are as follows: The life prediction data drift of the CNC machine tool in the preset CNC machine tool life prediction accuracy time detection period is obtained through the edge computing device; The accuracy evaluation index of CNC machine tool life prediction data is obtained by comprehensive analysis of the CNC machine tool life prediction data quality reliability evaluation index, CNC machine tool life prediction signal quality evaluation index and CNC machine tool life prediction data drift.

6. The reliability life prediction method of a low-power frequency conversion system according to claim 1, characterized in that: The specific steps of the method for optimizing the quality reliability of CNC machine tool life prediction data are as follows: If the reliability evaluation index of the quality of the life prediction data of the CNC machine tool is greater than or equal to the first threshold value of the reliability evaluation index of the quality of the life prediction data of the CNC machine tool, it is not necessary to optimize the reliability of the quality of the life prediction data of the CNC machine tool; If the CNC machine tool life prediction data quality reliability assessment index is lower than the first threshold value of the CNC machine tool life prediction data quality reliability assessment index, the corresponding adjustment plan in the reliability life prediction database is matched through the difference between the CNC machine tool life prediction data quality reliability assessment index and the first threshold value of the CNC machine tool life prediction data quality reliability assessment index.

7. The reliability life prediction method of a low-power frequency conversion system according to claim 1, characterized in that: The specific steps of the method for optimizing and adjusting the quality of CNC machine tool life prediction signal are as follows: If the quality evaluation index of the CNC machine tool life prediction signal is lower than or equal to the second threshold value of the quality evaluation index of the CNC machine tool life prediction signal, it is not necessary to optimize and adjust the quality of the CNC machine tool life prediction signal; If the CNC machine tool life prediction signal quality evaluation index is greater than the second threshold value of the CNC machine tool life prediction signal quality evaluation index, the corresponding adjustment plan in the reliability life prediction database is matched through the difference between the CNC machine tool life prediction signal quality evaluation index and the second threshold value of the CNC machine tool life prediction signal quality evaluation index.

8. The reliability life prediction method of a low-power frequency conversion system according to claim 1, characterized in that: The specific steps of the method for optimizing and adjusting the accuracy of CNC machine tool life prediction are as follows: Extracting the comprehensive threshold of the accuracy evaluation index of the life prediction data of the CNC machine tool from the reliability life prediction database, and comparing the accuracy evaluation index of the life prediction data of the CNC machine tool with the comprehensive threshold of the accuracy evaluation index of the life prediction data of the CNC machine tool; If the CNC machine tool life prediction data accuracy evaluation index is greater than or equal to the CNC machine tool life prediction data accuracy evaluation index comprehensive threshold, there is no need to optimize and adjust the CNC machine tool life prediction accuracy.

9. The reliability life prediction method of a low-power frequency conversion system according to claim 1, characterized in that: The method for optimizing and adjusting the accuracy of prediction of the life of a CNC machine tool further includes: If the accuracy assessment index of the CNC machine tool life prediction data is lower than the comprehensive threshold of the CNC machine tool life prediction data accuracy assessment index, the corresponding adjustment plan in the reliability life prediction database is matched through the difference between the CNC machine tool life prediction data accuracy assessment index and the comprehensive threshold of the CNC machine tool life prediction data accuracy assessment index.

10. The reliability life prediction system of small power frequency conversion system is characterized by: It includes a module for collecting CNC machine tool reliability life prediction data, a module for analyzing CNC machine tool reliability life prediction data, a comprehensive analysis module, and a module for optimizing and adjusting the accuracy of CNC machine tool life prediction: Module for collecting CNC machine tool reliability life prediction data: used to collect and process CNC machine tool reliability life prediction data; CNC machine tool reliability life prediction data analysis module: used to analyze the CNC machine tool reliability life prediction data, obtain the CNC machine tool life prediction data quality reliability evaluation index and obtain the CNC machine tool life prediction signal quality evaluation index; Comprehensive analysis module: used to comprehensively analyze and obtain the accuracy evaluation index of CNC machine tool life prediction data; Optimize and adjust the CNC machine tool life prediction accuracy module: used to compare and analyze the CNC machine tool life prediction data quality reliability evaluation index with the first threshold of the CNC machine tool life prediction data quality reliability evaluation index, and optimize the CNC machine tool life prediction data quality reliability method; compare and analyze the CNC machine tool life prediction signal quality evaluation index with the second threshold of the CNC machine tool life prediction signal quality evaluation index, and optimize and adjust the CNC machine tool life prediction signal quality method; compare and analyze the CNC machine tool life prediction data accuracy evaluation index with the comprehensive threshold of the CNC machine tool life prediction data accuracy evaluation index, and optimize and adjust the CNC machine tool life prediction accuracy method.

Images