Production line equipment intelligent management system for automobile part processing

Abstract

The invention belongs to the field of automobile part processing, relates to a data processing technology, and aims to solve the problem that a production line cannot be optimally controlled by combining process parameters and performance attenuation characteristics during equipment operation fatigue in the prior art, in particular to a production line equipment intelligent management system for automobile part processing. Comprising a production test module, a test analysis module, a production control module, a deep analysis module and a deep optimization module. The production test module is used for carrying out production test analysis on production line equipment and generating a plurality of test processes; according to the method, the optimization interval based on the effective process data is established, so that the parameter control range adaptively changes along with the operation state of the equipment, for example, when the effective process range is reduced due to equipment performance degradation, the optimization interval synchronously shrinks to prevent parameter setting from exceeding the current bearing capacity of the equipment; and quality abnormity caused by parameter overrun is avoided, and meanwhile, the operation cost of manually and repeatedly debugging the process parameters is reduced.

Description

Technical Field

[0001] This invention belongs to the field of automotive parts processing and involves data processing technology, specifically an intelligent management system for production line equipment used in automotive parts processing. Background Art

[0002] The intelligent management system for automotive parts processing production line equipment is a comprehensive solution integrating the Internet of Things, big data analysis, artificial intelligence, and automated control technologies. It aims to improve the production efficiency, product quality, and equipment management level of automotive parts manufacturing enterprises.

[0003] The invention patent with publication number CN116664699B discloses a data management system and method for an automobile production line. This system can perform standard calibration of target standard parts at standard workstations, determine the qualification of production line calibration at production line workstations, mark qualified target center data, and then perform production line verification and recording based on the target center data. However, this system cannot combine process parameters and the performance degradation characteristics of equipment during operation fatigue to optimize and control the production line, resulting in difficulty in controlling product quality.

[0004] In response to the above technical problems, this application proposes a solution. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent management system for production line equipment used in the processing of automotive parts, which solves the problem that existing technologies cannot optimize and control the production line by combining process parameters and the performance degradation characteristics of equipment during operation fatigue. The technical problem to be solved by this invention is: how to provide an intelligent management system for production line equipment used in automotive parts processing that can optimize and control the production line by combining process parameters and the performance degradation characteristics of equipment during operation fatigue.

[0006] The purpose of the present invention can be achieved through the following technical solutions: An intelligent management system for production line equipment used in automotive parts processing includes a production testing module, a test analysis module, a production control module, an in-depth analysis module, and an in-depth optimization module. The production testing module is used to perform production testing and analysis on production line equipment and generate several test processes. The test analysis module is used to process and analyze the test process of the production line equipment and mark the test process as invalid or valid. It generates an optimized dataset through the valid processes and sends the optimized dataset and the valid processes of the production line to the production control module and the deep analysis module, respectively. The deep analysis module is used to perform in-depth analysis of the effective processes of production line equipment: the effective processes are divided into several test periods, and the abnormal quality periods, abnormal loss periods, and abnormal energy consumption periods in the test periods are filtered; all abnormal quality periods, abnormal loss periods, and abnormal energy consumption periods are sent to the deep optimization module. The deep optimization module is used to perform deep optimization analysis on the production line equipment and obtain the critical dataset of the production line. The critical dataset is then sent to the production control module. Managers can set the maximum continuous running time of the production line based on their own needs using the critical dataset.

[0007] Furthermore, the specific process of conducting production testing and analysis on production line equipment includes: retrieving the adjustment range FWi of the process parameter i of the production equipment; randomly selecting a value from the adjustment range FWi as the setting value SZi of the process parameter i; sequentially setting the process parameter i of all production equipment in the production line to the setting value SZi; controlling the production line to run for L1 hours to obtain a test process; performing quality inspection on the automotive parts produced by the production line during the test process and obtaining the product qualification rate of the test process; then reselecting the setting value SZi and generating the test process again, and so on, until the number of test processes reaches L2.

[0008] Furthermore, the specific process for marking a test process as invalid or valid includes: comparing the product pass rate of the test process with a preset evaluation threshold; if the product pass rate is less than the evaluation threshold, the corresponding test process is marked as invalid; if the product pass rate is greater than or equal to the evaluation threshold, the corresponding test process is marked as valid.

[0009] Furthermore, the process of generating the optimized dataset for the production line includes: the maximum and minimum values ​​of the setting values ​​SZi corresponding to all effective processes for process parameter i constitute the optimization interval YHi of process parameter i; the optimized dataset of the production line is composed of the optimization intervals YHi of all process parameters i; after receiving the optimized dataset, the production control module controls the process parameter i according to the optimization interval YHi in the optimized dataset.

[0010] Furthermore, the screening process for abnormal quality periods, abnormal loss periods, and abnormal energy consumption periods includes: obtaining the pass value, loss value, and energy consumption value for each test period; comparing the pass value, loss value, and energy consumption value of each test period with preset pass thresholds, loss thresholds, and energy consumption thresholds respectively; marking test periods with pass values ​​less than the pass threshold as abnormal quality periods, marking test periods with loss values ​​greater than or equal to the loss threshold as abnormal loss periods, and marking test periods with energy consumption values ​​greater than or equal to the energy consumption threshold as abnormal energy consumption periods.

[0011] Furthermore, the pass rate is defined as the product pass rate produced during the test period, the loss rate is defined as the amount of raw material loss produced during the test period, and the energy consumption rate is defined as the amount of electrical energy consumed by the production line during the test period.

[0012] Furthermore, the specific process of the deep optimization module to perform deep optimization analysis on production line equipment includes: marking the test period numbers of the quality anomaly period, loss anomaly period, and energy consumption anomaly period in their respective effective processes as quality anomaly values, loss anomaly values, and energy consumption anomaly values, respectively; constructing a quality anomaly set from the quality anomaly values ​​of all effective processes, constructing a loss anomaly set from the loss anomaly values ​​of all effective processes, and constructing an energy consumption anomaly set from the energy consumption anomaly values ​​of all effective processes; cleaning the quality anomaly set, loss anomaly set, and energy consumption anomaly set to obtain the quality critical value, loss critical value, and energy consumption critical value; and constructing the critical dataset of the production line from the quality critical value, loss critical value, and energy consumption critical value.

[0013] Furthermore, the specific process of cleaning the quality anomaly set to obtain the quality critical value includes: calculating the variance of all elements in the quality anomaly set to obtain the concentration coefficient, comparing the concentration coefficient with a preset concentration threshold; if the concentration coefficient is greater than or equal to the concentration threshold, the largest and smallest elements in the quality anomaly set are removed, and the concentration coefficient is recalculated, and so on, until the concentration coefficient is less than the concentration threshold; if the concentration coefficient is less than the concentration threshold, the smallest element in the quality anomaly set is marked as the cleaning value, and the continuous test duration at the start of the test period corresponding to the cleaning value in the effective process is marked as the quality critical value; the specific process of cleaning the loss anomaly set and the energy consumption anomaly set is the same as the process of obtaining the quality critical value.

[0014] The present invention has the following beneficial effects: This application establishes an optimization interval based on effective process data, enabling the parameter control range to adapt to changes in the equipment's operating status. For example, when equipment performance deteriorates, causing the effective process range to shrink, the optimization interval shrinks synchronously to avoid setting parameters beyond the equipment's current capacity. This avoids quality anomalies caused by parameter overruns and reduces the operational costs of repeatedly manually adjusting process parameters. This application, by cleaning abnormal data sets, can accurately capture the performance inflection points of equipment at different operating stages, and establish a quantitative evaluation model of equipment fatigue state by combining time series analysis, thus solving the technical defect that static thresholds cannot adapt to the dynamic decay of equipment. This application can eliminate the interference of occasional abnormal data on equipment performance evaluation, accurately identify the starting point of quality deterioration during continuous equipment operation, and provide data support for setting the optimal operating time of production line equipment by establishing a multi-dimensional evaluation system of quality critical value, loss critical value and energy consumption critical value, thereby avoiding the problems of decreased pass rate and increased raw material loss caused by equipment fatigue operation. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a system block diagram of the present invention; Figure 2 This is a flowchart of the cleaning process of the present invention. Detailed Implementation

[0017] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] In existing technologies, automotive parts processing production line equipment management systems typically achieve production control based on fixed process parameters, lacking the ability to dynamically respond to performance degradation during equipment operation. For example, the invention patent with publication number CN116664699B achieves data management through standard calibration, but does not consider performance changes caused by continuous equipment operation. When the equipment experiences quality fluctuations due to fatigue, the system cannot adjust parameter settings in a timely manner, resulting in a decrease in product qualification rate and an increase in raw material loss.

[0019] like Figure 1 As shown, the intelligent management system for production line equipment used in automotive parts processing includes a production testing module, a test analysis module, and a production control module connected in sequence. The test analysis module is also communicatively connected to a deep analysis module, which in turn communicates with the production control module through a deep optimization module.

[0020] The production testing module is used to perform production testing analysis on production line equipment: it retrieves the adjustment range FWi of the process parameter i of the production equipment, randomly selects a value from the adjustment range FWi as the setting value SZi of the process parameter i, sets the process parameter i of all production equipment in the production line to the setting value SZi in sequence, controls the production line to run for L1 hours to obtain a test process, performs quality inspection on the automotive parts produced by the production line during the test process and obtains the product qualification rate of the test process, then reselects the setting value SZi and generates the test process again, and so on, until the number of test processes reaches L2.

[0021] Here, the adjustment range FWi of process parameter i refers to the upper and lower limits of process parameter i that the production equipment is allowed to adjust. This range can be determined through the equipment technical manual or historical operating data, and is used to define the safety boundary for parameter adjustment. The setting value SZi refers to a specific value of process parameter i randomly selected from the adjustment range, for example, by using a computer algorithm to generate random numbers. Its purpose is to cover different possibilities within the parameter range to comprehensively test production line performance. The test process is generated by controlling the production line to run for a fixed duration L1, such as 2 hours or 4 hours, to simulate production states under different parameter combinations.

[0022] Specifically, production test analysis is achieved by systematically adjusting process parameters and recording the results. First, for each process parameter i, a setpoint SZi is randomly selected from its adjustment range FWi, and this value is applied sequentially to the production line equipment. Then, the production line runs continuously for L1 hours under the set parameters, for example, collecting production data in real time during the operation. After the test is completed, the parts produced on the production line are subjected to quality inspection, and the product pass rate for this test process is calculated. This process is repeated, with the setpoint SZi being reselected each time, until the accumulated number of test processes reaches a preset value L2, for example, L2 could be 10 or 20 times. This forms a test dataset covering different parameter combinations, providing a foundation for subsequent analysis.

[0023] The test analysis module is used to process and analyze data during the testing process of production line equipment: it compares the product pass rate of the test process with a preset evaluation threshold; if the product pass rate is less than the evaluation threshold, the corresponding test process is marked as invalid; if the product pass rate is greater than or equal to the evaluation threshold, the corresponding test process is marked as valid; the maximum and minimum values ​​of the setting values ​​SZi corresponding to all valid processes of process parameter i constitute the optimization interval YHi of process parameter i; the optimization interval YHi of all process parameter i constitutes the optimized dataset of the production line, and the optimized dataset and valid processes of the production line are sent to the production control module and the deep analysis module respectively. After receiving the optimized dataset, the production control module controls the process parameter i according to the optimization interval YHi in the optimized dataset.

[0024] The product qualification rate refers to the proportion of qualified products produced during the testing process to the total output of that process. This can be calculated statistically through sampling inspection or full inspection, and is used to quantify the quality output level of the testing process. The evaluation threshold is a pre-set benchmark value for the qualification rate, which can be set based on historical production data or industry standards, and is used to screen out effective testing processes that meet basic quality requirements.

[0025] Specifically, after a testing process is completed on the production line equipment, the number of qualified automotive parts produced during that process needs to be counted, and the corresponding product pass rate needs to be calculated. For example, when the evaluation threshold is set to 95%, if the product pass rate for a certain testing process is 93%, the process is deemed invalid and excluded from subsequent analysis; if the pass rate reaches 96%, it is marked as a valid process and included in the optimization dataset. Thus, abnormal process parameter combinations corresponding to invalid processes are automatically filtered out, preventing low-quality data from interfering with subsequent in-depth analysis and optimization control.

[0026] The optimization interval YHi refers to the boundary range of the actual operating value of process parameter i during effective testing. Specifically, it can be determined by statistically analyzing the extreme values ​​of the set values ​​during the effective testing process, for example, by dynamically updating the extreme value range using a sliding window algorithm. This interval reflects the controllable range of process parameters under stable equipment operating conditions, avoiding product quality fluctuations due to parameter exceeding limits.

[0027] The optimized dataset refers to a collection that integrates all process parameter optimization ranges. It can be stored in matrix or database form, for example, by establishing a mapping table between process parameters and their corresponding optimization ranges. This dataset provides a baseline range for parameter adjustments in production control, ensuring that equipment operation always remains within a safe range validated by the effective process.

[0028] Specifically, after the effective process screening is completed, the effective setting values ​​corresponding to each process parameter are extracted and sorted. The maximum and minimum values ​​are taken to form a closed interval as the optimization interval for that parameter. The optimization intervals of all process parameters are summarized to form a structured dataset, which is then encapsulated in JSON format and transmitted to the production control module. After parsing this dataset, the production control module limits the real-time adjustment range of the process parameters to the corresponding optimization interval. For example, when the current value of parameter i exceeds the YHi range, it is automatically corrected to the interval boundary value.

[0029] The deep analysis module is used to perform in-depth analysis of the effective processes of production line equipment: It divides the effective processes into several test periods, obtaining the pass rate, loss rate, and energy consumption rate for each test period. The pass rate is the product pass rate produced within the test period, the loss rate is the amount of raw material loss produced within the test period, and the energy consumption rate is the electrical energy consumption of the production line within the test period. The pass rate, loss rate, and energy consumption rate of each test period are compared with preset pass thresholds, loss thresholds, and energy consumption thresholds, respectively. Test periods with pass rates less than the pass threshold are marked as quality anomaly periods, test periods with loss rates greater than or equal to the loss threshold are marked as loss anomaly periods, and test periods with energy consumption rates greater than or equal to the energy consumption threshold are marked as energy consumption anomaly periods. All quality anomaly periods, loss anomaly periods, and energy consumption anomaly periods are sent to the deep optimization module.

[0030] Specifically, during the operation of the production line equipment, the pass / fail value, loss value, and energy consumption value for each testing period are acquired in real time. When the pass / fail value is lower than the preset pass / fail threshold, it indicates that there may be quality fluctuations due to decreased equipment performance or improper process parameter settings during that period, and is therefore marked as a quality abnormality period. When the loss value exceeds the preset loss threshold, it indicates that there may be resource waste due to increased equipment wear or reduced raw material processing efficiency during that period, and is therefore marked as a loss abnormality period. When the energy consumption value exceeds the preset energy consumption threshold, it indicates that there may be excessive energy consumption due to abnormal equipment load or failure of energy management strategies during that period, and is therefore marked as an energy consumption abnormality period. Through the above screening process, abnormal periods in the operation of the production line can be accurately identified.

[0031] During production line equipment operation, each testing period is divided into fixed time units, such as 15 minutes or 1 hour. The pass / fail value is generated by real-time statistics of the ratio of the total number of parts produced to the number of parts that pass quality inspection within that period. When this value falls below a preset threshold, a quality anomaly warning is triggered. The waste value is calculated by comparing the actual input of raw materials with the theoretical consumption during that period. When the difference exceeds the allowable range, it is judged as an abnormality in raw material waste. The energy consumption value is obtained by collecting electricity metering data from the main circuit of the production line during that period. When the cumulative energy consumption exceeds the economic indicators, it is marked as an energy consumption anomaly. These three dimensions of quantitative data together constitute a dynamic monitoring system for the production line's operating status, providing data support for subsequent screening of abnormal periods.

[0032] The deep optimization module is used to perform in-depth optimization analysis on production line equipment: the test period numbers of the quality abnormal period, loss abnormal period, and energy consumption abnormal period in their respective effective processes are marked as quality abnormal values, loss abnormal values, and energy consumption abnormal values, respectively; a quality abnormal set is formed by the quality abnormal values ​​of all effective processes, a loss abnormal set is formed by the loss abnormal values ​​of all effective processes, and an energy consumption abnormal set is formed by the energy consumption abnormal values ​​of all effective processes; the quality abnormal set, loss abnormal set, and energy consumption abnormal set are cleaned to obtain the quality critical value, loss critical value, and energy consumption critical value. like Figure 2 As shown, the specific process of cleaning the quality anomaly set to obtain the quality critical value includes: calculating the variance of all elements in the quality anomaly set to obtain the concentration coefficient, comparing the concentration coefficient with a preset concentration threshold; if the concentration coefficient is greater than or equal to the concentration threshold, the largest and smallest elements in the quality anomaly set are removed, and the concentration coefficient is recalculated, and so on, until the concentration coefficient is less than the concentration threshold; if the concentration coefficient is less than the concentration threshold, the smallest element in the quality anomaly set is marked as the cleaning value, and the continuous test duration at the start of the test period corresponding to the cleaning value in the effective process is marked as the quality critical value; the specific process of cleaning the loss anomaly set and the energy consumption anomaly set is the same as the process of obtaining the quality critical value; the quality critical value, loss critical value, and energy consumption critical value constitute the critical dataset of the production line, and the critical dataset is sent to the production control module; the management personnel set the maximum continuous running time of the production line according to their own needs through the critical dataset.

[0033] Quality outliers refer to the test period sequence numbers corresponding to the quality anomaly periods within the valid process. This can be achieved using timestamps or sequence numbers, and is used to pinpoint the temporal location of the anomaly. Cleaning involves filtering out outlier elements with excessive dispersion in the dataset through variance calculation. This can be achieved by iteratively removing the maximum and minimum values ​​to eliminate the interference of extreme data on the critical value calculation. The quality critical value refers to the continuous test duration at the start time of the test period corresponding to the minimum element in the cleaned set. This can be achieved using a time accumulation algorithm and is used to characterize the stable operating limit of the equipment in terms of quality.

[0034] Specifically, each test period in the effective process is assigned a unique sequence number. When an anomaly in quality, loss, or energy consumption is detected, the sequence number of that period is recorded as the corresponding outlier. Outliers from all effective processes are aggregated into three independent datasets. The central tendency of the data distribution is determined by variance calculation. If the variance exceeds a preset threshold, the data dispersion is gradually reduced by iteratively eliminating the maximum and minimum values ​​until the variance meets the requirements. The continuous test duration corresponding to the smallest retained outlier is extracted as the critical value. This critical value reflects the longest duration for which the equipment maintains stable operation under a specific dimension. By integrating the critical values ​​from the three dimensions, the critical dataset provides data support for the dynamic adjustment of the continuous operating time of the production line.

[0035] During production line operation, the test period numbers recorded in the quality anomaly set may contain interference data caused by occasional anomalies or equipment malfunctions. By calculating the variance, a concentration factor can be obtained to quantify the degree of concentration of the anomaly periods. When the concentration factor exceeds a preset threshold, it indicates that the anomaly data is too dispersed, and iterative elimination of maximum and minimum values ​​is necessary to remove the anomaly interference.

[0036] The intelligent management system for production line equipment used in automotive parts processing performs production testing and analysis on the production line equipment during operation, generating L2 test processes. It processes and analyzes the test processes, marking them as invalid or valid processes. It conducts in-depth analysis of the valid processes: dividing the valid processes into several test periods, filtering out periods with abnormal quality, abnormal losses, and abnormal energy consumption, and then performing in-depth optimization analysis on the production line equipment to obtain the critical dataset.

[0037] The above content is merely an example and explanation of the structure of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the scope of protection of the present invention.

[0038] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0039] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent management system for production line equipment used in automotive parts processing, characterized in that, It includes a production testing module, a test analysis module, a production control module, an in-depth analysis module, and an in-depth optimization module; The production testing module is used to perform production testing and analysis on production line equipment and generate several test processes. The test analysis module is used to process and analyze the test process of the production line equipment and mark the test process as invalid or valid. It generates an optimized dataset through the valid processes and sends the optimized dataset and the valid processes of the production line to the production control module and the deep analysis module, respectively. The deep analysis module is used to perform in-depth analysis of the effective processes of production line equipment: the effective processes are divided into several test periods, and the abnormal quality periods, abnormal loss periods, and abnormal energy consumption periods in the test periods are filtered; all abnormal quality periods, abnormal loss periods, and abnormal energy consumption periods are sent to the deep optimization module. The deep optimization module is used to perform deep optimization analysis on the production line equipment and obtain the critical dataset of the production line, and then send the critical dataset to the production control module. Managers set the maximum continuous operating time of the production line based on their own needs using critical datasets.

2. The intelligent management system for production line equipment in automotive parts processing according to claim 1, characterized in that, The specific process of production testing and analysis of production line equipment includes: retrieving the adjustment range FWi of the process parameter i of the production equipment; randomly selecting a value from the adjustment range FWi as the setting value SZi of the process parameter i; sequentially setting the process parameter i of all production equipment in the production line to the setting value SZi; controlling the production line to run for L1 hours to obtain a test process; performing quality inspection on the automotive parts produced by the production line during the test process and obtaining the product qualification rate of the test process; then reselecting the setting value SZi and generating the test process again, and so on, until the number of test processes reaches L2.

3. The intelligent management system for production line equipment in automotive parts processing according to claim 2, characterized in that, The specific process for marking a test process as invalid or valid includes: comparing the product pass rate of the test process with a preset evaluation threshold; if the product pass rate is less than the evaluation threshold, the corresponding test process is marked as invalid; if the product pass rate is greater than or equal to the evaluation threshold, the corresponding test process is marked as valid.

4. The intelligent management system for production line equipment in automotive parts processing according to claim 3, characterized in that, The process of generating the production line optimization dataset includes: the maximum and minimum values ​​of the setting values ​​SZi corresponding to all effective processes of process parameter i constitute the optimization interval YHi of process parameter i; the optimization interval YHi of all process parameters i constitutes the production line optimization dataset; after receiving the optimization dataset, the production control module controls the process parameter i according to the optimization interval YHi in the optimization dataset.

5. The intelligent management system for production line equipment in automotive parts processing according to claim 4, characterized in that, The screening process for quality anomaly periods, loss anomaly periods, and energy consumption anomaly periods includes: obtaining the pass value, loss value, and energy consumption value for each test period; comparing the pass value, loss value, and energy consumption value of each test period with preset pass thresholds, loss thresholds, and energy consumption thresholds respectively; marking test periods with pass values ​​less than the pass threshold as quality anomaly periods, marking test periods with loss values ​​greater than or equal to the loss threshold as loss anomaly periods, and marking test periods with energy consumption values ​​greater than or equal to the energy consumption threshold as energy consumption anomaly periods.

6. The intelligent management system for production line equipment in automotive parts processing according to claim 5, characterized in that, The pass rate is the product pass rate produced during the test period, the loss rate is the amount of raw material loss produced during the test period, and the energy consumption rate is the amount of electricity consumed by the production line during the test period.

7. The intelligent management system for production line equipment in automotive parts processing according to claim 6, characterized in that, The specific process of the deep optimization module for deep optimization analysis of production line equipment includes: marking the test period numbers of the quality anomaly period, loss anomaly period, and energy consumption anomaly period in their respective effective processes as quality anomaly values, loss anomaly values, and energy consumption anomaly values, respectively; constructing a quality anomaly set from the quality anomaly values ​​of all effective processes, a loss anomaly set from the loss anomaly values ​​of all effective processes, and an energy consumption anomaly set from the energy consumption anomaly values ​​of all effective processes; cleaning the quality anomaly set, loss anomaly set, and energy consumption anomaly set to obtain the quality critical value, loss critical value, and energy consumption critical value; and constructing the critical dataset of the production line from the quality critical value, loss critical value, and energy consumption critical value.

8. The intelligent management system for production line equipment in automotive parts processing according to claim 7, characterized in that, The specific process for cleaning the quality anomaly set to obtain the quality critical value includes: calculating the variance of all elements in the quality anomaly set to obtain the concentration coefficient; comparing the concentration coefficient with a preset concentration threshold; if the concentration coefficient is greater than or equal to the concentration threshold, the largest and smallest elements in the quality anomaly set are removed, and the concentration coefficient is recalculated, and so on, until the concentration coefficient is less than the concentration threshold; if the concentration coefficient is less than the concentration threshold, the smallest element in the quality anomaly set is marked as the cleaning value, and the continuous test duration at the start of the test period corresponding to the cleaning value in the effective process is marked as the quality critical value; the specific process for cleaning the loss anomaly set and the energy consumption anomaly set is the same as the process for obtaining the quality critical value.

Images