Online monitoring method and system for automobile industrial spare and accessory parts

Abstract

The invention relates to the technical field of on-line monitoring, in particular to an automobile industry part on-line monitoring method and system, and the method comprises the following steps: based on collected part production line data, extracting the assembly data flow of parts, carrying out the quality screening of the real-time assembly data flow, eliminating the noise and invalid data in the data flow, and carrying out the real-time quality screening of the real-time assembly data flow; and obtaining the screened assembly data. According to the method, early recognition and early warning of abnormal conditions in the production process are achieved by analyzing and predicting potential production deviation in real time, data points deviating from a standard process can be accurately recognized and rapidly adjusted by comprehensively evaluating assembly data and a production trend, production quality and improvement of efficiency are ensured, and the production efficiency is improved. Through continuous monitoring and analysis of key performance indexes, machine setting is optimized, the stability of the production process is ensured, meanwhile, resource waste is remarkably reduced, maximization of cost benefits is achieved, and control over a production line is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of online monitoring technology, and in particular to an online monitoring method and system for spare parts in the automobile industry. Background Art

[0002] The field of online monitoring technology mainly involves the use of various sensors, computer networks and data processing technologies to monitor and control the status of equipment, environment or system in real time. This technology is widely used in many industries. Online monitoring systems can provide real-time data, enabling operators to respond quickly to potential problems or abnormal situations, optimize maintenance plans, and improve overall operational efficiency. Such systems usually include key functions such as data collection, data transmission, data processing and display to ensure the accuracy and real-time nature of information.

[0003] In the field of automobile manufacturing and maintenance, technologies and methods are used to track and manage the status and performance of spare parts in real time through online monitoring systems. The main purpose of such systems is to ensure that the quality and performance of spare parts meet standards during production and use, and to detect faults or wear in a timely manner, thereby reducing downtime and improving automobile reliability and safety. Through this method, automobile manufacturers and maintenance teams can more effectively monitor the service life of parts and predict maintenance needs, thereby reducing costs and improving customer satisfaction.

[0004] Existing technologies lack in-depth predictive capabilities and sensitivity to subtle changes in the production process. They focus more on data collection and display, lack in-depth data analysis and trend-based early warning mechanisms. This limitation leads to delayed response times to potential problems in the production process, and sometimes quality problems cannot be avoided. Traditional monitoring systems do not fully consider the actual impact of environmental factors on production, resulting in untimely production adjustments when the environment changes suddenly, which in turn affects production efficiency and product quality. The lack of flexible adjustment mechanisms and forward-looking analysis makes it impossible to optimize the production process in real time, thereby limiting the improvement of production capacity and the reduction of costs. Summary of the invention

[0005] In order to solve the problems of the existing technology, which lacks in-depth prediction capabilities and sensitivity to subtle changes in the production process, the existing technology focuses more on data collection and display, lacks in-depth analysis of data and trend-based early warning mechanisms. This limitation leads to delayed response time for potential problems in the production process, and sometimes quality problems cannot be avoided. Traditional monitoring systems do not fully consider the actual impact of environmental factors on production, resulting in untimely production adjustments when the environment changes suddenly, which in turn affects production efficiency and product quality. The lack of flexible adjustment mechanisms and forward-looking analysis makes it impossible to optimize the production process in real time, thereby limiting the improvement of production capacity and the reduction of costs. The embodiment of the present invention provides an online monitoring method and system for automotive industry spare parts. The technical solution is as follows:

[0006] On the one hand, a method for online monitoring of automotive industry spare parts is provided, comprising the following steps:

[0007] S1: Based on the collected spare parts production line data, the assembly data stream of the spare parts is extracted, the real-time assembly data stream is quality screened, the noise and invalid data in the data stream are removed, and the screened assembly data is obtained;

[0008] S2: Based on the screened assembly data, the quality and assembly cycle of the target parts are extracted, the data points that deviate from the normal production process are identified, and compared with the current production trend, potential production deviations are predicted, and production deviation warnings are obtained;

[0009] S3: Based on the production deviation warning, evaluate the abnormal trend of the spare parts production line, identify the factors affecting the production quality according to the abnormal trend, and analyze the production line status and potential problems with reference to the factors to obtain production abnormality monitoring data;

[0010] S4: Based on the production abnormality monitoring data, the production data of spare parts are collected in real time, the quality indicators of spare parts in the production process are continuously evaluated, and the quality indicators are analyzed to determine the key factors affecting the production efficiency and the quality of spare parts, and obtain a key performance list;

[0011] S5: Based on the key performance list, analyze the quality changes of spare parts, monitor the machine speed and production temperature settings, and continuously optimize the production monitoring process based on the monitoring data to obtain online monitoring optimization results.

[0012] On the other hand, the screened assembly data includes accuracy index, integrity rating, and effective data volume; the production deviation warning includes assembly delay warning, quality deviation mark, and periodic abnormality mark; the production abnormality monitoring data includes abnormality type, abnormality occurrence frequency, and related influencing components; the key performance list includes key mechanical efficiency, quality accuracy, and production line stability index; the online monitoring optimization results include reaction speed optimization results and monitoring sensitivity.

[0013] On the other hand, based on the collected spare parts production line data, the assembly data stream of spare parts is extracted, the real-time assembly data stream is quality screened, and the noise and invalid data in the data stream are removed to obtain the screened assembly data. The specific steps are as follows:

[0014] S101: Based on the collected spare parts production line data, the movement and position information of the spare parts on the production line is captured in real time, the movement trajectory data of the spare parts are analyzed item by item, the data is segmented and classified according to the time axis, the feature values ​​related to the position are extracted, the specific position of the spare parts in the production stage is recorded, and the recording results are formatted to obtain the assembly data set;

[0015] S102: Based on the assembly data set, timestamp verification is performed on the accessed data batches, and data with time deviation exceeding a threshold is marked by comparing the time node with the recorded time interval of the production stage, and signal strength is checked for the marked data, and abnormal timestamp data is eliminated by comparing the signal curve fluctuation with the stable interval parameter to obtain a data stream cleaning record;

[0016] S103: Based on the data flow cleaning records, the data are compared with the spare parts quality standards, and the correspondence between the data fields and the quality standards is analyzed one by one, and the missing fields and the numerical records that do not meet the range are detected. The field integrity and numerical compliance of the eliminated data are re-checked to obtain the filtered assembly data.

[0017] On the other hand, based on the screened assembly data, the quality and assembly cycle of the target parts are extracted, the data points that deviate from the normal production process are identified, and compared with the current production trend to predict potential production deviations. The specific steps for obtaining production deviation warnings are as follows:

[0018] S201: Based on the screened assembly data, extract the quality and assembly cycle of spare parts, perform time node analysis, locate the assembly sequence, and organize the assembly data and cycle information according to the assembly sequence to obtain assembly cycle information;

[0019] S202: Based on the assembly cycle information, the quality parameters are compared with the standard quality, key values ​​and time points of the abnormal range are extracted, the location of the deviation data is marked, and an abnormal data directory is obtained;

[0020] S203: Based on the abnormal data catalog, cross-analysis is performed with the current production trend, the frequency of abnormal data occurrence is counted, the abnormal data changes are analyzed, and deviation parameters are marked to obtain a production deviation warning.

[0021] On the other hand, based on the production deviation warning, the abnormal trend of the spare parts production line is evaluated, the factors affecting the production quality are identified according to the abnormal trend, and the production line status and potential problems are analyzed with reference to the factors. The specific steps of obtaining the production abnormality monitoring data are as follows:

[0022] S301: Based on the production deviation warning, analyze the abnormal trend in the warning data, extract the frequency distribution of abnormal parameters by classifying the time nodes, screen the fluctuation range of abnormal parameters, and superimpose trend curves to analyze the correlation between trends and changes in characteristic points to obtain abnormal trend information;

[0023] S302: Based on the abnormal trend information, extract influencing factors associated with production quality, screen the influencing range and action relationship, analyze the action intensity in the abnormal trend, extract key driving parameters and classify them, and obtain a list of quality influencing factors;

[0024] S303: Based on the list of quality influencing factors, analyze the nodes of the production line operation status, extract key values, screen the abnormal intervals and fluctuation ranges in the operation status, identify the distribution areas and variation ranges of potential problems, and obtain production abnormality monitoring data.

[0025] On the other hand, the extraction and production quality related influencing factors are as follows:

[0026]

[0027] Calculate the sum of influencing factors Z;

[0028] In the formula, α i represents the criticality coefficient of the i-th influencing factor, X i represents the i-th original data point, β i represents the attenuation coefficient of the i-th influencing factor, t represents the time factor, and n represents the total number of influencing factors.

[0029] On the other hand, based on the production abnormality monitoring data, the production data of spare parts is collected in real time, the quality indicators of spare parts in the production process are continuously evaluated, and the quality indicators are analyzed to determine the key factors affecting production efficiency and spare parts quality. The steps of obtaining the key performance list are as follows:

[0030] S401: Based on the production abnormality monitoring data, real-time data of the spare parts production process is collected, the production links are analyzed, parameter values ​​of time nodes are extracted, the data integrity of the production stage is verified, and the production data is reorganized in chronological order to obtain a real-time data record set;

[0031] S402: Based on the real-time data record set, extract the quality data of spare parts in the production process, analyze the corresponding relationship with the production time node, screen the abnormal range of quality data, and compare it with the quality reference standard, mark the production stage associated with the abnormal quality, and obtain the quality abnormality result;

[0032] S403: Based on the abnormal quality results, key factors affecting production efficiency and spare parts quality are screened, the impact areas of abnormal quality and production links are analyzed, the impact range is statistically analyzed, and a key performance list is obtained.

[0033] On the other hand, the quality data of spare parts in the production process is extracted according to the formula:

[0034]

[0035] Get the quality data Q of the i-th component i ;

[0036] In the formula, δ i represents the data extraction coefficient associated with component i, D i represents the original data of spare part i obtained from the real-time data record set, λ i represents the environmental factor adjustment coefficient, S i represents the environmental sensitivity index, indicating the degree of response of the i-th component to environmental changes, γ i Represents the power coefficient of environmental factors, used to adjust the environmental sensitivity index S i degree of impact.

[0037] On the other hand, based on the key performance list, the quality changes of spare parts are analyzed, the machine speed and production temperature settings are monitored, and the production monitoring process is continuously optimized according to the monitoring data. The steps to obtain the online monitoring optimization results are as follows:

[0038] S501: Based on the key performance list, analyze the quality changes of spare parts, extract the quality parameters corresponding to the time nodes, screen the key parameter values, and identify the time period of parameter fluctuation and the abnormal value interval to obtain quality change information;

[0039] S502: Based on the quality change information, monitor the machine speed and production temperature parameters, extract the associated data between the operating parameters and the production links, filter the abnormal operating parameter values, and locate the production link corresponding to the abnormal point to obtain the equipment status monitoring log;

[0040] S503: Based on the equipment status monitoring log, analyze the correlation range of the operating parameters in the production process, extract the corresponding relationship with the production stage, adjust the time interval and value range of the operating parameters, optimize the distribution characteristics of the operating parameters in the monitoring process, and obtain online monitoring optimization results.

[0041] On the other hand, an online monitoring system for automobile industry spare parts is provided, which is applied to an online monitoring method for automobile industry spare parts, including:

[0042] The data quality control module extracts the assembly data stream of the parts based on the collected data of the parts production line, performs quality screening on the real-time assembly data stream, removes noise and invalid data in the data stream, and obtains the screened assembly data;

[0043] The deviation warning module extracts the quality and assembly cycle of target parts based on the screened assembly data, identifies data points that deviate from the normal production process, and compares them with the current production trend to predict potential production deviations and obtain production deviation warnings;

[0044] The abnormality monitoring module evaluates the abnormality trend of the spare parts production line based on the production deviation warning, identifies the factors affecting the production quality according to the abnormality trend, and analyzes the production line status and potential problems with reference to the factors to obtain production abnormality monitoring data;

[0045] Based on the production abnormality monitoring data, the optimization control module collects the production data of spare parts in real time, continuously evaluates the quality indicators of spare parts in the production process, analyzes the quality indicators, determines the key factors affecting production efficiency and spare parts quality, monitors machine speed and production temperature settings, continuously optimizes the production monitoring process, and obtains online monitoring optimization results.

[0046] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0047] By analyzing and predicting potential production deviations in real time, early identification and early warning of abnormal situations in the production process are achieved. By comprehensively evaluating assembly data and production trends, data points that deviate from standard processes can be accurately identified and quickly adjusted to ensure improved production quality and efficiency. Through continuous monitoring and analysis of key performance indicators, machine settings are optimized to ensure the stability of the production process, while significantly reducing resource waste, maximizing cost-effectiveness, and enhancing control over the production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 It is a main step flow chart of the present invention;

[0050] Figure 2 is a flow chart of the steps of S1 of the present invention;

[0051] Figure 3 is a flow chart of the steps of S2 of the present invention;

[0052] Figure 4 is a flow chart of the steps of S3 of the present invention;

[0053] Figure 5 is a flow chart of the steps of S4 of the present invention;

[0054] Figure 6 is a flow chart of the steps of S5 of the present invention;

[0055] Figure 7 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0056] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0057] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0058] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0059] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0060] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0061] The embodiment of the present invention provides an online monitoring method for automobile industry parts and components, such as Figure 1 As shown, the following steps are included:

[0062] S1: Based on the collected spare parts production line data, the assembly data stream of the spare parts is extracted, the real-time assembly data stream is quality screened, the noise and invalid data in the data stream are removed, and the screened assembly data is obtained;

[0063] Assembly data specifically refers to assembly time data, quality control data, operating parameter data, parts identification data, and resource consumption data;

[0064] S2: Based on the screened assembly data, the quality and assembly cycle of the target parts are extracted, the data points that deviate from the normal production process are identified, and compared with the current production trend to predict potential production deviations and obtain production deviation warnings;

[0065] S3: Based on production deviation warning, evaluate the abnormal trend of spare parts production line, identify the factors affecting production quality according to the abnormal trend, and analyze the production line status and potential problems with reference to the factors to obtain production abnormality monitoring data;

[0066] S4: Based on the production abnormality monitoring data, the production data of spare parts is collected in real time, the quality indicators of spare parts in the production process are continuously evaluated, and the quality indicators are analyzed to determine the key factors affecting production efficiency and spare parts quality, and obtain a key performance list;

[0067] S5: Based on the key performance list, analyze the quality changes of spare parts, monitor machine speed and production temperature settings, and continuously optimize the production monitoring process based on the monitoring data to obtain online monitoring optimization results.

[0068] The screened assembly data includes accuracy indicators, integrity ratings, and effective data volume. Production deviation warnings include assembly delay warnings, quality deviation marks, and periodic abnormality marks. Production abnormality monitoring data includes abnormality types, abnormality occurrence frequencies, and associated influencing components. The key performance list includes key mechanical efficiency, quality accuracy, and production line stability index. Online monitoring optimization results include response speed optimization results and monitoring sensitivity.

[0069] like Figure 2 As shown, based on the collected spare parts production line data, the assembly data stream of spare parts is extracted, the quality of the real-time assembly data stream is screened, and the noise and invalid data in the data stream are removed to obtain the screened assembly data. The specific steps are:

[0070] S101: Based on the collected spare parts production line data, the movement and position information of the spare parts on the production line is captured in real time, the movement trajectory data of the spare parts are analyzed item by item, the data is segmented and classified according to the time axis, the feature values ​​related to the position are extracted, the specific position of the spare parts in the production stage is recorded, and the recording results are formatted to obtain the assembly data set;

[0071] First, each movement of spare parts is time-correlated and path-traced. The movement trajectory of spare parts is disassembled and processed by extracting the position signal parameters of spare parts such as signal node identification, signal strength and collection time interval. The trajectory data is divided into multiple continuous segments according to the time axis. In each segment of data, characteristic parameters such as the fluctuation range of signal strength, the time the spare parts stay at a certain node and the switching frequency between nodes are extracted. These characteristic parameters are called to judge the continuity of the trajectory, and the breakpoint trajectory is repaired by comparing the signal loss time interval with the preset time threshold. For data segments with incomplete or unstable signals, the trajectory path is readjusted, and position encoding is performed according to the sorted data trajectory. Finally, the assembly data set is output, which records the specific location information of spare parts at each stage of the production line.

[0072] S102: Based on the assembly data set, timestamp verification is performed on the received data batches. By comparing the time node with the recorded time interval of the production stage, the data with time deviation exceeding the threshold is marked, the signal strength of the marked data is checked, and the abnormal timestamp data is eliminated by comparing the signal curve fluctuation with the stable interval parameter to obtain the data flow cleaning record;

[0073] First, the start and end time of the production stage in each batch of data is extracted, and the time range of the assembly data is verified to be compliant by setting the time range threshold. The time information recorded in the assembly data is compared with the time range of the production stage, and the data with deviations exceeding the time threshold range is marked. The signal strength parameter curve is further extracted for the marked data, and the fluctuation amplitude and stable interval length of the signal are analyzed as the basis for judging whether the timestamp data is abnormal. The signal strength mean is compared with the normal fluctuation range, and the data segments with abnormal signal fluctuations are eliminated. For the data after elimination, the time period record is re-analyzed to see if there are any missed abnormal intervals. The rationality of the remaining data is verified by gradually adjusting the time marking rules, and finally a complete data stream cleaning record is cleaned up.

[0074] S103: Based on the data flow cleaning records, the data is compared with the spare parts quality standards, and the correspondence between the data fields and the quality standards is analyzed one by one, and the missing fields and the value records that do not meet the range are detected. The field integrity and value compliance of the eliminated data are re-checked to obtain the filtered assembly data;

[0075] The dimensions, weights, material properties and other fields in the assembly data are extracted and matched and checked item by item with the upper and lower limit parameters specified in the quality standards. For the missing fields, the data entry number is recorded and the field information before and after is analyzed. Supplementary judgments are made on the missing fields. For the field records that do not meet the quality standard range, their historical change records are further extracted and it is determined whether their change rate is within the allowable range of the standard. The records with abnormal or non-compliant fields are eliminated. For the eliminated data, the field integrity and compliance are rechecked one by one. The integrity and compliance of the field content are ensured through repeated comparisons, and the filtered assembly data is finally output.

[0076] like Figure 3 As shown in the figure, based on the screened assembly data, the quality and assembly cycle of the target parts are extracted, the data points that deviate from the normal production process are identified, and compared with the current production trend to predict potential production deviations. The specific steps for obtaining production deviation warnings are as follows:

[0077] S201: Based on the screened assembly data, the quality and assembly cycle of the parts are extracted, time node analysis is performed, the assembly sequence is located, and the assembly data and cycle information are sorted according to the assembly sequence to obtain assembly cycle information;

[0078] By analyzing the start time and end time fields in the assembly data, the assembly cycle is divided into multiple time nodes, and the assembly step number and spare part number associated with each time node are extracted. The assembly sequence of each spare part is located in combination with the assembly sequence table of the production line. The sorting of the assembly data records is adjusted according to the assembly sequence, and the key time period information in the assembly cycle is extracted, such as the start time, stage conversion time and end time. The time nodes and the assembly sequence are formed into a multidimensional data table, and the time nodes are corrected in turn according to the assembly sequence. Unnecessary stagnation time in the assembly cycle is eliminated, and finally the complete assembly cycle information is sorted out.

[0079] Extract the quality and assembly cycle of spare parts and conduct time node analysis according to the formula:

[0080]

[0081] Get the assembly cycle time T;

[0082] In the formula, m represents the total number of assembly parts, which is used to indicate the total number of spare parts that need to be assembled, and a j represents the time required to assemble the jth component, the actual time required to assemble each component, and p j represents the corresponding production efficiency factor, the efficiency parameter that affects the assembly time of each component, λ is the time adjustment coefficient, θ j,j+1Represents the time interval adjustment between the jth and j+1th components, and j represents the serial number of the current assembly component.

[0083] In the actual production process, the assembly time is not only affected by the assembly time and production efficiency of each component, but also needs to consider the time interval between components in the continuous assembly process. The time interval θ j,j+1 It may be affected by factors such as workstation conversion, material handling, quality inspection, etc. The time adjustment coefficient λ can be used to adjust the impact of these interval times to more realistically reflect the time required for actual assembly;

[0084] Set the specific values ​​as follows:

[0085] Part 1: a1 = 30 minutes, p1 = 1.0;

[0086] Part 2: a2 = 45 minutes, p2 = 0.8;

[0087] Part 3: a3 = 20 minutes, p3 = 1.2;

[0088] The time interval adjustment factor λ = 1.5, the interval adjustment:

[0089] θ 1,2 =5 minutes;

[0090] θ 2,3 = 3 minutes;

[0091] The calculation formula is:

[0092] T=(30×1.0+45×0.8+20×1.2)+1.5×(5+3);

[0093] T = (30 + 36 + 24) + 1.5 × 8;

[0094] T = 90 + 12;

[0095] T = 102 minutes;

[0096] The total assembly cycle is 102 minutes. This calculation method simulates the actual production situation more accurately, provides useful insights into time management and process optimization, and makes production scheduling more efficient and adaptable.

[0097] S202: Based on the assembly cycle information, the quality parameters are compared with the standard quality, the key values ​​and time points of the abnormal range are extracted, the location of the deviation data is marked, and the abnormal data directory is obtained;

[0098] By extracting the spare parts numbers, assembly time nodes and related quality parameters in the assembly cycle information one by one, and checking the upper and lower limits of the quality parameters with the standard quality range in turn, the quality data that exceeds the standard range is extracted as abnormal value records. By locating the assembly time period corresponding to each abnormal value, the time point data and the corresponding assembly sequence position are extracted, and a complete abnormal value marking table is formed by combining the spare parts number and production line number. The abnormal data is sorted according to the time node, and the time point, assembly sequence position and related information of each abnormal data are sorted out, and finally the abnormal data directory is output.

[0099] S203: Based on the abnormal data catalog, cross-analyze with the current production trend, count the frequency of abnormal data, analyze the change of abnormal data, and mark the deviation parameters to obtain production deviation warning;

[0100] Cross-analyze the marked abnormal data with the current production trend information, extract the time node, production line number and assembly cycle information in the abnormal data directory, perform frequency statistics on the abnormal data according to the production stage, accumulate the abnormal frequency in the same production stage, and extract the deviation parameters and fluctuation range of the abnormal data. Compare the statistical results with the production stage parameters in the production trend record, analyze the time distribution and parameter changes of the abnormal data, annotate the deviation parameters and corresponding fluctuation trends of the data one by one, and organize the production deviation warning information in the production stage according to the deviation analysis records.

[0101] like Figure 4 As shown in the figure, based on the production deviation warning, the abnormal trend of the spare parts production line is evaluated, the factors affecting the production quality are identified according to the abnormal trend, and the production line status and potential problems are analyzed with reference to the factors. The specific steps to obtain the production abnormality monitoring data are as follows:

[0102] S301: Based on the production deviation warning, the abnormal trend in the warning data is analyzed, the frequency distribution of abnormal parameters is extracted by classifying the time nodes, the fluctuation range of abnormal parameters is screened, and the trend curve is superimposed to analyze the correlation between trends and the changes in characteristic points to obtain abnormal trend information;

[0103] Extract parameters related to time nodes in the warning data, such as the start time, duration and interval time of the anomaly, divide the warning data into different time periods through classification methods, statistically analyze the frequency distribution of abnormal parameters for each data segment and record the time concentration points of the anomaly, extract the numerical range of the abnormal parameters and filter out the part where the fluctuation exceeds the set range, superimpose these fluctuation parameters in chronological order, generate a trend change curve chart, and locate the characteristic points of trend changes by comparing the morphological changes of trend curves in different time periods, such as trend inflection points, maximum values ​​and minimum values, etc. By analyzing the relationship between these characteristic points, sort out the correlation information of the abnormal parameters on the time axis, and finally output the abnormal trend information.

[0104] S302: Based on the abnormal trend information, extract the influencing factors associated with the production quality, screen the influencing scope and action relationship, analyze the action intensity in the abnormal trend, extract and classify the key driving parameters, and obtain a list of quality influencing factors;

[0105] First, extract the parameters related to the production stage from the abnormal trend, such as the process link number, production equipment number and assembly step identification. By analyzing the changing characteristics of the abnormal trend curve, compare the fluctuation parameters with the control parameters in the production quality standard one by one, screen out the parameter range that may affect the quality, and extract the key parameters with greater intensity. By counting the frequency of key parameters in each production stage, and combining the intensity of action to analyze the specific impact range and related links of these parameters in the production line, all extracted key parameters are classified according to their associated production links to form a list of quality influencing factors, and finally output a detailed data table including the impact range and action relationship.

[0106] Extract the influencing factors associated with production quality according to the formula:

[0107]

[0108] Calculate the sum of influencing factors Z;

[0109] In the formula, α i represents the criticality coefficient of the i-th influencing factor, X i represents the i-th raw data point, indicating specific production data or quality data points, such as machine speed, temperature, raw material quality, etc., β i represents the attenuation coefficient of the i-th influencing factor, t represents the time factor, which represents the length of observation or calculation, usually in days, months or years, and n represents the total number of influencing factors.

[0110] There are five influencing factors, and their importance coefficients α i , attenuation coefficient β iAnd the corresponding time t = 12 (in months), the specific values ​​are as follows:

[0111] α1=0.4,β1=0.02;

[0112] α2=0.3, β2=0.015;

[0113] α3=0.15, β3=0.01;

[0114] α4=0.1, β4=0.005;

[0115] α5=0.05, β5=0.001;

[0116] Original data point X i X1=100, X2=80, X3=60, X4=40, X5=20 respectively. The calculation formula is as follows:

[0117] Z = 0.4 × 100 × e -0.02×12 +0.3×80×e -0.015×12 +0.15×60×

[0118] e -0.01×12 +0.1×40×e -0.005×12 +0.05×20×e -0.001×12 ;

[0119] Z = 40 × e -0.24 +24×e -0.18 +9×e -0.12 +4×e -0.06 +1×e -0.012 ;

[0120] Z≈32.3+19.8+8+3.8+1=64.9;

[0121] After considering the attenuation effect of influencing factors, the sum of comprehensive influencing factors is 64.9, which is lower than the result when attenuation is not considered. This more truly reflects the actual situation of the impact of time factors on production quality.

[0122] S303: Based on the list of quality influencing factors, analyze the nodes of the production line operation status, extract key values, screen the abnormal intervals and fluctuation ranges in the operation status, identify the distribution areas and variation ranges of potential problems, and obtain production abnormality monitoring data.

[0123] Extract the time nodes, equipment status and execution records of production tasks from the production line records, analyze the abnormal intervals and fluctuation ranges in the operating status data by comparing them with the parameters extracted from the influencing factor list, classify and mark the abnormal intervals according to the operating nodes, extract the key values ​​of each abnormal interval, such as the maximum and minimum values ​​of the fluctuations and the range of change, further locate the distribution areas of potential problems by counting the frequency and position of the abnormal intervals and combining the classification information of the influencing factors, record and analyze the parameter change range of each distribution area, and finally output the production abnormality monitoring data, including the specific information of the distribution position and change range of the abnormal intervals.

[0124] like Figure 5 As shown in the figure, based on the production abnormality monitoring data, the production data of spare parts is collected in real time, the quality indicators of spare parts in the production process are continuously evaluated, and the quality indicators are analyzed to determine the key factors affecting production efficiency and spare parts quality. The specific steps to obtain the key performance list are as follows:

[0125] S401: Based on the production abnormality monitoring data, collect the real-time data of the spare parts production process, analyze the production links, extract the parameter values ​​of the time nodes, verify the data integrity of the production stage, and reorganize the production data in chronological order to obtain a real-time data record set;

[0126] Collect real-time data of spare parts production process, extract time nodes of production links and their corresponding key parameters, such as spare parts processing status, equipment operation records and production time sequence, analyze the collected time node information, verify the data integrity of each production stage one by one, screen for missing or duplicate records, call the record number and time sequence in the production process, supplement the discontinuous time nodes, organize the complete data according to the production time sequence, mark the start and end time of the production stage and the corresponding parameter values, regenerate the production records for the organized data, and finally form a real-time data record set including time nodes, key parameters and stage identifiers.

[0127] S402: Based on the real-time data record set, extract the quality data of spare parts in the production process, analyze the corresponding relationship with the production time node, screen the abnormal range of quality data, and compare it with the quality reference standard, mark the production stage associated with the abnormal quality, and obtain the quality abnormality result;

[0128] Extract data fields related to spare parts quality, such as size, weight and material properties, associate these fields with production time nodes for analysis, screen the fluctuation range of quality data, compare actual data with quality reference standards one by one, locate abnormal value records that exceed the upper and lower limits of reference standards, and mark the distribution position and time nodes of abnormal values. By analyzing the production stages associated with abnormal quality data, classify and organize the corresponding production link information, extract the time nodes and related parameters that may cause quality abnormalities in each production stage, and finally form a result data table marked with quality abnormalities and their associated production stages.

[0129] Extract the quality data of spare parts in the production process according to the formula:

[0130]

[0131] Get the quality data Q of the i-th component i ;

[0132] In the formula, δ i represents the data extraction coefficient associated with component i, D i represents the raw data of component i obtained from the real-time data record set, including parameters directly monitored during the production process, such as temperature, pressure or speed, etc., i Represents the environmental factor adjustment coefficient, which is used to adjust the estimated value of the change in spare parts quality caused by changes in environmental conditions. i represents the environmental sensitivity index, indicating the degree of response of the i-th component to environmental changes, γ i Represents the power coefficient of environmental factors, used to adjust the environmental sensitivity index S i degree of impact.

[0133] When there are three parts on the production line whose data needs to be extracted, the specific parameters are as follows:

[0134] Part 1: δ1=0.8, D1=120, λ1=0.05, S1=10, γ1=2;

[0135] Part 2: δ2=0.65, D2=110, λ2=0.03, S2=8, γ2=1.5;

[0136] Part 3: δ3=0.9, D3=130, λ3=0.07, S3=15, γ3=1;

[0137] The calculation formula is:

[0138] Q1=0.8×(120+0.05×10 2 )=0.8×(120+5)=100;

[0139] Q2=0.65×(110+0.03×8 1.5 )≈0.65×(110+2.15)=72.9;

[0140] Q3=0.9×(130+0.07×15 1 )=0.9×(130+1.05)=118.35;

[0141] By combining environmental factors and real-time production data, the quality data of each spare part at a specific point in time can be calculated more accurately. This complex calculation takes into account the actual impact of environmental changes and better reflects the dynamic changes in production quality.

[0142] S403: Based on the abnormal quality results, screen the key factors affecting production efficiency and spare parts quality, analyze the impact areas of abnormal quality and production links, count the impact range, and obtain a key performance list.

[0143] Filter out the key factors that affect production efficiency and spare parts quality, extract the time nodes, fluctuation parameters and corresponding production equipment identification of abnormal data in each production link, analyze the scope of quality abnormalities on production links by comparing the operating parameters and abnormal distribution of the production stages, and statistically analyze the frequency and impact intensity of abnormal factors in each link. Extract the factors with the highest frequency or the largest impact range in the production link as key driving parameters, and compile a list of key performance indicators through classification and summary, which includes factors that have a significant impact on production efficiency and spare parts quality and their specific impact range.

[0144] like Figure 6 As shown in the figure, based on the key performance list, the quality changes of spare parts are analyzed, the machine speed and production temperature settings are monitored, and the production monitoring process is continuously optimized based on the monitoring data. The specific steps to obtain the online monitoring optimization results are as follows:

[0145] S501: Based on the key performance list, analyze the quality changes of spare parts, extract the quality parameters corresponding to the time nodes, screen the key parameter values, and identify the time period of parameter fluctuation and the abnormal value interval to obtain quality change information;

[0146] First, extract the time node data and spare parts quality parameters of the production process, including size, weight and surface treatment quality, sort the data according to the time axis and filter the key parameter values ​​one by one, count the fluctuation range of each parameter in the time node, identify the abnormal time period and the corresponding parameter value range, mark the starting and ending points of the abnormal parameter fluctuation, further refine the parameter value distribution within the time period, eliminate duplicate records or noise data, and finally combine the time period and parameter changes of the abnormal interval to generate complete quality change information.

[0147] Analyze the quality changes of spare parts, extract the quality parameters corresponding to the time nodes, and use the formula

[0148]

[0149] Calculate the quality parameter value Q(t);

[0150] Where β is the quality coefficient, which is used to adjust the sensitivity and range of the entire quality assessment, v k represents the influence weight of the kth parameter, indicating the relative importance of the parameter in quality assessment, v k (t) represents the actual observed value of the kth parameter at time t, including material strength, dimensional accuracy, etc., depending on the quality requirements of spare parts and the characteristics of the production process. n represents the total number of parameters, which indicates the number of different parameters considered in the quality assessment process.

[0151] In the production process, the quality parameters of spare parts are usually affected by many factors. In order to accurately evaluate the quality changes at different time points, the weighted summation method is used to calculate the various quality influencing parameters. k (t) may include material strength, dimensional accuracy, etc., whose values ​​at different time points are recorded by the real-time monitoring system. k It is obtained based on the statistical analysis of the impact of historical data on quality, and β is used as the overall quality coefficient to adjust the assessment range and sensitivity of the entire quality parameter;

[0152] Set the specific values ​​as follows:

[0153] Consider three quality influencing parameters, with weights φ1 = 0.5, φ2 = 0.3, and φ3 = 0.2;

[0154] The measured values ​​of the parameters at time t are v1(t)=100, v2(t)=85, v3(t)=90;

[0155] Quality factor β = 1.2;

[0156] The calculation formula is:

[0157] Q(t)=1.2×(0.5×100+0.3×85+0.2×90);

[0158] Q(t)=1.2×(50+25.5+18);

[0159] Q(t) = 1.2 × 93.5;

[0160] Q(t) = 112.2;

[0161] The quality parameter value at time t is 112.2. A higher value may indicate that the quality condition at this point in time is good or that there are certain abnormalities that require further analysis. Through such analysis, production management can monitor quality changes in real time and adjust production parameters in time to ensure product quality.

[0162] S502: Based on the quality change information, monitor the machine speed and production temperature parameters, extract the associated data between the operating parameters and the production links, filter the abnormal operating parameter values, and locate the production link corresponding to the abnormal point to obtain the equipment status monitoring log;

[0163] Carry out real-time monitoring of machine speed and production temperature parameters involved in the production process, extract the operating parameter values ​​of each time node from the records of production equipment, including speed range, temperature changes, and equipment operation time, etc., analyze the correspondence between these operating parameters and production links, screen the operating parameters of each link, and mark parameter values ​​that exceed the normal range as abnormal operating values. By comparing the time nodes of the abnormal points with the equipment operation records of the production links, locate the specific links where the abnormal operating parameters occur, classify and group each abnormal operating parameter value, and organize and generate equipment status monitoring logs.

[0164] S503: Based on the equipment status monitoring log, analyze the correlation range of the operating parameters in the production process, extract the corresponding relationship with the production stage, adjust the time interval and value range of the operating parameters, optimize the distribution characteristics of the operating parameters in the monitoring process, and obtain the online monitoring optimization results.

[0165] Perform correlation range analysis on the operating parameters recorded in the production process, extract parameter fields corresponding to the production stage, including the equipment's operating speed, temperature changes, and the start and end time of parameter fluctuations, adjust the time interval and value range of each operating parameter, eliminate duplicate records or error marks in the operation process, redistribute the adjusted operating parameters in chronological order, extract the key value range of the operating parameters based on the characteristic points of the production stage, and classify and count the parameter change characteristics of each stage, ultimately forming an optimized online monitoring result, including the distribution characteristics of the operating parameters and the adjusted time interval records.

[0166] like Figure 7 As shown, an online monitoring system for automotive spare parts includes:

[0167] The data quality control module extracts the assembly data stream of the parts based on the collected data of the parts production line, performs quality screening on the real-time assembly data stream, removes noise and invalid data in the data stream, and obtains the screened assembly data;

[0168] The deviation warning module extracts the quality and assembly cycle of target parts based on the screened assembly data, identifies data points that deviate from the normal production process, and compares them with the current production trend to predict potential production deviations and obtain production deviation warnings;

[0169] The abnormal monitoring module evaluates the abnormal trend of the spare parts production line based on the production deviation warning, identifies the factors affecting the production quality according to the abnormal trend, and analyzes the production line status and potential problems with reference to the factors to obtain production abnormality monitoring data;

[0170] Based on the production abnormality monitoring data, the optimization control module collects the production data of spare parts in real time, continuously evaluates the quality indicators of spare parts in the production process, analyzes the quality indicators, determines the key factors affecting production efficiency and spare parts quality, monitors machine speed and production temperature settings, continuously optimizes the production monitoring process, and obtains online monitoring optimization results.

[0171] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0172] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0173] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0174] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0175] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0176] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0177] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0178] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0179] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0180] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An online monitoring method for automobile industry spare parts, characterized in that: The method comprises: S1: Based on the collected spare parts production line data, the assembly data stream of the spare parts is extracted, the real-time assembly data stream is quality screened, the noise and invalid data in the data stream are removed, and the screened assembly data is obtained; S2: Based on the screened assembly data, the quality and assembly cycle of the target parts are extracted, the data points that deviate from the normal production process are identified, and compared with the current production trend, potential production deviations are predicted, and production deviation warnings are obtained; S3: Based on the production deviation warning, evaluate the abnormal trend of the spare parts production line, identify the factors affecting the production quality according to the abnormal trend, and analyze the production line status and potential problems with reference to the factors to obtain production abnormality monitoring data; S4: Based on the production abnormality monitoring data, the production data of spare parts are collected in real time, the quality indicators of spare parts in the production process are continuously evaluated, and the quality indicators are analyzed to determine the key factors affecting the production efficiency and the quality of spare parts, and obtain a key performance list; S5: Based on the key performance list, analyze the quality changes of spare parts, monitor the machine speed and production temperature settings, and continuously optimize the production monitoring process based on the monitoring data to obtain online monitoring optimization results.

2. The online monitoring method for automobile industry spare parts according to claim 1 is characterized in that: The screened assembly data includes accuracy index, integrity rating, and effective data volume; the production deviation warning includes assembly delay warning, quality deviation mark, and periodic abnormality mark; the production abnormality monitoring data includes abnormality type, abnormality occurrence frequency, and related influencing components; the key performance list includes key mechanical efficiency, quality accuracy, and production line stability index; the online monitoring optimization results include reaction speed optimization results and monitoring sensitivity.

3. The online monitoring method for automobile industry spare parts according to claim 1, characterized in that: Based on the collected spare parts production line data, the assembly data stream of spare parts is extracted, the real-time assembly data stream is quality screened, and the noise and invalid data in the data stream are removed to obtain the screened assembly data. The specific steps are as follows: S101: Based on the collected spare parts production line data, the movement and position information of the spare parts on the production line is captured in real time, the movement trajectory data of the spare parts are analyzed item by item, the data is segmented and classified according to the time axis, the feature values ​​related to the position are extracted, the specific position of the spare parts in the production stage is recorded, and the recording results are formatted to obtain the assembly data set; S102: Based on the assembly data set, timestamp verification is performed on the accessed data batches, and data with time deviation exceeding a threshold is marked by comparing the time node with the recorded time interval of the production stage, and signal strength is checked for the marked data, and abnormal timestamp data is eliminated by comparing the signal curve fluctuation with the stable interval parameter to obtain a data stream cleaning record; S103: Based on the data flow cleaning records, the data are compared with the spare parts quality standards, and the correspondence between the data fields and the quality standards is analyzed one by one, and the missing fields and the numerical records that do not meet the range are detected. The field integrity and numerical compliance of the eliminated data are re-checked to obtain the filtered assembly data.

4. The online monitoring method for automobile industry spare parts according to claim 1, characterized in that: Based on the screened assembly data, the quality and assembly cycle of the target parts are extracted, the data points that deviate from the normal production process are identified, and compared with the current production trend to predict potential production deviations. The specific steps for obtaining production deviation warnings are as follows: S201: Based on the screened assembly data, extract the quality and assembly cycle of spare parts, perform time node analysis, locate the assembly sequence, and organize the assembly data and cycle information according to the assembly sequence to obtain assembly cycle information; S202: Based on the assembly cycle information, the quality parameters are compared with the standard quality, key values ​​and time points of the abnormal range are extracted, the location of the deviation data is marked, and an abnormal data directory is obtained; S203: Based on the abnormal data catalog, cross-analysis is performed with the current production trend, the frequency of abnormal data occurrence is counted, the abnormal data changes are analyzed, and deviation parameters are marked to obtain a production deviation warning.

5. The online monitoring method for automobile industry spare parts according to claim 1, characterized in that: Based on the production deviation warning, the abnormal trend of the spare parts production line is evaluated, the factors affecting the production quality are identified according to the abnormal trend, and the production line status and potential problems are analyzed with reference to the factors. The specific steps for obtaining the production abnormality monitoring data are as follows: S301: Based on the production deviation warning, analyze the abnormal trend in the warning data, extract the frequency distribution of abnormal parameters by classifying the time nodes, screen the fluctuation range of abnormal parameters, and superimpose trend curves to analyze the correlation between trends and changes in characteristic points to obtain abnormal trend information; S302: Based on the abnormal trend information, extract influencing factors associated with production quality, screen the influencing range and action relationship, analyze the action intensity in the abnormal trend, extract key driving parameters and classify them, and obtain a list of quality influencing factors; S303: Based on the list of quality influencing factors, analyze the nodes of the production line operation status, extract key values, screen the abnormal intervals and fluctuation ranges in the operation status, identify the distribution areas and variation ranges of potential problems, and obtain production abnormality monitoring data.

6. The online monitoring method for automobile industry parts according to claim 5, characterized in that: The extraction and production quality related influencing factors are as follows: Calculate the sum of influencing factors Z; In the formula, α i represents the criticality coefficient of the i-th influencing factor, X i represents the i-th original data point, β i represents the attenuation coefficient of the i-th influencing factor, t represents the time factor, and n represents the total number of influencing factors.

7. The online monitoring method for automobile industry spare parts according to claim 1, characterized in that: Based on the production abnormality monitoring data, the production data of spare parts is collected in real time, the quality indicators of spare parts in the production process are continuously evaluated, and the quality indicators are analyzed to determine the key factors affecting production efficiency and spare parts quality. The specific steps for obtaining the key performance list are as follows: S401: Based on the production abnormality monitoring data, real-time data of the spare parts production process is collected, the production links are analyzed, parameter values ​​of time nodes are extracted, the data integrity of the production stage is verified, and the production data is reorganized in chronological order to obtain a real-time data record set; S402: Based on the real-time data record set, extract the quality data of spare parts in the production process, analyze the corresponding relationship with the production time node, screen the abnormal range of quality data, and compare it with the quality reference standard, mark the production stage associated with the abnormal quality, and obtain the quality abnormality result; S403: Based on the abnormal quality results, key factors affecting production efficiency and spare parts quality are screened, the impact areas of abnormal quality and production links are analyzed, the impact range is statistically analyzed, and a key performance list is obtained.

8. The online monitoring method for automobile industry spare parts according to claim 7, characterized in that: The quality data of spare parts in the production process is extracted according to the formula: Get the quality data Q of the i-th component i ; In the formula, δ i represents the data extraction coefficient associated with spare part i, D i represents the original data of spare part i obtained from the real-time data record set, λ i represents the environmental factor adjustment coefficient, S i represents the environmental sensitivity index, indicating the degree of response of the i-th component to environmental changes, γ i Represents the power coefficient of environmental factors, used to adjust the environmental sensitivity index S i degree of impact.

9. The online monitoring method for automobile industry spare parts according to claim 1, characterized in that: Based on the key performance list, analyze the quality changes of spare parts, monitor the machine speed and production temperature settings, and continuously optimize the production monitoring process based on the monitoring data. The specific steps to obtain the online monitoring optimization results are as follows: S501: Based on the key performance list, analyze the quality changes of spare parts, extract the quality parameters corresponding to the time nodes, screen the key parameter values, and identify the time period of parameter fluctuation and the abnormal value interval to obtain quality change information; S502: Based on the quality change information, monitor the machine speed and production temperature parameters, extract the associated data between the operating parameters and the production links, filter the abnormal operating parameter values, and locate the production link corresponding to the abnormal point to obtain the equipment status monitoring log; S503: Based on the equipment status monitoring log, analyze the correlation range of the operating parameters in the production process, extract the corresponding relationship with the production stage, adjust the time interval and value range of the operating parameters, optimize the distribution characteristics of the operating parameters in the monitoring process, and obtain online monitoring optimization results.

10. An online monitoring system for automobile industry spare parts, the online monitoring system for automobile industry spare parts is used to implement the online monitoring method for automobile industry spare parts as claimed in any one of claims 1 to 9, characterized in that: The system comprises: The data quality control module extracts the assembly data stream of the parts based on the collected data of the parts production line, performs quality screening on the real-time assembly data stream, removes noise and invalid data in the data stream, and obtains the screened assembly data; The deviation warning module extracts the quality and assembly cycle of target parts based on the screened assembly data, identifies data points that deviate from the normal production process, and compares them with the current production trend to predict potential production deviations and obtain production deviation warnings; The abnormality monitoring module evaluates the abnormality trend of the spare parts production line based on the production deviation warning, identifies the factors affecting the production quality according to the abnormality trend, and analyzes the production line status and potential problems with reference to the factors to obtain production abnormality monitoring data; Based on the production abnormality monitoring data, the optimization control module collects the production data of spare parts in real time, continuously evaluates the quality indicators of spare parts in the production process, analyzes the quality indicators, determines the key factors affecting production efficiency and spare parts quality, monitors machine speed and production temperature settings, continuously optimizes the production monitoring process, and obtains online monitoring optimization results.

Images