Quality statistical analysis method used in cable manufacturing process and readable storage medium

Abstract

The invention relates to the technical field of cable manufacturing, and discloses a quality statistical analysis method used in a cable manufacturing process and a readable storage medium, and the method comprises the steps: collecting various source data of a cable produced in the operation process of a production line in real time, calculating a characteristic value corresponding to each source data, configuring a filtering rule for each source data for filtering, and calculating the corresponding characteristic value of each source data; obtaining the filtered source data, selecting a corresponding control chart algorithm for the filtered source data, and drawing a control chart corresponding to each kind of source data based on a preset control boundary corresponding to each kind of source data; and based on the real-time updated control chart corresponding to each kind of source data, obtaining a cable quality analysis result represented by the source data. According to the invention, the control chart corresponding to the source data is drawn by matching the corresponding filtering rule and the control chart algorithm for different types of source data, and then the cable quality monitoring result corresponding to the source data is analyzed and obtained based on the preset control limit in the control chart, so that the real-time monitoring of the production process is realized, and the defective product rate is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of cable manufacturing, and in particular to a quality statistical analysis method and a readable storage medium used in a cable manufacturing process. Background Art

[0002] In the current manufacturing environment, quality statistical analysis methods are used to monitor the production process in real time, distinguish fluctuations in product quality during the production process, and thus issue early warnings for abnormal trends in the production process so that production managers can take timely measures to eliminate abnormalities and restore the stability of the production process, thereby achieving the goal of improving and controlling quality.

[0003] However, in actual use in the cable industry, due to non-critical factors such as mistakes made by production managers during data collection and positive / negative offsets of collected data, the results of the statistical process produce some unexpected anomalies, which in turn have an adverse impact on the control of subsequent production processes.

[0004] Specifically, in the data collection process, because the confidence interval of the collected data cannot be controlled, it may be necessary to eliminate the interference caused by non-critical factors in the process, and it may also be necessary to intervene to reduce random fluctuations in the process. The collected data needs to be manually filtered, compiled and sorted before statistical analysis can be performed, resulting in high complexity of the work based on raw data analysis and delayed statistical analysis. In addition, since the product specification range is very large, but the actual data distribution is relatively concentrated, close to the specification limit on one side, the bias is very serious, and the calculated process capability index is very unsatisfactory, but the product quality meets the product standards. The problem is that the CP / CPK and PP / PPK single indicator analysis of the quality control process capability meets the standard, but the comprehensive analysis does not match the actual production process, and the significance of statistical analysis is lost.

[0005] In summary, the existing quality statistical analysis methods in the cable manufacturing industry use fixed control chart algorithms and general exception judgment rules, and cannot meet the actual application scenarios where the data collected during the cable manufacturing process fluctuates and is concentrated in distribution. A large amount of manual processing of the data is required, the analysis efficiency is low, and the accuracy is poor, and the expected statistical effect cannot be achieved. Summary of the invention

[0006] Therefore, the technical problem to be solved by the present invention is to overcome the problem of low analysis efficiency and poor accuracy in the prior art of analyzing cable quality using a fixed control chart algorithm and a general abnormality judgment rule.

[0007] In order to solve the above technical problems, the present invention provides a quality statistical analysis method for a cable manufacturing process, comprising: Real-time collection of multiple source data of cables produced during the production line operation; Based on the properties of each source data, the eigenvalue corresponding to each source data is calculated; Based on the characteristic value corresponding to each source data, a corresponding filtering rule is configured for each source data to filter and obtain the filtered source data; For each filtered source data, a corresponding control chart algorithm is selected, and a control chart corresponding to each source data is drawn based on a preset control limit corresponding to each source data; Based on the real-time updated control chart corresponding to each source data, obtain the cable quality analysis result represented by the source data; The cable quality monitoring results are composed based on the cable quality analysis results corresponding to each source data.

[0008] Preferably, based on the real-time updated control chart corresponding to each source data, obtaining the cable quality analysis result represented by the source data includes: In the control chart corresponding to each source data, the variable value corresponding to each source data is calculated and compared with the preset control limit: If the variable value corresponding to the source data exceeds the preset control limit, it indicates that the production line is operating abnormally and an abnormal cable quality alarm is issued; If the variable value corresponding to the source data does not exceed the preset control limit, it indicates that the production line is operating normally.

[0009] Preferably, the method for calculating the variable value corresponding to each source data is the difference method, the quotient method or the standard error bias method.

[0010] Preferably, the control chart algorithm is a mean-range control chart, a mean-standard deviation control chart, or a single value moving-range control chart.

[0011] Preferably, the source data includes cable diameter, cable insulation layer thickness, insulation layer resistance value and cable temperature.

[0012] Preferably, based on the properties of each source data, the characteristic value corresponding to each source data is calculated, including: When the source data is the cable diameter, the standard deviation of the cable diameter is calculated in real time based on the average value of the cable diameters produced within a preset production time period as the characteristic value of the source data; When the source data is the thickness of the cable insulation layer, the cable insulation layer range is calculated based on the maximum and minimum values ​​of the cable insulation layer thickness produced within a preset production time period as the characteristic value of the source data; When the source data is the insulation layer resistance value of a cable, the median of the insulation layer resistance values ​​of the cables produced within a preset production time period is used as the characteristic value of the source data; When the source data is cable temperature, the average value of the cable temperature produced within a preset production time period is calculated as the characteristic value of the source data.

[0013] Preferably, based on the characteristic value corresponding to each source data, a corresponding filtering rule is configured for each source data for filtering, including: If the characteristic value of the source data is the average value, the source data is filtered using the average filtering rule; If the characteristic value of the source data is the extreme difference, the source data is filtered using the extreme difference filtering rule; If the eigenvalue of the source data is the median, the source data is filtered using the average filtering rule.

[0014] Preferably, after obtaining the cable quality monitoring result, the method further includes: correcting the production parameters of the production line according to the cable quality monitoring result.

[0015] Preferably, after obtaining the cable quality monitoring result, the method further includes: Collect multiple source data of cables in real time, as well as their corresponding characteristic values ​​and cable quality monitoring results, to build a preliminary knowledge base; Use the preliminary knowledge base to train the machine learning model and obtain a trained quality analysis model; The trained quality analysis model is used to analyze the cable source data collected in real time to obtain quality monitoring results.

[0016] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed, the steps of the quality statistical analysis method for the cable manufacturing process as described above are implemented.

[0017] The above technical solution of the present invention has the following beneficial effects compared with the prior art: The quality statistical analysis method for the cable manufacturing process described in the present invention matches corresponding filtering rules and control chart algorithms for different types of source data, draws a control chart corresponding to the source data, and then analyzes and obtains the cable quality monitoring results corresponding to the source data based on the preset control limits in the control chart, thereby realizing real-time monitoring of the production process, being able to promptly discover abnormal situations in the production process, improving the monitoring accuracy of cable product quality, and reducing the defective product rate.

[0018] Moreover, for the different filtering rules and control chart algorithms in this application, one or more of them can be flexibly selected for use in combination to ensure the timeliness of monitoring and effectively control the quality of production; and the production parameters of the production line can be corrected in time based on the cable quality monitoring results to reduce fluctuations caused by non-critical factors, thereby ensuring the stability of subsequent production processes, further improving the quality of cable products, reducing costs, and optimizing production processes. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below according to specific embodiments of the present invention in conjunction with the accompanying drawings, wherein: Figure 1 It is a flow chart of the steps of the quality statistical analysis method for the cable manufacturing process provided by the present invention; Figure 2 It is a quality statistical analysis flow chart provided by the present invention; Figure 3 It is a schematic diagram of the filtering process provided by the present invention; Figure 4 It is a schematic diagram of the principle of generating filtering rules by the calculation formula provided by the present invention; Figure 5 It is a schematic diagram of the principle of generating a combination of filtering rules by the filtering rule provided by the present invention; Figure 6 It is a schematic diagram of the principle of generating a filtering rule combination by the filtering rule and the filtering rule combination provided by the present invention; Figure 7 It is a flow chart of the control diagram algorithm provided by the present invention; Figure 8 It is an extended schematic diagram of the custom control diagram algorithm and the custom abnormality judgment rule configuration provided by the present invention; Fig. 9 is a schematic diagram of the custom expansion operation of the exception judgment rule provided by the present invention, Fig.10 It is a schematic diagram of machine learning and knowledge base construction provided by the present invention; Fig.11 This is a manufacturing process diagram of the cable product provided by the present invention. DETAILED DESCRIPTION

[0020] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0021] Reference Figure 1 As shown, the step flow chart of the quality statistical analysis method for the cable manufacturing process provided by the present invention includes the following steps: S101: Real-time collection of multiple source data of cables produced during the production line operation; S102: Calculate a characteristic value corresponding to each source data based on the property of each source data; S103: Based on the characteristic value corresponding to each source data, configure a corresponding filtering rule for each source data to perform filtering, and obtain filtered source data; S104: For each type of filtered source data, a corresponding control chart algorithm is selected, and based on a preset control limit corresponding to each type of source data, a control chart corresponding to each type of source data is drawn; S105: based on the real-time updated control chart corresponding to each source data, obtaining the cable quality analysis result represented by the source data; S106: Composing a cable quality monitoring result based on the cable quality analysis result corresponding to each source data.

[0022] Specifically, in step S105, based on the real-time updated control chart corresponding to each source data, the cable quality analysis result represented by the source data is obtained, including: in the control chart corresponding to each source data, calculating the variable value corresponding to each source data, and comparing it with the preset control limit: If the variable value corresponding to the source data exceeds the preset control limit, it indicates that the production line is operating abnormally and an abnormal cable quality alarm is issued; If the variable value corresponding to the source data does not exceed the preset control limit, it indicates that the production line is operating normally. The method for calculating the variable value corresponding to each source data is the difference method, the quotient method or the standard error bias method. The control chart algorithm is the mean-range control chart, the mean-standard deviation control chart or the single value moving-range control chart.

[0023] Specifically, the source data includes cable diameter, cable insulation thickness, insulation resistance and cable temperature. Based on the properties of each source data, the characteristic value corresponding to each source data is calculated, including: When the source data is the cable diameter, the standard deviation of the cable diameter is calculated in real time based on the average value of the cable diameters produced within a preset production time period as the characteristic value of the source data; When the source data is the thickness of the cable insulation layer, the cable insulation layer range is calculated based on the maximum and minimum values ​​of the cable insulation layer thickness produced within a preset production time period as the characteristic value of the source data; When the source data is the insulation layer resistance value of a cable, the median of the insulation layer resistance values ​​of the cables produced within a preset production time period is used as the characteristic value of the source data; When the source data is cable temperature, the average value of the cable temperature produced within a preset production time period is calculated as the characteristic value of the source data.

[0024] Based on the above embodiment, based on the characteristic value corresponding to each source data, a corresponding filtering rule is configured for each source data to perform filtering, including: If the characteristic value of the source data is the average value, the source data is filtered using the average filtering rule; If the characteristic value of the source data is the extreme difference, the source data is filtered using the extreme difference filtering rule; If the eigenvalue of the source data is the median, the source data is filtered using the average filtering rule.

[0025] In the embodiment of the present invention, after obtaining the cable quality monitoring result, the method further includes: correcting the production parameters of the production line according to the cable quality monitoring result.

[0026] In an embodiment of the present invention, after obtaining the cable quality monitoring results, it also includes: real-time acquisition of various source data of the cable, and its corresponding characteristic values ​​and cable quality monitoring results, to construct a preliminary knowledge base; using the preliminary knowledge base to train the machine learning model to obtain a trained quality analysis model; using the trained quality analysis model to analyze the cable source data acquired in real time to obtain quality monitoring results.

[0027] The quality statistical analysis method for the cable manufacturing process described in the present invention matches corresponding filtering rules and control chart algorithms for different types of source data, draws a control chart corresponding to the source data, and then analyzes and obtains the cable quality monitoring results corresponding to the source data based on the preset control limits in the control chart, thereby realizing real-time monitoring of the production process, being able to promptly discover abnormal situations in the production process, improving the monitoring accuracy of cable product quality, and reducing the defective product rate.

[0028] Cable manufacturing companies generally have multiple automated production lines with huge annual output. In the cable production process, quality control is the key to ensuring product performance and reliability. Traditional quality control methods rely on manual inspection and empirical judgment, which are inefficient and prone to errors. In order to improve production efficiency and product quality, the embodiment of the present invention adopts a quality statistical analysis method that combines data filtering, custom control chart algorithm and machine learning technology, aiming to provide a comprehensive quality analysis and improvement plan. Figure 2 The figure shows the quality statistical analysis flow chart. The specific scheme includes: S201: Data filtering processing: S201-1: Collect source data on the production line, including key parameters such as cable diameter, insulation thickness, resistance value and temperature; For example, in the cable extrusion process, the key is to ensure that the insulation material is evenly wrapped around the wire core. To this end, a high-precision laser diameter gauge is installed at the extruder outlet to measure the thickness of the insulation layer, and a temperature sensor is installed inside the extruder to monitor the heating state of the material.

[0029] S201-2: Configure filtering rules according to the characteristic values ​​of the source data; Reference Figure 3The figure shows a schematic diagram of the filtering process; the characteristic values ​​of each parameter are calculated, and filtering rules are set according to the characteristic values ​​to filter the source data and remove abnormal values; the characteristic values ​​of parameters include data sum, maximum value, minimum value, square root, mean value, standard deviation and range; Specifically, the filter module is a functional enhancement of the data acquisition module. It is based on the calculation formula of industry data collection. It combines one or more calculation formulas through logical methods to form the most basic unit in this module - the filter rule. Then, it combines multiple filter rules through logical methods to form another functional unit - the filter rule combination. Not only that, the filter rules and filter rule combinations can also be combined into a new filter rule combination through logical methods, and finally form a filter rule / filter rule combination through free combination to work in the filter module. Figure 4 As shown, it is a schematic diagram of the principle of generating filtering rules by calculation formula; Figure 5 As shown, it is a schematic diagram of the principle of generating a combination of filtering rules by filtering rules; Figure 6 As shown, it is a schematic diagram of the principle of generating a filtering rule combination by filtering rules and filtering rule combinations; For example, according to the data characteristic values ​​(such as mean, standard deviation, range, etc.) collected by the laser diameter gauge and temperature sensor, the filtering rules are configured. The average filtering rule is used to remove the instantaneous fluctuations in the temperature data, and the sample mean size is set to 105 degrees Celsius; for the thickness of the insulation layer, the standard range filtering rule is used, and the range target value is set to be greater than 2 to eliminate outliers caused by measurement errors.

[0030] S202: Adapting the corresponding control chart algorithm to the source data after filtering; Reference Figure 7 The figure shows the flow chart of the control chart algorithm. The difference method, quotient method, standard error bias method and other algorithms are used to monitor the detection factors in the production process in real time. The appropriate control chart algorithm is selected. The data is input into the algorithm to generate the control chart. The control chart is monitored in real time and the detection factors are analyzed.

[0031] Specifically, the difference method is used to monitor the trend of temperature data, that is, the difference between two adjacent temperature measurements is calculated and a control chart is drawn; if seven consecutive points fall on one side of the center line, it is considered that there is a systematic deviation. At the same time, the quotient method is used to detect the stability of the thickness of the insulation layer, that is, the ratio of the two measurements before and after is calculated, and the control limit is set. For temperature control, the standard error deviation method is used to identify situations that exceed the normal fluctuation range; when the deviation between the actual temperature and the target temperature is greater than 2 times the standard error, the system will issue an alarm to prompt the operator to check the working status of the heating element.

[0032] Reference Figure 8As shown, it is an extended schematic diagram of the custom control chart algorithm and the custom exception judgment rule configuration; the custom control chart algorithm and the custom exception judgment rule configuration are extensions of the basic functions of the statistical process control system. The standard statistical process control system calculates the control chart through a fixed algorithm and eight general exception judgment rules. The degree of configurability is low and cannot meet the requirements of certain situations in the cable industry. Therefore, the introduction of pluggable custom algorithms can greatly increase the flexibility of data calculation and the expansion of the eight general exception judgment rules, which further improves the freedom of the control chart and enables managers to use the statistical process control system more in line with the actual production process.

[0033] Specifically, taking Xbar-R Chart as an example, the SPC standard algorithm is optimized to obtain a custom algorithm; refer to Fig. 9 The figure shows a schematic diagram of the operation of customizing the difference judgment rule extension. The customizing of the difference judgment rule is realized by modifying the parameter m in the custom algorithm.

[0034] ①SPC standard algorithm, including: Control Limits: Xbar Chart: Data value CLx=X̿; Upper control limit UCLx = X̿ + (3* ) / =X̿+A2* ; Lower control limit LCLx = X̿–(3* ) / =X̿-A2* ; Sigma actual process value: = / d2; R Chart: Data value CLr= ; Upper control limit UCLr=D4* ; Lower control limit LCLr = D3* ; Compute constants: A2=3 / (d2* ); D3=1–3(d3 / d2); D4=1+3(d3 / d2); ② The optimized custom algorithm is expressed as: Control Limits: Xbar Chart: Data value CLx=X̿; Upper control limit UCLx = X̿ + (m* ) / =X̿+A2* ; Lower control limit LCLx = X̿–(m* ) / =X̿-A2* ; Sigma actual process value = / d2; R Chart: Data value CLr= ; Upper control limit UCLr=D4* ; Lower control limit LCLr = D3* ; Compute constants: A2=3 / (d2* ); D3=1–m(d3 / d2); D4=1+m(d3 / d2); S203: Collect process data and data on exception handling methods, conduct machine learning, build a knowledge base, and implement quality prediction, parameter correction suggestions, and exception handling method recommendations; Reference Fig.10 The figure shows a schematic diagram of machine learning and knowledge base construction, which specifically includes: data accumulation to form a preliminary knowledge base; using machine learning algorithms to train the knowledge base; monitoring the generation process to achieve quality prediction; and proposing parameter correction suggestions and exception handling methods based on the prediction results.

[0035] Specifically, based on the accumulated data, supervised learning algorithms (such as random forests and support vector machines) are used to train the model, enabling it to identify potential factors that lead to quality problems and propose preventive measures or parameter adjustment suggestions accordingly; the model is regularly updated and continuously optimizes its predictive ability and the effectiveness of its suggestions by continuously learning the latest production data. When the model predicts that the insulation layer may be insufficiently thick under certain conditions, it will recommend adjusting the extrusion speed or changing the material formula to prevent quality problems from occurring.

[0036] This embodiment gradually forms a knowledge base of the difference judgment results through the day-to-day data accumulation of the difference judgment results generated in the actual process and the result analysis reasons given by the management personnel. By analyzing the key information of the accumulated data, the labels are extracted. In the subsequent difference judgment process, the results are matched by labels, and the possible reasons are predicted by similarity. The management personnel confirm whether to adopt or give new result analysis reasons again. In this way, the system can be continuously improved so that it can give predictions more accurately, and the work efficiency of the entire difference judgment and cause analysis can be improved repeatedly. And the statistical process control system is not a one-time system, it is a process of continuous improvement. By continuously monitoring, analyzing and improving the production process, higher production efficiency and better product quality can be achieved. Therefore, through the method of the present invention, by enhancing, expanding and assisting the system, it can more perfectly fit the production process of the cable industry and make the process control more accurate and stable.

[0037] The method proposed in the embodiment of the present invention is in line with the use scenario of the actual production process. It combines the filtering processing of data, the control chart algorithm, the custom extension of the abnormality judgment rule and the pre-judgment of the abnormality judgment result, so that the statistical process control method is more accurate and stable, the process is closer to the production scene, and the result is more practical; and through efficient analysis and processing, the monitoring accuracy of the cable product quality is improved and the defective rate is reduced. Compared with the traditional quality control method, the present invention can timely discover abnormal conditions in the production process, effectively monitor the production process in real time, and can also flexibly and conveniently select one or several items for use in combination, ultimately ensuring the timeliness of monitoring; at the same time, the self-learning ability of the system can continuously improve the accuracy of prediction and adapt to changes in the production process. In addition, the present invention also has the following advantages: first, it enhances the competitiveness of enterprises and meets the needs of customers for high-quality cable products; second, it provides a decision-making basis for the management of enterprises, which helps to continuously improve product quality; third, it promotes technological progress in the cable industry and promotes industrial upgrading. The present invention has significant beneficial effects in improving the quality of cable products, reducing costs, optimizing production processes, etc., which fully reflects its technological advancement.

[0038] Reference Fig.11 As shown in the figure, it is a cable product manufacturing process diagram. In the cable product manufacturing process, it is necessary to first collect data on factors such as wiring, attenuation, size, and separation force, and match the corresponding filtering rules according to the characteristic values ​​of each factor. According to the calculation of the filtering rules, the collected data will be automatically retained / eliminated (it can also be set to non-automatic, marked data, and manual confirmation is required). After filtering is completed, it is organized and stored. In order to solve the problem of bias in the collected data, a Figure 1The algorithm supports plug-in custom algorithms, so that the distribution of data can better reflect the trend of the product production process, ensuring that the control chart is closer to the actual production process; and introduces custom judgment rules, so that production management personnel can flexibly control the tightness of judgment in the actual production process, so that the flexibility of the quality control process is greatly improved; using the knowledge learning model, the judgment results and factor analysis are learned, and the subsequent judgment results are given factor predictions, so as to help production management personnel improve work efficiency, respond to abnormal fluctuations more quickly, and solve problems. This embodiment can more conveniently monitor the production process effectively in real time, and can also flexibly and conveniently select one or several items to use together, ultimately ensuring the timeliness of monitoring and effectively controlling the quality of production.

[0039] Based on the above embodiments, this embodiment further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed, the steps of the quality statistical analysis method for the cable manufacturing process as described above are implemented.

[0040] The quality statistical analysis method used in the cable manufacturing process described in the present invention matches the corresponding filtering rules and control chart algorithms for different types of source data, draws the control chart corresponding to the source data, and then analyzes and obtains the cable quality monitoring results corresponding to the source data based on the preset control limits in the control chart, thereby realizing real-time monitoring of the production process, being able to timely discover abnormal conditions in the production process, improving the monitoring accuracy of cable product quality, and reducing the defective product rate. And for the different filtering rules and control chart algorithms in this application, one or more of them can be flexibly selected for use in combination to ensure the timeliness of monitoring and effectively control the quality of production; and timely calibrate the production parameters of the production line based on the cable quality monitoring results to reduce the fluctuations caused by non-critical factors, ensure the stability of the subsequent production process, further improve the quality of cable products, reduce costs, and optimize the production process.

[0041] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0042] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0043] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0044] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0045] Obviously, the above embodiments are merely examples for the purpose of clear explanation and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the present invention.

Claims

1. A quality statistical analysis method for a cable manufacturing process, characterized in that: include: Real-time collection of multiple source data of cables produced during the production line operation; Based on the properties of each source data, the eigenvalue corresponding to each source data is calculated; Based on the characteristic value corresponding to each source data, a corresponding filtering rule is configured for each source data to filter and obtain the filtered source data; For each filtered source data, a corresponding control chart algorithm is selected, and a control chart corresponding to each source data is drawn based on a preset control limit corresponding to each source data; Based on the real-time updated control chart corresponding to each source data, obtain the cable quality analysis result represented by the source data; The cable quality monitoring results are composed based on the cable quality analysis results corresponding to each source data.

2. The quality statistical analysis method for cable manufacturing process according to claim 1, characterized in that: Based on the real-time updated control chart corresponding to each source data, the cable quality analysis results represented by the source data are obtained, including: In the control chart corresponding to each source data, the variable value corresponding to each source data is calculated and compared with the preset control limit: If the variable value corresponding to the source data exceeds the preset control limit, it indicates that the production line is operating abnormally and an abnormal cable quality alarm is issued; If the variable value corresponding to the source data does not exceed the preset control limit, it indicates that the production line is operating normally.

3. The quality statistical analysis method for cable manufacturing process according to claim 2, characterized in that: The methods for calculating the variable value corresponding to each source data are the difference method, the quotient method, or the standard error bias method.

4. The quality statistical analysis method for cable manufacturing process according to claim 1, characterized in that: The control chart algorithms are mean-range control chart, mean-standard deviation control chart, or individual moving value-range control chart.

5. The quality statistical analysis method for cable manufacturing process according to claim 1, characterized in that: The source data includes cable diameter, cable insulation thickness, insulation resistance and cable temperature.

6. The quality statistical analysis method for cable manufacturing process according to claim 5, characterized in that: Based on the properties of each source data, the eigenvalues ​​corresponding to each source data are calculated, including: When the source data is the cable diameter, the standard deviation of the cable diameter is calculated in real time based on the average value of the cable diameters produced within a preset production time period as the characteristic value of the source data; When the source data is the thickness of the cable insulation layer, the cable insulation layer range is calculated based on the maximum and minimum values ​​of the cable insulation layer thickness produced within a preset production time period as the characteristic value of the source data; When the source data is the insulation layer resistance value of a cable, the median of the insulation layer resistance values ​​of the cables produced within a preset production time period is used as the characteristic value of the source data; When the source data is cable temperature, the average value of the cable temperature produced within a preset production time period is calculated as the characteristic value of the source data.

7. The quality statistical analysis method for cable manufacturing process according to claim 6, characterized in that: Based on the characteristic values ​​corresponding to each source data, the corresponding filtering rules are configured for each source data for filtering, including: If the characteristic value of the source data is the average value, the source data is filtered using the average filtering rule; If the characteristic value of the source data is the extreme difference, the source data is filtered using the extreme difference filtering rule; If the eigenvalue of the source data is the median, the source data is filtered using the average filtering rule.

8. The quality statistical analysis method for cable manufacturing process according to claim 1, characterized in that: After obtaining the cable quality monitoring result, the method further includes: correcting the production parameters of the production line according to the cable quality monitoring result.

9. The quality statistical analysis method for cable manufacturing process according to claim 1, characterized in that: After obtaining the cable quality monitoring results, it also includes: Collect multiple source data of cables in real time, as well as their corresponding characteristic values ​​and cable quality monitoring results, to build a preliminary knowledge base; Use the preliminary knowledge base to train the machine learning model and obtain a trained quality analysis model; The trained quality analysis model is used to analyze the cable source data collected in real time to obtain quality monitoring results.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the steps of the quality statistical analysis method for a cable manufacturing process as claimed in any one of claims 1 to 9 are implemented.

Images