Cable quality prediction method and system based on cable manufacturing link monitoring

Abstract

The embodiment of the invention discloses a cable quality prediction method and system based on cable manufacturing link monitoring, electronic equipment and a storage medium. According to the technical scheme provided by the embodiment of the invention, the cable quality parameter and the production fluctuation parameter of each sub-link in the cable production process are detected; determining a corresponding quality monitoring standard based on each sub-link, performing quality evaluation on the cable quality parameter of each sub-link based on the corresponding quality monitoring standard to obtain a sub-evaluation result, and calculating to obtain a sub-link evaluation value based on the sub-evaluation result and the production fluctuation parameter; and performing comprehensive calculation according to the calculated evaluation value of each sub-link to obtain a cable quality evaluation coefficient of the current production cable. By adopting the technical means, the cable quality is evaluated by integrating each sub-link and the production fluctuation condition of the cable production process, the cable quality evaluation accuracy can be improved, and the evaluation error of the cable quality is avoided. And the application stability and reliability of the cable are improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of cable, in particular to a cable quality prediction method and system based on cable manufacturing link monitoring. BACKGROUND

[0002] At present, in the cable manufacturing scene, accurate evaluation of product quality is the core link to ensure the stability and safety of power transmission. With the continuous development of industrial technology and the increasingly fierce market competition, customers have higher requirements for the performance, quality and delivery cycle of cable products. Therefore, in the cable manufacturing link, it is usually necessary to detect the conventional parameters (such as conductive performance, insulation performance, pressure strength, etc.) of the cable, and then evaluate the quality of the cable according to the detected conventional parameters, so as to ensure the stability of the cable production link. However, simply evaluating the quality of the cable according to the conventional parameters of the cable lacks monitoring of the cable generation link, resulting in that the cable quality evaluation result is difficult to accurately and comprehensively reflect the actual production quality of the cable, and the error of the cable quality evaluation result is relatively large. SUMMARY

[0003] Embodiments of the present application provide a cable quality prediction method and system based on cable manufacturing link monitoring, an electronic device and a storage medium, which can evaluate the quality of the cable by comprehensively considering each sub-link and production fluctuation of the cable production process, improve the accuracy of cable quality evaluation, and solve the problem of evaluation error of cable quality.

[0004] In a first aspect, embodiments of the present application provide a cable quality prediction method based on cable manufacturing link monitoring, comprising: detecting cable quality parameters and production fluctuation parameters of each sub-link in the cable production process; determining a corresponding quality monitoring standard based on each sub-link, performing quality evaluation on the cable quality parameters of each sub-link based on the corresponding quality monitoring standard to obtain a sub-evaluation result, and calculating a sub-link evaluation value based on the sub-evaluation result and the production fluctuation parameter; comprehensively calculating a cable quality evaluation coefficient of the current production cable according to the calculated sub-link evaluation values.

[0005] Further, the quality evaluation of the cable quality parameters of each sub-link based on the corresponding quality monitoring standard to obtain a sub-evaluation result comprises: determining a parameter deviation value based on the comparison of the cable quality parameters of each sub-link based on the corresponding quality monitoring standard; determining a sub-evaluation result according to the ratio of the parameter deviation value to a set quality evaluation threshold.

[0006] Further, the sub-link evaluation value is calculated based on the sub-evaluation result and the production fluctuation parameter, and the sub-evaluation result is generated based on the fluctuation parameter. The sub-evaluation result is generated based on the fluctuation parameter, and a correction coefficient is generated based on the fluctuation parameter.

[0007] Further, the cable quality evaluation coefficient of the current production cable is calculated based on the calculated sub-link evaluation values. The cable quality evaluation coefficient of the current production cable is calculated based on the calculated sub-link evaluation values and the process influence weight factor of each sub-link.

[0008] Further, the process influence weight factor is dynamically corrected based on the historical quality abnormality occurrence frequency of the corresponding sub-link.

[0009] Further, the quality monitoring standard is dynamically updated based on the qualified parameter range in the historical production data.

[0010] Further, the production fluctuation parameter includes at least two of the production equipment running state parameter, the environment state parameter and the material tension fluctuation parameter.

[0011] In a second aspect, the embodiments of the present application provide a cable quality prediction system based on cable manufacturing link monitoring, comprising: a detection module configured to detect cable quality parameters and production fluctuation parameters of each sub-link in a cable production process; a sub-link evaluation module configured to determine a corresponding quality monitoring standard based on each sub-link, perform quality evaluation on the cable quality parameters of each sub-link based on the corresponding quality monitoring standard to obtain a sub-evaluation result, and calculate a sub-link evaluation value based on the sub-evaluation result and the production fluctuation parameter; a comprehensive evaluation module configured to calculate a cable quality evaluation coefficient of a current production cable based on the calculated sub-link evaluation values.

[0012] In a third aspect, the embodiments of the present application provide an electronic device, comprising: a memory and one or more processors; the memory is configured to store one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the cable quality prediction method based on cable manufacturing link monitoring as described in the first aspect.

[0013] In a fourth aspect, the embodiments of the present application provide a storage medium containing computer executable instructions for executing the cable quality prediction method based on cable manufacturing link monitoring when executed by a computer processor.

[0014] The embodiments of the present application detect the cable quality parameters and production fluctuation parameters of each sub-link in the cable production process, determine the corresponding quality monitoring standards based on each sub-link, perform quality evaluation on the cable quality parameters of each sub-link based on the corresponding quality monitoring standards to obtain sub-evaluation results, and calculate sub-link evaluation values based on the sub-evaluation results and the production fluctuation parameters. The cable quality evaluation coefficient of the current production cable is obtained by comprehensive calculation according to the calculated sub-link evaluation values. By using the above technical means, the cable quality is evaluated by comprehensively evaluating each sub-link and production fluctuation of the cable production process, which can improve the accuracy of cable quality evaluation and avoid the evaluation error of cable quality. Further, the stability and reliability of the cable application are improved. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 is a flowchart of a cable quality prediction method based on cable manufacturing link monitoring provided by the first embodiment of the present application; Figure 2 is a flowchart of the determination of sub-evaluation results in the first embodiment of the present application; Figure 3 is a structural schematic diagram of a cable quality prediction system based on cable manufacturing link monitoring provided by the second embodiment of the present application; Figure 4 is a structural schematic diagram of an electronic device provided by the third embodiment of the present application. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application will be further described in detail below in combination with the drawings. It can be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the convenience of description, only the parts related to the present application are shown in the drawings, but not all the contents. Before discussing the example embodiments in more detail, it should be mentioned that some example embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be implemented in parallel, concurrently or simultaneously. In addition, the order of the operations can be rearranged. The processes can be terminated when the operations are completed, but can also have additional steps not included in the drawings. The processes can correspond to methods, functions, procedures, subroutines, subprograms, etc.

[0017] Embodiment I: Figure 1 A flowchart of a cable quality prediction method based on monitoring of the cable manufacturing process, provided in Embodiment 1 of this application, is given. This method can be executed by a cable quality prediction device based on monitoring of the cable manufacturing process. This device can be implemented through software and / or hardware. The device can consist of two or more physical entities, or it can be a single physical entity. Generally, this device can be a computing device such as a system server.

[0018] The following description uses a system server as the main entity executing a cable quality prediction method based on monitoring the cable manufacturing process. (Refer to...) Figure 1 The cable quality prediction method based on monitoring during the cable manufacturing process specifically includes: S110, Detect cable quality parameters and production fluctuation parameters at each sub-stage of the cable production process.

[0019] This application utilizes high-precision sensors and data acquisition systems deployed at various sub-stages of the cable manufacturing process to monitor cable quality parameters and production fluctuation parameters in real time.

[0020] In key processes such as conductor stranding, insulation extrusion, and sheath forming, monitoring points for quality parameters such as temperature, tension, and linear velocity are set up, while production fluctuation parameters such as equipment vibration, cooling water circulation stability, and material feeding uniformity are collected simultaneously. Real-time acquisition of multi-dimensional parameters constructs a digital mirror of the production process, covering both cable physical performance indicators and factors affecting process stability. This provides comprehensive data support for quality assessment, avoiding the lag and limitations of traditional end-point testing.

[0021] Optionally, the production fluctuation parameters include at least two of the following: production equipment operating status parameters, environmental status parameters, and material tension fluctuation parameters.

[0022] The introduction of production fluctuation parameters, by integrating multi-dimensional dynamic data such as equipment operating status, environmental conditions, and material properties, constructs a more accurate quality assessment model. For example, by deploying a multimodal sensor network at key workstations in the cable production line, real-time data is collected on equipment operating parameters such as extruder screw speed fluctuations and cooling water tank temperature drift. Simultaneously, environmental parameters such as temperature and humidity changes and dust concentration in the production workshop are monitored. Furthermore, material tension fluctuation curves throughout the entire process from the pay-off frame to the take-up device are captured using laser diameter gauges and tension sensors, thereby obtaining production fluctuation parameters such as equipment operating status parameters, environmental status parameters, and material tension fluctuation parameters.

[0023] It should be noted that, based on the actual cable quality monitoring needs, the types of sub-processes monitored, cable quality parameters, and production fluctuation parameters can be adaptively set and collected. This application does not impose fixed restrictions on the specific types of sub-processes, cable quality parameters, and production fluctuation parameters, and will not elaborate further here.

[0024] S120. Determine the corresponding quality monitoring standards for each sub-link, conduct quality assessments on the cable quality parameters of each sub-link based on the corresponding quality monitoring standards to obtain sub-assessment results, and calculate the sub-link assessment value based on the sub-assessment results and production fluctuation parameters.

[0025] Furthermore, by defining the corresponding quality monitoring standards for each sub-stage, a preliminary quality assessment of the cable quality parameters in each sub-stage is conducted based on these standards. For example, a dynamic quality monitoring standard library is established based on the process characteristics of each sub-stage, and edge computing nodes are used to perform real-time comparative analysis of the cable quality parameters collected in real time. For instance, in the insulation extrusion process, the real-time measured cable quality parameters such as eccentricity and wall thickness are compared with preset quality monitoring standard parameters for compliance judgment. The corresponding sub-evaluation results are obtained by quantifying the differences between the cable quality parameters and the standards. At the same time, production fluctuation parameters are introduced to construct a correction model. In specific implementation, a correlation model between equipment vibration spectrum and sheath surface defects can be established through machine learning algorithms. For example, based on the detected extruder screw vibration parameters, the quantified sub-evaluation results are adjusted according to the difference between the extruder screw vibration parameters and the standard vibration parameters, thereby obtaining the sub-stage evaluation value for that sub-stage.

[0026] The evaluation value of each sub-process is calculated by sub-evaluation results and production fluctuation parameters, so that the quality evaluation criteria of each sub-process can be made adaptive to the process. Through the compensation mechanism of production fluctuation parameters, the quality evaluation is closer to the actual working conditions, effectively reducing the misjudgment rate caused by process fluctuations and improving the process relevance of the evaluation results.

[0027] Optionally, refer to Figure 2 Based on the corresponding quality monitoring standards, the cable quality parameters of each sub-stage are evaluated to obtain sub-evaluation results, including: S1201. Determine the parameter deviation value by comparing the cable quality parameters of each sub-link with the corresponding quality monitoring standards. S1202. Determine the sub-evaluation result based on the ratio of the parameter deviation value to the set quality assessment threshold.

[0028] The application realizes dynamic comparison and analysis of cable quality parameters by constructing a dynamic quality monitoring standard library for each production link. For example, in the conductor stranding process, the system collects parameters such as conductor diameter and pitch in real time, and compares them with the tolerance range (i.e., the corresponding quality monitoring standard) of the corresponding specification cable in the dynamic quality monitoring standard library, and calculates the absolute deviation of the actual value from the median value in the standard. In the insulation extrusion link, the laser scanning device is used to obtain the sheath thickness distribution data, and the spatial fitting is performed with the preset concentricity model to generate the deviation matrix of parameters such as eccentricity and wall thickness uniformity. By establishing a quantitative judgment mechanism for parameter abnormalities, the accurate calculation of deviation values is used to replace the traditional binary judgment of qualified / unqualified, which can not only identify obvious out-of-tolerance items, but also capture the gradual quality degradation trend. For example, by continuously recording the positive deviation cumulative value of the conductor resistivity, the risk of conductive performance degradation caused by material purity fluctuations can be predicted in advance.

[0029] Further, a deviation-threshold ratio algorithm is used to construct a quality judgment system. Each quality parameter has a quality evaluation threshold, which represents the standard value of the allowable deviation of the corresponding quality parameter. According to the ratio of the parameter deviation value to the set quality evaluation threshold, the over-standard situation of the deviation value can be determined, and a quantitative sub-evaluation result of the current sub-link is obtained according to the over-standard situation. Taking the insulation withstand voltage test as an example, when the deviation ratio of the test voltage to the breakdown voltage reaches 1.15, it means that the current parameter is out of standard, and at this time the deviation ratio is taken as the sub-evaluation result, so as to quantitatively obtain the cable quality monitoring situation reflecting the insulation withstand voltage test link.

[0030] Further, based on the sub-evaluation result and the production fluctuation parameter, a sub-link evaluation value is calculated, including: A correction coefficient of the sub-evaluation result is generated based on the fluctuation parameter, and the sub-link evaluation value is calculated based on the correction coefficient and the sub-evaluation result.

[0031] In the process of calculating the sub-link evaluation value, first, real-time acquisition of production fluctuation parameters such as temperature fluctuation value, equipment vibration frequency, extrusion speed variation coefficient, etc. is performed, and data cleaning algorithm is used to eliminate abnormal noise data. Subsequently, the principal component analysis method is used to determine the contribution weight of each fluctuation parameter to the cable quality, and the fluctuation-quality influence relationship curve is established combined with the historical production data, and the fluctuation parameter is converted into the correction coefficient in the interval [0, 1]. The correction coefficient is fused with the sub-evaluation result through a dynamic weighting algorithm, for example, for the thickness qualified rate sub-evaluation result of the insulation extrusion link, multiply it by the temperature fluctuation correction coefficient and the extrusion speed stability correction coefficient, and finally generate the sub-link evaluation value reflecting the actual production stability. By converting dynamic factors such as equipment state and environmental interference into quantifiable correction factors, the quality evaluation can respond to production fluctuations in real time, avoid misjudgment caused by short-term process fluctuations, and at the same time provide data support for process parameter optimization, for example, when it is detected that the equipment vibration significantly affects the sheath uniformity at a certain period of time, the compensation adjustment of the extrusion die can be automatically triggered, forming a closed-loop linkage mechanism of quality prediction and process control.

[0032] Specifically, when the sub-link evaluation value is calculated based on the sub-evaluation result and the production fluctuation parameter, a dynamic correlation model of production fluctuation and quality evaluation can also be constructed to realize the process self-adaptive correction of the quality judgment result. Among them, by extracting the features of the production fluctuation parameters, the principal component analysis method (PCA) is used to select the key fluctuation factors whose impact weight on the cable quality is more than 15%. Subsequently, based on the historical quality data, a fluctuation-quality influence matrix is trained and generated. For example, when the fluctuation amplitude of the extruder screw speed exceeds ±2 rpm, the evaluation threshold of the sheath surface roughness parameter needs to be relaxed by 8%; if the environmental humidity rises by 5% RH, the correction coefficient of the insulation resistance test value needs to be increased by 0.12 times. Through the comparison and calculation of the real-time monitored fluctuation parameters and the influence matrix, a quality correction coefficient between 0.85-1.15 is dynamically generated. Finally, the original sub-evaluation result and the correction coefficient are subjected to nonlinear weighting operation, for example, in the conductor stranding process, when the tension fluctuation coefficient reaches 1.12, the system automatically adjusts the sub-evaluation result of the conductor resistivity parameter from 0.92 to 0.92x1.12=1.03, and obtains the corresponding sub-link evaluation value.

[0033] Further, the quality monitoring standard of the present application is dynamically updated based on the qualified parameter range in the historical production data.

[0034] The dynamic updating mechanism of the quality monitoring standard realizes the continuous synchronization of the quality evaluation benchmark and the actual production conditions. Among them, by establishing a historical database, the cable production parameter set confirmed as qualified by inspection is stored according to product specifications, material batches, equipment models, etc. dimensions, and a sliding time window mechanism is adopted, and the historical data in the last 3 months are preferentially used as the standard updating benchmark to reflect the natural decay trend of the process equipment state. On this basis, the kernel density estimation (KDE) algorithm is used to non-parametrically fit the qualified parameter distribution, automatically identify the dynamic boundaries of each sub-link parameter, for example, the standard range of the conductor resistivity is no longer a fixed ±3% deviation band, but is dynamically adjusted to a flexible interval of ±2.5% to ±3.5% according to the equipment accuracy level of the current production line and the material conductivity fluctuation characteristics. When the parameter distribution of the new production batch is detected to deviate significantly, the system starts the incremental learning process, and only uses the latest data to fine-tune the monitoring model, avoiding the evaluation error caused by the drift of historical data. This dynamic updating mechanism aligns the quality standard with the actual production in real time, so that the evaluation threshold can adapt to normal process changes such as equipment aging and material change, avoiding misjudgment of parameter deviation caused by process optimization as a quality problem; and by establishing an immune memory function of abnormal parameters, when a certain type of defect repeatedly occurs, the system automatically narrows the qualified range of the corresponding parameter, for example, after 3 batches of cables with sheath adhesion problems, the standard upper limit of the cooling water temperature is dynamically reduced from 45°C to 42°C, strengthening the management of key risk points; in addition, through traceable audit of the standard updating process, a continuous improvement closed loop of quality control is realized, and management personnel can query the standard version and change basis at any time node, providing process restoration capability accurate to the parameter dimension for quality accident investigation.

[0035] S130, according to the calculated evaluation values of each sub-link, the cable quality evaluation coefficient of the current production cable is calculated.

[0036] Finally, based on the above calculated evaluation values of each sub-link, the application uses multi-source data fusion to comprehensively calculate the evaluation values of each sub-link to generate the final cable quality evaluation coefficient. For example, by mapping the real-time sub-link evaluation values of each process to a three-dimensional process flow, a topological network analysis algorithm is used to identify the quality risk propagation path. For example, when the tension fluctuation evaluation value of the conductor stranding process and the abnormal value of the spark test of the insulation extrusion process form an associated cluster, the system automatically increases the risk weight of the overall quality coefficient. This dynamic weighting calculation mode realizes the leap from single process qualification to whole process quality prediction, through spatio-temporal correlation analysis of quality risks, it can early warning of quality problems, providing quantitative decision basis for production scheduling, and changing the quality control from passive inspection to active prevention.

[0037] Optionally, a cable quality evaluation coefficient of the current production cable is obtained by comprehensive calculation according to the calculated evaluation values of each sub-process. The cable quality evaluation coefficient of the current production cable is obtained by weighted summation according to the calculated evaluation values of each sub-process and the process influence weight factors set for each sub-process.

[0038] By constructing a multi-dimensional weight distribution model, the cable quality evaluation is refined and dynamic. Based on the historical quality defect database, the decision tree algorithm is used to identify the influence weight of each production sub-process on the final quality. For example, through analysis, it is found that the correlation strength of the insulation layer micro-hole defect and the extrusion temperature fluctuation is 2.3 times that of the take-up tension, and accordingly a higher weight coefficient is allocated to the extrusion process. Subsequently, an adaptive adjustment mechanism for the weight factor is established. When the influence degree of the quality fluctuation of a certain process on the overall qualification rate changes by more than 15%, the weight recalibration process is automatically triggered.

[0039] Further, when calculating the cable quality evaluation coefficient, the sub-process evaluation values of the key processes such as conductor stranding, insulation extrusion and sheath forming are input into the weighted summation model. For example, the conductor resistivity evaluation value of a batch of cables is 0.85 (weight 0.3), the insulation withstand voltage evaluation value is 0.92 (weight 0.4), and the sheath thickness evaluation value is 0.78 (weight 0.3). The comprehensive evaluation coefficient is 0.85x0.3+0.92x0.4+0.78x0.3=0.851, and the cable quality evaluation coefficient of the batch of cables is obtained in this way.

[0040] Through the differential configuration of the weight factor, the quality control resources can be tilted towards the key processes. When the comprehensive coefficient is lower than the threshold value, the system can accurately locate the abnormalities of the high-weight sub-processes such as conductor preheating deficiency. The dynamic weight mechanism enables the evaluation model to adapt to the changes in product structure, and the comprehensive evaluation coefficient provides a quantitative decision basis for production scheduling. Management personnel can start the quality traceability program immediately when the coefficient drops below the set value (such as 0.85) according to the coefficient change curve. Compared with the traditional end detection mode, the response speed of production quality problems can be greatly improved, and through the process weight analysis, the input-output ratio of quality improvement can be improved.

[0041] In addition, the process influence weight factor of the present application is dynamically modified according to the historical quality abnormality frequency of the corresponding sub-process.

[0042] By establishing a sub-link abnormal event log, record the quality problem type, frequency and severity of each process occurring in the past 12 months. For example, statistics show that the micro-hole defect rate of the insulation extrusion process reaches 3.7%, while the wire breakage rate of the conductor stranding process is only 0.8%. Based on these historical data, the marginal contribution rate of each process abnormality to the overall quality loss is calculated, and when the abnormal contribution rate of a certain process exceeds the set threshold, the weight adjustment process is automatically triggered. For example, when the surface scratch defect of the sheath forming process has a contribution rate of more than 15% for 3 consecutive months, the system will increase its process impact weight from 0.25 to 0.32, and simultaneously reduce the weight proportion of other stable processes. This dynamic correction mechanism can keep the quality weight distribution consistent with the actual risk distribution at all times, avoiding evaluation misalignment caused by process improvement or equipment update. When the weight of a certain process continues to rise, the system can automatically generate process optimization suggestions, such as upgrading the tension control system or optimizing the layout of the pay-off reel for the stranding process with a sudden increase in weight. In addition, the dynamic weight provides a forward-looking indicator for quality warning, and when a process with a weight adjustment amplitude of more than 20% is detected, a special quality audit is started in advance. Compared with the traditional periodic review mode, the problem discovery cycle can be shortened, and through trend analysis of weight changes, potential quality risk hotspots in the future can be predicted to provide data support for preventive maintenance.

[0043] The above, by detecting the cable quality parameters and production fluctuation parameters of each sub-link in the cable production process; based on each sub-link, determine the corresponding quality monitoring standard, based on the corresponding quality monitoring standard, perform quality evaluation on the cable quality parameters of each sub-link to obtain a sub-evaluation result, and based on the sub-evaluation result and the production fluctuation parameter, calculate a sub-link evaluation value; according to the calculated evaluation values of each sub-link, perform comprehensive calculation to obtain a cable quality evaluation coefficient of the current production cable. By using the above technical means, the cable quality is evaluated by comprehensively evaluating each sub-link and production fluctuation of the cable production process, which can improve the accuracy of cable quality evaluation and avoid evaluation errors of cable quality. Further, the stability and reliability of the cable application are improved.

[0044] Embodiment two: On the basis of the above embodiment, Figure 3 A structure diagram of a cable quality prediction system based on cable manufacturing link monitoring is provided for the second embodiment of the application. Referring to Figure 3 The cable quality prediction system based on cable manufacturing link monitoring provided by the embodiment specifically includes: The detection module 21 is configured to detect the cable quality parameters and production fluctuation parameters of each sub-link in the cable production process. The sub-link evaluation module 22 is configured to determine a corresponding quality monitoring standard based on each sub-link, perform quality evaluation on the cable quality parameter of each sub-link based on the corresponding quality monitoring standard to obtain a sub-evaluation result, and calculate a sub-link evaluation value based on the sub-evaluation result and the production fluctuation parameter. The comprehensive evaluation module 23 is configured to perform comprehensive calculation based on the calculated sub-link evaluation values to obtain a cable quality evaluation coefficient of the current production cable.

[0045] Specifically, the production fluctuation parameter includes at least two of a production equipment operation state parameter, an environmental state parameter, and a material tension fluctuation parameter.

[0046] Specifically, the quality evaluation on the cable quality parameter of each sub-link based on the corresponding quality monitoring standard to obtain a sub-evaluation result includes: comparing the cable quality parameter of each sub-link based on the corresponding quality monitoring standard to determine a parameter deviation value; determining the sub-evaluation result according to the ratio of the parameter deviation value to a set quality evaluation threshold.

[0047] The sub-link evaluation value is calculated based on the sub-evaluation result and the production fluctuation parameter, including: generating a correction coefficient of the sub-evaluation result based on the fluctuation parameter, calculating the sub-link evaluation value based on the correction coefficient and the sub-evaluation result.

[0048] The quality monitoring standard is dynamically updated based on the qualified parameter range in the historical production data.

[0049] Specifically, the comprehensive calculation based on the calculated sub-link evaluation values to obtain a cable quality evaluation coefficient of the current production cable includes: performing weighted summation according to the calculated sub-link evaluation values and a set process influence weight factor of each sub-link to obtain the cable quality evaluation coefficient of the current production cable.

[0050] The process influence weight factor is dynamically corrected according to the historical quality abnormality occurrence frequency of the corresponding sub-link.

[0051] The above, by detecting the cable quality parameters and production fluctuation parameters of each sub-link in the cable production process; determining the corresponding quality monitoring standard based on each sub-link, performing quality evaluation on the cable quality parameters of each sub-link based on the corresponding quality monitoring standard to obtain a sub-evaluation result, and calculating a sub-link evaluation value based on the sub-evaluation result and the production fluctuation parameters; and performing comprehensive calculation according to the calculated sub-link evaluation values to obtain a cable quality evaluation coefficient of the current production cable. By using the above technical means, the cable quality is evaluated by comprehensively considering each sub-link and production fluctuation in the cable production process, which can improve the accuracy of cable quality evaluation and avoid evaluation errors of the cable quality. Further, the stability and reliability of the cable application are improved.

[0052] The cable quality prediction system based on cable manufacturing link monitoring provided in Embodiment Two of the present application can be used to execute the cable quality prediction method based on cable manufacturing link monitoring provided in Embodiment One of the present application, and has corresponding functions and beneficial effects.

[0053] Embodiment Three: Embodiment Three of the present application provides an electronic device, which refers to Figure 4 The electronic device includes a processor 31, a memory 32, a communication module 33, an input device 34, and an output device 35. The number of processors in the electronic device can be one or more, and the number of memories in the electronic device can be one or more. The processor, memory, communication module, input device, and output device of the electronic device can be connected through a bus or other means.

[0054] The memory, as a computer readable storage medium, can be used to store software programs, computer executable programs, and modules, such as the program instructions / modules corresponding to the cable quality prediction method based on cable manufacturing link monitoring (for example, each module in the cable quality prediction system based on cable manufacturing link monitoring) described in any embodiment of the present application. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required by a function; the data storage area can store data created according to the use of the device, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some examples, the memory can further include a memory remotely arranged with respect to the processor, which can be connected to the device through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0055] The communication module is used for data transmission.

[0056] The processor executes various function applications and data processing of the device by running software programs, instructions and modules stored in the memory, i.e. implements the above-mentioned cable quality prediction method based on cable manufacturing link monitoring.

[0057] The input device can be used to receive inputted digital or character information, and generate key signal input related to user settings and function control of the device. The output device can include a display device such as a display screen.

[0058] The above-mentioned electronic device can be used to execute the cable quality prediction method based on cable manufacturing link monitoring provided by the above-mentioned embodiment one, and has corresponding functions and beneficial effects.

[0059] Embodiment four: The embodiment of the present application also provides a storage medium containing computer executable instructions, which are used to execute a cable quality prediction method based on cable manufacturing link monitoring when executed by a computer processor. The cable quality prediction method based on cable manufacturing link monitoring comprises: detecting cable quality parameters and production fluctuation parameters of each sub-link in a cable production process; determining corresponding quality monitoring standards based on each sub-link, performing quality evaluation on the cable quality parameters of each sub-link based on the corresponding quality monitoring standards to obtain a sub-evaluation result, and calculating a sub-link evaluation value based on the sub-evaluation result and the production fluctuation parameters; and performing comprehensive calculation according to the calculated sub-link evaluation values to obtain a cable quality evaluation coefficient of a current production cable.

[0060] Storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include an installation medium, e.g., a CD-ROM, floppy disks, or tape device; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; or a non-volatile memory such as a magnetic medium (e.g., a hard disk or optical storage); registers, or other similar types of memory elements, etc. The storage medium can also include other types of storage medium or combinations thereof. Moreover, the storage medium can be located in a first computer system in which the program is executed, or it can be located in a second different computer system which connects to the first computer system over a network such as the Internet. The second computer system can provide program instructions to the first computer system for execution. The term "storage medium" can include two or more storage mediums that reside in different locations, e.g., in different computer systems that are connected over a network. The storage medium can store program instructions (e.g., a computer program in which the program instructions are embodied) that can be executed by one or more processors.

[0061] Of course, the storage medium provided by the embodiments of the present application contains computer executable instructions, which are not limited to the cable quality prediction method based on cable manufacturing link monitoring as described above, but can also perform the related operations in the cable quality prediction method based on cable manufacturing link monitoring provided by any of the embodiments of the present application.

[0062] The cable quality prediction system based on cable manufacturing link monitoring, the storage medium and the electronic device provided in the above embodiments can execute the cable quality prediction method based on cable manufacturing link monitoring provided by any of the embodiments of the present application, and the technical details not described in detail in the above embodiments can be referred to the cable quality prediction method based on cable manufacturing link monitoring provided by any of the embodiments of the present application.

[0063] The above is only the preferred embodiments of the present application and the technical principles applied. The present application is not limited to the specific embodiments described herein, and various obvious changes, re-adjustments and substitutions made by those skilled in the art will not deviate from the protection scope of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments, and can include more other equivalent embodiments without deviating from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A method for predicting cable quality based on monitoring during the cable manufacturing process, characterized in that, include: Detect cable quality parameters and production fluctuation parameters at each sub-stage of the cable production process; Based on each sub-stage, corresponding quality monitoring standards are determined. Based on the corresponding quality monitoring standards, the cable quality parameters of each sub-stage are evaluated to obtain sub-evaluation results. Based on the sub-evaluation results and the production fluctuation parameters, the sub-stage evaluation value is calculated. The cable quality assessment coefficient for the currently produced cable is obtained by comprehensively calculating the evaluation values ​​of each sub-link.

2. The cable quality prediction method based on monitoring of the cable manufacturing process according to claim 1, characterized in that, The sub-evaluation results are obtained by performing quality assessments on the cable quality parameters of each sub-stage based on the corresponding quality monitoring standards, including: The parameter deviation value is determined by comparing the cable quality parameters of each sub-link with the corresponding quality monitoring standards. The sub-evaluation result is determined based on the ratio of the parameter deviation value to the set quality assessment threshold.

3. The cable quality prediction method based on monitoring of the cable manufacturing process according to claim 2, characterized in that, The calculation of the sub-process evaluation value based on the sub-evaluation results and the production fluctuation parameters includes: Based on the fluctuation parameters, a correction coefficient is generated for the sub-evaluation result, and based on the correction coefficient and the sub-evaluation result, the sub-stage evaluation value is calculated.

4. The cable quality prediction method based on monitoring of the cable manufacturing process according to claim 1, characterized in that, The process of comprehensively calculating the cable quality assessment coefficient for the currently produced cable based on the calculated evaluation values ​​of each sub-step includes: The cable quality evaluation coefficient for the current production cable is obtained by weighting and summing the calculated evaluation values ​​of each sub-step and the process influence weighting factors set for each sub-step.

5. The cable quality prediction method based on monitoring of the cable manufacturing process according to claim 4, characterized in that, The process influence weighting factor is dynamically adjusted based on the historical frequency of quality anomalies in the corresponding sub-process.

6. The cable quality prediction method based on monitoring of the cable manufacturing process according to claim 1, characterized in that, The quality monitoring standards are dynamically updated based on the range of acceptable parameters in historical production data.

7. The cable quality prediction method based on monitoring of the cable manufacturing process according to any one of claims 1-6, characterized in that, The production fluctuation parameters include at least two of the following: production equipment operating status parameters, environmental status parameters, and material tension fluctuation parameters.

8. A cable quality prediction system based on monitoring of the cable manufacturing process, characterized in that, include: The detection module is used to detect cable quality parameters and production fluctuation parameters at each sub-stage of the cable production process; The sub-process evaluation module is used to determine the corresponding quality monitoring standards for each sub-process, evaluate the cable quality parameters of each sub-process based on the corresponding quality monitoring standards to obtain sub-evaluation results, and calculate the sub-process evaluation value based on the sub-evaluation results and the production fluctuation parameters. The comprehensive evaluation module is used to calculate the cable quality evaluation coefficient of the currently produced cable based on the evaluation values ​​of each of the sub-links.

9. An electronic device, characterized in that, include: Memory and one or more processors; The memory is used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the cable quality prediction method based on cable manufacturing process monitoring as described in any one of claims 1-7.

10. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the cable quality prediction method based on monitoring of the cable manufacturing process as described in any one of claims 1-7.

Images