A method for controlling the production quality of cables and ground wires based on big data

Abstract

The present invention relates to the field of cable and ground wire production, and particularly to a method for quality control of cable and ground wire production based on big data. The method includes: obtaining the operation status data during the production process and performing preprocessing; constructing an anomaly index of the cable based on the relationship between the preprocessed data and the cable length, which is used to represent the anomaly degree of cable production at each data acquisition moment; calculating the coordination and adaptation degree between each device according to the difference between the anomaly index and the equipment data of each production process to obtain the relative efficiency index of the cable; modifying the objective function of the particle swarm optimization algorithm according to the relative efficiency index of the cable, obtaining the optimization result based on the modified particle swarm optimization algorithm, and completing the quality control of cable and ground wire production. Through the optimization result, the present invention adjusts the equipment operation parameters in real time to ensure that the equipment operates in the optimal state, thereby improving the efficiency of quality control of cable and ground wire production.

Description

Technical Field

[0001] The present invention relates to the field of cable and ground wire production. In particular, it relates to a method for quality control of cable and ground wire production based on big data. Background Art

[0002] As key components of the power transmission system, cables and ground wires undertake the important task of power transmission, and their performance and quality directly affect the safe and stable operation of the power system. A cable usually consists of a conductor, an insulating layer, a sheath, etc., and is used to transmit electrical energy; while the ground wire is an important component in the overhead line for transmitting current and bearing mechanical loads. They play a crucial role in the power system and are the key carriers to ensure power supply and transmission efficiency.

[0003] High-quality cables and ground wires can effectively ensure the safe and stable operation of the power system, reduce failures and accidents caused by quality problems, and ensure continuous and reliable power supply. Therefore, it is of great significance to strictly control the production quality of cables and ground wires. At the same time, strict quality control helps to improve product performance and service life, reduce the operation and maintenance costs of the power system and the equipment replacement frequency, and improve economic benefits.

[0004] However, in the process of quality control of cable and ground wire production, multiple objectives often need to be considered simultaneously, such as improving production efficiency, reducing costs, and ensuring product quality. The particle swarm optimization algorithm can handle multi-objective optimization problems. By introducing multiple objective functions, it can find the balance point between different objectives and achieve the maximization of comprehensive benefits. However, when dealing with complex optimization problems, the traditional particle swarm optimization algorithm is prone to falling into local optimal solutions or having problems with low convergence accuracy. A larger inertia weight is beneficial for global search but is likely to miss local optimal solutions; while a smaller inertia weight is beneficial for local search but may cause the algorithm to fall into local optimal solutions. In addition, fixed parameter settings are difficult to adapt to complex and changeable optimization problems, such as raw material differences and equipment limitations. This restricts the application of the traditional particle swarm optimization algorithm in the production process of cables and ground wires, unable to accurately reflect the coordinated adaptation of different equipment, resulting in poor optimization results and thus affecting the efficient control of production quality. Summary of the Invention

[0005] To solve the problems that the traditional particle swarm optimization algorithm in the quality control of cable and ground wire production cannot accurately reflect the coordinated adaptation of equipment, is prone to falling into local optimal solutions, resulting in poor optimization results and affecting the efficient control of production quality, the present invention provides solutions in the following aspects.

[0006] A method for controlling the production quality of cables and ground wires based on big data, comprising: acquiring the operation status data detected during the production process of cables and ground wires, and performing preprocessing; constructing an anomaly index of the cable based on the relationship between the preprocessed data and the cable length, which is used to represent the anomaly degree of cable production at each data acquisition moment; analyzing the difference of the relevant equipment data between each production process based on the anomaly index of the cable, calculating the coordination and adaptation degree between each equipment and the rest of the equipment, and obtaining the relative efficiency index of the cable; modifying the objective function of the particle swarm optimization algorithm according to the relative efficiency index of the cable, obtaining the optimization result based on the modified particle swarm optimization algorithm, and completing the control of the production quality of cables and ground wires.

[0007] By constructing the cable anomaly index by analyzing the relationship between the relevant data of different equipment during the production process of cables and ground wires and the production length of cables and ground wires, it is possible to accurately identify the anomaly degree of cable production at each data acquisition moment, which helps to timely discover problems in the production process and improve production efficiency and product quality; by constructing the relative efficiency index of the cable in combination with the continuity between each production process through the anomaly index of the cable, it is possible to respectively identify the difference degree between the production efficiency of each production process and the efficiency of the rest of the production processes, which is beneficial to optimizing the equipment used in each production process, thereby improving the overall production efficiency; by improving the objective function of the particle swarm optimization algorithm through the relative efficiency index of the cable, it is possible to more accurately optimize the power of the equipment used in each production process during the production process of cables and ground wires, significantly improving the control efficiency of the production quality of cables and ground wires and ensuring the high efficiency, stability and reliability of the production process.

[0008] Preferably, the operation status data includes: the instantaneous power, instantaneous voltage, instantaneous current data, linear velocity data and cable production length data of the equipment. The data of each dimension is aligned according to the time sequence, the missing values are filled or deleted, and the operation status data is standardized.

[0009] By accurately aligning the multi-dimensional data according to the time series, the synchronism and relevance of the data are ensured. For the possible missing values in the data, filling or deletion strategies are adopted to effectively handle data anomalies and ensure the integrity and reliability of the data. Further standardizing the operation status data eliminates the influence of different dimensions and magnitudes, enabling the data to be compared and analyzed on the same scale, and improving the comparability and usability of the data.

[0010] Preferably, the anomaly index of the cable includes:

[0011] Taking any equipment as the target equipment, taking the data of any moment of the target equipment as the marked data, and setting a sliding window with a preset number of data before the marked data;

[0012] Calculate the ratio between the difference in the values of the dimensional data of each data within the calculation window and the cable length produced corresponding to the dimensional data at the previous moment, plus the hyperparameter, to obtain the production speed change rate of the dimensional data of each data. Take the absolute value of the difference between the production speed change rate and the fixed proportionality constant between the dimensional data and the production speed change rate during the normal operation period, and perform normalization summation to obtain the anomaly index of the cable for each data of the target device within the window.

[0013] By setting a sliding window, calculate the production speed change rate of each data of the target device in real time, and compare it with the proportionality constant during normal operation, so as to accurately detect the abnormal degree of the device operation; monitor the production status in real time, timely detect abnormal fluctuations in the production process, dynamically adapt to the changes in the production process, timely capture short-term abnormal fluctuations, and avoid misjudgment caused by data lag.

[0014] Preferably, the anomaly index of the cable further includes:

[0015] Take any device as the target device, take the data at any moment of the target device as the marked data, and set a sliding window with a preset number of data before the marked data;

[0016] Calculate the absolute value of the difference between the value of the dimensional data of each data within the window and the product of the fixed proportionality constant between each dimensional data and the production speed change rate during the normal operation period and the cable length produced corresponding to the dimensional data of the previous moment in the sliding window, to obtain the degree of deviation of the device at the production speed;

[0017] Use the hyperbolic tangent function to sum the degree of deviation to obtain the anomaly index of the cable for each data of the target device within the window.

[0018] By calculating the degree of deviation at the production speed in real time through the sliding window, it is possible to timely detect abnormal fluctuations in the operating state of the device, ensure the stability of the production process, use the hyperbolic tangent function to perform non-linear mapping on the degree of deviation, convert the degree of deviation to a reasonable interval, and improve the accuracy and reliability of anomaly detection.

[0019] Preferably, the relative cable effectiveness index satisfies the following relationship:

[0020] ;

[0021] In the formula, represents the relative cable effectiveness index of the th data in the th device, represents the anomaly index of the cable of the th device for the th data, represents the number of dimensional data in the operating data, Indicates the number of equipment required for the corresponding processes of producing cables and ground wires, Indicates the th data of the th dimension among the th equipment, Indicates the th data of the th dimension among the th equipment, Indicates the cable equivalent coefficient of the th equipment and the th equipment in the th dimension.

[0022] By combining the cable anomaly index and the data difference between equipment, comprehensively evaluate the operating status of equipment during production. By analyzing the data differences of different equipment in each dimension, promote the coordinated operation of each equipment, reduce production problems caused by equipment differences, and by optimizing equipment operation parameters and coordination, reduce abnormal situations during production, improve product quality and stability.

[0023] Preferably, the construction of the cable relative efficiency index further includes:

[0024] Taking any equipment as the target equipment, calculate the product of the sum of the differences between the maximum and minimum values of all dimension data of each data in the target equipment and the cable anomaly index of each data of the target equipment, to obtain the cable relative efficiency index of each data in the target equipment.

[0025] Based on comprehensively evaluating the operating status of equipment during production, reflect the stability of equipment operation through the data fluctuation range, and accurately identify bottlenecks and problems in the production process by combining the anomaly index, which helps to improve production efficiency and product quality, and at the same time facilitates the optimization of resource allocation.

[0026] Preferably, the objective function of the particle swarm optimization algorithm is corrected according to the cable relative efficiency index, where the corrected objective function satisfies the following relational expression:

[0027] ;

[0028] In the formula, Indicates the corrected objective function of the th data corresponding to the particle swarm optimization algorithm, Indicates the number of equipment required for the corresponding processes of producing cables and ground wires, Indicates the th data of the length of the cable and ground wire of the th equipment, th data of the The relative efficiency index of the cable for a single data, indicating a hyperparameter.

[0029] Preferably, obtaining the optimization result includes:

[0030] Using the particle swarm optimization algorithm, taking the operation data collected in real time during the production process of the cable and the ground wire as the input of the particle swarm optimization algorithm, and the output is the optimal working power of each device at the current data collection moment. Based on the optimal working power, control each production device.

[0031] Preferably, the optimal working power includes:

[0032] Taking the duration included in a sliding window as an adjustment period, calculating the mean value of the optimal working power of each device at each data collection moment within the adjustment period, and taking the mean value as the optimal working power within the adjustment period.

[0033] Preferably, controlling each device in different production processes of the cable and the ground wire includes:

[0034] Based on the PID control algorithm, controlling each device in different production processes of the cable and the ground wire during the production process of the cable and the ground wire in units of the adjustment period, and adjusting the operation parameters of the device in real time to ensure that the device operates in the optimal state.

[0035] The present invention has the following effects:

[0036] 1. By collecting and preprocessing the operation status data in real time during the production process of the cable and the ground wire, the present invention can effectively remove noise and outliers, ensuring the accuracy and consistency of the data. Constructing a cable anomaly index can accurately identify the anomaly degree of cable production at each data collection moment, timely discover problems in the production process, and avoid production interruptions or product quality degradation caused by abnormal situations. Further analyzing the differences in the data of related devices between different production processes, calculating the coordination and adaptation degree of each device with the rest of the devices, and obtaining the relative efficiency index of the cable, so as to identify the bottleneck processes and devices in the production process, thereby improving production efficiency and quality.

[0037] 2. Based on the relative efficiency index of the cable, the present invention corrects the objective function of the particle swarm optimization algorithm, which can more accurately optimize the power of the devices used in each production process. The corrected particle swarm optimization algorithm avoids falling into the local optimal solution and speeds up the convergence rate by introducing mechanisms such as adaptive inertia weight and local optimal solution perturbation, ensuring the global optimality of the optimization result. Adjusting the operation parameters of the device in real time to ensure that the device operates in the optimal state significantly improves the production quality control efficiency of the cable and the ground wire. It not only improves production efficiency but also ensures the stability of the production process and the high quality of the product, realizing continuous improvement of production quality. Brief Description of the Drawings

[0038] Figure 1 It is a flowchart of the methods in steps S1 - S4 of a method for controlling the production quality of cables and ground wires based on big data according to an embodiment of the present invention.

[0039] Figure 2 It is the optimal working power of the equipment in the process of producing cables and ground wires in an embodiment of a method for controlling the production quality of cables and ground wires based on big data according to the present invention. Detailed Embodiments

[0040] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention.

[0041] Specific implementation scenario: When conducting on - line monitoring of cables, the main monitoring processes are: wire drawing, stranding, cabling, insulation, and double - wiring. Instantaneous power, instantaneous voltage, and instantaneous current data of the equipment used in each process, the linear velocity data of the equipment for producing cables in each production process, and the cable production length data are respectively collected in real - time through a cable production data acquisition system for the 5 processes.

[0042] Refer to Figure 1 , a method for controlling the production quality of cables and ground wires based on big data includes steps S1 - S4, specifically as follows:

[0043] S1: Obtain the operation status data detected during the production of cables and ground wires, and perform pre - processing.

[0044] The operation status data includes, but is not limited to: instantaneous power, instantaneous voltage, instantaneous current data, linear velocity data, and cable production length data of the equipment, etc. Align the data of each dimension according to time series, fill in or delete missing values, and perform standardization processing on the operation status data.

[0045] It should be noted that the data acquisition interval is 1 second. Here, the data acquisition interval is a hyper - parameter and can be selected according to the actual situation.

[0046] Since different equipment is used in different production processes, the value ranges of the instantaneous power, instantaneous voltage, and instantaneous current data of different equipment may vary greatly, and the dimensions of different data are different. Therefore, to avoid the influence of the data value range on subsequent calculations, the data collected in this application is subjected to standardization processing, and the analysis is based on the standardized data. Among them, the standardization processing of data is a well - known technology and will not be elaborated here.

[0047] Since the monitoring data and data processing methods for different processes are the same, for the sake of convenient description, this application takes the data processing in the wire drawing process as an example for description.

[0048] S2: Based on the relationship between the preprocessed data and the cable length, construct an anomaly index of the cable to represent the anomaly degree of the cable production at each data acquisition moment.

[0049] During the wire drawing process of the cable and the ground wire, under normal production rhythm, the monitoring data of the equipment and the length of the produced cable should be in a relatively fixed proportional relationship. For example, if the instantaneous power of the equipment increases within a period of time, the wire drawing length within this period should increase accordingly. Therefore, within the same time period, the ratio of the monitoring data values of the equipment to the change in the cable length produced should be close to a constant.

[0050] Since different control parameters of different equipment may have different influences on the production speed of the cable and the ground wire, by collecting the historical data of the operation of each equipment used in each production process during the production process of the cable and the ground wire, when the equipment is operating normally, calculate the proportional constants between the instantaneous voltage, instantaneous current, instantaneous power, linear velocity data of each equipment within the stable operation time period and the production length data of the cable and the ground wire respectively based on the obtained historical data.

[0051] The anomaly index includes:

[0052] Taking any equipment as the target equipment, taking the data at any moment of the target equipment as the marked data, and setting a sliding window with a preset number of data before the marked data;

[0053] Calculate the ratio of the difference between the value of the dimension data of each data in the window and the cable length corresponding to the dimension data at the previous moment plus the hyperparameter, obtain the production speed change rate of the dimension data of each data, and take the absolute value of the difference between the production speed change rate and the fixed proportional constant between the dimension data and the production speed change rate within the normal operation time period, and perform normalization summation to obtain the anomaly index of the cable of each data of the target equipment within the window.

[0054] Specifically, the anomaly index of the cable satisfies the following relational expression:

[0055] ;

[0056] In the formula, represents the anomaly index of the cable of the th equipment for the th data, represents the number of data in the sliding window, represents the number of dimension data in the operation data, represents function represents the value of the -th data in the -th data of the -th dimensional data in the sliding window of the represents the difference between the -th data and the cable length at the previous moment in the sliding window of the -th data of the represents a hyperparameter represents the fixed proportionality constant between the -th dimensional data and the production speed change rate during the normal operation period of the

[0057] That is to say, takes a value of 1 to avoid the inability to calculate due to a zero denominator and can be selected according to the actual situation.

[0058] The anomaly index of the cable is used to quantify the anomaly degree in the production process of the cable and the ground wire. When the instantaneous power of the equipment is large, but the cable length does not change correspondingly, it indicates that there may be an anomaly in the production process, and the calculated anomaly index will be larger. By introducing a sliding window, the calculation can consider the data change trend over a period of time, rather than just individual data, so as to more comprehensively capture the dynamic characteristics of the equipment operation. At the same time, by comparing the operation data of the current data with the proportionality constant in the normal operation state, the anomaly degree of the equipment in a specific dimension can be quantified. This method combines a sliding window, function and multi-dimensional data, providing strong support for the production quality control of the cable and the ground wire.

[0059] In addition, in another embodiment, it further includes:

[0060] Taking any device as the target device, using the data at any moment of the target device as the marked data, and setting a sliding window with a preset number of data before the marked data;

[0061] Calculating the absolute value of the difference between the product of the value of the dimensional data of each data in the window and the fixed proportionality constant between the dimensional data and the production speed change rate during the normal operation period and the product of each data in the sliding window and the cable length corresponding to the dimensional data at the previous moment, to obtain the deviation degree of the device at the production speed;

[0062] Using the hyperbolic tangent function to sum the deviation degrees to obtain the anomaly index of the cable of each data of the target device in the window.

[0063] Specifically, the anomaly index of the cable satisfies the following relational expression:

[0064] ;

[0065] In the formula, represents the anomaly index of the cable of the th device at the th data, represents the number of data within the sliding window, represents the number of dimensional data in the running data, represents the hyperbolic tangent function, represents the th device at the th data in the sliding window of the th data, the value of the th dimensional data, represents the th device at the th data in the sliding window of the th data, the difference between the th data and the cable length at the previous moment, represents the th device, the fixed proportionality constant between the

[0066] That is to say, it can directly reflect the speed of cable production from the change in cable length. reflects the th device at the th data in the sliding window of the th data, the difference between the th dimensional data and the dimensional data expected at the normal production speed; a large difference may mean that the operating state of the device deviates from the normal track and there is an anomaly. For example, if the instantaneous power of the device is large, but the change in cable length (production speed) does not increase correspondingly, then this difference will be large, indicating that there may be an anomaly in the production process.

[0067] Each production process of the cable and the ground wire is coherent and interconnected. The cable produced in the previous process will be transferred to the next production process through a conveyor belt or other means. Therefore, it is necessary to keep the production rates between each production process similar to avoid cable accumulation caused by a certain production process being too fast or affecting efficiency due to a production process being too slow. To ensure the mutual adaptation between each production process of the cable and the ground wire, it is necessary to construct a cable relative effectiveness index to reflect the relative production efficiency between each production process. The construction process of the cable relative effectiveness index is as follows:

[0068] S3: Analyze the differences in the data of related equipment between various production processes based on the anomaly index of the cable, calculate the coordination and adaptation degree of each equipment with the rest of the equipment, and obtain the relative efficiency index of the cable.

[0069] Specifically, the relative efficiency index of the cable satisfies the following relational expression:

[0070] ;

[0071] In the formula, represents the relative efficiency index of the cable for the th data in the th equipment, represents the anomaly index of the cable for the th equipment at the th data, represents the number of dimension data in the operation data, represents the number of equipment required for the corresponding processes of producing cables and ground wires, represents the th data in the th equipment for the th dimension data value, represents the th data in the th equipment for the th dimension data value, represents the cable equivalent coefficient for the th equipment and the th equipment at the th dimension.

[0072] That is to say, the relative efficiency index of the cable comprehensively considers the anomaly degree of the equipment and the data differences between the equipment, and reflects the relative efficiency of the th equipment in the production process. The smaller the value, the higher the production efficiency of the equipment and the better the coordination with other equipment. By comparing the data differences of different equipment in each dimension, evaluating the coordination and consistency between the equipment helps to discover the bottlenecks and problems in the production process.

[0073] The data differences of the equipment refer to the differences between the working parameters (voltage, power, current) of different equipment during operation. From the raw materials to the production of a complete cable, multiple links and multiple equipment are required. For example, during the wire drawing process, a wire drawing machine is needed, during the insulation process, an extrusion machine is needed, and during the double-wire process, a double-wire machine is needed. These equipment have corresponding working parameters during operation, such as the voltage and current of the wire drawing machine during operation, the power of the extrusion machine during operation, etc. There are certain differences in the parameters of different equipment during operation.

[0074] The cable relative efficiency index reflects the degree of coordination and adaptation between one process and the rest in the process of producing cables and ground wires. If the cable anomaly index of a device is larger at a certain moment, it indicates that the overall production process is more likely to have abnormal production conditions at this time. At the same time, the greater the difference in relevant parameters of different devices at the same moment, the greater the difference in production rates between different devices is likely to be at this time, so the calculated cable relative efficiency index is larger.

[0075] It should be noted that in the production process of cables and ground wires, the production rates of different links are closely related to the working parameters of the devices. For example, the higher the power of the wire drawing machine, the faster the wire drawing rate, and thus more cable wires are produced. However, the production process involves multiple links, and different devices are used in each link. If the power of the wire drawing machine is high, while the power of the devices in subsequent processes (such as stranding or cabling) is low, the subsequent devices may not be able to process the cable wires produced by the wire drawing machine in time, resulting in the accumulation of cable wires and affecting production efficiency. On the contrary, if the power of the subsequent devices is high and the processing speed is too fast, the wire drawing machine may not be able to supply enough cable wires in time, resulting in production interruption. In this case, the degree of coordination and adaptation between the wire drawing machine and other devices is low.

[0076] To quantify this degree of coordination and adaptation, we constructed the cable relative efficiency index to reflect the coordination between a certain device and other devices. Specifically, the cable relative efficiency index evaluates the coordination between devices by analyzing the relationship between the operating parameters (such as power, linear velocity, etc.) of different devices in the production process and the cable production rate. If the operating parameters of a certain device do not match the overall production rate, the cable relative efficiency index of this device will be higher, indicating that its coordination with other devices is poor.

[0077] In addition, at the same cable production rate, the working parameters of different devices may vary. For example, when the cable production speed is 5 m / s, the power of the wire drawing machine may be 100 kW, while the power of the stranding machine may be 80 kW. To balance these differences, we introduced the cable equivalent coefficient. The cable equivalent coefficient is used to adjust the differences in relevant parameters between different devices to ensure that the operating states of different devices can be fairly compared when evaluating device coordination.

[0078] By combining the cable relative efficiency index and the cable equivalent coefficient, we can comprehensively evaluate the degree of coordination and adaptation of each device in the production process, identify the bottleneck links in production efficiency, and thus optimize the device operating parameters to ensure the high efficiency, stability, and high quality of the entire production process.

[0079] In addition to this, in another embodiment, it further includes:

[0080] Taking any device as the target device, calculate the product of the sum of the differences between the maximum and minimum values of all dimensional data of each data in the target device and the anomaly index of each data cable of the target device, and obtain the cable relative efficiency index of each data in the target device.

[0081] Specifically, the cable relative efficiency index satisfies the following relational expression:

[0082] ;

[0083] In the formula, represents the cable relative efficiency index of the th data in the th device, represents the anomaly index of the cable of the th device for the th data, represents the number of dimensional data in the operation data, represents the maximum value of the th dimension of the th data in each device, represents the minimum value of the th dimension of the th data in each device.

[0084] That is to say, reflects the maximum difference degree of the production speeds of different production devices at the same production time, that is, the degree of production efficiency difference between different devices.

[0085] S4: Modify the objective function of the particle swarm optimization algorithm according to the cable relative efficiency index, obtain the optimization result based on the modified particle swarm optimization algorithm, and complete the production quality control of the cable and ground wire.

[0086] The modified objective function satisfies the following relational expression:

[0087] ;

[0088] In the formula, represents the objective function modified by the particle swarm optimization algorithm corresponding to the th data, represents the number of devices required for the corresponding process of producing the cable and ground wire, represents the length of the cable and ground wire of the th device for the th data, represents the cable relative efficiency index of the th device for the th data, represents the hyperparameter.

[0089] Exemplarily, , to avoid the inability to calculate due to a zero denominator, it can be selected according to the actual situation.

[0090] The optimization results include:

[0091] Using the particle swarm optimization algorithm, the operation data collected in real time during the production process of cables and ground wires is used as the input of the particle swarm optimization algorithm, and the output is the optimal working power of each device at the current data collection moment. Each production device is controlled based on the optimal working power.

[0092] The optimal working power includes:

[0093] Taking the duration included in a sliding window as an adjustment period, calculating the mean value of the optimal working power of each device at each data collection moment within the adjustment period, and taking the mean value as the optimal working power within the adjustment period.

[0094] Referring to Figure 2 , the figure shows the power variation of a certain device (such as a wire drawing machine or a stranding machine) during the cable production process, and the operating power of the device is optimized through PID control. Among them, the abscissa is the time series of the device operation (unit: second), and the ordinate is the power value of the device at different time points (unit: kilowatt).

[0095] The original power in the figure is represented by a blue curve, indicating the power variation of the device when no optimization control is performed. The power fluctuates greatly, especially near the time points of 500 seconds and 2000 seconds, where there are obvious peaks and valleys in the power. This kind of fluctuation may reflect the load changes of the device in different production stages, such as the wire drawing speed changes of the wire drawing machine in different stages or the stranding requirements changes of the stranding machine in different stages.

[0096] The optimized target power is represented by an orange curve: indicating the target power calculated by the optimization algorithm (such as the particle swarm optimization algorithm). The power change is relatively smooth and the fluctuation is small, reflecting the adjustment target of the optimization algorithm for the device operating power. The change of the optimized power curve is relatively stable near the time points of 500 seconds and 2000 seconds, avoiding the drastic fluctuations in the original power.

[0097] The power after PID control is represented by a green curve: indicating the actual power after the real-time adjustment of the device power through the PID control algorithm. The power change is between the original power and the optimized target power, and is relatively close to the optimized target power. PID control can dynamically adjust the operating parameters of the device, making the actual power of the device closer to the optimized target power, thereby improving the operating efficiency and stability of the device.

[0098] Based on the PID control algorithm, the equipment for different production processes of cables and ground wires is controlled in units of adjustment cycles, and the operating parameters of the equipment are adjusted in real time to ensure that the equipment operates in an optimal state.

[0099] Applying big data analysis technology to the production management and control process of cables and ground wires can significantly improve the efficiency of production quality control for cables and ground wires. By constructing a complete quality information collection system that covers the entire process from raw material entry to product shipment, specifically: through the information platform, the information synchronization between the sales end and the production end is more timely, eliminating information gaps, ensuring the security of order information. At the sales end, purchase orders required for production can be compiled and sent down, and the production progress of the corresponding orders can be viewed at any time; at the production end, the issued purchase orders can be viewed, and online production scheduling can be organized according to the orders, achieving efficient control over the production quality of cables and ground wires.

[0100] It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several variations and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent shall be subject to the appended claims.

Claims

1. A method for controlling the production quality of cables and ground wires based on big data, characterized in that, Including: Obtain the operation status data detected during the production process of cables and ground wires, and perform preprocessing; Based on the relationship between the preprocessed data and the cable length, construct an anomaly index for the cable to represent the anomaly degree of cable production at each data acquisition moment; Take any device as the target device, take the data at any moment of the target device as the marked data, and set a sliding window with a preset number of data before the marked data; Calculate the ratio of the difference between the value of the dimensional data of each data in the window and the cable length produced corresponding to the dimensional data at the previous moment plus the hyperparameter, obtain the production speed change rate of the dimensional data of each data, calculate the absolute value of the difference between the production speed change rate and the fixed proportional constant, and perform normalization summation to obtain the anomaly index of the cable for each data of the target device within the window; the fixed proportional constant is the fixed proportional constant between the dimensional data and the production speed change rate during the normal operation period; Analyze the differences in the data of related devices between each production process based on the anomaly index of the cable, calculate the coordination and adaptation degree between each device and the other devices, and obtain the relative efficiency index of the cable; Modify the objective function of the particle swarm optimization algorithm according to the relative efficiency index of the cable, obtain the optimization result based on the modified particle swarm optimization algorithm, and complete the production quality control of the cables and ground wires.

2. The method for controlling the production quality of cables and ground wires based on big data according to claim 1, wherein, The operation status data includes: the instantaneous power, instantaneous voltage, instantaneous current data, linear velocity data, and cable production length data of the device. Align the data of each dimension according to the time sequence, fill in or delete the missing values, and perform standardization processing on the operation status data.

3. A method for controlling the production quality of cables and ground wires based on big data according to claim 1, characterized in that, The anomaly index of the cable can also be calculated in another way, including: Take any device as the target device, take the data at any moment of the target device as the marked data, and set a sliding window with a preset number of data before the marked data; Calculate the absolute value of the difference between the value of the dimensional data of each data in the window and the product of the fixed proportional constant between the dimensional data and the production speed change rate during the normal operation period and the difference between each data in the sliding window and the cable length produced corresponding to the dimensional data at the previous moment, to obtain the deviation degree of the device at the production speed; Use the hyperbolic tangent function to sum the deviation degrees to obtain the anomaly index of the cable for each data of the target device within the window.

4. A method for quality control of cable and ground wire production based on big data according to claim 1, characterized in that The relative efficiency index of the cable satisfies the following relational expression: ； In the formula, represents the cable relative effectiveness index of the th data in the th device, represents the anomaly index of the cable of the th device for the th data, represents the number of dimensional data in the operation data, represents the number of devices required for the corresponding processes of the production cable and ground wire, represents the th data of the th dimensional data value in the th device, represents the th data of the th dimensional data value in the th device, represents the cable equivalent coefficient of the th device and the th device for the th dimension.

5. The quality control method for the production of cables and ground wires based on big data according to claim 1, characterized in that, The construction of the relative efficiency index of the cable also includes: Take any device as the target device, calculate the product of the sum of the differences between the maximum and minimum values of all dimensional data of each data in the target device and the anomaly index of the cable for each data of the target device, to obtain the relative efficiency index of the cable for each data in the target device.

6. A method for controlling the production quality of cables and ground wires based on big data according to claim 1, characterized in that, Modify the objective function of the particle swarm optimization algorithm according to the relative efficiency index of the cable, where the modified objective function satisfies the following relational expression: ； Wherein, represents the objective function after correction by the particle swarm optimization algorithm corresponding to the th data, represents the number of equipment required for the corresponding processes of producing cables and ground wires, represents the th data of the length of the cable and ground wire among the th equipment, represents the relative efficiency index of the cable corresponding to the th data among the represents a hyperparameter.

7. A method for controlling the production quality of cables and ground wires based on big data according to claim 1, characterized in that, Obtain the optimization result, including: Use the particle swarm optimization algorithm, take the operation data collected in real time during the production process of the cables and ground wires as the input of the particle swarm optimization algorithm, and the output is the optimal working power of each device at the current data acquisition moment, and control each production device based on the optimal working power.

8. A method for controlling the production quality of cables and ground wires based on big data according to claim 7, characterized in that, The optimal working power includes: Take the duration contained within a sliding window as an adjustment period, calculate the mean value of the optimal operating power of each device at each data acquisition moment within the adjustment period, and use the mean value as the optimal operating power within the adjustment period.

9. A method for controlling the production quality of cables and ground wires based on big data according to claim 1, characterized in that, Control each device in different production processes of cables and ground wires, including: Based on the PID control algorithm, control each device in different production processes of cables and ground wires during the production process of cables and ground wires in units of the adjustment period, and adjust the operating parameters of the devices in real time to ensure that the devices operate in the optimal state.

Images