Cable insulation eccentricity control method and device based on big data analysis, equipment, storage medium and product

Abstract

The invention discloses a cable insulation eccentricity control method and device based on big data analysis, equipment, a storage medium and a product, and relates to the technical field of cable production. According to the method, the preset sample data in actual production is adopted for model training, the obtained eccentricity prediction model serves as the constraint condition, the optimal process parameters under the target eccentricity are obtained through the Bayesian parameter optimization algorithm, and therefore the relevant parameters are adjusted to be the optimal process parameters in the actual production process, and the production efficiency is improved. The control of the overall level of the insulation eccentricity is realized, a worker does not need to debug according to experience, the production efficiency can be improved, and the consistency of the production quality is improved.

Description

Technical Field

[0001] The present application relates to the technical field of cable production, and particularly relates to a method, device, equipment, storage medium and product for controlling the insulation eccentricity of a cable based on big data analysis. Background Art

[0002] In the related art, medium-voltage cables, as important products of the power transmission and distribution system, have strict requirements for the insulation eccentricity of the cables. At present, most of the methods for controlling the insulation eccentricity are to set the process formula according to experience and adjust the corresponding insulation eccentricity control scheme according to customer requirements. It is highly dependent on the experience of process personnel, and the efficiency is low during the adjustment process, making it difficult to meet the production requirements.

[0003] Therefore, how to efficiently control the insulation eccentricity of a cable is an urgent problem to be solved currently. Summary of the Invention

[0004] The main purpose of the present application is to provide a method, device, equipment, storage medium and product for controlling the insulation eccentricity of a cable based on big data analysis, aiming to solve the technical problem of how to efficiently control the insulation eccentricity of a cable.

[0005] To achieve the above purpose, the present application proposes a method for controlling the insulation eccentricity of a cable based on big data analysis. The method for controlling the insulation eccentricity of a cable based on big data analysis includes: Obtain an eccentricity prediction model, wherein the eccentricity prediction model is trained based on preset sample data, the input of the eccentricity prediction model is process parameters, and the output is the cable eccentricity; Take the eccentricity prediction model as a constraint condition of the Bayesian parameter optimization algorithm, and calculate the optimal process parameters under the target eccentricity through the Bayesian parameter optimization algorithm.

[0006] In some embodiments, before obtaining the eccentricity prediction model, the method further includes: Obtain production line data of multiple production lines within a set time range, where the production line data includes process parameters related to the production line and the cable eccentricity; Perform data preprocessing on the target production line data, where the target production line data is the production line data corresponding to the production line with the best data quality among the production line data of the multiple production lines; Determine the adjustable parameters and the cable eccentricity in the target production line data as the preset sample data; wherein the adjustable parameters are process parameters related to the cable eccentricity and can be adjusted; Train the eccentricity prediction model based on the preset sample data.

[0007] In some embodiments, before performing data preprocessing on the target production line data, the method further includes: For the production line data corresponding to each production line, based on preset rules, the accuracy, validity, completeness, timeliness, consistency and uniqueness of the production line data are evaluated to obtain a comprehensive evaluation result; The production line data corresponding to the production line with the best comprehensive evaluation result is determined as the target production line data.

[0008] In some embodiments, the target production line data includes a conductor diameter and temperatures of different regions of a plurality of extruders; after determining the production line data corresponding to the production line with the best comprehensive evaluation result as the target production line data, the method further includes: Based on the variation rules of the temperatures of different regions in the target production line data and the variation rules of the conductor diameters, the target production line data is divided to obtain debugging stage data and stabilization stage data; The debugging phase data is eliminated from the target production line data.

[0009] In some embodiments, the training to obtain the eccentricity prediction model based on the preset sample data includes: The preset deep neural network model is trained by using the preset sample data to obtain a preliminary model; Evaluating the preliminary model through a preset evaluation model; Based on the evaluation results, an eccentricity prediction model is determined, wherein the input of the eccentricity prediction model includes the body temperature, screw speed, flange temperature, glue guide temperature, die head temperature, and pulling speed of each of the multiple extruders.

[0010] In some embodiments, the eccentricity prediction model is used as a constraint condition of the Bayesian parameter optimization algorithm, and the optimal process parameters under the target eccentricity are calculated by the Bayesian parameter optimization algorithm, including: Taking the target eccentricity as an objective function, establishing prior knowledge on the global behavior of the objective function; By observing the output of the objective function at the current sampling point, the prior knowledge is updated to obtain the posterior distribution; Based on the posterior distribution, determine the next sampling point, and return to execute the step of observing the output of the objective function at the current sampling point, updating the prior knowledge, and obtaining the posterior distribution; When the number of loop executions reaches the set number, the output of the objective function finally obtained is used as the optimal process parameter.

[0011] In addition, to achieve the above object, the present application also proposes a cable insulation eccentricity control device based on big data analysis. The cable insulation eccentricity control device based on big data analysis includes: A model acquisition module, configured to acquire an eccentricity prediction model, wherein the eccentricity prediction model is trained based on preset sample data, the input of the eccentricity prediction model is process parameters, and the output is the cable eccentricity; A parameter generation module, configured to use the eccentricity prediction model as a constraint condition of the Bayesian parameter optimization algorithm, and calculate the optimal process parameters under the target eccentricity through the Bayesian parameter optimization algorithm.

[0012] In addition, to achieve the above object, the present application also proposes a cable insulation eccentricity control device based on big data analysis. The cable insulation eccentricity control device based on big data analysis includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. The computer program is configured to implement the steps of the cable insulation eccentricity control method based on big data analysis as described above.

[0013] In addition, to achieve the above object, the present application also proposes a storage medium. The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the cable insulation eccentricity control method based on big data analysis as described above are implemented.

[0014] In addition, to achieve the above object, the present application also provides a computer program product. The computer program product includes a computer program. When the computer program is executed by a processor, the steps of the cable insulation eccentricity control method based on big data analysis as described above are implemented.

[0015] One or more technical solutions proposed by the present application have at least the following technical effects: Using the preset sample data in actual production for model training, taking the obtained eccentricity prediction model as a constraint condition, and obtaining the optimal process parameters under the target eccentricity through the Bayesian parameter optimization algorithm, so as to adjust the relevant parameters to the optimal process parameters in the actual production process, realizing the control of the overall level of insulation eccentricity, without the need for staff to debug according to experience, which can improve production efficiency and the consistency of production quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0017] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 Fig. 4 shows a schematic flowchart of a method for controlling the cable insulation eccentricity based on big data analysis provided by an embodiment of the present application; Figure 2 Fig. 7 shows a schematic structural diagram of a device for controlling the cable insulation eccentricity based on big data analysis provided by an embodiment of the present application; Figure 3 Fig. 10 shows a schematic structural diagram of a device for controlling the cable insulation eccentricity based on big data analysis provided by an embodiment of the present application.

[0019] The realization of the purpose, functional characteristics and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0020] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0021] To better understand the technical solutions of the present application, the following will be described in detail in combination with the accompanying drawings of the specification and the specific embodiments.

[0022] The main solution of the embodiment of the present application is: obtaining an eccentricity prediction model, wherein the eccentricity prediction model is trained based on preset sample data, the input of the eccentricity prediction model is process parameters, and the output is the cable eccentricity; Taking the eccentricity prediction model as a constraint condition of the Bayesian parameter optimization algorithm, and calculating the optimal process parameters under the target eccentricity through the Bayesian parameter optimization algorithm.

[0023] In the related art, as an important product of the power transmission and distribution system, the requirement of the insulation eccentricity of medium-voltage cables is an important technical index of the product. At present, most of the methods for enterprises to control the insulation eccentricity are to set the process formula according to experience and adjust the corresponding insulation eccentricity control scheme according to customer requirements. It is difficult to establish a perfect and clear process formula system in a targeted and data-supported manner. From a business perspective, the insulation eccentricity is affected by multiple links and various factors such as people, machines, materials, methods, environment, and measurement in the production process. When there are changes in equipment, product types, or raw materials on the production line, on-site process personnel can only debug individual parameters through experience. This black-box debugging method not only affects production efficiency but also leads to inconsistent product quality.

[0024] In summary, how to efficiently control the eccentricity of cable insulation.

[0025] Based on this, the present application provides a solution, enabling the control during the cable production process without relying on the experience of process personnel, but generating relevant process parameters under the required eccentricity based on the method of industrial big data analysis, so as to efficiently control the insulation eccentricity of the produced cable.

[0026] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a cable insulation eccentricity control device based on big data analysis that can implement the above functions. Hereinafter, taking the cable insulation eccentricity control device based on big data analysis as an example, this embodiment and the following embodiments will be described.

[0027] Refer to Figure 1 , Figure 1 shows a schematic flow chart of a cable insulation eccentricity control method provided by an embodiment of the present application based on big data analysis. The cable insulation eccentricity control method based on big data analysis can be applied to a cable insulation eccentricity control device based on big data analysis, including the following steps S110 to step S120: Step S110, obtain an eccentricity prediction model.

[0028] In some embodiments, the eccentricity prediction model is trained based on preset sample data.

[0029] Before step S110, an eccentricity prediction model can be trained in advance through preset sample data, which can specifically include the following steps S210 to step S240: Step S210: Obtain production line data of multiple production lines within a set time range.

[0030] Among them, the production line data includes process parameters related to the production line and the cable eccentricity.

[0031] The application scenario of this embodiment can be set as the medium-voltage workshop of a suspension chain cross-linked cable production line, where the production voltage of the medium-voltage workshop is between 6kv and 35kv. As an example, all data including raw materials, process parameters, equipment parameters, production parameters, and inspection related in 5 suspension chain cross-linked cable production lines in the medium-voltage workshop within 4 months (i.e., production line data) can be obtained. Among them, the data collection frequency of the production line data can be preset to once every 10s, and this embodiment does not make a limitation here.

[0032] Among them, a cross-linked cable refers to a cable with better performance formed by chemically cross-linking the conductive wire core after extrusion of the inner shield, insulation layer, and outer shield, then entering the cross-linking tube, making the extruded polyethylene molecules form cross-linked polyethylene, and then entering the cooling tube for cooling. The production line of cross-linked cables can include an extrusion unit (including multiple extruders), a cross-linking machine cooling system, upper and lower traction devices, wire pay-off, take-up and storage devices, a control system, and various auxiliary devices.

[0033] In some embodiments, after obtaining the production line data of multiple production lines, for the production line data corresponding to each production line, based on preset rules, evaluate the accuracy, effectiveness, integrity, timeliness, consistency, and uniqueness of the production line data to obtain a comprehensive evaluation result; determine the production line data corresponding to the production line with the optimal comprehensive evaluation result as the target production line data.

[0034] Specifically, conduct quality analysis on all the collected production line data and evaluate the analysis value to ensure the accuracy of the subsequent obtained samples, and further ensure the accuracy of the eccentricity prediction model trained. Among them, accuracy refers to the authenticity and correctness of the production line data, ensuring that the data must reflect the real business content; effectiveness refers to whether the data meets the expected use, and the value and format requirements of the data should meet the requirements of the data definition or business definition; integrity refers to the comprehensiveness of the data, which measures the completeness of the production line data; timeliness refers to the timeliness and update frequency of the production line data, ensuring that the data is updated in a timely manner; consistency refers to whether the logic of the data meets the expectations, that is, the type, format, standard, and meaning of the data must be consistent and clear; uniqueness refers to that in the production line data, for a certain data item or a group of data, there are no duplicate data values.

[0035] Based on the above rules, evaluating the production line data shows that for the production line with the best comprehensive performance in the above items, the corresponding production line data has the best evaluation value, that is, it can be determined as the target production line data.

[0036] Step S220: Perform data preprocessing on the target production line data.

[0037] In some embodiments, data preprocessing may include the following parts: ① Outlier handling.

[0038] Outlier handling refers to the correction of outliers including format outliers, unit outliers, and indentation outliers. The way of outlier correction can be modified by the staff themselves, which is not limited in this embodiment.

[0039] ② Missing value filling.

[0040] Missing value filling refers to filling the missing data in the records according to the data definition and time series relationship, using the mean value, adjacent value, median value, or filling by category.

[0041] ③ Outlier removal.

[0042] In this embodiment, data outside 1.5 times the interquartile range can be defined as outlier data, and this part of the outlier data is removed as outliers.

[0043] Specifically, 1.5 times the interquartile range specifically means 1.5 times the distance between the number at the 1 / 4 position (denoted as Q1) and the number at the 3 / 4 position (denoted as Q3) among all the data. Data outside this range is regarded as an outlier and removed. The calculation formula for the interquartile range IQR is:

[0044] ④ Normalization.

[0045] Normalization means changing the data to the range of [0, 1], which can be executed through the following expression:

[0046] Among them, Xi is the i-th sample value, Xmin is the minimum value in the sample, Xmax is the maximum value in the sample, and X is the value of the i-th sample after normalization.

[0047] After performing the above preprocessing on the target production line data, the target production line data can be divided into stages based on the key factors in the preprocessed target production line data. It can be understood that during the production process, there are an equipment debugging stage and a stable production stage. During the equipment debugging stage, the staff continuously adjusts various parameters to make the production tend to be stable. And during the stable production stage, the parameters have been adjusted to the specified values and no longer change, and the various data generated during the production process show regular changes.

[0048] Specifically, the target production line data can be divided based on the change rules of the temperature in different regions and the change rules of the conductor diameter in the target production line data to obtain debugging stage data and stable stage data; the debugging stage data is removed from the target production line data.

[0049] Among them, the temperature set values of each zone of the extruder and the conductor diameter can represent different production periods and different wires. During the stable production stage, the data changes stably or fluctuates regularly without being interfered by human factors, and at this time the extruder operates normally; during the equipment debugging stage, it may include operations such as machine preheating, conductor replacement, and personnel operation, and is greatly affected by human operation.

[0050] Step S230: determining the adjustable parameters and cable eccentricity in the target production line data as the preset sample data.

[0051] After excluding the data from the debugging phase, the target production line data obtained includes some inherent parameters and some adjustable parameters. Among them, inherent parameters refer to parameters that cannot be adjusted by staff, and adjustable parameters refer to parameters that can be adjusted through equipment, processes, etc., thus affecting the entire production process.

[0052] Since the ultimate purpose of this embodiment is to adjust the parameters so as to control the eccentricity, it is necessary to screen out the adjustable parameters in the target production line data for subsequent further processing.

[0053] Step S240: Based on the preset sample data, the eccentricity prediction model is trained and obtained.

[0054] In some embodiments, the produced cables can be divided into different categories according to preset characterization indicators, so that eccentricity prediction models can be established for different categories respectively, thereby further ensuring accuracy.

[0055] Specifically, the characterization index may include the conductor diameter and the conductor voltage level. In a feasible example, the produced conductors may be divided into 7 categories according to the characterization indexes, and subsequent eccentricity prediction models may be established for each category.

[0056] In some implementations, different machine learning and deep learning algorithms can be selected for different categories to establish eccentricity prediction models. Specifically, the machine learning algorithm can include but is not limited to gradient boosting decision tree, XGBOOT, support vector machine, random forest, ridge regression model, etc., and the deep learning algorithm can include but is not limited to DNN deep neural network, LSTM model, etc., which are not limited in this embodiment.

[0057] After establishing the eccentricity prediction model for each category, the ability of the eccentricity prediction model can be further evaluated. Specifically, the evaluation can be performed using mean square error, R² score, etc.

[0058] The mean square error refers to the square mean of the difference between the predicted value and the true value. The mean square error can be calculated by expression (1): (1) Where n is the number of samples, is the true value of the i-th sample, is the model's predicted value for the i-th sample.

[0059] The R² score refers to the coefficient of determination, which is used to characterize the proportion of data variance explained by the model. The R² score can be calculated using expression (2): R² = SSR / SST (2) Among them, SSR stands for the regression sum of squares, which measures the strength of the linear relationship between the independent variable and the dependent variable; SST stands for the total sum of squares, which measures the degree of variation of the dependent variable. It can be understood that the R² value is between 0 and 1. The closer it is to 1, the better the model fits the data, indicating that the independent variable can explain a higher proportion of the variation of the dependent variable; the closer it is to 0, the worse the model fits, and the weaker the ability of the independent variable to explain the variation of the dependent variable.

[0060] In some implementations, the eccentricity prediction model may also be evaluated by a custom evaluation model. Specifically, the custom evaluation model may be expression (3): (3) Npre represents the number of integer digits of the predicted value and the integer digits of the true value whose absolute value is less than 0.2, and Ntotal represents the total number of samples, that is: (4) Among them, Count is the counting function, Xpre is the predicted value, and Xpre is the actual value.

[0061] By evaluating the trained eccentricity prediction model, the staff can correct the model in time to ensure a higher prediction accuracy.

[0062] In some embodiments, based on the eccentricity prediction model obtained in the above steps, a deep neural network (DNN) can be selected to establish a regression model for subsequent analysis. A deep neural network is a computational model that simulates the structure and function of a human brain neural network. Its basic unit is a neuron. Each neuron receives input from other neurons. The weight is adjusted to change the impact of the input on the neuron. Through multiple layers of nonlinear hidden layers, complex functions can be approximated to achieve a universal approximation effect.

[0063] In DNN, the input data starts from the input layer, is calculated layer by layer through the hidden layer, and finally reaches the output layer. The output of each layer serves as the input of the next layer, and nonlinear transformation is achieved through the activation function.

[0064] In some embodiments, the input layer may include the body temperature, screw speed, flange temperature, glue guide temperature, die head temperature, and pulling speed data of the inner screen, insulation, and outer screen extruders.

[0065] As a feasible implementation, four hidden layers can be set, and the number of neurons in each hidden layer is set in the order of increasing first and then decreasing, and the activation function is selected as "relu". The output content of the output layer is the prediction result, and the prediction result is a single output, and the activation function can be selected as "tanh".

[0066] After obtaining the prediction result, the absolute value of the integer part of the predicted value and the actual value can be calculated. If the absolute value is less than the set error, it can be defined as a correct prediction. By counting the accuracy rate, the effect of the model can be verified.

[0067] In some embodiments, if the effect of the model does not meet the expectation, the RMSprop optimizer can also be selected to optimize the learning rate and the stochastic gradient descent value of the model. Finally, the prediction accuracy rate of the eccentricity prediction model can be adjusted to more than 96%.

[0068] Step S120: Take the eccentricity prediction model as the constraint condition of the Bayesian parameter optimization algorithm, and calculate the optimal process parameters at the target eccentricity through the Bayesian parameter optimization algorithm.

[0069] In this embodiment, the Bayesian parameter optimization algorithm can be adopted. According to the set optimization target (i.e., the target eccentricity), the eccentricity is reduced below a certain target eccentricity, and the eccentricity prediction model trained in the previous embodiment is used as the constraint condition to automatically optimize and obtain the optimal process parameters at the target eccentricity.

[0070] Specifically, the target eccentricity can be used as the objective function to establish prior knowledge about the global behavior of the objective function; where the global behavior refers to the change trend or change law of the objective function (i.e., the target eccentricity) in the entire parameter space. Since there are interactions between process parameters, the change trend of the target eccentricity (i.e., the global behavior) objectively exists. For example, the target eccentricity may change smoothly within certain parameter ranges and change violently within other ranges. In this embodiment, the prior knowledge is the initial assumption of the Bayesian parameter optimization algorithm for the objective function (i.e., the target eccentricity), and can be assumed to be a constant or a simple function, for example.

[0071] Add the output of the objective function at the current set of sampling points to the Gaussian process model, and update the mean and covariance functions of the Gaussian process; update the hyperparameters of the Gaussian process through an optimization method to obtain the posterior distribution; based on the posterior distribution, determine the next set of sampling points, and use the posterior distribution obtained this time as the prior knowledge for the next execution, and return to execute the steps of "add the output of the objective function at the current set of sampling points to the Gaussian process model, and update the mean and covariance functions of the Gaussian process; update the hyperparameters of the Gaussian process through an optimization method to obtain the posterior distribution; based on the posterior distribution, determine the next set of sampling points"; when the number of loop executions reaches the set number (for example, it can be 200 times), use the set of sampling points corresponding to the last loop as the optimal process parameters.

[0072] In this embodiment, the prior knowledge selected for the first iteration can be data randomly selected from the preset sample data; in addition, during the process of using the Bayesian parameter optimization algorithm, the target eccentricity and some of the involved functions (such as the marginal probability function involved in the Bayesian parameter optimization algorithm) can be preset by the staff.

[0073] In this embodiment, according to the initial value (i.e., prior knowledge) randomly selected from the sample and the boundary values of the usage characteristics, after several iterations, the inferred density function distribution concentrates all the relevant information in the population, sample, and prior, and at the same time excludes the irrelevant information, which can ensure the accuracy of the finally obtained optimal process parameters.

[0074] This embodiment provides a method for controlling the cable insulation eccentricity based on big data analysis. The preset sample data in actual production is used for model training, and the obtained eccentricity prediction model is used as a constraint condition. The optimal process parameters under the target eccentricity are obtained through the Bayesian parameter optimization algorithm, so as to adjust the relevant parameters to the optimal process parameters during the actual production process, realize the control of the overall level of insulation eccentricity, and there is no need for the staff to debug according to experience, which can improve production efficiency and the consistency of production quality.

[0075] This application also provides a device for controlling the cable insulation eccentricity based on big data analysis. Please refer to Figure 2 , the device 100 for controlling the cable insulation eccentricity based on big data analysis includes: A model acquisition module 110, configured to acquire an eccentricity prediction model, where the eccentricity prediction model is trained based on preset sample data, and the input of the eccentricity prediction model is process parameters and the output is the cable eccentricity; A parameter generation module 120, configured to use the eccentricity prediction model as a constraint condition of the Bayesian parameter optimization algorithm, and calculate the optimal process parameters under the target eccentricity through the Bayesian parameter optimization algorithm.

[0076] The cable insulation eccentricity control device 100 based on big data analysis provided by the present application adopts the cable insulation eccentricity control method based on big data analysis in the above-mentioned embodiment, and can solve the technical problem of how to efficiently control the cable insulation eccentricity. Compared with the prior art, the beneficial effects of the cable insulation eccentricity control device 100 based on big data analysis provided by the present application are the same as those of the cable insulation eccentricity control method based on big data analysis provided by the above-mentioned embodiment, and other technical features in the cable insulation eccentricity control device 100 based on big data analysis are the same as the features disclosed in the method of the above-mentioned embodiment, which will not be elaborated herein.

[0077] The present application provides a cable insulation eccentricity control device based on big data analysis. The cable insulation eccentricity control device based on big data analysis includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the cable insulation eccentricity control method in Embodiment 1 above.

[0078] Next, refer to Figure 3 , which shows a schematic structural diagram of a cable insulation eccentricity control device suitable for implementing the embodiment of the present application. The cable insulation eccentricity control device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description: tablet computers), PMPs (Portable Media Player: portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The shown cable insulation eccentricity control device is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present application.

[0079] As Figure 3As shown, the cable insulation eccentricity control device 200 based on big data analysis may include a processing device 210 (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 220 or a program loaded from a storage device 230 into a random access memory (RAM: Random Access Memory) 240. In the RAM 240, various programs and data required for the operation of the cable insulation eccentricity control device based on big data analysis are also stored. The processing device 210, the ROM 220, and the RAM 240 are connected to each other through a bus 250. An input / output (I / O) interface 260 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 260: an input device 270 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 280 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 230 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 290. The communication device 290 may allow the cable insulation eccentricity control device based on big data analysis to communicate with other devices wirelessly or wirelesly to exchange data. Although the figure shows a cable insulation eccentricity control device with various systems based on big data analysis, it should be understood that it is not required to implement or have all the shown systems. Instead, more or fewer systems may be implemented or had.

[0080] Particularly, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device, or installed from the storage device 230, or installed from the ROM 220. When the computer program is executed by the processing device 210, the above functions defined in the methods of the embodiments disclosed in the present application are executed.

[0081] The cable insulation eccentricity control device based on big data analysis provided by this application adopts the cable insulation eccentricity control method based on big data analysis in the above-mentioned embodiment, and can solve the technical problem of how to efficiently control the cable insulation eccentricity. Compared with the prior art, the beneficial effects of the cable insulation eccentricity control device based on big data analysis provided by this application are the same as those of the cable insulation eccentricity control method based on big data analysis provided by the above-mentioned embodiment, and other technical features in the cable insulation eccentricity control device based on big data analysis are the same as the features disclosed in the method of the previous embodiment, and will not be elaborated here.

[0082] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0083] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0084] This application provides a computer-readable storage medium with computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the cable insulation eccentricity control method based on big data analysis in the above-mentioned embodiment.

[0085] The computer-readable storage medium provided by the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium can be transmitted by any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0086] The above computer-readable storage medium may be included in the cable insulation eccentricity control device based on big data analysis; or it may exist alone without being assembled into the cable insulation eccentricity control device based on big data analysis.

[0087] The above computer-readable storage medium carries one or more programs. When the above one or more programs are executed by the cable insulation eccentricity control device based on big data analysis, the cable insulation eccentricity control device based on big data analysis can write computer program code for performing the operations of the present application in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages - such as Java, Smalltalk, C++, and also include conventional procedural programming languages - such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0088] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0089] The modules described in the embodiments of the present application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation to the unit itself in some cases.

[0090] The readable storage medium provided by the present application is a computer-readable storage medium, and the computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned method for controlling the eccentricity of cable insulation based on big data analysis, which can solve the technical problem of how to efficiently control the eccentricity of cable insulation. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as those of the method for controlling the eccentricity of cable insulation based on big data analysis provided by the above embodiments, and will not be elaborated here.

[0091] The present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it realizes the steps of the method for controlling the eccentricity of cable insulation based on big data analysis as described above.

[0092] The computer program product provided by the present application can solve the technical problem of how to efficiently control the eccentricity of cable insulation. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the method for controlling the eccentricity of cable insulation based on big data analysis provided by the above embodiments, and will not be elaborated here.

[0093] The above are only some embodiments of the present application, and do not limit the patent scope of the present application. All equivalent structural transformations made under the technical concept of the present application by using the content of the specification and drawings of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A cable insulation eccentricity control method based on big data analysis, characterized in that: The cable insulation eccentricity control method based on big data analysis includes: Obtaining an eccentricity prediction model, wherein the eccentricity prediction model is trained based on preset sample data, the input of the eccentricity prediction model is a process parameter, and the output is the cable eccentricity; The eccentricity prediction model is used as a constraint condition of the Bayesian parameter optimization algorithm, and the optimal process parameters under the target eccentricity are calculated through the Bayesian parameter optimization algorithm.

2. The cable insulation eccentricity control method based on big data analysis according to claim 1, characterized in that: Before obtaining the eccentricity prediction model, the cable insulation eccentricity control method based on big data analysis also includes: Acquire production line data of multiple production lines within a set time range, wherein the production line data includes process parameters related to the production lines and cable eccentricity; Performing data preprocessing on target production line data, wherein the target production line data is production line data corresponding to a production line with the best data quality among the production line data of the multiple production lines; Determine the adjustable parameters and cable eccentricity in the target production line data as the preset sample data; wherein the adjustable parameters are process parameters related to the cable eccentricity and adjustable; The eccentricity prediction model is trained based on the preset sample data.

3. The cable insulation eccentricity control method based on big data analysis according to claim 2, characterized in that: Before the target production line data is preprocessed, the cable insulation eccentricity control method based on big data analysis further includes: For the production line data corresponding to each of the production lines, based on preset rules, the accuracy, validity, completeness, timeliness, consistency and uniqueness of the production line data are evaluated to obtain a comprehensive evaluation result; The production line data corresponding to the production line with the best comprehensive evaluation result is determined as the target production line data.

4. The cable insulation eccentricity control method based on big data analysis according to claim 3 is characterized in that: The target production line data includes conductor diameter and temperature of different areas of multiple extruders; after determining the production line data corresponding to the production line with the best comprehensive evaluation result as the target production line data, the cable insulation eccentricity control method based on big data analysis also includes: Based on the variation rules of the temperatures of different regions in the target production line data and the variation rules of the conductor diameters, the target production line data is divided to obtain debugging stage data and stabilization stage data; The debugging phase data is eliminated from the target production line data.

5. The cable insulation eccentricity control method based on big data analysis according to claim 2, characterized in that: The step of training the eccentricity prediction model based on the preset sample data includes: The preset deep neural network model is trained by using the preset sample data to obtain a preliminary model; Evaluating the preliminary model through a preset evaluation model; Based on the evaluation results, an eccentricity prediction model is determined, wherein the input of the eccentricity prediction model includes the body temperature, screw speed, flange temperature, glue guide temperature, die head temperature, and pulling speed of each of the multiple extruders.

6. The cable insulation eccentricity control method based on big data analysis according to claim 1, characterized in that: The eccentricity prediction model is used as a constraint condition of the Bayesian parameter optimization algorithm, and the optimal process parameters under the target eccentricity are calculated by the Bayesian parameter optimization algorithm, including: Taking the target eccentricity as an objective function, establishing prior knowledge on the global behavior of the objective function; Add the output of the objective function at the current set of sampling points to the Gaussian process model, and update the mean and covariance function of the Gaussian process; Update the hyperparameters of the Gaussian process through optimization methods to obtain the posterior distribution; Based on the posterior distribution, determine the next set of sampling points, use the posterior distribution as the prior knowledge for the next execution, and return to execute the step of adding the output of the objective function at the current set of sampling points to the Gaussian process model and updating the mean and covariance function of the Gaussian process; When the number of execution cycles reaches the set number, a group of sampling points corresponding to the last cycle is used as the optimal process parameters.

7. A cable insulation eccentricity control device based on big data analysis, characterized in that: The cable insulation eccentricity control device based on big data analysis includes: A model acquisition module, used to acquire an eccentricity prediction model, wherein the eccentricity prediction model is obtained by training based on preset sample data, the input of the eccentricity prediction model is a process parameter, and the output is the cable eccentricity; The parameter generation module is used to use the eccentricity prediction model as a constraint condition of the Bayesian parameter optimization algorithm, and calculate the optimal process parameters under the target eccentricity through the Bayesian parameter optimization algorithm.

8. A cable insulation eccentricity control device based on big data analysis, characterized in that: The cable insulation eccentricity control device based on big data analysis includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the cable insulation eccentricity control method based on big data analysis as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the cable insulation eccentricity control method based on big data analysis as described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the cable insulation eccentricity control method based on big data analysis as claimed in any one of claims 1 to 6 are implemented.

Images