Temperature intelligent monitoring and control method and system for cable material production

Abstract

The present invention discloses a temperature intelligent monitoring and control method and system for cable material production, which relates to the technical field related to data processing. The method comprises: obtaining the conceptual performance design of the conceptual cable material, obtaining the conceptual raw material cost, and determining the production raw material set by matching the conceptual performance design with the conceptual raw material cost. Obtain a target extruder and obtain a corresponding historical processing data set. Construct a material performance prediction network based on the historical processing data set, and reversely predict to obtain abnormal data. Batch production is carried out with the target screw control parameter as the constraint control, and a temperature monitoring array is arranged to perform temperature monitoring. A temperature anomaly recognition network is pre-constructed, and temperature anomaly recognition and warning are performed based on real-time temperature array information. The technical problem that the temperature monitoring method for cable material production in the prior art has a low matching degree with the extruder, resulting in low accuracy of temperature monitoring in cable material production, thereby affecting the quality of cable production is solved.

Description

Technical Field

[0001] The present application relates to data processing technology-related fields, and specifically to a temperature intelligent monitoring and control method and system for cable material production. Background Art

[0002] In modern industrial production, cable materials serve as the outer sheath of cables, providing physical protection for the internal conductors and insulation layers to prevent mechanical damage, friction, impact, etc. The performance design of cable materials and the optimization of extruder production processes are the key to ensuring cable quality and production efficiency. However, the temperature monitoring method for cable material production in the prior art has a low matching degree with the extruder, resulting in low accuracy of temperature monitoring in cable material production, which makes it difficult to improve the quality of cable production.

[0003] Therefore, in the prior art, the temperature monitoring method for cable material production has a low matching degree with the extruder, resulting in low accuracy of temperature monitoring for cable material production, thus affecting the technical problem of cable production quality. Summary of the invention

[0004] This application provides a temperature intelligent monitoring and control method and system for cable material production, which solves the technical problem that the temperature monitoring method for cable material production in the prior art has a low matching degree with the extruder, resulting in low accuracy of temperature monitoring in cable material production, thereby affecting the quality of cable production. The application achieves the technical effect of matching the corresponding raw material ratio and extruder based on the performance design parameters of the cable material, and setting a temperature monitoring array corresponding to the extruder, thereby improving the accuracy of temperature monitoring and the quality of cable production.

[0005] The present application provides a temperature intelligent monitoring and control method for cable material production, the method comprising: interactively obtaining a conceptual performance design of a conceptual cable material, wherein the conceptual performance design comprises a plurality of conceptual performance parameters of a plurality of conceptual performance indicators and a plurality of conceptual performance deviation thresholds; interactively obtaining a conceptual raw material cost, and determining a production raw material set with the conceptual performance design and the conceptual raw material cost as constraint matching, wherein the production raw material set comprises a plurality of production raw materials and a plurality of additive ratio identifiers; interactively obtaining a plurality of material characteristic sets of the plurality of production raw materials, and matching a target extruder with the plurality of material characteristic sets and the plurality of conceptual performance parameters as constraints; performing data networking calls with the model information of the target extruder and the production raw material set as constraints, and obtaining a historical processing data set, wherein the historical processing data set comprises a plurality of sample heating section lengths; degree distribution, multiple sample heating section temperature distribution, multiple sample screw control parameters and multiple sample performance measured information; construct a material performance prediction network based on the historical processing data set, and reversely predict the target heating section length distribution, target heating section temperature distribution and target screw control parameters based on the material performance prediction network and the multiple conceptual performance parameters; control the target extruder to carry out batch production of the concept cable material with the target screw control parameters as constraints, and arrange a temperature monitoring array on the target extruder according to the target heating section length distribution and the target heating section temperature distribution to carry out temperature monitoring of the batch production process of the concept cable material; pre-construct a temperature anomaly recognition network, and the temperature anomaly recognition network receives and analyzes the real-time temperature array information sent back by the temperature monitoring array to carry out temperature anomaly recognition and early warning.

[0006] The present application also provides a temperature intelligent monitoring and control system for cable material production, including:

[0007] A performance data interaction module, used for interactively obtaining a conceptual performance design of a conceptual cable material, wherein the conceptual performance design includes a plurality of conceptual performance parameters of a plurality of conceptual performance indicators and a plurality of conceptual performance deviation thresholds;

[0008] A raw material ratio acquisition module, used for interactively obtaining a conceptual raw material cost, and determining a production raw material set by matching the conceptual performance design and the conceptual raw material cost as constraints, wherein the production raw material set includes a plurality of production raw materials and a plurality of additive ratio identifiers;

[0009] An extruder matching module, used for interactively obtaining a plurality of material characteristic sets of the plurality of production raw materials, and matching and obtaining a target extruder with the plurality of material characteristic sets and the plurality of conceptual performance parameters as constraints;

[0010] A processing data acquisition module, used to perform data networking call based on the model information of the target extruder and the production raw material set as constraints to obtain a historical processing data set, wherein the historical processing data set includes a plurality of sample heating section length distributions, a plurality of sample heating section temperature distributions, a plurality of sample screw control parameters and a plurality of sample performance measured information;

[0011] A control parameter acquisition module, configured to construct a material performance prediction network based on the historical processing data set, and reversely predict the target heating section length distribution, the target heating section temperature distribution and the target screw control parameters based on the material performance prediction network and the plurality of conceptual performance parameters;

[0012] A temperature monitoring module, used for controlling the target extruder to carry out batch production of the concept cable material with the target screw control parameter as a constraint, and arranging a temperature monitoring array in the target extruder according to the target heating section length distribution and the target heating section temperature distribution to carry out temperature monitoring of the batch production process of the concept cable material;

[0013] The temperature warning module is used to pre-build a temperature anomaly recognition network, which receives and analyzes the real-time temperature array information sent back by the temperature monitoring array to perform temperature anomaly recognition and warning.

[0014] The temperature intelligent monitoring and control method and system for cable material production proposed in this application are proposed to interactively obtain the conceptual performance design of the conceptual cable material, wherein the conceptual performance design includes multiple conceptual performance parameters and multiple conceptual performance deviation thresholds of multiple conceptual performance indicators. The conceptual raw material cost is interactively obtained, and the production raw material set is determined by matching the conceptual performance design and the conceptual raw material cost as constraints, wherein the production raw material set includes multiple production raw materials and multiple addition ratio identifiers. Multiple material characteristic sets of the multiple production raw materials are interactively obtained, and the target extruder is matched by matching the multiple material characteristic sets and the multiple conceptual performance parameters as constraints. The model information of the target extruder and the production raw material set are constrained to perform data networking calls to obtain a historical processing data set, wherein the historical processing data set includes multiple sample heating section length distributions, multiple sample heating section temperature distributions, multiple sample screw control parameters and multiple sample performance measured information. A material performance prediction network is constructed based on the historical processing data set, and a target heating section length distribution, a target heating section temperature distribution and a target screw control parameter are obtained by reverse prediction based on the material performance prediction network and the multiple conceptual performance parameters. The target extruder is controlled with the target screw control parameter as a constraint to carry out batch production of the concept cable material. A temperature monitoring array is arranged in the target extruder according to the target heating section length distribution and the target heating section temperature distribution to carry out temperature monitoring of the batch production process of the concept cable material. A temperature anomaly recognition network is pre-constructed, and the temperature anomaly recognition network receives and analyzes the real-time temperature array information sent back by the temperature monitoring array to carry out temperature anomaly recognition and early warning. The technical problem that the temperature monitoring method for cable material production in the prior art has a low matching degree with the extruder, resulting in low accuracy of temperature monitoring in cable material production, thereby affecting the quality of cable production is solved. The corresponding raw material ratio and extruder are obtained based on the performance design parameters of the cable material, and a temperature monitoring array corresponding to the extruder is set, thereby improving the accuracy of temperature monitoring and the technical effect of cable production quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0016] Figure 1 A schematic diagram of a flow chart of a temperature intelligent monitoring and control method for cable material production provided in an embodiment of the present application;

[0017] Figure 2 A schematic diagram of the structure of a temperature intelligent monitoring and control system for cable material production provided in an embodiment of the present application.

[0018] Explanation of the reference numerals: performance data interaction module 11 , raw material ratio acquisition module 12 , extruder matching module 13 , processing data acquisition module 14 , control parameter acquisition module 15 , temperature monitoring module 16 , temperature early warning module 17 . DETAILED DESCRIPTION

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0020] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0021] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0022] The present application provides a temperature intelligent monitoring and control method and system for cable material production, such as Figure 1 As shown, the method includes:

[0023] Interactively obtaining a conceptual performance design of a conceptual cable material, wherein the conceptual performance design includes a plurality of conceptual performance parameters of a plurality of conceptual performance indicators and a plurality of conceptual performance deviation thresholds;

[0024] Interactively obtain the conceptual raw material cost, and determine the production raw material set by matching the conceptual performance design and the conceptual raw material cost as constraints, wherein the production raw material set includes multiple production raw materials and multiple additive ratio identifiers;

[0025] Interactively obtain multiple material property sets of the multiple production raw materials, and match and obtain a target extruder with the multiple material property sets and the multiple conceptual performance parameters as constraints;

[0026] The interactive recording data obtains the conceptual performance design of the conceptual cable material, wherein the conceptual performance design requirements and the conceptual raw material cost requirements of the conceptual cable material are recorded in the recorded data. The conceptual performance design is the preset performance data recorded for the conceptual cable material, and the conceptual performance design includes multiple conceptual performance parameters and multiple conceptual performance deviation thresholds of multiple conceptual performance indicators. The conceptual performance indicators are the performance indicator categories of the conceptual cable materials, such as cable performance indicators such as heat resistance and electrical insulation performance. The conceptual performance parameters are specific indicator parameters corresponding to the conceptual performance indicators, such as the specific temperature of heat resistance. The conceptual performance deviation threshold is the deviation floating range of the conceptual performance parameters, such as plus or minus 5 degrees Celsius. Subsequently, the interactive recording data obtains the conceptual raw material cost, and the production raw material set is determined by matching the conceptual performance design and the conceptual raw material cost as constraints, wherein the production raw material set includes a plurality of production raw materials, i.e., raw material types, and a plurality of added ratio identifiers, i.e., specific ratio data of the raw materials. Furthermore, multiple material property sets of the multiple production raw materials are interactively obtained, where the material property sets are material properties of the raw materials such as material melting point, softening point, melt viscosity, thermal stability, etc., and the target extruder is matched and obtained using the multiple material property sets and the multiple conceptual performance parameters as constraints.

[0027] The method provided in the embodiment of the present application also includes:

[0028] Pre-constructing a production raw material information database, wherein the production raw material information database includes a performance comparison execution layer and a raw material cost calculation layer, the performance comparison execution layer is pre-configured with a performance comparison engine, and the raw material cost calculation layer is pre-configured with a cost calculation engine;

[0029] Interactively obtain multiple sample raw material ratio information and multiple sample performance measured information of multiple sample cable materials, associate and store the multiple sample raw material ratio information and the multiple sample performance measured information, and then synchronize them to the performance comparison execution layer;

[0030] Interactively obtain real-time unit prices of multiple sample raw materials, and synchronize the real-time unit prices of the multiple sample raw materials to the raw material cost calculation layer to complete the construction of the production raw material information database;

[0031] The production raw material set is determined by matching the production raw material information database with the conceptual performance design and the conceptual raw material cost as constraints.

[0032] Pre-construct a production raw material information library, and record the sample raw material ratio information and sample performance measured information of various sample cable materials of historical production data in the production raw material information library. Among them, the production raw material information library includes a performance comparison execution layer and a raw material cost calculation layer, the performance comparison execution layer is pre-configured with a performance comparison engine, and the raw material cost calculation layer is pre-configured with a cost calculation engine. The performance comparison engine in the performance comparison execution layer is used to match the corresponding sample cable data according to the conceptual performance design, and the cost calculation engine in the raw material cost calculation layer is used to calculate the real-time cost parameters according to the acquired sample cable data. The interactive production raw material information library obtains multiple sample raw material ratio information and multiple sample performance measured information of multiple sample cable materials, and after associating and storing the multiple sample raw material ratio information and the multiple sample performance measured information, synchronizes them to the performance comparison execution layer, so as to facilitate the subsequent matching of corresponding samples based on the conceptual performance design. Interactively obtain the real-time unit prices of multiple sample raw materials, and synchronize the real-time unit prices of the multiple sample raw materials to the raw material cost calculation layer to complete the construction of the production raw material information library. Finally, taking the conceptual performance design and the conceptual raw material cost as constraints, the production raw material set is determined by matching in the production raw material information library through the performance comparison execution layer and the raw material cost calculation layer.

[0033] The method provided in the embodiment of the present application also includes:

[0034] generating a plurality of concept performance matching thresholds according to the plurality of concept performance parameters and the plurality of concept performance deviation thresholds;

[0035] Activating the performance comparison engine of the performance comparison execution layer based on the multiple concept performance matching thresholds to traverse and compare the multiple sample performance measured information to obtain multiple screening raw material ratio information;

[0036] At the raw material cost calculation layer, traverse and match the real-time unit prices of the multiple sample raw materials according to the multiple screening raw material ratio information to obtain multiple screening raw material unit price groups, and perform cost calculation on the multiple screening raw material ratio information and the multiple screening raw material unit price groups through the cost calculation engine to obtain multiple screening raw material costs;

[0037] The multiple screening raw material costs are serialized, compared with the conceptual raw material cost, and the production raw material set is obtained by calling, wherein the screening raw material cost of the production raw material set is closest to the conceptual raw material cost.

[0038] The method further comprises generating multiple concept performance matching thresholds according to the multiple concept performance parameters and multiple concept performance deviation thresholds, wherein the multiple concept performance matching thresholds are the obtained performance parameter intervals. In the exemplary concept performance parameters, the temperature is 80 degrees Celsius and the corresponding concept performance deviation threshold is plus or minus 5 degrees Celsius, and the concept performance matching threshold is 75 degrees Celsius to 85 degrees Celsius. Subsequently, based on the multiple concept performance matching thresholds, the performance comparison engine of the performance comparison execution layer is activated to traverse and compare the multiple sample performance measured information, obtain samples in which all performance indicators in the sample performance measured information fall within the corresponding concept performance matching threshold interval, and obtain the corresponding raw material ratio information to obtain multiple screening raw material ratio information. Further, based on the multiple screening raw material ratio information, the real-time unit prices of multiple sample raw materials are traversed and matched in the raw material cost calculation layer to obtain multiple screening raw material unit price groups, and the cost calculation engine is used to calculate the cost of the multiple screening raw material ratio information and the multiple screening raw material unit price groups to obtain multiple screening raw material costs. The multiple screening raw material costs are serialized according to the cost level, and compared with the conceptual raw material cost, and the production raw material set is obtained by calling, wherein the screening raw material cost of the production raw material set is the production raw material set that is closest to the conceptual raw material cost.

[0039] The method provided in the embodiment of the present application also includes:

[0040] Preset extrusion-related indicators, wherein the extrusion-related indicators include material melting point, softening point, melt viscosity and thermal stability;

[0041] Using the extrusion-related index to traverse the multiple material characteristic sets, and screen to obtain multiple extrusion-related characteristic sets;

[0042] Performing temperature intersection calculation on the multiple extrusion-related characteristic sets to obtain a target processing temperature threshold;

[0043] Interactively obtaining a plurality of sample design parameters and a plurality of sample processing-related information of a plurality of sample screws, wherein the data structure of each sample processing-related information includes a sample processing temperature threshold and a plurality of sample performance parameters;

[0044] Obtaining multiple screw fitness coefficients of the multiple conceptual performance parameters, the target processing temperature threshold, and the multiple sample processing associated information based on Euclidean distance calculation;

[0045] The plurality of screw fitness coefficients are serialized and extreme value calls are performed to obtain target screw design parameters, and extruder pairing is performed according to the target screw design parameters to obtain the target extruder.

[0046] Interactively obtain multiple material property sets of the multiple production raw materials, and match and obtain the target extruder with the multiple material property sets and the multiple conceptual performance parameters as constraints. The method also includes: presetting extrusion-related indicators, wherein the extrusion-related indicators include material melting point, softening point, melt viscosity and thermal stability. Use the extrusion-related indicators to traverse the material properties corresponding to the extrusion-related indicators in the multiple material property sets, and screen to obtain multiple extrusion-related characteristic sets, each of which contains the extrusion-related indicators and the material properties of the corresponding materials. Further, perform temperature intersection calculation on the multiple extrusion-related characteristic sets to obtain the target processing temperature threshold, that is, obtain the temperature intersection of the extrusion-related characteristic sets of each material, determine the temperature range corresponding to the temperature intersection, and obtain the target processing temperature threshold. Interactively obtain multiple sample design parameters and multiple sample processing-related information of multiple sample screws through historical sample screw data, wherein each sample screw corresponds to a set of sample screw design parameters and corresponding one or more sample processing-related information, and the data structure of each sample processing-related information includes a sample processing temperature threshold and multiple sample performance parameters, and the sample performance parameters are the performance parameters of the cable. Based on the Euclidean distance calculation, multiple screw fitness coefficients of the multiple conceptual performance parameters, the target processing temperature threshold and the multiple sample processing associated information are obtained, that is, the Euclidean distance calculation of the corresponding parameters of each sample screw is performed according to the multiple conceptual performance parameters, the target processing temperature threshold and the multiple sample processing associated information of the multiple sample screws, and the fitness coefficients of the multiple sample screws are obtained. Further, the multiple screw fitness coefficients are serialized and extreme value calls are performed, and the minimum value of the screw fitness coefficient is called. Since the smaller the Euclidean distance calculation result, the higher the consistency of the corresponding parameter, the sample processing associated information corresponding to the minimum value of the screw fitness coefficient is obtained, the corresponding screw design parameters are obtained, the target screw design parameters are obtained, and the extruder pairing is performed according to the target screw design parameters to obtain the target extruder.

[0047] Using the model information of the target extruder and the production raw material set as constraints, a data networking call is performed to obtain a historical processing data set, wherein the historical processing data set includes a plurality of sample heating section length distributions, a plurality of sample heating section temperature distributions, a plurality of sample screw control parameters, and a plurality of sample performance measured information;

[0048] Constructing a material property prediction network based on the historical processing data set, and reversely predicting based on the material property prediction network and the plurality of conceptual performance parameters to obtain a target heating section length distribution, a target heating section temperature distribution, and a target screw control parameter;

[0049] The target extruder is controlled to carry out batch production of the concept cable material with the target screw control parameter as a constraint, and a temperature monitoring array is arranged in the target extruder according to the target heating section length distribution and the target heating section temperature distribution to carry out temperature monitoring of the batch production process of the concept cable material;

[0050] A temperature anomaly recognition network is pre-built, and the temperature anomaly recognition network receives and analyzes the real-time temperature array information sent back by the temperature monitoring array to perform temperature anomaly recognition and early warning.

[0051] After obtaining the target extruder, the data network call is performed with the model information of the target extruder and the production raw material set as constraints to obtain the historical processing data set of the model of the target extruder when preparing the production raw material set products. Among them, the historical processing data set includes multiple sample heating section length allocations, i.e., the length settings of different heating sections in the extruder, multiple sample heating section temperature allocations, i.e., the specific temperature values ​​set for the heating sections, multiple sample screw control parameters, i.e., the conditions affecting the screw operation, such as speed, torque, screw position, etc., and multiple sample performance measured information, i.e., the actual measured performance data of the cable products. A material performance prediction network is constructed based on the historical processing data set, and the multiple conceptual performance parameters are input into the material performance prediction network for reverse prediction to obtain the target heating section length allocation, target heating section temperature allocation, and target screw control parameters. Furthermore, the target extruder is controlled with the target screw control parameter as a constraint to carry out batch production of the concept cable material. A temperature monitoring array is arranged in the target extruder according to the target heating section length distribution and the target heating section temperature distribution. The temperature monitoring array covers all target heating section length distributions, and the temperature monitoring of the batch production process of the concept cable material is carried out. Finally, a temperature anomaly recognition network is pre-constructed, and the temperature anomaly recognition network receives and analyzes the real-time temperature array information sent back by the temperature monitoring array to perform temperature anomaly recognition and early warning. The technical problem that the temperature monitoring method for cable material production in the prior art has a low matching degree with the extruder, resulting in low accuracy of temperature monitoring in cable material production, thereby affecting the quality of cable production is solved. The performance design parameters based on the cable material are matched to the corresponding raw material ratio and the acquisition of the extruder, and a temperature monitoring array corresponding to the extruder is set, which improves the accuracy of temperature monitoring and the technical effect of cable production quality.

[0052] The method provided in the embodiment of the present application also includes:

[0053] Constructing the material property prediction network based on RNN, and optimizing the prediction error of the material property prediction network using the historical processing data set until the prediction error of the material property prediction network is lower than a preset error rate;

[0054] Weights are assigned to the multiple concept performance parameters to obtain multiple concept performance weights, the multiple concept performance weights are introduced using Euclidean distance as a performance similarity calculation principle, and the multiple concept performance deviation thresholds and the multiple concept sample approximations of the multiple sample performance measured information are calculated;

[0055] Serializing the approximations of the plurality of concept samples and performing extreme value calls to obtain a control optimization starting point, wherein the control optimization starting point includes a length distribution optimization starting point, a temperature distribution optimization starting point, and a control parameter optimization starting point;

[0056] The target heating section length distribution, target heating section temperature distribution and target screw control parameters are obtained by reverse prediction using the material property prediction network and the control optimization starting point.

[0057] The material performance prediction network is constructed based on RNN. When constructing the material performance prediction network, multiple sample heating section length distributions, multiple sample heating section temperature distributions, and multiple sample screw control parameters in the historical processing data set are obtained as training data, and multiple sample performance measured information is used as supervision data to perform supervised training of the RNN recursive neural network, and the historical processing data set is used to optimize the prediction error of the material performance prediction network until the prediction error of the material performance prediction network is lower than the preset error rate, and the constructed material performance prediction network is obtained. The multiple concept performance parameters are weighted to obtain multiple concept performance weights, and the specific weight parameters are allocated according to the actual performance parameter importance. The multiple concept performance weights are introduced based on the Euclidean distance as the performance similarity calculation principle, and the multiple concept sample approximations of the multiple concept performance deviation thresholds and the multiple sample performance measured information are calculated, that is, the Euclidean distance calculation method is used to calculate the median parameters of the multiple concept performance deviation thresholds and the weighted calculation results of the multiple sample performance measured information after weighting by the concept performance weights. For example, the median parameter of the temperature resistance value of the conceptual performance deviation threshold is a, the corresponding parameter in the sample performance measured information is b, the conceptual performance weight of the temperature resistance value is 0.6, the median parameter of the mechanical strength of the conceptual performance deviation threshold is c, the corresponding parameter in the sample performance measured information is d, and the conceptual performance weight of the mechanical strength is 0.4. Then, the corresponding Euclidean distance calculation after introducing the conceptual performance weight is The concept sample approximation is obtained according to the calculation results. Further, the multiple concept sample approximations are serialized in order from large to small and extreme value calls are performed, and the minimum value, the corresponding heating section length distribution, heating section temperature distribution, and screw control parameters are called as the control optimization starting point, wherein the control optimization starting point includes the length distribution optimization starting point, the temperature distribution optimization starting point, and the control parameter optimization starting point. Finally, the material property prediction network and the control optimization starting point are used for reverse prediction to obtain the target heating section length distribution, the target heating section temperature distribution, and the target screw control parameters.

[0058] The method provided in the embodiment of the present application also includes:

[0059] Preset the optimization adjustment step length and optimization adjustment constraint, wherein the optimization adjustment step length includes the heating section optimization step length, the heating temperature optimization step length, and the screw control optimization step length;

[0060] The optimization adjustment step size and the optimization adjustment constraint are used to adjust and enumerate the control optimization starting point to obtain a plurality of control optimization adjustment information;

[0061] Synchronizing the plurality of control optimization adjustment information to the material performance prediction network to obtain a plurality of optimization performance prediction information;

[0062] The plurality of concept performance weights are introduced by taking Euclidean distance as the performance similarity calculation principle, and the plurality of concept optimization approximations of the plurality of concept performance parameters and the plurality of optimization performance prediction information are calculated and obtained;

[0063] Serializing the plurality of concept optimization approximations, and obtaining target performance prediction information by calling the plurality of optimization performance prediction information according to the extreme value;

[0064] The target heating section length distribution, the target heating section temperature distribution and the target screw control parameters are obtained by calling the plurality of control optimization adjustment information according to the target performance prediction information.

[0065] Preset optimization adjustment step and optimization adjustment constraint, wherein the optimization adjustment step includes heating section optimization step, heating temperature optimization step, screw control optimization step, and optimization adjustment constraint is pre-set heating section optimization parameter interval, heating temperature optimization parameter interval, screw control optimization parameter interval. The optimization adjustment step and the optimization adjustment constraint are used to adjust and enumerate the control optimization starting point to obtain multiple control optimization adjustment information. The multiple control optimization adjustment information is synchronized to the material performance prediction network, and the corresponding material performance prediction is performed to obtain multiple optimization performance prediction information. The multiple concept performance weights are introduced based on the Euclidean distance as the performance similarity calculation principle, and the multiple concept optimization approximations of the multiple concept performance parameters and the multiple optimization performance prediction information are calculated. The lower the concept optimization approximation, the higher the corresponding approximation. The multiple concept optimization approximations are serialized, and the target performance prediction information is obtained by calling the multiple optimization performance prediction information according to the extreme value. The target performance prediction information is the minimum value of the concept optimization approximation. Finally, the target heating section length distribution, target heating section temperature distribution and target screw control parameters are obtained by calling the multiple control optimization adjustment information according to the target performance prediction information, that is, multiple control optimization adjustment information of the original input of the target performance prediction information is obtained.

[0066] The method provided in the embodiment of the present application also includes:

[0067] Performing segment division and calling according to the target heating segment length allocation to obtain a plurality of heating segments;

[0068] Calling the zone temperature according to the target heating zone temperature distribution to obtain multiple zone heating temperatures;

[0069] Constructing a plurality of temperature uniformity comparison branches based on the plurality of heating sections, and synchronizing the heating temperatures of the plurality of sections to the plurality of temperature uniformity comparison branches;

[0070] Connecting the plurality of temperature uniformity comparison branches in parallel to complete the construction of the temperature anomaly identification network;

[0071] The temperature anomaly recognition network receives and analyzes the real-time temperature array information to perform temperature anomaly recognition and early warning.

[0072] According to the target heating section length distribution, the section division call is performed, that is, the section division in the target heating section length distribution is called to obtain multiple heating sections. According to the target heating section temperature distribution, the section temperature call is performed to obtain multiple section heating temperatures of the corresponding section. Based on the multiple heating sections, multiple temperature uniformity comparison branches are constructed, each temperature uniformity comparison branch corresponds to a heating section, and the multiple section heating temperatures are synchronized to the multiple temperature uniformity comparison branches. Among them, the temperature uniformity comparison branch is used to obtain the difference between the real-time temperature monitored at each position of the section and the section heating temperature according to the section heating temperature, and the mean of the difference is calculated to obtain the output result. The multiple temperature uniformity comparison branches are connected in parallel to complete the construction of the temperature anomaly recognition network. The temperature anomaly recognition network receives and analyzes the real-time temperature array information to perform temperature anomaly recognition and warning. When the output result is greater than or equal to the preset threshold, the corresponding temperature is abnormal and a temperature warning is required. Otherwise, the temperature is normal and no warning is required.

[0073] In the above, refer to Figure 1 The temperature intelligent monitoring and control method for cable material production according to an embodiment of the present invention is described in detail. Figure 2 The intelligent temperature monitoring and control system for cable material production according to an embodiment of the present invention is described.

[0074] The temperature intelligent monitoring and control system for cable material production according to the embodiment of the present invention solves the technical problem that the temperature monitoring method for cable material production in the prior art has a low matching degree with the extruder, resulting in low accuracy of temperature monitoring in cable material production, thereby affecting the quality of cable production. The performance design parameters based on the cable material are matched with the corresponding raw material ratio and the acquisition of the extruder, and a temperature monitoring array corresponding to the extruder is set, thereby improving the accuracy of temperature monitoring and the technical effect of cable production quality. The temperature intelligent monitoring and control system for cable material production includes: a performance data interaction module 11, a raw material ratio acquisition module 12, an extruder matching module 13, a processing data acquisition module 14, a control parameter acquisition module 15, a temperature monitoring module 16, and a temperature early warning module 17.

[0075] The performance data interaction module 11 is used to interactively obtain the conceptual performance design of the conceptual cable material, wherein the conceptual performance design includes a plurality of conceptual performance parameters of a plurality of conceptual performance indicators and a plurality of conceptual performance deviation thresholds;

[0076] A raw material ratio acquisition module 12 is used to interactively obtain the conceptual raw material cost, and determine the production raw material set by matching the conceptual performance design and the conceptual raw material cost as constraints, wherein the production raw material set includes multiple production raw materials and multiple addition ratio identifiers;

[0077] An extruder matching module 13 is used to interactively obtain a plurality of material characteristic sets of the plurality of production raw materials, and match and obtain a target extruder with the plurality of material characteristic sets and the plurality of conceptual performance parameters as constraints;

[0078] A processing data acquisition module 14 is used to perform data networking call based on the model information of the target extruder and the production raw material set as constraints to obtain a historical processing data set, wherein the historical processing data set includes a plurality of sample heating section length distributions, a plurality of sample heating section temperature distributions, a plurality of sample screw control parameters and a plurality of sample performance measured information;

[0079] A control parameter acquisition module 15, for constructing a material performance prediction network based on the historical processing data set, and reversely predicting the target heating section length distribution, the target heating section temperature distribution and the target screw control parameters based on the material performance prediction network and the plurality of conceptual performance parameters;

[0080] A temperature monitoring module 16, for controlling the target extruder to carry out batch production of the concept cable material with the target screw control parameter as a constraint, and arranging a temperature monitoring array in the target extruder according to the target heating section length distribution and the target heating section temperature distribution to carry out temperature monitoring of the batch production process of the concept cable material;

[0081] The temperature warning module 17 is used to pre-build a temperature anomaly recognition network, which receives and analyzes the real-time temperature array information sent back by the temperature monitoring array to perform temperature anomaly recognition and warning.

[0082] The specific configuration of the raw material ratio acquisition module 12 will be described in detail below. The raw material ratio acquisition module 12 may further include: pre-constructing a production raw material information library, wherein the production raw material information library includes a performance comparison execution layer and a raw material cost calculation layer, the performance comparison execution layer is pre-configured with a performance comparison engine, and the raw material cost calculation layer is pre-configured with a cost calculation engine; interactively obtaining multiple sample raw material ratio information and multiple sample performance measured information of multiple sample cable materials, associating and storing the multiple sample raw material ratio information and the multiple sample performance measured information, and then synchronizing them to the performance comparison execution layer; interactively obtaining multiple sample raw material real-time unit prices, and synchronizing the multiple sample raw material real-time unit prices to the raw material cost calculation layer to complete the construction of the production raw material information library; matching and determining the production raw material set in the production raw material information library with the conceptual performance design and the conceptual raw material cost as constraints.

[0083] The specific configuration of the raw material ratio acquisition module 12 will be described in detail below. The raw material ratio acquisition module 12 further includes: generating multiple concept performance matching thresholds according to the multiple concept performance parameters and multiple concept performance deviation thresholds; activating the performance comparison engine of the performance comparison execution layer based on the multiple concept performance matching thresholds to traverse and compare the multiple sample performance measured information to obtain multiple screening raw material ratio information; traversing and matching the multiple sample raw material real-time unit prices according to the multiple screening raw material ratio information at the raw material cost calculation layer to obtain multiple screening raw material unit price groups, and performing cost calculation on the multiple screening raw material ratio information and the multiple screening raw material unit price groups through the cost calculation engine to obtain multiple screening raw material costs; serializing the multiple screening raw material costs, and comparing the concept raw material costs, and calling to obtain the production raw material set, wherein the screening raw material cost of the production raw material set is closest to the concept raw material cost.

[0084] The specific configuration of the extruder matching module 13 will be described in detail below. The extruder matching module 13 may further include: presetting extrusion-related indicators, wherein the extrusion-related indicators include material melting point, softening point, melt viscosity and thermal stability; using the extrusion-related indicators to traverse the multiple material characteristic sets, and screen to obtain multiple extrusion-related characteristic sets; performing temperature intersection calculation on the multiple extrusion-related characteristic sets to obtain a target processing temperature threshold; interactively obtaining multiple sample design parameters and multiple sample processing-related information of multiple sample screws, wherein the data structure of each sample processing-related information includes a sample processing temperature threshold and multiple sample performance parameters; obtaining multiple screw fitness coefficients of the multiple conceptual performance parameters, the target processing temperature threshold and the multiple sample processing-related information based on Euclidean distance calculation; serializing the multiple screw fitness coefficients and performing extreme value calls to obtain target screw design parameters, and performing extruder pairing according to the target screw design parameters to obtain the target extruder.

[0085] The specific configuration of the control parameter acquisition module 15 will be described in detail below. The control parameter acquisition module 15 further includes: constructing the material performance prediction network based on RNN, and using the historical processing data set to optimize the prediction error of the material performance prediction network, until the prediction error of the material performance prediction network is lower than the preset error rate; weighting the multiple concept performance parameters to obtain multiple concept performance weights, introducing the multiple concept performance weights based on the Euclidean distance as the performance similarity calculation principle, and calculating the multiple concept performance deviation thresholds and the multiple concept sample approximations of the multiple sample performance measured information; serializing the multiple concept sample approximations and performing extreme value calls to obtain the control optimization starting point, wherein the control optimization starting point includes the length distribution optimization starting point, the temperature distribution optimization starting point and the control parameter optimization starting point; using the material performance prediction network and the control optimization starting point to reversely predict the target heating section length distribution, the target heating section temperature distribution and the target screw control parameters.

[0086] The specific configuration of the control parameter acquisition module 15 will be described in detail below. The control parameter acquisition module 15 further includes: presetting the optimization adjustment step and the optimization adjustment constraint, wherein the optimization adjustment step includes the heating section optimization step, the heating temperature optimization step, and the screw control optimization step; using the optimization adjustment step and the optimization adjustment constraint to adjust and enumerate the control optimization starting point to obtain multiple control optimization adjustment information; synchronizing the multiple control optimization adjustment information to the material performance prediction network to obtain multiple optimization performance prediction information; introducing the multiple concept performance weights based on the Euclidean distance as the performance similarity calculation principle, and calculating the multiple concept optimization approximations of the multiple concept performance parameters and the multiple optimization performance prediction information; serializing the multiple concept optimization approximations, and obtaining the target performance prediction information by calling the multiple optimization performance prediction information according to the extreme value; and obtaining the target heating section length distribution, the target heating section temperature distribution and the target screw control parameter by calling the multiple control optimization adjustment information according to the target performance prediction information.

[0087] The specific configuration of the temperature warning module 17 will be described in detail below. The temperature warning module 17 further includes: performing segment division calling according to the target heating segment length distribution to obtain multiple heating segments; performing segment temperature calling according to the target heating segment temperature distribution to obtain multiple segment heating temperatures; constructing multiple temperature uniformity comparison branches based on the multiple heating segments, and synchronizing the multiple segment heating temperatures to the multiple temperature uniformity comparison branches; connecting the multiple temperature uniformity comparison branches in parallel to complete the construction of the temperature anomaly recognition network; the temperature anomaly recognition network receives and analyzes the real-time temperature array information to perform temperature anomaly recognition warning.

[0088] The temperature intelligent monitoring and control system for cable material production provided by the embodiment of the present invention can execute the temperature intelligent monitoring and control method for cable material production provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0089] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0090] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. Intelligent temperature monitoring and control method for cable material production, It is characterized in that The method comprises: Interactively obtaining a conceptual performance design of a conceptual cable material, wherein the conceptual performance design includes a plurality of conceptual performance parameters of a plurality of conceptual performance indicators and a plurality of conceptual performance deviation thresholds; Interactively obtain the conceptual raw material cost, and determine the production raw material set by matching the conceptual performance design and the conceptual raw material cost as constraints, wherein the production raw material set includes multiple production raw materials and multiple additive ratio identifiers; Interactively obtain multiple material property sets of the multiple production raw materials, and match and obtain a target extruder with the multiple material property sets and the multiple conceptual performance parameters as constraints; Using the model information of the target extruder and the production raw material set as constraints, a data networking call is performed to obtain a historical processing data set, wherein the historical processing data set includes a plurality of sample heating section length distributions, a plurality of sample heating section temperature distributions, a plurality of sample screw control parameters, and a plurality of sample performance measured information; Constructing a material property prediction network based on the historical processing data set, and reversely predicting based on the material property prediction network and the plurality of conceptual performance parameters to obtain a target heating section length distribution, a target heating section temperature distribution, and a target screw control parameter; The target extruder is controlled to carry out batch production of the concept cable material with the target screw control parameter as a constraint, and a temperature monitoring array is arranged in the target extruder according to the target heating section length distribution and the target heating section temperature distribution to carry out temperature monitoring of the batch production process of the concept cable material; A temperature anomaly recognition network is pre-built, and the temperature anomaly recognition network receives and analyzes the real-time temperature array information sent back by the temperature monitoring array to perform temperature anomaly recognition and early warning.

2. The method according to claim 1, It is characterized in that The method further comprises: Pre-constructing a production raw material information database, wherein the production raw material information database includes a performance comparison execution layer and a raw material cost calculation layer, the performance comparison execution layer is pre-configured with a performance comparison engine, and the raw material cost calculation layer is pre-configured with a cost calculation engine; Interactively obtain multiple sample raw material ratio information and multiple sample performance measured information of multiple sample cable materials, associate and store the multiple sample raw material ratio information and the multiple sample performance measured information, and then synchronize them to the performance comparison execution layer; Interactively obtain real-time unit prices of multiple sample raw materials, and synchronize the real-time unit prices of the multiple sample raw materials to the raw material cost calculation layer to complete the construction of the production raw material information database; The production raw material set is determined by matching the production raw material information database with the conceptual performance design and the conceptual raw material cost as constraints.

3. The method according to claim 2, It is characterized in that The method further includes: determining the production raw material set by matching the production raw material information base with the concept performance design and the concept raw material cost as constraints; generating a plurality of concept performance matching thresholds according to the plurality of concept performance parameters and the plurality of concept performance deviation thresholds; Activating the performance comparison engine of the performance comparison execution layer based on the multiple concept performance matching thresholds to traverse and compare the multiple sample performance measured information to obtain multiple screening raw material ratio information; At the raw material cost calculation layer, traverse and match the real-time unit prices of the multiple sample raw materials according to the multiple screening raw material ratio information to obtain multiple screening raw material unit price groups, and perform cost calculation on the multiple screening raw material ratio information and the multiple screening raw material unit price groups through the cost calculation engine to obtain multiple screening raw material costs; The multiple screening raw material costs are serialized, compared with the conceptual raw material cost, and the production raw material set is obtained by calling, wherein the screening raw material cost of the production raw material set is closest to the conceptual raw material cost.

4. The method according to claim 1, It is characterized in that Interactively obtaining a plurality of material property sets of the plurality of production raw materials, and matching and obtaining a target extruder with the plurality of material property sets and the plurality of conceptual performance parameters as constraints, the method further comprising: Preset extrusion-related indicators, wherein the extrusion-related indicators include material melting point, softening point, melt viscosity and thermal stability; Using the extrusion-related index to traverse the multiple material characteristic sets, and screen to obtain multiple extrusion-related characteristic sets; Performing temperature intersection calculation on the multiple extrusion-related characteristic sets to obtain a target processing temperature threshold; Interactively obtaining a plurality of sample design parameters and a plurality of sample processing-related information of a plurality of sample screws, wherein the data structure of each sample processing-related information includes a sample processing temperature threshold and a plurality of sample performance parameters; Obtaining multiple screw fitness coefficients of the multiple conceptual performance parameters, the target processing temperature threshold, and the multiple sample processing associated information based on Euclidean distance calculation; The plurality of screw fitness coefficients are serialized and extreme value calls are performed to obtain target screw design parameters, and extruder pairing is performed according to the target screw design parameters to obtain the target extruder.

5. The method according to claim 1, It is characterized in that A material property prediction network is constructed based on the historical processing data set, and a target heating section length distribution, a target heating section temperature distribution and a target screw control parameter are obtained by reverse prediction based on the material property prediction network and the plurality of conceptual performance parameters. The method further comprises: Constructing the material property prediction network based on RNN, and optimizing the prediction error of the material property prediction network using the historical processing data set until the prediction error of the material property prediction network is lower than a preset error rate; Weights are assigned to the multiple concept performance parameters to obtain multiple concept performance weights, the multiple concept performance weights are introduced using Euclidean distance as a performance similarity calculation principle, and the multiple concept performance deviation thresholds and the multiple concept sample approximations of the multiple sample performance measured information are calculated; Serializing the approximations of the plurality of concept samples and performing extreme value calls to obtain a control optimization starting point, wherein the control optimization starting point includes a length distribution optimization starting point, a temperature distribution optimization starting point, and a control parameter optimization starting point; The target heating section length distribution, target heating section temperature distribution and target screw control parameters are obtained by reverse prediction using the material property prediction network and the control optimization starting point.

6. The method according to claim 5, It is characterized in that The target heating section length distribution, target heating section temperature distribution and target screw control parameters are obtained by reverse prediction using the material property prediction network and the control optimization starting point, and the method further includes: Preset the optimization adjustment step length and optimization adjustment constraint, wherein the optimization adjustment step length includes the heating section optimization step length, the heating temperature optimization step length, and the screw control optimization step length; The optimization adjustment step size and the optimization adjustment constraint are used to adjust and enumerate the control optimization starting point to obtain a plurality of control optimization adjustment information; Synchronizing the plurality of control optimization adjustment information to the material performance prediction network to obtain a plurality of optimization performance prediction information; The plurality of concept performance weights are introduced by taking Euclidean distance as the performance similarity calculation principle, and the plurality of concept optimization approximations of the plurality of concept performance parameters and the plurality of optimization performance prediction information are calculated and obtained; Serializing the plurality of concept optimization approximations, and obtaining target performance prediction information by calling the plurality of optimization performance prediction information according to the extreme value; The target heating section length distribution, the target heating section temperature distribution and the target screw control parameters are obtained by calling the plurality of control optimization adjustment information according to the target performance prediction information.

7. The method according to claim 1, It is characterized in that A temperature anomaly recognition network is pre-built, and the temperature anomaly recognition network receives and analyzes the real-time temperature array information sent back by the temperature monitoring array to perform temperature anomaly recognition and early warning. The method further includes: Performing segment division and calling according to the target heating segment length allocation to obtain a plurality of heating segments; Calling the zone temperature according to the target heating zone temperature distribution to obtain multiple zone heating temperatures; Constructing a plurality of temperature uniformity comparison branches based on the plurality of heating sections, and synchronizing the heating temperatures of the plurality of sections to the plurality of temperature uniformity comparison branches; Connecting the plurality of temperature uniformity comparison branches in parallel to complete the construction of the temperature anomaly identification network; The temperature anomaly recognition network receives and analyzes the real-time temperature array information to perform temperature anomaly recognition and early warning.

8. Intelligent temperature monitoring and control system for cable material production, It is characterized in that The system comprises: A performance data interaction module, used for interactively obtaining a conceptual performance design of a conceptual cable material, wherein the conceptual performance design includes a plurality of conceptual performance parameters of a plurality of conceptual performance indicators and a plurality of conceptual performance deviation thresholds; A raw material ratio acquisition module, used for interactively obtaining a conceptual raw material cost, and determining a production raw material set by matching the conceptual performance design and the conceptual raw material cost as constraints, wherein the production raw material set includes a plurality of production raw materials and a plurality of additive ratio identifiers; An extruder matching module, used for interactively obtaining a plurality of material characteristic sets of the plurality of production raw materials, and matching and obtaining a target extruder with the plurality of material characteristic sets and the plurality of conceptual performance parameters as constraints; A processing data acquisition module, used to perform data networking call based on the model information of the target extruder and the production raw material set as constraints to obtain a historical processing data set, wherein the historical processing data set includes a plurality of sample heating section length distributions, a plurality of sample heating section temperature distributions, a plurality of sample screw control parameters and a plurality of sample performance measured information; A control parameter acquisition module, configured to construct a material performance prediction network based on the historical processing data set, and reversely predict the target heating section length distribution, the target heating section temperature distribution and the target screw control parameters based on the material performance prediction network and the plurality of conceptual performance parameters; A temperature monitoring module, used for controlling the target extruder to carry out batch production of the concept cable material with the target screw control parameter as a constraint, and arranging a temperature monitoring array in the target extruder according to the target heating section length distribution and the target heating section temperature distribution to carry out temperature monitoring of the batch production process of the concept cable material; The temperature warning module is used to pre-build a temperature anomaly recognition network, which receives and analyzes the real-time temperature array information sent back by the temperature monitoring array to perform temperature anomaly recognition and warning.

Images