Cooperative control method and system for multi-pass rolling and annealing of copper wire based on intelligent network

Abstract

The present invention relates to the field of copper wire manufacturing control technology, and in particular to a method and system for coordinated control of multi-pass rolling and annealing of copper wire based on an intelligent network. The method comprises: setting a process control node according to an industrial control process, establishing a coordinated communication network based on the process control node and collecting multi-mode industrial control signals; setting a data transmission processing protocol and establishing an industrial control perception platform, integrating multi-mode industrial control signals and generating process operation parameters according to process position conversion; analyzing the nonlinear correlation between process steps, combining copper wire performance indicators, and calculating process adjustment parameters; transmitting the process operation parameters to a coordinated control center according to the data transmission processing protocol, and comparing and analyzing with the process adjustment parameters to generate parameter coordinated control instructions; and feeding back the parameter coordinated control instructions to the rolling control node and the annealing temperature control node based on the coordinated communication network for parameter correction. Through the present invention, the problems of low process coordination efficiency and insufficient signal processing capability in copper wire manufacturing are effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of copper wire manufacturing control, and in particular to a method and system for coordinated control of multi-pass rolling and annealing of copper wire based on an intelligent network. Background Art

[0002] The traditional copper wire manufacturing method requires multiple rolling and annealing processes. Specifically, the multiple rolling processes require multiple deformation treatments, while the annealing process requires precise temperature control operations based on the metal properties of the copper wire at different processing stages.

[0003] The traditional method controls multiple rolling and annealing processes separately, lacks modeling of nonlinear correlations between processes and real-time coordinated adjustment mechanisms. The pressure parameters of each rolling process cannot be effectively transmitted to subsequent processes, nor can the temperature control parameters in the annealing process be adjusted in a coordinated manner. Since parameter changes between multiple processes have complex timing and interactions, the information of each node in the traditional process is isolated and delayed, resulting in poor coordination between rolling and annealing processes and difficulty in achieving linkage of multiple processes.

[0004] On the other hand, the signals involved in multiple processes are complex and numerous, and these signals have highly nonlinear and dynamic characteristics between different processes. Traditional processes are difficult to effectively capture and quantify the correlation between these multi-mode signals, and cannot accurately analyze and optimize the interaction effects between multiple processes. In addition, traditional processes lack efficient data transmission and collaborative communication mechanisms, and the efficiency of data sharing and feedback adjustment between multiple processes is low, which further aggravates the difficulty of collaborative control of multiple processes.

[0005] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present disclosure, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art known to those skilled in the art. Summary of the invention

[0006] The present invention provides a method and system for coordinated control of multi-pass rolling and annealing of copper wire based on an intelligent network, which can effectively solve the problems in the background technology.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is:

[0008] A method for coordinated control of multi-pass rolling and annealing of copper wire based on an intelligent network, the method comprising:

[0009] Setting process control nodes according to the industrial control process, establishing a collaborative communication network based on the process control nodes and collecting multi-mode industrial control signals, the process control nodes including rolling control nodes and annealing temperature control nodes;

[0010] Setting a data transmission processing protocol and establishing an industrial control perception platform, integrating the multi-mode industrial control signals according to the industrial control perception platform and converting them into process operation parameters according to process position;

[0011] Based on the industrial control perception platform, the nonlinear correlation between process steps is analyzed, and the process adjustment parameters are calculated in combination with the copper wire performance index;

[0012] Establishing a collaborative control center, transmitting the process operation parameters to the collaborative control center according to the data transmission processing protocol, and comparing and analyzing the process adjustment parameters to generate parameter collaborative control instructions;

[0013] The parameter collaborative control instruction is fed back to the rolling control node and the annealing temperature control node based on the collaborative communication network to perform parameter correction.

[0014] Furthermore, the nonlinear correlation between process steps is analyzed based on the industrial control perception platform, including:

[0015] Modeling the nonlinear relationship between the different running times of the industrial control processes according to the industrial control perception platform and the collaborative communication network to generate a multi-time series nonlinear mapping model;

[0016] According to the multi-time nonlinear mapping model, timing modeling is performed on the multi-mode industrial control signal to analyze the timing correlation and interaction effect between the process steps;

[0017] According to the timing correlation and the interaction effect, analyzing the interaction effect intensity between the process control nodes through time-varying nonlinear association;

[0018] The interaction effect strength is quantified, combined with the multi-time series nonlinear mapping model, and feedback adjustment is performed on the multi-mode industrial control signal through the data transmission processing protocol.

[0019] Furthermore, analyzing the temporal correlation and interaction effects between the process steps includes:

[0020] Based on the multi-time series nonlinear mapping model, construct a time series data set for each of the process steps, and identify the time series correlation between the process steps;

[0021] Mapping the time series data set to multiple time scales, and analyzing the time series dependencies between different process steps through time window sliding and multi-scale decomposition;

[0022] Performing interaction effect analysis based on the timing dependency to quantify the interaction effects between different process steps;

[0023] The timing correlation and the interaction effect are fed back to the industrial control perception platform, and corresponding parameters are adjusted in the multi-scale nonlinear mapping model.

[0024] Furthermore, a parameter collaborative control instruction is generated, including:

[0025] Extracting the signal transmission characteristics of the process operation parameters based on the industrial control perception platform, wherein the signal transmission characteristics include process step timing characteristics and copper wire performance correlation characteristics;

[0026] Constructing a signal coding model, generating a signal compression frame that meets the communication requirements of the plurality of process control nodes based on the signal transmission characteristics, and adding error correction coding to the signal compression frame;

[0027] Based on the data transmission processing protocol, transmitting the signal compression frame to the collaborative control center through the collaborative communication network;

[0028] The collaborative control center decodes and restores the received signal compression frame, combines the process adjustment parameters, determines the parameter adjustment weight, and generates a parameter collaborative control instruction.

[0029] Further, generating a signal compression frame that meets the communication requirements of the plurality of process control nodes based on the signal characteristics includes:

[0030] Preprocessing the process operation parameters, extracting the signal transmission characteristics, and performing feature stratification according to the signal transmission characteristics;

[0031] According to the signal coding model, the process operation parameters are subjected to hierarchical compression coding to generate hierarchical compressed signals, wherein the hierarchical compression includes time compression, frequency compression and feature mapping compression;

[0032] According to the data transmission processing protocol, the error correction code is added to each level of the layered compressed signal, and the error correction code is responsible for adjusting the coding redundancy according to the channel condition of the process control node;

[0033] The layered compressed signal and the error correction coding are processed and packaged in a layered structure to generate the signal compression frame, and the signal compression frame includes a check segment, a basic data segment and a feature mapping segment.

[0034] Further, the parameters are corrected based on the feedback from the cooperative communication network to the rolling control node and the annealing temperature control node, including:

[0035] Decomposing the parameter coordinated control instructions layer by layer, and extracting rolling parameter correction sub-instructions and annealing temperature control correction sub-instructions;

[0036] Distributing the rolling parameter correction sub-instruction and the annealing temperature control correction sub-instruction to the corresponding rolling control node and the annealing temperature control node through the collaborative communication network;

[0037] Compare the data of the rolling control node with the rolling parameter correction sub-instruction to extract the rolling deviation, generate a rolling pressure correction value, and adjust the rolling pressure accordingly;

[0038] Based on the analysis of the on-site temperature data, the temperature control deviation is calculated according to the thermal field gradient of the copper wire surface, the temperature control correction value is generated by combining the temperature control deviation with the annealing temperature control correction sub-instruction, and the temperature control is adjusted accordingly.

[0039] Furthermore, the temperature control deviation is calculated based on the thermal field gradient on the copper wire surface, including:

[0040] Based on the annealing temperature control node, the temperature distribution signal and heat flux density signal on the surface of the copper wire are collected, and the collected signals are adaptively filtered and optimized to remove high-frequency noise and mutation signal interference to form a thermal field multi-mode signal set;

[0041] The thermal field multimode signal set is parsed to extract the thermal field gradient on the surface of the copper wire, and the thermal field gradient on the surface of the copper wire is combined with a time series to generate a thermal field feature matrix;

[0042] Performing a nonlinear comparison between the thermal field gradient on the surface of the copper wire and the target temperature distribution in the annealing temperature control correction sub-instruction, and establishing a thermal field gradient equation;

[0043] The thermal field characteristic matrix is ​​substituted into the thermal field gradient equation. During the equation solving process, the thermal field multi-mode signal set is updated according to different copper wire materials and production environment changes to calculate the temperature control deviation.

[0044] Furthermore, a data transmission processing protocol is set, including:

[0045] defining a data transmission format, encoding the multi-mode process signal in a standardized manner according to the data transmission format, and synchronizing the signal to the collaborative communication network;

[0046] Analyze the network load requirements of each of the process control nodes, and determine the transmission rate and delay control strategy based on the data transmission format;

[0047] Establishing a redundant data verification algorithm, combining the delay control strategy with data integrity and error detection, and selecting an appropriate retransmission strategy according to the network status;

[0048] Establishing data transmission priority management according to the detection results of the data integrity and error detection, and setting the data transmission priorities of different multi-mode process signals;

[0049] The data transmission processing protocol is generated based on the data transmission format, delay control strategy, redundant data verification algorithm and data transmission priority management integration.

[0050] Based on intelligent network copper wire multi-pass rolling and annealing coordinated control system, the system includes:

[0051] The data acquisition module sets process control nodes according to the industrial control process, establishes a collaborative communication network based on the process control nodes, and collects multi-mode industrial control signals. The process control nodes include rolling control nodes and annealing temperature control nodes;

[0052] The signal conversion module sets the data transmission processing protocol and establishes an industrial control perception platform. It integrates multi-mode industrial control signals according to the industrial control perception platform and converts them into process operation parameters according to process position.

[0053] Adjust the calculation module, analyze the nonlinear correlation between process steps based on the industrial control perception platform, and calculate the process adjustment parameters based on the copper wire performance indicators;

[0054] Collaborative control module: establishes a collaborative control center, transmits process operation parameters to the collaborative control center according to the data transmission processing protocol, compares and analyzes them with process adjustment parameters, and generates parameter collaborative control instructions;

[0055] The feedback correction module feeds back the parameter collaborative control instructions to the rolling control node and the annealing temperature control node based on the collaborative communication network for parameter correction.

[0056] Furthermore, the adjustment calculation module includes:

[0057] The mapping model unit models the nonlinear relationship between the different running times of each industrial control process based on the industrial control perception platform and the collaborative communication network, and generates a multi-time series nonlinear mapping model;

[0058] The spatiotemporal interaction unit performs temporal modeling of multi-mode industrial control signals based on a multi-temporal nonlinear mapping model, and analyzes the temporal correlation and interaction effects between process steps;

[0059] The correlation analysis unit analyzes the interaction effect strength between process control nodes through time-varying nonlinear correlation based on temporal correlation and interaction effect;

[0060] The quantitative adjustment unit quantifies the intensity of the interaction effect and combines the multi-time series nonlinear mapping model to perform feedback adjustment on the multi-mode industrial control signal through the data transmission processing protocol.

[0061] The technical solution of the present invention can achieve the following technical effects:

[0062] It improves the coordinated efficiency of the rolling and annealing processes, solves the problem of information isolation in traditional processes, reduces process deviations through precise adjustment of process parameters, improves the quality stability of copper wire products, optimizes the production process in terms of energy and material utilization, and reduces energy consumption and costs.

[0063] 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. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 It is a flow chart of the coordinated control method of multi-pass rolling and annealing of copper wire based on intelligent network;

[0066] Figure 2 A schematic diagram of the process for analyzing the nonlinear relationship between process steps;

[0067] Figure 3 A flow chart for generating parameter coordinated control instructions;

[0068] Figure 4 The figure is a flow chart for performing parameter correction on process control nodes. DETAILED DESCRIPTION

[0069] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0070] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0071] Embodiment 1:

[0072] like Figure 1As shown, the present application provides a method for coordinated control of multi-pass rolling and annealing of copper wire based on an intelligent network, the method comprising:

[0073] S10: setting process control nodes according to the industrial control process, establishing a collaborative communication network based on the process control nodes and collecting multi-mode industrial control signals, the process control nodes including rolling control nodes and annealing temperature control nodes;

[0074] S20: Setting a data transmission processing protocol and establishing an industrial control perception platform, integrating multi-mode industrial control signals according to the industrial control perception platform and converting and generating process operation parameters according to process position;

[0075] S30: Analyze the nonlinear correlation between process steps based on the industrial control perception platform, and calculate the process adjustment parameters based on the copper wire performance indicators;

[0076] S40: Establish a collaborative control center, transmit the process operation parameters to the collaborative control center according to the data transmission processing protocol, compare and analyze with the process adjustment parameters, and generate parameter collaborative control instructions;

[0077] S50: Feedback the parameter collaborative control instruction to the rolling control node and the annealing temperature control node based on the collaborative communication network to perform parameter correction.

[0078] Specifically, according to the copper wire manufacturing process, rolling control nodes and annealing temperature control nodes are set up, and these nodes are connected through a collaborative communication network to collect multi-mode industrial control signals, including pressure, temperature, and material performance data, etc., define the data transmission and processing protocol, and establish an industrial control perception platform. The collected multi-mode industrial control signals are integrated, and the process operation parameters are generated according to the process position conversion. Based on the industrial control perception platform, a multi-time series nonlinear mapping model is used to model the nonlinear correlation between each process step. The correlation and interaction effects between processes are analyzed in combination with the copper wire performance indicators, and the process adjustment parameters are calculated. In the collaborative control center, the process operation parameters are received through the data transmission protocol, compared and analyzed with the process adjustment parameters, and parameter collaborative control instructions are generated. The collaborative control instructions are fed back to the rolling control node and the annealing temperature control node through the collaborative communication network to adjust the process parameters in real time. For the rolling control node, the rolling parameter correction sub-instruction is extracted, and the rolling deviation is generated by comparing with the real-time data. The rolling pressure correction value is calculated and the pressure is adjusted. For the annealing temperature control node, the copper wire surface temperature distribution signal and heat flux density signal are collected, and the thermal field multi-mode signal set is generated after adaptive filtering optimization processing. After analyzing the signal, the thermal field gradient of the copper wire surface is extracted, and the thermal field gradient equation is established in combination with the target temperature distribution in the annealing temperature control correction sub-instruction. The temperature control deviation is calculated and the temperature control correction value is generated, and the temperature control parameters are adjusted.

[0079] Through the technical solution of the present invention, the coordinated efficiency of the rolling and annealing processes is improved, the problem of information isolation in the traditional process is solved, the process deviation is reduced by precise adjustment of the process parameters, the quality stability of the copper wire products is improved, the production process is optimized in terms of energy and material utilization, and energy consumption and costs are reduced.

[0080] Further, if Figure 2 As shown in the figure, the nonlinear correlation between process steps is analyzed based on the industrial control perception platform, including:

[0081] Based on the industrial control perception platform and collaborative communication network, the nonlinear relationship between the different running times of each industrial control process is modeled to generate a multi-time series nonlinear mapping model;

[0082] Based on the multi-time nonlinear mapping model, the time series modeling of multi-mode industrial control signals is carried out to analyze the time series correlation and interaction effect between process steps;

[0083] According to the time series correlation and interaction effect, the interaction effect strength between process control nodes is analyzed through time-varying nonlinear association;

[0084] The intensity of the interaction effect is quantified, and a multi-time series nonlinear mapping model is combined to feedback-regulate the multi-mode industrial control signals through the data transmission and processing protocol.

[0085] As a preferred embodiment of the above, the industrial control perception platform collects the pressure signals, temperature signals and material performance data generated during the rolling and annealing processes, and transmits the pressure fluctuation data of the rolling process and the annealing temperature change data to the industrial control perception platform through a collaborative communication network. During the rolling process, it records in real time whether the pressure change shows a nonlinear oscillation trend over time and the correlation between the temperature fluctuation and the cooling rate during the annealing process. Through nonlinear multivariate modeling, a multi-time series nonlinear mapping model is generated, and the nonlinear relationship between the pressure and temperature changes at different time nodes and the material hardness is clarified; based on the nonlinear mapping model, the rolling pressure signal and the annealing temperature signal are time-series modeled to generate a time series data set, and analysis shows that there is a positive correlation between the peak point of the pressure during the rolling process and the heating rate of the annealing temperature. Through the time-varying sliding window technology, it is found out whether the temperature adjustment frequency of the temperature control node affects the subsequent rolling uniformity, and the time-series dependency between the processes is revealed; through the time-varying nonlinear correlation technology, the interaction effect intensity between the rolling control node and the annealing temperature control node is calculated, and the relationship curve between the pressure fluctuation amplitude and the temperature control delay time is determined through the quantitative analysis of the interaction effect intensity; after completing the quantification of the interaction effect intensity, the multi-time-series nonlinear mapping model is used to feed the analysis results back to the industrial control perception platform, and the production process is optimized by adjusting the rolling pressure and annealing temperature control parameters based on the copper wire product control target. In response to the abnormal thermal field gradient found, the temperature response time of the temperature control node is adjusted through the data transmission protocol. At the same time, a feedback adjustment signal is generated for the problem of excessive pressure fluctuation amplitude during the rolling process.

[0086] Furthermore, the temporal correlation and interaction effects between process steps are analyzed, including:

[0087] Based on the multi-time series nonlinear mapping model, a time series data set for each process step is constructed, and the time series correlation between process steps is identified;

[0088] Map the time series data set to multiple time scales, and analyze the temporal dependencies between different process steps through time window sliding and multi-scale decomposition;

[0089] Perform interaction effect analysis based on temporal dependencies to quantify the interaction effects between different process steps;

[0090] The timing correlation and interaction effects are fed back to the industrial control perception platform, and the corresponding parameters are adjusted in the multi-scale nonlinear mapping model.

[0091] As a preferred embodiment of the above, a multi-time series nonlinear mapping model is used to extract data from the multi-mode industrial control signals collected by the industrial control perception platform to construct a time series data set of the process steps. For example, for the rolling process and the annealing process, the time series data of the pressure signal and the temperature signal are recorded respectively. The time series recorded in the rolling process is the pressure data sampled per second, and the time series of the annealing temperature control process is the temperature change curve over time. The correlation analysis algorithm is used to analyze the time series correlation between the pressure change in the rolling process and the temperature change in the annealing temperature control. The time series data set is mapped to multiple time scales, and the time series dependency between the process steps is analyzed through time window sliding and multi-scale decomposition technology. Through time window sliding, the signal data of the rolling pressure and the annealing temperature are decomposed into short time windows, medium time windows and long time windows for multi-scale decomposition. The pressure fluctuation in the short time window mainly affects the instantaneous temperature control adjustment in the annealing process, the pressure fluctuation in the medium time window will have a trend effect on the overall temperature control curve, and the long time window The change in pressure data is directly related to the final quality of the copper wire hardness; based on the timing dependency, the interaction effect analysis is further carried out and the mutual influence between the process steps is quantified. The interaction effect strength is calculated using the nonlinear mapping model. For example, the impact of rolling pressure fluctuations on the temperature response time of annealing temperature control is calculated, and the feedback effect of annealing temperature control parameter changes on the subsequent pressure adjustment accuracy is calculated. In the specific example, when the rolling pressure fluctuation exceeds the threshold of ±5%, the temperature control response time delay increases significantly, and the interaction effect strength value reaches 0.85, indicating that the interaction between the two process steps is significant at this time. Through quantitative analysis, the parameter range and interaction nodes that need to be adjusted first in actual production are clarified; the identified timing correlation and interaction effect strength are fed back to the industrial control perception platform, and the relevant parameters in the multi-time series nonlinear mapping model are updated. For example, for rolling pressure fluctuations under high interaction intensity, the pressure control response time of the rolling node is adjusted to reduce the amplitude of the pressure fluctuation, and the annealing temperature control response time is optimized through the industrial control perception platform.

[0092] Further, if Figure 3 As shown, the parameter coordination control instruction is generated, including:

[0093] The signal transmission characteristics of the process operation parameters are extracted based on the industrial control perception platform. The signal transmission characteristics include the process step timing characteristics and the copper wire performance correlation characteristics.

[0094] Construct a signal coding model, generate signal compression frames that meet the communication requirements of multiple process control nodes based on signal transmission characteristics, and add error correction coding to the signal compression frames;

[0095] Based on the data transmission processing protocol, the signal compression frame is transmitted to the collaborative control center through the collaborative communication network;

[0096] The collaborative control center decodes and restores the received signal compression frames, adjusts the parameters in combination with the process, determines the parameter adjustment weights, and generates parameter collaborative control instructions.

[0097] As a preferred embodiment of the above, the process operation parameters of each process control node are collected and analyzed through the industrial control perception platform to extract signal transmission characteristics. The signal transmission characteristics include process step timing characteristics and copper wire performance correlation characteristics. The process step timing characteristics record the operation time series data of each process, such as the real-time fluctuation curve of the pressure signal of the rolling node, the temperature adjustment frequency of the annealing temperature control node, etc. The copper wire performance correlation characteristics analyze the correlation between the process parameters and the final performance of the copper wire (such as hardness, ductility, conductivity), such as extracting the relationship between the pressure amplitude change during the rolling process and the hardness of the copper wire, the correlation between the annealing temperature change curve and the conductivity, etc. In actual implementation, through The operation data of each batch of copper wires is collected through sensors, and the signal features are stored according to node classification and sent to the feature extraction model for data processing; based on the extracted signal transmission features, a signal coding model is constructed to generate signal compression frames that meet the communication requirements of multiple process control nodes, and the extracted timing features and performance-related features are layered for hierarchical feature encoding, such as time scale features, frequency features, and process-related features. The layered features are compressed using the coding model to generate signal compression frames. For example, for the pressure signal fluctuation of the rolling node, a time compression algorithm is applied to compress the continuous signal into feature points, and frequency compression is applied to the temperature data of the annealing temperature control. The algorithm extracts the main components of the temperature control frequency; error correction coding is added to the generated signal compression frame, and the redundancy is adjusted according to the channel conditions of each node. For example, for the high-interference channel of the rolling node, redundant error correction bits are added, and for the low-interference channel of the annealing node, redundancy is reduced. The generated signal compression frame includes three parts: a check segment (for error detection), a basic data segment (compressed timing and performance characteristics) and a feature mapping segment (multi-layer feature association information); based on the data transmission processing protocol, the signal compression frame is transmitted to the collaborative control center through the collaborative communication network. In actual production, the network load is monitored and the delay is controlled to ensure that the signal frame is transmitted between multiple nodes. Real-time synchronization. If signal damage or loss is detected during channel transmission, error correction coding is used to reconstruct data or request retransmission to ensure signal integrity. The collaborative control center decodes and restores the received signal compression frame, restores the signal timing characteristics and copper wire performance correlation characteristics, and calculates the adjustment weights and generates parameter collaborative control instructions based on the process adjustment parameters. This includes decoding the signal and calculating the parameter adjustment weights. According to the process adjustment parameters provided by the industrial control perception platform, the priority and adjustment range of each node adjustment are determined. Based on the adjustment weights, parameter collaborative control instructions are generated and fed back to each process control node through the collaborative communication network to drive real-time adjustment and optimize process parameters.

[0098] Further, based on the signal characteristics, a signal compression frame that meets the communication requirements of multiple process control nodes is generated, including:

[0099] Preprocess the process operation parameters, extract the signal transmission characteristics, and perform feature stratification based on the signal transmission characteristics;

[0100] According to the signal coding model, the process operation parameters are hierarchically compressed and encoded to generate hierarchical compressed signals. The hierarchical compression includes time compression, frequency compression and feature mapping compression.

[0101] According to the data transmission processing protocol, error correction coding is added to each level of the layered compressed signal. The error correction coding is responsible for adjusting the coding redundancy according to the channel conditions of the process control node;

[0102] The layered compressed signal and the error correction coding are processed and packaged in a layered structure to generate a signal compression frame, which includes a check segment, a basic data segment and a feature mapping segment.

[0103] As a preferred embodiment of the above, the process operation parameters in the rolling and annealing process are collected through the industrial control perception platform, and preprocessed to extract signal transmission characteristics, including timing characteristics, frequency characteristics and feature mapping, wherein the timing characteristics record the time series changes of the process operation, such as the real-time fluctuation of the rolling pressure and the temperature adjustment of the annealing temperature control, the frequency characteristics extract the main frequency components by analyzing the spectrum composition of the signal, such as the thermal field frequency in the annealing temperature control, and the feature mapping reflects the correlation between the copper wire performance (such as hardness, conductivity) and the process parameters. The extracted signal transmission characteristics are layered according to the time level, frequency level and feature mapping level to form data structures of different dimensions; the process operation parameters are layered and compressed based on the signal coding model to reduce the amount of data and retain key information. In time compression, important time series data points are extracted by sliding window technology to reduce redundant sampling. In frequency compression, Fourier transform and other methods are used to extract the main frequency components and ignore secondary signals. In feature mapping compression, the complex relationship between copper wire performance and process parameters is simplified. The data complexity is reduced through discretization processing. After hierarchical compression, the generated signal compression data contains the key features of the time series, the main frequency information and the simplified performance mapping relationship. According to the data transmission processing protocol, error correction coding is added to each level of the hierarchical compressed signal to improve the reliability and anti-interference ability of signal transmission. Specifically, for high-interference channels (such as the real-time pressure signal of the rolling node), redundant error correction bits are added to reduce data loss. For low-interference channels (such as the temperature data of the annealing temperature control node), redundancy is appropriately reduced to improve transmission efficiency. The dynamic adjustment of error correction coding is carried out according to the channel conditions, so that the transmission of signals between different nodes can adapt to the complex network environment. The compressed and error-corrected signals are packaged according to the hierarchical structure to generate signal compression frames. The compressed frames include three parts: a check segment, which is used to verify the integrity of data transmission; a basic data segment, which stores compressed timing data and frequency data, representing the main information of the process operation; a feature mapping segment, which contains the mapping relationship between copper wire performance and process parameters, which is used as a reference for subsequent parameter adjustment. Taking the rolling process as an example, by compressing the pressure signal, the sampling rate is reduced from 1000 times per second to 100 times per second. At the same time, the data structure is simplified through frequency compression and feature mapping. Combined with the high-interference channel conditions, redundant error correction coding is set. The generated signal compression frame greatly improves the transmission efficiency while ensuring data integrity.

[0104] Further, if Figure 4 As shown, the parameters are corrected based on the feedback from the cooperative communication network to the rolling control node and the annealing temperature control node, including:

[0105] Decompose the parameter collaborative control instructions layer by layer, and extract the rolling parameter correction sub-instructions and annealing temperature control correction sub-instructions;

[0106] Distribute rolling parameter correction sub-instructions and annealing temperature control correction sub-instructions to corresponding rolling control nodes and annealing temperature control nodes through a collaborative communication network;

[0107] Compare the data of the rolling control node with the rolling parameter correction sub-instruction to extract the rolling deviation, generate the rolling pressure correction value, and adjust the rolling pressure accordingly;

[0108] Based on the analysis of the on-site temperature data, the temperature control deviation is calculated according to the thermal field gradient of the copper wire surface. The temperature control correction value is generated by combining the temperature control deviation with the annealing temperature control correction sub-instruction, and the temperature control is adjusted accordingly.

[0109] As a preferred embodiment of the above embodiment, the parameter collaborative control instructions generated by the collaborative control center are decomposed layer by layer to extract the rolling parameter correction sub-instructions and the annealing temperature control correction sub-instructions. For example, in the copper wire production process, the control instructions of the collaborative control center include pressure adjustment and temperature correction parameters. The decomposed rolling parameter correction sub-instructions specifically indicate the adjustment value of the pressure deviation, while the annealing temperature control correction sub-instructions provide the temperature control adjustment range and the target temperature value; the extracted rolling parameter correction sub-instructions and annealing temperature control correction sub-instructions are distributed to the corresponding rolling control nodes and annealing temperature control nodes through the collaborative communication network. For example, in the rolling node, the rolling parameter correction sub-instruction is transmitted to the equipment control end in real time, and in the annealing temperature control node, the annealing temperature control correction sub-instruction is sent through the network. The distributed instructions enter their respective execution processes to ensure that the parameter adjustment in the production process is carried out synchronously; in the rolling control node, the real-time collected rolling data is compared with the rolling parameter correction sub-instructions. The rolling deviation is extracted by comparing with the instruction. For example, when the real-time rolling pressure is 200MPa and the correction sub-instruction requires 210MPa, the rolling deviation is calculated to be 10MPa. According to the deviation, the rolling pressure correction value is generated, and the rolling pressure is adjusted by the pressure regulator. At the annealing temperature control node, the surface temperature data of the copper wire collected on site is analyzed and the temperature control correction sub-instruction is combined with the annealing temperature control correction sub-instruction to perform temperature control correction, that is, the surface temperature distribution and heat flux density signal of the copper wire are collected, and a multi-mode signal set of the thermal field is formed after adaptive filtering. The thermal field gradient of the copper wire surface is extracted, and the calculated thermal field gradient is compared with the target temperature distribution. For example, the actual surface gradient is 15℃ / mm, and the target value in the correction instruction is 10℃ / mm, then the deviation is 5℃ / mm. According to the temperature control deviation and the correction sub-instruction, a specific temperature control correction value is generated, for example, the temperature control device is adjusted to reduce or increase the surface temperature to the target value, and the output temperature of the temperature control node is adjusted in real time.

[0110] Furthermore, the temperature control deviation is calculated based on the thermal field gradient on the copper wire surface, including:

[0111] Based on the annealing temperature control node, the temperature distribution signal and heat flux density signal on the surface of the copper wire are collected, and the collected signals are adaptively filtered and optimized to remove high-frequency noise and mutation signal interference, forming a thermal field multi-mode signal set;

[0112] The thermal field multi-mode signal set is parsed to extract the thermal field gradient on the copper wire surface, and the thermal field gradient on the copper wire surface is combined with the time series to generate a thermal field feature matrix;

[0113] The thermal field gradient on the copper wire surface is nonlinearly compared with the target temperature distribution in the annealing temperature control correction sub-instruction to establish the thermal field gradient equation;

[0114] The thermal field characteristic matrix is ​​substituted into the thermal field gradient equation. During the equation solving process, the thermal field multi-mode signal set is updated according to the different copper wire materials and production environment changes, and the temperature control deviation is calculated.

[0115] As a preferred embodiment of the above embodiment, in the annealing temperature control node, the temperature distribution signal and the heat flux density signal of the copper wire surface are collected by the sensor, and the collected signals are subjected to adaptive filtering optimization processing. The adaptive filtering technology is used to remove high-frequency noise and mutation signal interference in the signal, such as abnormal data caused by environmental vibration or instantaneous temperature fluctuation, so as to form a stable and reliable thermal field multi-mode signal set, which includes the thermal field data of the copper wire surface at different time and space positions; the thermal field multi-mode signal set is analyzed to extract the thermal field gradient of the copper wire surface. The thermal field gradient of the copper wire surface reflects the temperature change trend of different areas of the copper wire surface. For example, within a certain period of time, the rate of change of the copper wire surface temperature from one position to another is 10°C / mm. This value is the thermal field gradient of the copper wire surface. The extracted thermal field gradient of the copper wire surface is The field gradient is combined with the time series data to generate a thermal field characteristic matrix, which integrates the dynamic characteristics of the thermal field gradient over time; the thermal field gradient on the copper wire surface is nonlinearly compared with the target temperature distribution in the annealing temperature control correction sub-instruction. Through nonlinear comparison analysis, the thermal field gradient equation is established. The equation describes the relationship between the actual thermal field gradient on the copper wire surface and the target temperature distribution. For example, when the target temperature distribution is a uniform linear distribution, the actual thermal field gradient may show a nonlinear deviation state, and the equation will quantify this deviation; the thermal field characteristic matrix is ​​substituted into the thermal field gradient equation for solution. During the solution process, according to the different materials of the copper wire (for example, the thermal conductivity of pure copper and alloy copper is different) and the dynamic changes of the production environment (such as ambient temperature fluctuations), the thermal field multi-mode signal set is updated in real time to ensure the accuracy of the calculation results. The temperature control deviation is calculated through the above steps. For example, the deviation between the actual thermal field gradient and the target thermal field gradient is ±3℃ / mm, and it is used to guide the adjustment of the annealing temperature control parameters.

[0116] Specifically, the data transmission processing protocol is set up, including:

[0117] Define the data transmission format, encode the multi-mode process signals in a standardized manner according to the data transmission format, and synchronize them to the collaborative communication network;

[0118] Analyze the network load requirements of each process control node and determine the transmission rate and delay control strategy based on the data transmission format;

[0119] Establish a redundant data verification algorithm, combine it with the delay control strategy to perform data integrity and error detection, and select an appropriate retransmission strategy based on the network status;

[0120] Establish data transmission priority management based on the test results of data integrity and error detection, and set the data transmission priority of different multi-mode process signals;

[0121] A data transmission processing protocol is generated based on the data transmission format, delay control strategy, redundant data verification algorithm and data transmission priority management integration.

[0122] As a preferred embodiment of the above, a data transmission format suitable for multi-mode process signals is defined, and the collected multi-mode process signals (such as pressure signals, temperature signals and material performance data) are standardized and encoded according to a preset transmission format. For example, the pressure signal of the rolling node can be encoded as a time series sampled per second, and the temperature signal of the annealing temperature control node can be encoded in the form of frequency layers. After the encoding is completed, the standardized data is synchronized through a collaborative communication network, so that different control nodes can share data in real time; the network load requirements of each process control node are analyzed. For example, the rolling node needs to process real-time pressure adjustment, so the network load is large, while the annealing node has a lower real-time requirement for temperature adjustment and the load requirement is relatively small. Based on the network load analysis and combined with the data transmission format, a specific transmission rate and delay control strategy is formulated for each node. For example, the data transmission rate of the rolling node is set to 1000 samples per second, and the allowed transmission delay does not exceed 1 millisecond; the data transmission rate of the annealing node is set to 100 samples per second, and the allowed transmission delay does not exceed 10 milliseconds; a redundant data verification algorithm is established, and data integrity and error detection are performed in combination with the delay control strategy to address signal loss or errors that may occur in network transmission. , the integrity of the data packet is detected by the verification algorithm, for example, CRC checksum is embedded in each data packet to verify the accuracy of the data. When the network status is poor, an appropriate retransmission strategy is selected, for example, a fast retransmission mechanism is enabled for the key data packets of the rolling node, and a delayed retransmission strategy is adopted for the secondary data packets of the annealing node; according to the results of data integrity and error detection, a data transmission priority management mechanism is established to assign priorities to different types of process signals. For example, the real-time pressure signal of the rolling node is set to the highest priority to ensure priority transmission, the temperature signal of the annealing temperature control node is set to the medium priority, and the diagnostic data related to production performance is set to the lowest priority and transmitted when the network is idle; according to the above data transmission format, delay control strategy, redundant data verification algorithm and data transmission priority management settings, a complete data transmission processing protocol is integrated and generated to dynamically adapt to the network requirements of different process nodes, and improve the reliability and real-time performance of data transmission while ensuring signal transmission efficiency. For example, in the copper wire production process, the real-time pressure data of the rolling node is ensured to be transmitted without delay through priority scheduling and fast retransmission mechanism, while the temperature data of the annealing temperature control node effectively reduces the network load through layered transmission and standardized coding.

[0123] Embodiment 2:

[0124] Based on the same inventive concept as the intelligent network copper wire multi-pass rolling and annealing coordinated control method in the aforementioned embodiment, the present invention also provides an intelligent network copper wire multi-pass rolling and annealing coordinated control system, the system comprising:

[0125] The data acquisition module sets process control nodes according to the industrial control process, establishes a collaborative communication network based on the process control nodes, and collects multi-mode industrial control signals. The process control nodes include rolling control nodes and annealing temperature control nodes;

[0126] The signal conversion module sets the data transmission processing protocol and establishes an industrial control perception platform. It integrates multi-mode industrial control signals according to the industrial control perception platform and converts them into process operation parameters according to process position.

[0127] Adjust the calculation module, analyze the nonlinear correlation between process steps based on the industrial control perception platform, and calculate the process adjustment parameters based on the copper wire performance indicators;

[0128] Collaborative control module: establishes a collaborative control center, transmits process operation parameters to the collaborative control center according to the data transmission processing protocol, compares and analyzes them with process adjustment parameters, and generates parameter collaborative control instructions;

[0129] The feedback correction module feeds back the parameter collaborative control instructions to the rolling control node and the annealing temperature control node based on the collaborative communication network for parameter correction.

[0130] The above-mentioned adjustment system in the present invention can effectively realize the coordinated control method of multi-pass rolling and annealing of copper wire based on intelligent network, and the technical effects that can be achieved are as described in the above-mentioned embodiments and will not be repeated here.

[0131] More specifically, this includes:

[0132] The mapping model unit models the nonlinear relationship between the different running times of each industrial control process based on the industrial control perception platform and the collaborative communication network, and generates a multi-time series nonlinear mapping model;

[0133] The spatiotemporal interaction unit performs temporal modeling of multi-mode industrial control signals based on a multi-temporal nonlinear mapping model, and analyzes the temporal correlation and interaction effects between process steps;

[0134] The correlation analysis unit analyzes the interaction effect strength between process control nodes through time-varying nonlinear correlation based on temporal correlation and interaction effect;

[0135] The quantitative adjustment unit quantifies the intensity of the interaction effect and combines the multi-time series nonlinear mapping model to perform feedback adjustment on the multi-mode industrial control signal through the data transmission processing protocol.

[0136] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the optimization effects corresponding to the method in Example 1, which will not be repeated here.

[0137] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application as defined therein, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A method for coordinated control of multi-pass rolling and annealing of copper wire based on intelligent network, characterized in that: The method comprises: Setting process control nodes according to the industrial control process, establishing a collaborative communication network based on the process control nodes and collecting multi-mode industrial control signals, the process control nodes including rolling control nodes and annealing temperature control nodes; Setting a data transmission processing protocol and establishing an industrial control perception platform, integrating the multi-mode industrial control signals according to the industrial control perception platform and converting them into process operation parameters according to process position; Based on the industrial control perception platform, the nonlinear correlation between the process steps is analyzed, and the process adjustment parameters are calculated in combination with the copper wire performance indicators, including: The industrial control perception platform collects pressure signals, temperature signals and material performance data generated during rolling and annealing, and transmits the pressure fluctuation data of the rolling process and the annealing temperature change data to the industrial control perception platform through the collaborative communication network. During the rolling process, it records in real time whether the pressure change shows a nonlinear oscillation trend over time and the correlation between the temperature fluctuation and the cooling rate during the annealing process. Through nonlinear multivariate modeling, a multi-time series nonlinear mapping model is generated, which clarifies the nonlinear relationship between the pressure and temperature changes at different time nodes and the material hardness. Based on the multi-time series nonlinear mapping model, the rolling pressure signal and the annealing temperature signal are modeled in time series to generate a time series data set. The analysis reveals the positive correlation between the peak point of the pressure in the rolling process and the heating rate of the annealing temperature. Through the time series sliding window technology, it is found whether the temperature adjustment frequency of the temperature control node affects the subsequent rolling uniformity, revealing the time series dependency between the processes. By using time-varying nonlinear correlation technology, the interaction effect strength between the rolling control node and the annealing temperature control node is calculated, and by quantitative analysis of the interaction effect strength, a relationship curve between the pressure fluctuation amplitude and the temperature control delay time is determined; After completing the quantification of the intensity of the interaction effect, the multi-time series nonlinear mapping model is used to feed back the analysis results to the industrial control perception platform, and the performance index control target of the copper wire product is used to optimize the production process by adjusting the rolling pressure and annealing temperature control parameters. For the abnormal thermal field gradient found, the temperature response time of the temperature control node is adjusted through the data transmission protocol, and at the same time, a feedback adjustment signal is generated for the problem of excessive pressure fluctuations during the rolling process; Establishing a collaborative control center, transmitting the process operation parameters to the collaborative control center according to the data transmission processing protocol, and comparing and analyzing the process adjustment parameters to generate parameter collaborative control instructions; The parameter collaborative control instruction is fed back to the rolling control node and the annealing temperature control node based on the collaborative communication network to perform parameter correction.

2. The intelligent network-based copper wire multi-pass rolling and annealing coordinated control method according to claim 1 is characterized in that: The nonlinear correlation between process steps is analyzed based on the industrial control perception platform, including: Modeling the nonlinear relationship between the different running times of the industrial control processes according to the industrial control perception platform and the collaborative communication network to generate the multi-time series nonlinear mapping model; According to the multi-time nonlinear mapping model, timing modeling is performed on the multi-mode industrial control signal to analyze the timing correlation and interaction effect between the process steps; According to the timing correlation and the interaction effect, analyzing the interaction effect intensity between the process control nodes through time-varying nonlinear association; The interaction effect strength is quantified, combined with the multi-time series nonlinear mapping model, and feedback adjustment is performed on the multi-mode industrial control signal through the data transmission processing protocol.

3. The intelligent network-based copper wire multi-pass rolling and annealing coordinated control method according to claim 2 is characterized in that: Analyze the temporal dependencies and interaction effects between the process steps, including: Based on the multi-time series nonlinear mapping model, construct the time series data set of each process step, and identify the time series correlation between the process steps; Mapping the time series data set to multiple time scales, and analyzing the temporal dependencies between different process steps through time window sliding and multi-scale decomposition; Performing interaction effect analysis based on the timing dependency to quantify the interaction effects between different process steps; The timing correlation and the interaction effect are fed back to the industrial control perception platform, and corresponding parameters are adjusted in the multi-timing nonlinear mapping model.

4. The intelligent network-based copper wire multi-pass rolling and annealing coordinated control method according to claim 1 is characterized in that: Generate parameter coordination control instructions, including: Extracting the signal transmission characteristics of the process operation parameters based on the industrial control perception platform, wherein the signal transmission characteristics include process step timing characteristics and copper wire performance correlation characteristics; Constructing a signal coding model, generating a signal compression frame that meets the communication requirements of the plurality of process control nodes based on the signal transmission characteristics, and adding error correction coding to the signal compression frame; Based on the data transmission processing protocol, transmitting the signal compression frame to the collaborative control center through the collaborative communication network; The collaborative control center decodes and restores the received signal compression frame, combines the process adjustment parameters, determines the parameter adjustment weight, and generates a parameter collaborative control instruction.

5. The intelligent network-based copper wire multi-pass rolling and annealing coordinated control method according to claim 4 is characterized in that: Generating a signal compression frame that meets the communication requirements of a plurality of the process control nodes based on the signal transmission characteristics includes: Preprocessing the process operation parameters, extracting the signal transmission characteristics, and performing feature stratification according to the signal transmission characteristics; According to the signal coding model, the process operation parameters are subjected to hierarchical compression coding to generate hierarchical compressed signals, wherein the hierarchical compression includes time compression, frequency compression and feature mapping compression; According to the data transmission processing protocol, the error correction code is added to each level of the layered compressed signal, and the error correction code is responsible for adjusting the coding redundancy according to the channel condition of the process control node; The layered compressed signal and the error correction coding are processed and packaged in a layered structure to generate the signal compression frame, and the signal compression frame includes a check segment, a basic data segment and a feature mapping segment.

6. The intelligent network-based copper wire multi-pass rolling and annealing coordinated control method according to claim 1 is characterized in that: Feedback to the rolling control node and the annealing temperature control node based on the collaborative communication network to perform parameter correction, including: Decomposing the parameter coordinated control instructions layer by layer, and extracting rolling parameter correction sub-instructions and annealing temperature control correction sub-instructions; Distributing the rolling parameter correction sub-instruction and the annealing temperature control correction sub-instruction to the corresponding rolling control node and the annealing temperature control node through the collaborative communication network; Compare the data of the rolling control node with the rolling parameter correction sub-instruction to extract the rolling deviation, generate a rolling pressure correction value, and adjust the rolling pressure accordingly; Based on the analysis of the on-site temperature data, the temperature control deviation is calculated according to the thermal field gradient of the copper wire surface, the temperature control correction value is generated by combining the temperature control deviation with the annealing temperature control correction sub-instruction, and the temperature control is adjusted accordingly.

7. The intelligent network-based copper wire multi-pass rolling and annealing coordinated control method according to claim 6 is characterized in that: The temperature control deviation is calculated based on the thermal field gradient on the copper wire surface, including: Based on the annealing temperature control node, the temperature distribution signal and heat flux density signal on the surface of the copper wire are collected, and the collected signals are adaptively filtered and optimized to remove high-frequency noise and mutation signal interference to form a thermal field multi-mode signal set; The thermal field multimode signal set is parsed to extract the thermal field gradient on the surface of the copper wire, and the thermal field gradient on the surface of the copper wire is combined with a time series to generate a thermal field feature matrix; Performing a nonlinear comparison between the thermal field gradient on the surface of the copper wire and the target temperature distribution in the annealing temperature control correction sub-instruction, and establishing a thermal field gradient equation; The thermal field characteristic matrix is ​​substituted into the thermal field gradient equation. During the equation solving process, the thermal field multi-mode signal set is updated according to different copper wire materials and production environment changes to calculate the temperature control deviation.

8. The intelligent network-based copper wire multi-pass rolling and annealing coordinated control method according to claim 1 is characterized in that: Set up data transfer processing protocols, including: Defining a data transmission format, encoding the multi-mode industrial control signal in a standardized manner according to the data transmission format, and synchronizing the signal to the collaborative communication network; Analyze the network load requirements of each of the process control nodes, and determine the transmission rate and delay control strategy based on the data transmission format; Establishing a redundant data verification algorithm, combining the delay control strategy with data integrity and error detection, and selecting an appropriate retransmission strategy according to the network status; Establishing data transmission priority management according to the detection results of the data integrity and error detection, and setting the data transmission priorities of different multi-mode industrial control signals; The data transmission processing protocol is generated based on the data transmission format, delay control strategy, redundant data verification algorithm and data transmission priority management integration.

9. Intelligent network based copper wire multi-pass rolling and annealing coordinated control system, characterized in that: The method for coordinated control of multi-pass rolling and annealing of copper wire based on intelligent network as claimed in claim 1 is adopted, and the system comprises: The data acquisition module sets process control nodes according to the industrial control process, establishes a collaborative communication network based on the process control nodes, and collects multi-mode industrial control signals. The process control nodes include rolling control nodes and annealing temperature control nodes; The signal conversion module sets the data transmission processing protocol and establishes an industrial control perception platform. It integrates multi-mode industrial control signals according to the industrial control perception platform and converts them into process operation parameters according to process position. Adjust the calculation module, analyze the nonlinear correlation between process steps based on the industrial control perception platform, and calculate the process adjustment parameters based on the copper wire performance indicators; Collaborative control module: establishes a collaborative control center, transmits process operation parameters to the collaborative control center according to the data transmission processing protocol, compares and analyzes them with process adjustment parameters, and generates parameter collaborative control instructions; The feedback correction module feeds back the parameter collaborative control instructions to the rolling control node and the annealing temperature control node based on the collaborative communication network for parameter correction.

10. The intelligent network-based copper wire multi-pass rolling and annealing coordinated control system according to claim 9, characterized in that: The adjustment calculation module comprises: The mapping model unit models the nonlinear relationship between the different running times of each industrial control process based on the industrial control perception platform and the collaborative communication network, and generates a multi-time series nonlinear mapping model; The spatiotemporal interaction unit performs temporal modeling of multi-mode industrial control signals based on a multi-temporal nonlinear mapping model, and analyzes the temporal correlation and interaction effects between process steps; The correlation analysis unit analyzes the interaction effect strength between process control nodes through time-varying nonlinear correlation based on temporal correlation and interaction effect; The quantitative adjustment unit quantifies the intensity of the interaction effect and combines the multi-time series nonlinear mapping model to perform feedback adjustment on the multi-mode industrial control signal through the data transmission processing protocol.

Images