A cable production line whole-process process optimization control system based on digital twinning

Abstract

The application relates to the technical field of cable production line process optimization, in particular to a cable production line whole-process process optimization control system based on digital twinning, which comprises a database, a simulation simulation module, a data acquisition module and a data analysis module; the simulation simulation module is used to construct a digital twinning model of a whole process of target cable production, so that the process production process of the target cable is simulated and simulated; the data acquisition module is used to acquire process parameters of each working procedure in the process production process of the target cable in real time; the data analysis module is used to determine a plurality of to-be-tested working procedures based on working procedure stability and working procedure accuracy of each working procedure; the sensitive test module is used to perform sensitivity test on the process parameters of each to-be-tested working procedure, so as to determine a key process parameter combination; the process optimization module is used to perform iterative adjustment optimization on the process parameters of each to-be-tested working procedure, and adjust the process parameters of each to-be-adjusted working procedure. The application can improve the whole-process process optimization efficiency and effect of the cable production line.

Description

Technical Field

[0001] This invention relates to the field of cable production line process optimization technology, and in particular to a cable production line full-process process optimization control system based on digital twins. Background Technology

[0002] As a fundamental supporting industry of the national economy, cables are widely used in key areas such as power transmission, rail transportation, communication networks, new energy construction, and national defense. Cable manufacturing is a typical multi-stage continuous production process, typically involving multiple processes such as wire drawing, stranding, insulation extrusion, cross-linking, sheath extrusion, armoring, and cabling. These processes are characterized by continuous material flow, temporal coupling, and parameter interlocking. Taking cross-linked polyethylene insulated power cables as an example, process parameters such as extrusion temperature, extrusion speed, traction speed, and cross-linking temperature are interdependent. Extrusion temperature directly affects melt flowability and the surface quality of the insulation layer; abnormal temperature control can lead to pre-cross-linking of the material, forming protruding particles on the surface of the extruded layer, ultimately causing cable breakdown. Cross-linking temperature and cross-linking time together determine the degree of cross-linking of the insulation layer; insufficient cross-linking will result in substandard thermal elongation performance of the insulation layer. The strong coupling between the various processes makes the global optimization of process parameters extremely challenging.

[0003] In recent years, digital twin technology has emerged as a core enabling technology for intelligent manufacturing. By constructing high-fidelity virtual mirrors of physical entities, it achieves deep integration and interactive mapping between physical and information spaces. In the cable manufacturing industry, exploratory practices of digital twin technology have been implemented. By collecting production data and uploading it to an edge cloud platform, digital twin models are constructed to visualize production status. Based on model simulations, capacity prediction, production switching scheduling, and energy consumption regulation are optimized.

[0004] Chinese Patent Publication No. CN121882339A discloses a method and system for optimizing multi-process cable manufacturing using digital twins. The method constructs a multi-process digital twin model of cables, including a core library and a core list; collects multi-source data from multiple cable manufacturing processes, preprocesses the data to generate a time-series dataset; based on the dataset, calculates the load coefficient of each process using a process load coefficient algorithm, and dynamically identifies bottleneck processes in the production line by combining bottleneck judgment rules; uses the digital twin model to predict quality indicators, calculates risk values, and issues graded warnings based on warning thresholds, initiates reverse tracing, and locates quality anomalies by combining the associated data from the core library; and optimizes process parameters using simulated annealing and a dual-population genetic algorithm, generating parameter compensation schemes to complete the multi-process optimization of cables.

[0005] Existing technologies have the following problems: they lack deep coupling between material properties and extreme environmental parameters; the results of process optimization can only guarantee product quality under normal working conditions, and cannot guarantee the long-term reliability of products under extreme environments; they only consider the load coefficient of the process and ignore the process stability and accuracy, making it difficult to guarantee the stability of the production quality of the process. Summary of the Invention

[0006] To address this, the present invention provides a digital twin-based full-process optimization control system for cable production lines, which overcomes the problems in existing technologies that cannot ensure the long-term reliability of products under extreme environments, and that considering only the load factor of the process makes it difficult to guarantee the stability of the production quality of the process.

[0007] To achieve the above objectives, this invention provides a digital twin-based end-to-end process optimization control system for cable production lines, comprising:

[0008] The database is used to store the design process parameters, material formulas, and extreme environmental parameters of the target cable within the target area;

[0009] The simulation module is used to build a digital twin model of the entire production process of the target cable based on the design process parameters and material formula of the target cable, so as to simulate the production process of the target cable and output the predicted process parameters and predicted product quality indicators of each process in the production process.

[0010] The data acquisition module is used to acquire process parameters of each step in the manufacturing process of the target cable in real time.

[0011] The data analysis module is used to determine the process stability of each process based on the real-time process parameters and predicted process parameters of each process in the production process, and to determine the process accuracy of each completed process based on the real-time product quality indicators and corresponding predicted product quality indicators of several completed processes, and to determine several processes to be tested based on the process stability of each process and the process accuracy of the completed processes.

[0012] A sensitivity testing module is used to perform sensitivity testing on the process parameters of each of the test steps based on the extreme environmental parameters, so as to determine the combination of key process parameters.

[0013] The process optimization module is used to iteratively adjust and optimize the process parameters of each of the test processes based on the digital twin model and the combination of key process parameters to obtain a target process parameter combination, and to determine several processes to be adjusted based on the target process parameter combination, so as to adjust the process parameters of each process to be adjusted.

[0014] Furthermore, the simulation module includes:

[0015] The model building unit is used to construct a geometric twin of the target cable based on the design process parameters of the target cable, determine the material property parameters based on the material formula of the target cable, and generate process models of each layer of the target cable based on the geometric twin and material property parameters, so as to construct a digital twin model of the entire production process of the target cable.

[0016] Furthermore, the simulation module includes:

[0017] The simulation unit is used to simulate the production process of the target cable based on the digital twin model of the entire production process of the target cable and the combination of simulation process parameters corresponding to each process, so as to obtain several simulation results. Based on the simulation results, the unit outputs the predicted process parameters and predicted product quality indicators of each process in the production process. The simulation results include the simulated product quality indicators corresponding to each combination of simulation process parameters.

[0018] Furthermore, the data analysis module includes:

[0019] The first analysis unit is used to determine the stability of a process based on the parameter deviation coefficient of any of the processes and a preset deviation coefficient, wherein the parameter deviation coefficient of the process is determined based on the real-time process parameters and the predicted process parameters of the process.

[0020] Furthermore, the data analysis module includes:

[0021] The second analysis unit is used to determine the process accuracy of the completed process based on the index deviation coefficient of any completed process and the index deviation coefficient of the preceding completed process, wherein the index deviation coefficient of the completed process is determined based on the real-time product quality index of the completed process and the corresponding predicted product quality index.

[0022] Furthermore, the data analysis module includes:

[0023] The analysis and judgment unit is used to determine the process to be tested based on the judgment result that the process stability of any of the processes does not meet the preset stability standard.

[0024] Furthermore, the analysis and determination unit is also used to determine the completed process as a candidate process based on the determination result that the process stability of any of the completed processes meets the preset stability standard. If the process accuracy of any of the candidate processes does not meet the preset accuracy standard, then the candidate process is determined as a process to be tested.

[0025] Furthermore, the sensitivity testing module includes:

[0026] The sensitive testing unit is used to adjust the process parameters of each of the test processes based on the digital twin model to obtain a test cable twin, and to perform environmental simulation testing on the test cable twin based on the extreme environmental parameters to obtain the corresponding test duration margin. Each test cable twin has a corresponding combination of test process parameters and a corresponding test product quality index.

[0027] Furthermore, the sensitivity testing module includes:

[0028] The test analysis unit is used to determine several key cable twins based on the test duration margin and test product quality indicators corresponding to each of the test cable twins, and to determine the combination of key process parameters based on the process parameters of each of the key cable twins.

[0029] Furthermore, the process optimization module includes:

[0030] The process optimization unit is used to iteratively adjust and optimize the process parameters of each of the test steps based on the digital twin model and the combination of key process parameters, so as to obtain the target process parameter combination.

[0031] The adjustment control unit is used to determine the reference process parameters of each process based on the target process parameter combination and the digital twin model, and to determine several processes to be adjusted based on the reference process parameters and real-time process parameters of each process, so as to adjust the process parameters of each process to be adjusted.

[0032] Compared with existing technologies, the beneficial effects of this invention are as follows: By building a digital twin model of the entire target cable production process based on design process requirements and actual formulas, this invention synchronously outputs predicted process parameters and predicted product quality indicators for each process, thereby shortening the cable commissioning cycle and improving production efficiency and quality. By comprehensively considering the comparison results of real-time process parameters and predicted process parameters for each process during production, and the comparison results of product quality indicators for completed processes and predicted product quality indicators, the invention introduces process stability and process accuracy to screen and identify processes to be tested for sensitivity testing. This allows for the analysis of key process parameter combinations that are sensitive to extreme environments, enabling targeted iterative adjustments and optimizations. This avoids indiscriminate adjustments throughout the entire production line, improving production optimization efficiency and effectiveness, and further enhancing the product quality of the finished cable.

[0033] Furthermore, the simulation module generates process models of each layer of the target cable by integrating the cable's physical geometry and material properties. This accurately captures the changing trends of different material layers in each process. The resulting digital twin model of the entire cable production process enables parallel simulation of multiple sets of process parameters, thereby obtaining predicted process parameters and predicted product quality indicators, and improving prediction accuracy.

[0034] Furthermore, the data analysis module quantifies the deviation between real-time process parameters and simulation prediction parameters using parameter deviation coefficients. It then calculates process stability by comparing the deviation coefficients with preset values, enabling precise identification of local parameter deviations in single processes. By comparing the actual product quality indicators of completed processes with the simulation prediction quality indicators using index deviation coefficients, it can accurately quantify the deviation between the output of each process and the theoretical product quality during actual production. By comprehensively considering both process stability and process accuracy, a two-dimensional evaluation is achieved, accurately identifying processes with significant parameter deviations or substandard product quality, thus improving the efficiency and effectiveness of subsequent optimization.

[0035] Furthermore, the sensitive testing module adaptively adjusts the constructed digital twin model to obtain the corresponding test cable twin, and performs environmental simulation tests on the test cable twin in conjunction with extreme environmental parameters to determine the output test duration margin. This allows for accurate assessment of the cable's durability in extreme environments. By comprehensively considering both the test duration margin and the test product quality indicators, key cable twins are selected, which can accurately identify process parameters that are more sensitive to extreme environments, providing data support for subsequent process optimization. Attached Figure Description

[0036] Figure 1 This is a structural block diagram of the cable production line process optimization control system based on digital twins, as described in an embodiment of the present invention.

[0037] Figure 2 This is a structural block diagram of the simulation module in an embodiment of the present invention;

[0038] Figure 3 This is a structural block diagram of the data analysis module in an embodiment of the present invention;

[0039] Figure 4 This is a structural block diagram of the sensitive testing module according to an embodiment of the present invention;

[0040] Figure 5 This is a structural block diagram of the optimized module in an embodiment of the present invention. Detailed Implementation

[0041] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0042] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0043] Please see Figure 1 The diagram shown is a structural block diagram of the cable production line full-process process optimization control system based on digital twins according to an embodiment of the present invention. The cable production line full-process process optimization control system provided in this embodiment of the present invention includes:

[0044] The database is used to store the design process parameters, material formulas, and extreme environmental parameters of the target cable within the target area;

[0045] In this embodiment, the specific architecture of the database is not limited. For example, it can be divided into three independent storage partitions: a process parameter storage partition, a material formula storage partition, and an extreme environment parameter storage partition. The process parameter storage partition is used to input and store the design process parameters of various high-altitude special cables. The target cable includes at least an inner conductor, an insulation layer, and a sheath layer. The design process parameters include, but are not limited to: inner conductor cross-section, nominal insulation layer thickness, nominal sheath layer thickness, armor layer type and specifications, cable outer diameter, the arrangement order of each layer structure, insulation extrusion temperature, etc. It also stores the process tolerance thresholds for cables of different voltage levels and different laying scenarios, and supports retrieval by cable model and laying area index. The method of obtaining the design process parameters is not limited. For example, the product design specification of the target cable can be read directly from the database, or the structural parameters of the target cable can be input through the user interface. The system includes a structural design parameters section and a material formula storage area. This area is used to pre-store complete formulas for PVC cold-resistant materials, halogen-free low-smoke LSZH, cross-linked XLPE insulation materials, and UV-resistant sheathing materials, adapted to the operating conditions of the target area. Simultaneously, it binds the corresponding material property parameters for each formula, including low-temperature embrittlement temperature, UV aging degradation coefficient, insulation dielectric strength, thermal expansion and contraction deformation coefficient, impact strength of armored steel, and sealing adhesion coefficient of aluminum-plastic composite tape. An extreme environment parameter storage area is used to input standardized extreme environmental parameters for the target area, covering low-pressure values ​​at altitudes above 4000m, extreme low-temperature thresholds in the -40℃ to -50℃ range, total annual UV radiation over 3000 hours, day-night temperature difference cycle curves from -50℃ to +85℃, mountainous mechanical impact loads, and biting mechanical loads, among other environmental boundary conditions. All parameters comply with national standards for cable environmental testing, such as GB / T12706.

[0046] The simulation module, connected to the database, is used to build a digital twin model of the entire production process of the target cable based on the design process parameters and material formula of the target cable. It simulates the production process of the target cable and outputs the predicted process parameters and predicted product quality indicators of each process.

[0047] Please see Figure 2 The diagram shown is a structural block diagram of the simulation module according to an embodiment of the present invention; specifically, the simulation module includes:

[0048] The model building unit is used to build a geometric twin of the target cable based on the design process parameters of the target cable, and to determine the material property parameters based on the material formula of the target cable. Based on the geometric twin and material property parameters of the target cable, it generates process models of each layer of the target cable to build a digital twin model of the entire production process of the target cable.

[0049] In this embodiment, the process of constructing the geometric twin of any target cable includes: establishing a cylindrical coordinate system with the centerline of the target cable as the Z-axis; constructing geometric models of the conductor layer, insulation layer, outer sheath layer, etc., sequentially according to the structural design parameters of each layer of the target cable. Each layer's geometric model is a coaxial cylinder or annular cylinder, and its radius and thickness are determined according to the design process parameters. The geometric models of each layer are constructed in three-dimensional space according to the above parameters, and the geometric models of each layer are spatially superimposed in an order from the inside out to form a complete cable geometric twin. Preferably, for non-circular irregularly shaped cables, such as flat cables or branched cables, the corresponding irregularly shaped geometric twin can be constructed using a non-uniform rational B-spline surface modeling method based on the cross-sectional shape description in the design process parameters.

[0050] It is understood that the material properties are determined based on the material formulation of the target cable. The material formulation is stored in a database, including but not limited to: the type and grade of the base resin for each layer, the type and amount of UV stabilizer, the content and dispersion of carbon black, the type and amount of cold-resistant plasticizer, the type and amount of crosslinking agent, the type and amount of antioxidant, and the type and amount of filler. For each material formulation, the corresponding material properties are determined by querying the material properties database. The material properties include but are not limited to: density, elastic modulus, Poisson's ratio, coefficient of thermal expansion, thermal conductivity, specific heat capacity, melting temperature, glass transition temperature, embrittlement temperature, dielectric constant, dielectric loss tangent, breakdown field strength, volume resistivity, UV aging rate constant, and thermo-oxidative aging rate constant.

[0051] Understandably, for each layer of cable material, and in conjunction with the design process parameters of the corresponding process, process models for conductor stranding, insulation extrusion crosslinking, sheath extrusion, and segmented cooling are constructed respectively. Each layer process model contains embedded coupling calculation equations for the process parameters and material deformation, aging, and electrical performance. The process models of each layer process are coupled in series according to the production line sequence to establish the parameter linkage constraint relationship between processes, resulting in a complete digital twin model of the entire target cable production process. The model has a built-in multi-physics field coupling solver that supports simultaneous simulation calculations of multiple fields such as mechanics, thermodynamics, ultraviolet radiation, and electrical insulation.

[0052] The simulation unit, connected to the model building unit, is used to simulate the production process of the target cable based on the digital twin model of the entire production process of the target cable and the combination of simulation process parameters corresponding to each process, so as to obtain several simulation results. Based on the simulation results, the predicted process parameters and predicted product quality indicators of each process in the production process are output. The simulation results include the simulated product quality indicators corresponding to each combination of simulation process parameters.

[0053] In this embodiment, the simulated process parameter combination refers to the combination of values ​​for each process parameter set during simulation on the digital twin model. The simulated process parameter combination can be determined based on the initial design process parameters in the database, or it can be generated using a parameter combination generation strategy (such as full factorial design, orthogonal design, etc.) based on a preset parameter value range. For any process i, its process parameter vector is denoted as P_i=(p_{i,1},p_{i,2},...,p_{i,k}), where k is the number of process parameters for that process. For example, for the wire drawing process, process parameters include wire drawing speed, annealing voltage, annealing temperature, etc.; for the insulation extrusion process, process parameters include extrusion temperature, screw speed, die head temperature, traction speed, etc.

[0054] Understandably, when generating multiple sets of simulated process parameter combinations, the following approach can be adopted: For each process parameter, its central value is determined based on the design process parameters in the database, and its upper and lower bounds are determined based on the actual capacity range of the process equipment. Then, multiple sets of process parameter combinations are generated using full factorial design or response surface methodology. Taking the insulation extrusion process as an example, the design value for the extrusion temperature is 115℃, and the equipment's allowable range is 105℃~125℃. Five levels can be generated with a step size of 5℃. The design value for the traction speed is 8.5m / min, and the equipment's allowable range is 6.0m / min~11.0m / min. Six levels can be generated with a step size of 1m / min. Through full factorial combination, 5×6=30 sets of simulated process parameter combinations can be generated. For each set of simulated process parameter combinations, the simulation unit inputs it into the digital twin model to perform a complete full-process simulation to obtain the simulated product quality index corresponding to each simulated process parameter combination. With the goal of maximizing the final process product quality index, the predicted process parameters and predicted product quality indexes corresponding to each process are obtained.

[0055] Specifically, the simulation module generates process models of each layer of the target cable by integrating the cable's physical geometry and material properties. This accurately captures the changing trends of different material layers in each process. The resulting digital twin model of the entire cable production process enables parallel simulation of multiple sets of process parameters, thereby obtaining predicted process parameters and predicted product quality indicators, and improving prediction accuracy.

[0056] The data acquisition module is used to acquire process parameters of each step in the manufacturing process of the target cable in real time.

[0057] In this embodiment, the data acquisition module collects process parameters of each process in real time through a sensor network deployed on each process equipment, without limiting the specific structure of the sensor network.

[0058] The data analysis module, which is connected to the data acquisition module and the simulation module respectively, is used to determine the process stability of each process based on the real-time process parameters and predicted process parameters of each process in the production process, and to determine the process accuracy of each completed process based on the real-time product quality indicators and corresponding predicted product quality indicators of several completed processes, and to determine several processes to be tested based on the process stability of each process and the process accuracy of the completed processes.

[0059] Please see Figure 3 The diagram shown is a structural block diagram of the data analysis module according to an embodiment of the present invention; specifically, the data analysis module includes:

[0060] The first analysis unit is used to determine the stability of a process based on the parameter deviation coefficient of any of the processes and a preset deviation coefficient, wherein the parameter deviation coefficient of the process is determined based on the real-time process parameters and the predicted process parameters of the process.

[0061] In this embodiment, the process of determining process stability includes: for any process, retrieving the normalized real-time process parameters of that process under the same time sequence, and the predicted process parameters of that process corresponding to the same working condition and the same type of cable output by the simulation module; using the Euclidean distance weighted algorithm to calculate the overall deviation of the multi-dimensional parameters of that process, generating the parameter deviation coefficient corresponding to that process; the larger the parameter deviation value, the higher the fluctuation of the real-time operating state of that process compared to the simulation baseline working condition; the database pre-stores the preset deviation coefficients corresponding to the cable specifications and processes; the ratio of the parameter deviation coefficient obtained in real-time to the preset deviation coefficient is determined as the process stability; the closer the process stability value is to 1, the more stable the process operation and the higher the fit between the real-time parameters and the simulation prediction parameters; the closer the process stability value is to 0, the more serious the process parameter drift and the more drastic the operational fluctuation. This process is repeated for all processes on the production line to generate a unique process stability for each process, and the process stability of each process is transmitted to the analysis and judgment unit.

[0062] The second analysis unit is used to determine the process accuracy of the completed process based on the index deviation coefficient of any of the completed processes and the index deviation coefficient of the preceding completed processes, wherein the index deviation coefficient of the completed process is determined based on the real-time product quality index of the completed process and the corresponding predicted product quality index.

[0063] In this embodiment, the process of determining the accuracy of a process includes: for any completed process, retrieving the real-time product quality indicators measured after the process is completed, and the predicted product quality indicators corresponding to the same combination of process parameters output by the simulation module; calculating the weighted relative error of the multi-dimensional quality indicators to obtain the independent index deviation coefficient of the process; the larger the index deviation coefficient, the greater the simulation prediction error of the digital twin model for the performance of the finished product of the process; traversing all upstream completed processes, retrieving the index deviation coefficients corresponding to each upstream process, and performing a weighted fusion operation according to the coupling weight of upstream and downstream processes to synthesize the comprehensive index deviation of the current completed process; performing a reverse normalization conversion on the comprehensive index deviation to obtain the process accuracy; the higher the process accuracy, the higher the prediction fit of the entire simulation model, including upstream chain processes, for the extreme environmental performance of the finished product of the process; the lower the process accuracy, the more serious the accumulation of simulation deviation after the superposition of upstream and downstream processes. This process is repeated for all completed processes to generate the process accuracy corresponding to each completed process, and is simultaneously pushed to the analysis and judgment unit.

[0064] An analysis and judgment unit, which is connected to the first analysis unit and the second analysis unit respectively, is used to determine the process as the process to be tested based on the judgment result that the process stability of any of the processes does not meet the preset stability standard.

[0065] Specifically, the analysis and determination unit is further used to determine the completed process as a candidate process based on the determination result that the process stability of any of the completed processes meets the preset stability standard. If the process accuracy of any of the candidate processes does not meet the preset accuracy standard, then the candidate process is determined to be a process to be tested.

[0066] In this embodiment, the implementer can pre-store preset stability standards and preset accuracy standards in the database to calibrate whether the fluctuation of the process operation exceeds the allowable range and the allowable range of model error.

[0067] Specifically, the data analysis module quantifies the deviation between real-time process parameters and simulation prediction parameters using parameter deviation coefficients. It then calculates process stability by comparing the deviation coefficients with preset ones, enabling precise identification of local parameter deviations in single processes. By comparing the actual product quality indicators of completed processes with the simulation prediction quality indicators using index deviation coefficients, it can accurately quantify the deviation between the output of each process and the theoretical product quality during actual production. By comprehensively considering both process stability and process accuracy, a two-dimensional evaluation is achieved, accurately identifying processes with significant parameter deviations or substandard product quality, thus improving the efficiency and effectiveness of subsequent optimization.

[0068] The sensitivity testing module is connected to the database, the simulation module, and the data analysis module, respectively, and is used to perform sensitivity testing on the process parameters of each of the test procedures based on the extreme environmental parameters, so as to determine the combination of key process parameters.

[0069] Please see Figure 4 The diagram shown is a structural block diagram of a sensitive testing module according to an embodiment of the present invention; specifically, the sensitive testing module includes:

[0070] A sensitive testing unit is used to adjust the process parameters of each of the test processes based on the digital twin model to obtain a test cable twin, and to perform environmental simulation testing on the test cable twin based on the extreme environmental parameters to obtain the corresponding test time margin. Each test cable twin has a corresponding combination of test process parameters and a corresponding test product quality index.

[0071] In this embodiment, the process parameters of all processes in the entire production line, except for the process to be tested, are kept constant. The process parameters of each process to be tested are adjusted based on the simulated process parameters of the corresponding process in each simulated process parameter combination to obtain several sensitive test process parameter combinations and corresponding test cable twins. For each test cable twin, the extreme environmental parameters of the target area are read from the database, and environmental simulation tests are performed on the test cable twin based on the extreme environmental parameters. According to the single variable method, the extreme environmental parameters are adjusted sequentially to perform several environmental simulation tests. In each environmental simulation test, the time when the test cable twin begins to show defects such as damage or aging is determined as the corresponding test duration margin. The larger the test duration margin, the longer the survival time of the corresponding test cable twin in extreme environments.

[0072] The test analysis unit, which is connected to the sensitive test unit, is used to identify several key cable twins based on the test duration margin and the test product quality indicators corresponding to each of the test cable twins, and to determine the combination of key process parameters based on the process parameters of each of the key cable twins.

[0073] In this embodiment, if the test duration margin is greater than a preset duration and the test product quality indicators meet the preset quality indicator standards, then the corresponding test cable twin is identified as a critical cable twin, and the corresponding process parameters are identified as a critical process parameter combination. Practitioners can set the preset duration based on the average test duration margin of cables that have passed cable product inspection in actual conditions or historical data, and determine the preset quality indicator standards based on the maximum range of quality indicators of cables that have passed cable product inspection in actual conditions or historical data.

[0074] Specifically, the sensitive testing module adaptively adjusts the constructed digital twin model to obtain the corresponding test cable twin, and performs environmental simulation tests on the test cable twin in combination with extreme environmental parameters to determine the output test duration margin. This allows for an accurate assessment of the cable's durability in extreme environments. By comprehensively considering both the test duration margin and the test product quality indicators, key cable twins are selected, which can accurately identify process parameters that are more sensitive to extreme environments, providing data support for subsequent process optimization.

[0075] The process optimization module, which is connected to the sensitive testing module and the simulation module, is used to iteratively adjust and optimize the process parameters of each process to be tested based on the digital twin model and the combination of key process parameters to obtain the target process parameter combination, and to determine several processes to be adjusted based on the target process parameter combination, so as to adjust the process parameters of each process to be adjusted.

[0076] Please see Figure 5The diagram shown is a structural block diagram of the optimization module according to an embodiment of the present invention; specifically, the process optimization module includes:

[0077] The process optimization unit is used to iteratively adjust and optimize the process parameters of each of the test steps based on the digital twin model and the combination of key process parameters, so as to obtain the target process parameter combination.

[0078] In this embodiment, the iterative adjustment and optimization process includes: initializing optimization parameters and optimization objectives, taking the key process parameters of each test process as optimization decision variables, taking the comprehensive maximization of product quality indicators and extreme environmental performance indicators as the optimization objective, and the constraints include hard constraints on product quality indicators and process equipment capability constraints. Under any combination of decision variables, if the product quality indicators simulated by the digital twin model do not meet the hard constraints, the combination is marked as an infeasible solution and is excluded during the optimization process. Using Latin hypercube sampling or uniform design methods, N initial solutions are generated in the decision variable space, forming N initial populations. Each initial solution represents a combination of key process parameters for each test step within the feasible range. For each individual in the population, it is input into a digital twin model, and a full-process simulation is performed to obtain the predicted process parameters and predicted product quality indicators for each step under the parameter combination. Environmental simulation testing (using the same method as the environmental simulation test in the sensitive testing module) is conducted on the test cable twin under this parameter combination based on extreme environmental parameters to obtain the test duration margin. Based on the simulation results and environmental test results, the fitness value of the individual is calculated according to the optimization objective. A multi-objective evolutionary algorithm is used to iteratively optimize the population. After each iteration, convergence is determined. The iteration terminates when the maximum number of iterations is reached or fitness convergence is achieved. After iteration termination, an optimal compromise solution is selected from the optimal solution set of the final population according to a preset decision rule as the target process parameter combination. The decision rule includes, but is not limited to, selecting the process parameter combination corresponding to the individual with the highest fitness value as the target process parameter combination.

[0079] The adjustment control unit, which is connected to the process optimization unit, is used to determine the reference process parameters of each process based on the target process parameter combination and the digital twin model, and to determine several processes to be adjusted based on the reference process parameters and real-time process parameters of each process, so as to adjust the process parameters of each process to be adjusted.

[0080] In this embodiment, the target process parameter combination includes the optimized key process parameter values ​​of each process to be tested. For each process to be tested, its reference process parameters are directly adopted from the corresponding parameter values ​​in the target process parameter combination. For processes not to be tested (i.e., other processes not marked as processes to be tested by the data analysis module), the reference process parameters are determined through a full-process simulation based on the target process parameter combination and the digital twin model. Specifically, the target process parameter combination is input into the digital twin model, a full-process simulation is performed, and the predicted process parameters of the processes not to be tested are extracted from the simulation results as their reference process parameters, thereby ensuring that each process in the entire process has corresponding reference process parameters.

[0081] Understandably, the real-time process parameters of each process are read from the data acquisition module, and the need for adjustment of each process is determined as follows: For any process, the deviation between the reference process parameter and the real-time process parameter is calculated. If the deviation of any process parameter is greater than a preset deviation threshold, the process is determined to be a process to be adjusted. For each process to be adjusted, the process parameter of the process is adjusted from the real-time value to the reference value, or gradually approaches the reference value according to a preset adjustment range.

[0082] In one specific embodiment, a direct adjustment method is adopted, in which reference process parameters are sent as new set values ​​to the equipment controller of the corresponding process through an industrial communication protocol, and the equipment controller performs parameter adjustment according to the new set values.

[0083] In another specific embodiment, a step-by-step adjustment method is adopted to avoid process fluctuations caused by sudden parameter changes. For any process to be adjusted, a maximum single adjustment range is set, and the adjustment process is divided into multiple steps and executed step by step. After each step of adjustment, real-time process parameters are re-acquired to verify the adjustment effect: if the deviation between the actual process parameters and the reference process parameters is within the allowable range, the next adjustment is continued; if the deviation exceeds the allowable range, an abnormal alarm is triggered and the adjustment is paused.

[0084] This invention utilizes a digital twin model to construct the entire production process of the target cable based on design process requirements and actual formulas. It synchronously outputs predicted process parameters and predicted product quality indicators for each step, shortening the cable commissioning cycle and improving production efficiency and quality. By comprehensively considering the comparison between real-time and predicted process parameters for each step in the production process, and the comparison between completed and predicted product quality indicators, the invention introduces process stability and accuracy criteria to select the steps to be tested for sensitivity testing. This analysis identifies key process parameter combinations that are sensitive to extreme environments, enabling targeted iterative adjustments and optimizations. This avoids indiscriminate adjustments across the entire production line, improving production optimization efficiency and effectiveness, and further enhancing the quality of the finished cable.

[0085] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A digital twin-based end-to-end process optimization control system for cable production lines, characterized in that, include: The database is used to store the design process parameters, material formulas, and extreme environmental parameters of the target cable within the target area; The simulation module is used to build a digital twin model of the entire production process of the target cable based on the design process parameters and material formula of the target cable, so as to simulate the production process of the target cable and output the predicted process parameters and predicted product quality indicators of each process in the production process. The data acquisition module is used to acquire process parameters of each step in the manufacturing process of the target cable in real time. The data analysis module is used to determine the process stability of each process based on the real-time process parameters and predicted process parameters of each process in the production process, and to determine the process accuracy of each completed process based on the real-time product quality indicators and corresponding predicted product quality indicators of several completed processes, and to determine several processes to be tested based on the process stability of each process and the process accuracy of the completed processes. A sensitivity testing module is used to perform sensitivity testing on the process parameters of each of the test steps based on the extreme environmental parameters, so as to determine the combination of key process parameters. The process optimization module is used to iteratively adjust and optimize the process parameters of each of the test processes based on the digital twin model and the combination of key process parameters to obtain a target process parameter combination, and to determine several processes to be adjusted based on the target process parameter combination, so as to adjust the process parameters of each process to be adjusted.

2. The cable production line full-process optimization control system based on digital twin as described in claim 1, characterized in that, The simulation module includes: The model building unit is used to construct a geometric twin of the target cable based on the design process parameters of the target cable, determine the material property parameters based on the material formula of the target cable, and generate process models of each layer of the target cable based on the geometric twin and material property parameters, so as to construct a digital twin model of the entire production process of the target cable.

3. The cable production line full-process optimization control system based on digital twin as described in claim 2, characterized in that, The simulation module includes: The simulation unit is used to simulate the production process of the target cable based on the digital twin model of the entire production process of the target cable and the combination of simulation process parameters corresponding to each process, so as to obtain several simulation results. Based on the simulation results, the unit outputs the predicted process parameters and predicted product quality indicators of each process in the production process. The simulation results include the simulated product quality indicators corresponding to each combination of simulation process parameters.

4. The cable production line full-process optimization control system based on digital twin as described in claim 3, characterized in that, The data analysis module includes: The first analysis unit is used to determine the stability of a process based on the parameter deviation coefficient of any of the processes and a preset deviation coefficient, wherein the parameter deviation coefficient of the process is determined based on the real-time process parameters and the predicted process parameters of the process.

5. The cable production line full-process optimization control system based on digital twin as described in claim 4, characterized in that, The data analysis module includes: The second analysis unit is used to determine the process accuracy of the completed process based on the index deviation coefficient of any completed process and the index deviation coefficient of the preceding completed process, wherein the index deviation coefficient of the completed process is determined based on the real-time product quality index of the completed process and the corresponding predicted product quality index.

6. The cable production line full-process optimization control system based on digital twin as described in claim 5, characterized in that, The data analysis module includes: The analysis and judgment unit is used to determine the process to be tested based on the judgment result that the process stability of any of the processes does not meet the preset stability standard.

7. The cable production line full-process optimization control system based on digital twin as described in claim 6, characterized in that, The analysis and judgment unit is also used to determine the completed process as a candidate process based on the judgment result that the process stability of any of the completed processes meets the preset stability standard. If the process accuracy of any of the candidate processes does not meet the preset accuracy standard, then the candidate process is determined to be a process to be tested.

8. The cable production line full-process optimization control system based on digital twin as described in claim 7, characterized in that, The sensitivity testing module includes: The sensitive testing unit is used to adjust the process parameters of each of the test processes based on the digital twin model to obtain a test cable twin, and to perform environmental simulation testing on the test cable twin based on the extreme environmental parameters to obtain the corresponding test duration margin. Each test cable twin has a corresponding combination of test process parameters and a corresponding test product quality index.

9. The cable production line full-process optimization control system based on digital twin as described in claim 8, characterized in that, The sensitivity testing module includes: The test analysis unit is used to determine several key cable twins based on the test duration margin and test product quality indicators corresponding to each of the test cable twins, and to determine the combination of key process parameters based on the process parameters of each of the key cable twins.

10. The cable production line full-process optimization control system based on digital twin as described in claim 9, characterized in that, The process optimization module includes: The process optimization unit is used to iteratively adjust and optimize the process parameters of each of the test steps based on the digital twin model and the combination of key process parameters, so as to obtain the target process parameter combination. The adjustment control unit is used to determine the reference process parameters of each process based on the target process parameter combination and the digital twin model, and to determine several processes to be adjusted based on the reference process parameters and real-time process parameters of each process, so as to adjust the process parameters of each process to be adjusted.

Images