Intelligent collaborative control method and system for cable twisting

Abstract

The present invention discloses an intelligent collaborative control method and system for cable twisting, which relates to the field of intelligent control technology. The method includes: collecting data from multiple cable twisting devices to obtain multiple device operation data sets; determining target cable twisting process parameters, performing twisting analysis, and obtaining multiple twisting characteristics; controlling multiple cable twisting devices interactively, and determining cable twisting process requirement information based on interaction parameters; traversing multiple twisting characteristics for collaborative calculation, and formulating a cable twisting collaborative strategy; simulating the execution of the cable twisting collaborative strategy for multiple cable twisting devices to perform real-time monitoring, generate simulated twisting monitoring results, and dynamically update the cable twisting collaborative strategy based on the simulated twisting monitoring results to perform intelligent collaborative control on multiple cable twisting devices. The method solves the technical problem in the prior art that the cable twisting equipment has poor coordination, resulting in low twisting efficiency and unstable quality, and achieves the technical effect of improving the quality and efficiency of cable twisting.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to an intelligent collaborative control method and system for cable twisting. Background Art

[0002] Cable twisting is one of the important processes in the cable production process. Its purpose is to twist multiple conductors or optical fibers according to specific rules to form cable products that meet technical requirements. The twisting quality directly affects the electrical performance, mechanical strength and service life of the cable, and is an important link to ensure product performance. However, existing cable twisting technologies and equipment still face many challenges in practical applications. Traditional cable twisting equipment usually operates in stand-alone mode, and there is a lack of effective coordinated control between the various devices. Due to the different operating states of the equipment, synchronous operation cannot be achieved, resulting in frequent problems such as lay deviation and tension fluctuation during the twisting process, which affects the quality of the final product. In addition, most equipment relies on fixed parameters for operation and has weak adaptability to cables of different specifications or process conditions. In actual production, process parameter adjustments often require manual intervention, which is not only time-consuming and labor-intensive, but also easily limited by operating experience, making it difficult to achieve precise control. Summary of the Invention

[0003] The present application provides an intelligent collaborative control method and system for cable twisting, which solves the technical problem in the prior art that cable twisting equipment has poor coordination, resulting in low twisting efficiency and unstable quality.

[0004] In view of the above problems, the present application provides an intelligent collaborative control method and system for cable twisting.

[0005] In a first aspect of the present application, an intelligent coordinated control method for cable twisting is provided, the method comprising:

[0006] Data from multiple cable twisting devices are collected through intelligent sensing equipment to obtain multiple device operation data sets; target cable twisting process parameters are determined based on the multiple cable twisting devices, and twisting analysis is performed based on the multiple device operation data sets in combination with the target cable twisting process parameters to obtain multiple twisting characteristics; multiple cable twisting devices are interactively controlled according to the target cable twisting process parameters in combination with the multiple twisting characteristics, and cable twisting process requirement information is determined according to the interaction parameters; the multiple twisting characteristics are traversed according to the cable twisting process requirement information to perform collaborative calculation and formulate a cable twisting collaborative strategy; the cable twisting collaborative strategy is simulated and executed on multiple cable twisting devices to perform real-time monitoring, generate simulated twisting monitoring results, and dynamically update the cable twisting collaborative strategy according to the simulated twisting monitoring results to perform intelligent collaborative control on multiple cable twisting devices.

[0007] A second aspect of the present application provides an intelligent coordinated control system for cable twisting, the system comprising:

[0008] Data acquisition module: collects data from multiple cable twisting devices through intelligent sensing equipment to obtain multiple device operation data sets; twisting analysis module: determines the target cable twisting process parameters based on multiple cable twisting devices, and performs twisting analysis based on the multiple device operation data sets in combination with the target cable twisting process parameters to obtain multiple twisting characteristics; interaction module: controls and interacts multiple cable twisting devices according to the target cable twisting process parameters in combination with the multiple twisting characteristics, and determines the cable twisting process requirement information according to the interaction parameters; collaborative calculation module: traverses the multiple twisting characteristics according to the cable twisting process requirement information to perform collaborative calculation and formulate a cable twisting collaborative strategy; collaborative control module: simulates the execution of the cable twisting collaborative strategy on multiple cable twisting devices for real-time monitoring, generates simulated twisting monitoring results, and dynamically updates the cable twisting collaborative strategy according to the simulated twisting monitoring results to perform intelligent collaborative control on multiple cable twisting devices.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] First, data from multiple cable twisting devices is collected using intelligent sensing equipment to obtain multiple device operation data sets. Next, target cable twisting process parameters are determined based on the multiple cable twisting devices. Twisting analysis is performed based on the multiple device operation data sets combined with the target cable twisting process parameters to obtain multiple twisting characteristics. Then, control interactions are performed on the multiple cable twisting devices according to the target cable twisting process parameters combined with the multiple twisting characteristics, and cable twisting process requirement information is determined based on the interaction parameters. Furthermore, collaborative calculations are performed on multiple twisting characteristics based on the cable twisting process requirement information to formulate a cable twisting coordination strategy. Finally, the cable twisting coordination strategy is simulated and executed on multiple cable twisting devices in real time to generate simulated twisting monitoring results. Based on the simulated twisting monitoring results, the cable twisting coordination strategy is dynamically updated to perform intelligent collaborative control on the multiple cable twisting devices. This solves the technical problem in the prior art of poor coordination of cable twisting devices, which leads to low twisting efficiency and unstable quality, and achieves the technical effect of improving cable twisting quality and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic flow chart of an intelligent collaborative control method for cable twisting provided in an embodiment of the present application;

[0013] Figure 2 A schematic structural diagram of an intelligent collaborative control system for cable twisting provided in an embodiment of the present application.

[0014] Description of the accompanying drawings: data acquisition module 11, twist analysis module 12, interaction module 13, collaborative calculation module 14, collaborative control module 15. DETAILED DESCRIPTION

[0015] The present application solves the technical problem in the prior art that cable twisting equipment has poor coordination, resulting in low twisting efficiency and unstable quality, by providing an intelligent collaborative control method and system for cable twisting.

[0016] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0017] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0018] Example 1, as Figure 1 As shown, the present application provides an intelligent collaborative control method for cable twisting, wherein the method includes:

[0019] Data from multiple cable twisting devices is collected through intelligent sensing equipment to obtain multiple device operation data sets.

[0020] Intelligent sensing equipment is deployed on the cable stranding production line, including but not limited to temperature sensors, tension sensors, position sensors, speed sensors, etc.; the intelligent sensing equipment is used to monitor the operating status of multiple cable stranding equipment to obtain multiple equipment operation data sets, among which the equipment operation data sets include the speed of the pay-off wheel, the torque and speed of the stranding device, the tension and speed of the take-up wheel, and the equipment's operating environment parameters (such as temperature, humidity, etc.).

[0021] Target cable twisting process parameters are determined based on a plurality of cable twisting devices, twisting analysis is performed based on the plurality of device operation data sets in combination with the target cable twisting process parameters to obtain a plurality of twisting features.

[0022] The preset target cable twisting process parameters, including lay direction, lay length, tension, twisting speed, etc., are obtained from multiple cable twisting devices. The collected data sets of multiple equipment operations are combined with the target cable twisting process parameters to analyze the twisting process and identify multiple twisting characteristics (such as twist uniformity and tension stability). These characteristics directly reflect the key performance indicators of the cable twisting process.

[0023] Furthermore, target cable twisting process parameters are determined based on multiple cable twisting devices, twisting analysis is performed based on the multiple device operation data sets combined with the target cable twisting process parameters to obtain multiple twisting characteristics, the method comprising:

[0024] Based on multiple cable twisting devices, multiple initial twisting process parameters are extracted, and multiple cable twisting devices are traversed through the multiple initial twisting process parameters to perform multi-objective optimization and set twisting constraints; the multiple initial twisting process parameters are screened according to the twisting constraints to determine target cable twisting process parameters; the multiple device operation data sets are twisted and matched with the target cable twisting process parameters according to a time series to obtain multiple twisting data sets, and the multiple twisting data sets include a twisting direction data set and a twisting pitch data set; twisting calculation is performed based on the twisting direction data set in combination with the twisting pitch data set to obtain multiple twisting features.

[0025] Specifically, multiple initial twisting process parameters, including twist pitch, tension, and twisting speed, are extracted from multiple cable twisting devices. By traversing the extracted multiple initial twisting process parameters, a multi-objective optimization algorithm (such as a genetic algorithm or particle swarm optimization) is used to optimize the parameters while satisfying twisting constraints. The constraints include twist pitch range and tension stability, ensuring that the optimized parameters meet both process requirements and have optimal operating performance. Based on the optimization results, the multiple initial twisting process parameters are screened, parameter combinations that do not meet the constraints are eliminated, and the target cable twisting process parameters are ultimately determined. The collected equipment operation data set is time-series matched with the target process parameters, and the actual operating status of the equipment is compared with the target parameters point by point along the time axis for consistency. Multiple twisting data sets are generated, including a twisting direction data set and a twisting pitch data set, which respectively reflect the twisting direction change and the actual twist pitch distribution. Based on the twisting direction data set and the twisting pitch data set, the twisting process is calculated using a combination of mathematical models and data analysis methods to extract twisting characteristics, such as directional consistency, pitch fluctuation range, and tension distribution uniformity.

[0026] Twisting calculations are performed based on the twisting direction dataset in combination with the twisting pitch dataset. Specifically, for each time point in the twisting direction dataset, the deviation values of all wire directions from the target direction are calculated, and the direction consistency index is quantified using the mean square error formula to evaluate the degree of directional consistency between the wires. For each pitch in the twisting pitch dataset, the deviation rate between the actual twist pitch and the target twist pitch is calculated, and the maximum deviation rate, minimum deviation rate, and average deviation rate are statistically analyzed to describe the fluctuation range and stability of the twist pitch. Combined with the tension data, the tension uniformity index is obtained by calculating the difference between the maximum and minimum tension values and the mean distribution, reflecting the uniformity of the force applied to the wire during the twisting process.

[0027] According to the target cable twisting process parameters and the multiple twisting characteristics, multiple cable twisting devices are controlled interactively, and the cable twisting process requirement information is determined according to the interactive parameters.

[0028] According to the target cable twisting process parameters combined with multiple twisting characteristics, multiple cable twisting equipment are dynamically controlled and interacted. By adjusting the equipment operating parameters (such as direction, pitch and tension), the equipment feedback data during the interaction process is collected in real time. The interaction parameters are analyzed and generated to quantify the degree of match between the equipment and the target process. The specific cable twisting process requirement information is determined based on the matching results.

[0029] Furthermore, according to the target cable twisting process parameters and the plurality of twisting characteristics, a plurality of cable twisting devices are controlled interactively, and the cable twisting process requirement information is determined according to the interactive parameters. The method includes:

[0030] According to the target cable twisting process parameters, the twisting direction data set is mapped to multiple cable twisting devices to determine a first mapping coefficient; according to the target cable twisting process parameters, the twisting pitch data set is mapped to multiple cable twisting devices to determine a second mapping coefficient; the first mapping coefficient and the second mapping coefficient are associated with multiple cable twisting devices to generate associated interaction parameters; the associated interaction parameters are sent to multiple cable twisting devices for process matching calculation to generate multiple process matching coefficients; the multiple process matching coefficients are used as indexes to retrieve the target cable twisting process parameters to determine the cable twisting process requirement information.

[0031] Based on the target cable twisting process parameters, the actual direction data in the twisting direction data set are mapped one by one to multiple cable twisting devices. By calculating the proportional relationship between the actual direction and the target direction of each device, a first mapping coefficient is generated to quantify the device direction adjustment requirements; the actual pitch data in the twisting pitch data set are mapped to multiple cable twisting devices, and according to the ratio of the actual pitch to the target pitch of each device, a second mapping coefficient is generated to describe the device pitch adjustment requirements; the first mapping coefficient and the second mapping coefficient are combined according to the device association, and the associated interaction parameters of each device are obtained through weighted calculation, and sent to the corresponding device to perform process matching calculation to generate multiple process matching coefficients. , where the actual state represents the equipment's current actual process state (such as direction angle and pitch length), the associated interaction parameters represent expected values, and the process matching coefficient reflects the degree of match between the current process and the associated interaction parameters. A higher process matching coefficient indicates a higher degree of match. Using the process matching coefficient as a search index, a match is performed within the target cable stranding process parameter database. The process parameter corresponding to the current process matching coefficient is located within a preset threshold range or optimal condition. For example, if the process matching coefficient is above a set value, the corresponding process parameter is directly retrieved as the best match. If the matching coefficient is within a critical range, the adjusted process requirements are further derived by combining trend information of adjacent parameters. During the search process, index matching is performed one by one by parameter category (such as direction, pitch, and tension). Ultimately, a set of target process parameters matching the current operating state is generated, and cable stranding process requirement information is extracted, such as the required direction range, pitch optimization value, and tension compensation amplitude. This cable stranding process requirement information serves as a guide for subsequent optimization control, ensuring that the equipment's operating state dynamically approaches the target process requirements, achieving simultaneous improvements in stranding quality and efficiency.

[0032] The plurality of twisting features are traversed and collaborative calculations are performed according to the cable twisting process requirement information to formulate a cable twisting collaborative strategy.

[0033] The extracted twisting characteristics (such as directional consistency, pitch fluctuation, tension distribution, etc.) are matched and analyzed one by one with the cable twisting process requirement information. By traversing each eigenvalue, its influence and weight on the overall process requirement are calculated; then, a collaborative calculation model (such as a multi-objective optimization algorithm or a linear weighted algorithm) is used to comprehensively consider the weight and matching degree of each eigenvalue, analyze the operating relationship between each device, and optimize the interaction parameters and operating status between devices; finally, a cable twisting collaborative strategy is formulated based on the collaborative calculation results. This strategy includes a synchronous adjustment plan between devices, a tension compensation plan, and a pitch optimization path to ensure that the operating status of each device meets the target process requirements while achieving efficient collaborative operation, thereby improving the quality and overall efficiency of cable twisting.

[0034] Furthermore, according to the cable twisting process requirement information, the plurality of twisting features are traversed to perform collaborative calculations to formulate a cable twisting collaborative strategy, the method comprising:

[0035] Based on the multiple twisting features, data dependency analysis is performed to construct association rules; according to the association rules, the cable twisting process requirement information is mined to obtain data mining results; according to the data mining results, the multiple twisting features are traversed to perform fuzzy evaluation to generate multiple feature fuzzy scores; according to the multiple feature fuzzy scores, the multiple twisting features are graded to determine a priority sequence; according to the priority sequence, the multiple twisting features are collaboratively learned to generate collaborative learning results, and collaborative verification is performed based on the collaborative learning results to formulate the cable twisting collaborative strategy.

[0036] Data dependency analysis is performed based on multiple stranding characteristics (such as directional consistency, pitch fluctuation, and tension distribution). Association rules are constructed by mining correlations between features. For example, the Apriori algorithm is used to analyze the support, confidence, and lift between features, generating a rule set to clarify the inter-feature influence relationships. Subsequently, data mining is performed on cable stranding process requirements based on the constructed association rules to extract deviations between target process parameters and actual equipment status, such as directional deviation range, pitch adjustment requirements, and tension compensation requirements. The data mining results are used to reveal the priority of key features in affecting process requirements. Next, fuzzy mathematical methods are used to perform a fuzzy evaluation of each stranding characteristic. A membership function is used to quantify each feature's performance in meeting the target process requirements, generating fuzzy scores, such as directional consistency, tension fluctuation, and pitch stability. Based on the fuzzy scores, features are ranked and prioritized according to their scores, ensuring that key features are prioritized. For example, tension distribution, due to its wide range of influence, may be given a higher priority. On this basis, a collaborative learning algorithm is used to collaboratively learn the features. By analyzing the collaborative relationships and comprehensive impact effects between the features, collaborative learning results are generated. Based on this collaborative verification, the effectiveness of the collaborative strategy is evaluated through simulation testing or real-time monitoring. Finally, based on the collaborative verification results, a cable stranding collaborative strategy is formulated. This strategy includes a device synchronization control scheme, a tension compensation plan, a pitch optimization path, and adjustment suggestions for specific process requirements. This ensures the efficient coordination of the operating status of multiple cable stranding equipment while meeting the precise requirements of the target process, thereby improving stranding quality and production efficiency.

[0037] Furthermore, collaborative learning is performed on the plurality of twisting features according to the priority sequence to generate collaborative learning results, collaborative verification is performed based on the collaborative learning results, and the cable twisting collaborative strategy is formulated. The method includes:

[0038] Based on the priority sequence, weights are assigned to the multiple twisted features to generate multiple weight coefficients; based on the multiple weight coefficients, the multiple twisted features are integrated to construct multiple twisted spaces, which include twisted action spaces and twisted state spaces; a reward function is introduced to perform reinforcement learning on the twisted action space and the twisted state space to generate reinforcement learning results; based on the reinforcement learning results, continuous collaborative interactive feedback is performed on multiple twisted devices to generate the collaborative learning results.

[0039] Assign weights to multiple stranded features according to a priority sequence, using the formula: Calculate the weight coefficient of each feature to ensure that features with higher priority contribute more to collaborative learning, where represents the weight coefficient of the i-th feature, Indicates the priority of feature i, n indicates the total number of features, represents the sum of the priority values of all features. Based on assigned weight coefficients, multiple stranding features are integrated to construct a stranding space. The stranding action space defines the set of possible device operations (such as speed adjustment, tension regulation, and pitch optimization), while the stranding state space records the device's current operating state parameters (such as orientation angle, pitch distribution, and tension fluctuation). Next, a reward function is introduced to guide the learning process by quantifying the impact of device operations on the target process. The reward function formula is R(s, a) = |target state - actual state|, where s represents the current device state, a represents the executed action, and R(s, a) is the reward value for action a in state s. A higher reward value indicates that the operation is closer to the target process requirements. Combining the stranding action space with the stranding state space, a reinforcement learning algorithm (such as deep Q-learning or policy gradient method) is employed to find the optimal operating strategy for device operation through repeated trial and error, generating reinforcement learning results. Based on the results of reinforcement learning, continuous collaborative interactive feedback is provided to multiple cable twisting devices, adjusting the device's operating parameters (such as speed, tension, and pitch) in real time. The device's operating status is dynamically updated, and the reinforcement learning model is optimized based on the feedback status to form collaborative learning results. Finally, based on the collaborative learning results, the operating status of the devices is collaboratively verified. The effectiveness and stability of the collaborative strategy are evaluated through simulation tests or actual operation. Based on the verification results, a cable twisting collaborative strategy is ultimately formulated, including a device synchronization control scheme, a tension optimization path, and a pitch adjustment plan. This ensures efficient collaborative operation between devices, significantly improving cable twisting quality and production efficiency.

[0040] The cable twisting coordination strategy is simulated and executed on multiple cable twisting devices for real-time monitoring to generate simulated twisting monitoring results, and the cable twisting coordination strategy is dynamically updated according to the simulated twisting monitoring results to perform intelligent collaborative control on multiple cable twisting devices.

[0041] A cable stranding coordination strategy is simulated and monitored in real time across multiple cable stranding machines. Specifically, the strategy is input into a simulated environment, simulating the actual machine states and process parameters (such as tension, directional consistency, and pitch fluctuation) in real operation. The machines are then coordinated according to the strategy instructions. During the simulation, a sensor simulation module collects real-time machine operating data to generate simulated stranding monitoring results, including inter-machine synchronization, achievement of target process parameters, and deviation analysis. Based on these monitoring results, the effectiveness of the coordination strategy in the simulated environment is evaluated, identifying deviations and deficiencies. Based on these results, key coordination strategy parameters are dynamically optimized, such as adjusting machine speed, tension, or pitch distribution, and redistributing machine load to improve overall coordination. Finally, the optimized coordination strategy is applied to the actual machines. An intelligent collaborative control system adjusts the machine operating states in real time, compares them with target process requirements, and continuously optimizes them, ensuring efficient coordination, stable operation, and improved quality during the cable stranding process.

[0042] Furthermore, the cable twisting coordination strategy is simulated and executed on multiple cable twisting devices to perform real-time monitoring to generate simulated twisting monitoring results, and the method includes:

[0043] Retrieve historical operating environment information of multiple cable twisting devices, and construct a simulation execution environment based on the historical operating environment information; based on the simulation execution environment, load the cable twisting coordination strategy to simulate the execution of multiple cable devices and generate multiple simulated twisting parameters; combine the multiple simulated twisting parameters according to the target cable twisting process parameters to determine multiple simulated twisting groups; set an expected twisting threshold, traverse the multiple simulated twisting groups and perform deviation calculation with the expected twisting threshold to generate a simulated twisting deviation value; add the simulated twisting deviation value to the simulated twisting monitoring result.

[0044] First, historical operating environment information for multiple cable stranding devices (such as device speed, tension distribution, pitch deviation, and directional consistency) is retrieved. By analyzing this historical data, a simulation execution environment that closely matches actual operating conditions is constructed to simulate the actual device operation. Subsequently, a cable stranding coordination strategy is loaded into this simulation execution environment. Simulations are then performed on multiple cable devices according to the strategy's instructions, generating multiple simulated stranding parameters (such as simulated speed, tension adjustment, and pitch variation) in real time. These parameters reflect the device's operational performance under the coordinated strategy. These generated simulated stranding parameters are then combined according to the target cable stranding process parameters to form multiple simulated stranding groups, each representing the comprehensive device operating state under different process conditions. To evaluate the validity of the simulation results, desired stranding thresholds (such as tension stability range and pitch fluctuation range) are set. Multiple simulated stranding groups are then traversed and compared against the desired stranding thresholds. The deviation of each group is calculated and a simulated stranding deviation value is generated. A smaller deviation value indicates that the simulation is closer to the target process requirements. Finally, the calculated simulated twist deviation value is integrated into the simulated twist monitoring results to comprehensively evaluate the performance of the collaborative strategy in a simulated environment, providing important reference data for dynamic optimization and practical applications, thereby ensuring the efficiency and applicability of the cable twist collaborative strategy.

[0045] Furthermore, before adding the simulated twist deviation value to the simulated twist monitoring result, the method includes:

[0046] Perform twisting deviation analysis according to the expected twisting threshold, set a preset deviation distance, and determine whether the simulated twisting deviation value is greater than or equal to the preset deviation distance; if the simulated twisting deviation value is less than the preset deviation distance, generate a positive feedback parameter, activate the twisting monitoring instruction through the positive feedback parameter, perform continuous simulation monitoring of multiple twisting devices through the twisting monitoring instruction, and generate the simulated twisting monitoring result; if the simulated twisting deviation value is greater than or equal to the preset deviation distance, generate a negative feedback parameter, activate the twisting abnormality instruction through the negative feedback parameter, trace the abnormality through the twisting abnormality instruction, determine multiple twisting simulation abnormality points, and add the multiple twisting simulation abnormality points to the simulated twisting monitoring result.

[0047] Before adding the simulated twist deviation value to the simulated twist monitoring results, the following steps are required: First, the generated simulated twist deviation value is analyzed based on the expected twist threshold, and a preset deviation distance is set to determine whether the simulation results deviate from the target process requirements. Specifically, for each simulated twist deviation value, whether it is less than the preset deviation distance is determined. If the deviation value is less than the preset deviation distance, the simulated operation status is deemed to meet the target process requirements. A positive feedback parameter is generated, and the twist monitoring instruction is activated using this positive feedback parameter. Continuous simulated monitoring of multiple twisting equipment is performed to obtain more accurate equipment operation data and further improve the simulated twist monitoring results. If the simulated twist deviation value is greater than or equal to the preset deviation distance, it is deemed that the equipment operation status has a significant deviation. A negative feedback parameter is generated, and the twist abnormality instruction is activated using this negative feedback parameter. The abnormal points in the simulation results are traced and analyzed, and multiple twist simulation abnormality points (such as abnormal tension distribution points, points with large pitch deviation, or points with poor directional consistency) are identified and located. Subsequently, the identified multiple twist simulation abnormality points are recorded and added to the simulated twist monitoring results to improve the deviation analysis and guide subsequent strategy optimization. Through this process, the simulated twisting monitoring results can accurately reflect the operating performance of the equipment under the collaborative strategy, providing comprehensive data support and reliable basis for optimizing the cable twisting process and improving equipment coordination.

[0048] In summary, the embodiments of the present application have at least the following technical effects:

[0049] First, data from multiple cable twisting devices is collected using intelligent sensing equipment to obtain multiple device operation data sets. Next, target cable twisting process parameters are determined based on the multiple cable twisting devices. Twisting analysis is performed based on the multiple device operation data sets combined with the target cable twisting process parameters to obtain multiple twisting characteristics. Then, control interactions are performed on the multiple cable twisting devices according to the target cable twisting process parameters combined with the multiple twisting characteristics, and cable twisting process requirement information is determined based on the interaction parameters. Furthermore, collaborative calculations are performed on multiple twisting characteristics based on the cable twisting process requirement information to formulate a cable twisting coordination strategy. Finally, the cable twisting coordination strategy is simulated and executed on multiple cable twisting devices in real time to generate simulated twisting monitoring results. Based on the simulated twisting monitoring results, the cable twisting coordination strategy is dynamically updated to perform intelligent collaborative control on the multiple cable twisting devices. This solves the technical problem in the prior art of poor coordination of cable twisting devices, which leads to low twisting efficiency and unstable quality, and achieves the technical effect of improving cable twisting quality and efficiency.

[0050] Embodiment 2 is based on the same inventive concept as the intelligent cooperative control method for cable twisting in the above embodiment. Figure 2 As shown, the present application provides an intelligent collaborative control system for cable twisting, wherein the system includes:

[0051] Data acquisition module 11: collects data from multiple cable twisting devices through intelligent sensing equipment to obtain multiple device operation data sets; twisting analysis module 12: determines the target cable twisting process parameters based on multiple cable twisting devices, and performs twisting analysis based on the multiple device operation data sets in combination with the target cable twisting process parameters to obtain multiple twisting characteristics; interaction module 13: controls and interacts multiple cable twisting devices according to the target cable twisting process parameters in combination with the multiple twisting characteristics, and determines the cable twisting process requirement information according to the interaction parameters; collaborative calculation module 14: traverses the multiple twisting characteristics according to the cable twisting process requirement information to perform collaborative calculation and formulate a cable twisting collaborative strategy; collaborative control module 15: simulates the execution of the cable twisting collaborative strategy on multiple cable twisting devices for real-time monitoring, generates simulated twisting monitoring results, and dynamically updates the cable twisting collaborative strategy according to the simulated twisting monitoring results to perform intelligent collaborative control on multiple cable twisting devices.

[0052] Furthermore, the twist analysis module 12 is configured to perform the following method:

[0053] Based on multiple cable twisting devices, multiple initial twisting process parameters are extracted, and multiple cable twisting devices are traversed through the multiple initial twisting process parameters to perform multi-objective optimization and set twisting constraints; the multiple initial twisting process parameters are screened according to the twisting constraints to determine target cable twisting process parameters; the multiple device operation data sets are twisted and matched with the target cable twisting process parameters according to a time series to obtain multiple twisting data sets, and the multiple twisting data sets include a twisting direction data set and a twisting pitch data set; twisting calculation is performed based on the twisting direction data set in combination with the twisting pitch data set to obtain multiple twisting features.

[0054] Furthermore, the interaction module 13 is used to perform the following method:

[0055] According to the target cable twisting process parameters, the twisting direction data set is mapped to multiple cable twisting devices to determine a first mapping coefficient; according to the target cable twisting process parameters, the twisting pitch data set is mapped to multiple cable twisting devices to determine a second mapping coefficient; the first mapping coefficient and the second mapping coefficient are associated with multiple cable twisting devices to generate associated interaction parameters; the associated interaction parameters are sent to multiple cable twisting devices for process matching calculation to generate multiple process matching coefficients; the multiple process matching coefficients are used as indexes to retrieve the target cable twisting process parameters to determine the cable twisting process requirement information.

[0056] Furthermore, the collaborative computing module 14 is configured to execute the following method:

[0057] Based on the multiple twisting features, data dependency analysis is performed to construct association rules; according to the association rules, the cable twisting process requirement information is mined to obtain data mining results; according to the data mining results, the multiple twisting features are traversed to perform fuzzy evaluation to generate multiple feature fuzzy scores; according to the multiple feature fuzzy scores, the multiple twisting features are graded to determine a priority sequence; according to the priority sequence, the multiple twisting features are collaboratively learned to generate collaborative learning results, and collaborative verification is performed based on the collaborative learning results to formulate the cable twisting collaborative strategy.

[0058] Furthermore, the collaborative computing module 14 is configured to execute the following method:

[0059] Based on the priority sequence, weights are assigned to the multiple twisted features to generate multiple weight coefficients; based on the multiple weight coefficients, the multiple twisted features are integrated to construct multiple twisted spaces, which include twisted action spaces and twisted state spaces; a reward function is introduced to perform reinforcement learning on the twisted action space and the twisted state space to generate reinforcement learning results; based on the reinforcement learning results, continuous collaborative interactive feedback is performed on multiple twisted devices to generate the collaborative learning results.

[0060] Furthermore, the collaborative control module 15 is configured to execute the following method:

[0061] Retrieve historical operating environment information of multiple cable twisting devices, and construct a simulation execution environment based on the historical operating environment information; based on the simulation execution environment, load the cable twisting coordination strategy to simulate the execution of multiple cable devices and generate multiple simulated twisting parameters; combine the multiple simulated twisting parameters according to the target cable twisting process parameters to determine multiple simulated twisting groups; set an expected twisting threshold, traverse the multiple simulated twisting groups and perform deviation calculation with the expected twisting threshold to generate a simulated twisting deviation value; add the simulated twisting deviation value to the simulated twisting monitoring result.

[0062] Furthermore, the collaborative control module 15 is configured to execute the following method:

[0063] Perform twisting deviation analysis according to the expected twisting threshold, set a preset deviation distance, and determine whether the simulated twisting deviation value is greater than or equal to the preset deviation distance; if the simulated twisting deviation value is less than the preset deviation distance, generate a positive feedback parameter, activate the twisting monitoring instruction through the positive feedback parameter, perform continuous simulation monitoring of multiple twisting devices through the twisting monitoring instruction, and generate the simulated twisting monitoring result; if the simulated twisting deviation value is greater than or equal to the preset deviation distance, generate a negative feedback parameter, activate the twisting abnormality instruction through the negative feedback parameter, trace the abnormality through the twisting abnormality instruction, determine multiple twisting simulation abnormality points, and add the multiple twisting simulation abnormality points to the simulated twisting monitoring result.

[0064] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0065] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0066] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. An intelligent collaborative control method for cable twisting, characterized in that: The method comprises: Data from multiple cable twisting devices is collected through intelligent sensing equipment to obtain multiple equipment operation data sets; Determining target cable stranding process parameters based on multiple cable stranding devices, performing stranding analysis based on the multiple device operation data sets combined with the target cable stranding process parameters to obtain multiple stranding characteristics, the stranding characteristics including stranding uniformity and tension stability; Controlling and interacting a plurality of cable twisting devices according to the target cable twisting process parameters and the plurality of twisting characteristics, and determining cable twisting process requirement information according to the interaction parameters; Traversing the plurality of twisting features to perform collaborative calculations according to the cable twisting process requirement information, and formulating a cable twisting collaborative strategy; The cable twisting coordination strategy is simulated and executed on multiple cable twisting devices for real-time monitoring to generate simulated twisting monitoring results, and the cable twisting coordination strategy is dynamically updated according to the simulated twisting monitoring results to perform intelligent collaborative control on multiple cable twisting devices.

2. The intelligent coordinated control method for cable twisting according to claim 1, characterized in that: Determining target cable stranding process parameters based on multiple cable stranding devices, performing stranding analysis based on the multiple device operation data sets combined with the target cable stranding process parameters to obtain multiple stranding features, the method comprising: Extracting multiple initial twisting process parameters based on multiple cable twisting devices, traversing the multiple initial twisting process parameters to perform multi-objective optimization on the multiple cable twisting devices, and setting twisting constraint conditions; Screening the multiple initial twisting process parameters according to the twisting constraint conditions to determine target cable twisting process parameters; Performing twist matching on the multiple equipment operation data sets and the target cable twisting process parameters according to a time series to obtain multiple twisting data sets, wherein the multiple twisting data sets include a twisting direction data set and a twisting pitch data set; A twist calculation is performed based on the twist direction data set in combination with the twist pitch data set to obtain a plurality of twist features.

3. The intelligent coordinated control method for cable twisting according to claim 2, characterized in that: Controlling and interacting a plurality of cable twisting devices according to the target cable twisting process parameters in combination with the plurality of twisting characteristics, and determining cable twisting process requirement information according to the interaction parameters, the method comprising: Determining a first mapping coefficient by mapping the target cable twisting process parameter to a plurality of cable twisting devices according to the twisting direction data set; Determining a second mapping coefficient by mapping the target cable stranding process parameters to a plurality of cable stranding devices according to the stranding pitch data set; Associating the first mapping coefficient with the second mapping coefficient according to a plurality of cable twisting devices to generate an associated interaction parameter; Sending the associated interaction parameters to multiple cable twisting devices to perform process matching calculations to generate multiple process matching coefficients; The target cable twisting process parameters are retrieved using the multiple process matching coefficients as indexes to determine the cable twisting process requirement information.

4. The intelligent coordinated control method for cable twisting according to claim 1, characterized in that: Traversing the plurality of twisting features to perform collaborative calculations according to the cable twisting process requirement information, and formulating a cable twisting collaborative strategy, the method comprising: Performing data dependency analysis based on the plurality of twisted features to construct association rules; Mining the cable twisting process requirement information according to the association rules to obtain data mining results; traversing the plurality of twisted features to perform fuzzy evaluation according to the data mining results, and generating a plurality of feature fuzzy scores; Performing level identification on the plurality of twisted features according to the plurality of feature fuzzy scores to determine a priority sequence; The plurality of twisting features are collaboratively learned according to the priority sequence to generate collaborative learning results, collaborative verification is performed based on the collaborative learning results, and the cable twisting collaborative strategy is formulated.

5. The intelligent coordinated control method for cable twisting according to claim 4, characterized in that: The method includes: performing collaborative learning on the plurality of twisting features according to the priority sequence, generating collaborative learning results, performing collaborative verification based on the collaborative learning results, and formulating the cable twisting collaborative strategy. assigning weights to the plurality of twisting features based on the priority sequence to generate a plurality of weight coefficients; Integrating the plurality of twisting features according to the plurality of weight coefficients to construct a plurality of twisting spaces, wherein the plurality of twisting spaces include a twisting action space and a twisting state space; A reward function is introduced to perform reinforcement learning on the twisted action space and the twisted state space to generate a reinforcement learning result; Based on the reinforcement learning result, continuous collaborative interactive feedback is performed on multiple twisting devices to generate the collaborative learning result.

6. The intelligent coordinated control method for cable twisting according to claim 1, characterized in that: The method includes: simulating the execution of the cable twisting coordination strategy on multiple cable twisting devices to perform real-time monitoring and generate simulated twisting monitoring results. Retrieving historical operating environment information of a plurality of cable twisting devices, and constructing a simulation execution environment according to the historical operating environment information; Based on the simulation execution environment, the cable twisting coordination strategy is loaded to simulate and execute multiple cable devices to generate multiple simulation twisting parameters; Combining the plurality of simulated twisting parameters according to the target cable twisting process parameters to determine a plurality of simulated twisting groups; Setting an expected twisting threshold, traversing the plurality of simulated twisting groups and calculating deviations from the expected twisting threshold to generate a simulated twisting deviation value; The simulated twist deviation value is added to the simulated twist monitoring result.

7. The intelligent coordinated control method for cable twisting according to claim 6, characterized in that: Before adding the simulated twist deviation value to the simulated twist monitoring result, the method includes: Performing twist deviation analysis according to the expected twist threshold, setting a preset deviation distance, and determining whether the simulated twist deviation value is greater than or equal to the preset deviation distance; If the simulated twisting deviation value is less than the preset deviation distance, a positive feedback parameter is generated, a twisting monitoring instruction is activated by the positive feedback parameter, and a continuous simulated monitoring of multiple twisting devices is performed by the twisting monitoring instruction to generate the simulated twisting monitoring result; If the simulated twisting deviation value is greater than or equal to the preset deviation distance, a negative feedback parameter is generated, the twisting abnormal instruction is activated by the negative feedback parameter, the abnormality is traced through the twisting abnormal instruction, multiple twisting simulation abnormal points are determined, and the multiple twisting simulation abnormal points are added to the simulated twisting monitoring result.

8. Intelligent cooperative control system for cable twisting, characterized in that, A system for implementing the intelligent coordinated control method for cable twisting according to any one of claims 1 to 7, comprising: Data acquisition module: collects data from multiple cable twisting devices through intelligent sensing equipment to obtain multiple equipment operation data sets; Twisting analysis module: determines target cable twisting process parameters based on multiple cable twisting devices, performs twisting analysis based on the multiple device operation data sets combined with the target cable twisting process parameters, and obtains multiple twisting characteristics, including twisting uniformity and tension stability; Interaction module: controls and interacts multiple cable twisting devices according to the target cable twisting process parameters and the multiple twisting characteristics, and determines the cable twisting process requirement information according to the interaction parameters; Collaborative calculation module: traverses the plurality of twisting features to perform collaborative calculation according to the cable twisting process requirement information, and formulates a cable twisting collaborative strategy; Collaborative control module: simulates the execution of the cable twisting collaborative strategy on multiple cable twisting devices for real-time monitoring, generates simulated twisting monitoring results, and dynamically updates the cable twisting collaborative strategy based on the simulated twisting monitoring results to perform intelligent collaborative control on multiple cable twisting devices.

Images