An intelligent control method and system for an assembled cable manufacturing process

Abstract

This invention discloses an intelligent control method and system for the manufacturing process of assembled cables, relating to the field of industrial production control technology. The method includes: dividing the assembled cable manufacturing process into three steps: welding, corrugation forming, and threading; conducting a risk assessment on the welding step and calculating a plasticity risk value; adjusting the corrugation processing parameters based on the plasticity risk value; executing the corrugation forming step based on the corrugation processing parameters, and conducting a risk assessment on the corrugation forming step based on the plasticity risk value to calculate a corrugation forming quality risk value; adjusting the threading processing parameters based on the corrugation forming quality risk value; executing the threading step based on the threading processing parameters; and generating early warning information based on the plasticity risk value and the corrugation forming quality risk value. This invention can combine the plasticity risk value and the corrugation forming quality risk value to adjust the processing parameters of different steps, thereby achieving manufacturing process control and improving accuracy and product quality.

Description

Technical Field

[0001] This invention relates to the field of industrial production control technology, and in particular to an intelligent control method and system for the assembly cable manufacturing process. Background Technology

[0002] In modern industrial production, prefabricated cables play a crucial role in specialized communication and power transmission fields due to their unique performance. The manufacturing process of these cables typically involves multiple continuous and closely interconnected steps, such as welding stainless steel strips into tubes, corrugating, and inserting the cable core. To ensure high product quality and production efficiency, existing systems strive to maintain production indicators within a preset ideal range by real-time monitoring and adjustment of various process parameters. However, with the increasing market demand for small-batch, multi-specification customized products, production lines need to frequently switch product specifications. This switching means that adjustments to parameters in upstream processes can trigger a series of unpredictable chain reactions in downstream processes, affecting product quality, production stability, and control accuracy.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0004] The main objective of this invention is to propose an intelligent control method and system for the prefabricated cable manufacturing process. This method combines plasticity risk value and corrugated forming quality risk value to adjust the processing parameters of different processes, thereby achieving manufacturing process control and improving accuracy and product quality.

[0005] On one hand, embodiments of the present invention provide an intelligent control method for the manufacturing process of assembled cables, including the following steps: The manufacturing process of prefabricated cables is divided into three steps: welding, corrugation forming, and threading. After the welding process is performed, a risk assessment is conducted on the welding process, and the plasticity risk value is calculated. Based on the plasticity risk value, adjust the corrugation processing parameters, including the pressing depth and rotation speed of the forming wheel; According to the corrugated processing parameters, a corrugated forming process is performed, and a risk assessment is conducted on the corrugated forming process based on the plasticity risk value to calculate the corrugated forming quality risk value. Based on the corrugated forming quality risk value, the threading processing parameters are adjusted. The threading processing parameters include the target value of the threading motor torque, the threading motor speed control curve, and the control parameters of the proportional-integral-derivative controller, which include the proportional gain, integral time, and derivative gain. Perform the threading process according to the threading parameters; After the threading process is performed, an early warning message is generated based on the plasticity risk value and the corrugation forming quality risk value.

[0006] On the other hand, embodiments of the present invention provide an intelligent control system for the assembly cable manufacturing process, comprising: The process division module is used to divide the assembly cable manufacturing process into processes, namely welding process, corrugation forming process and wire threading process. The welding risk assessment module is used to assess the risk of the welding process after it is performed and to calculate the plasticity risk value. The corrugated processing parameter adjustment module is used to adjust the corrugated processing parameters according to the plasticity risk value. The corrugated processing parameters include the pressing depth and rotation speed of the forming wheel. The corrugated forming risk assessment module is used to execute the corrugated forming process according to the corrugated processing parameters, and to perform a risk assessment on the corrugated forming process according to the plasticity risk value, and to calculate the corrugated forming quality risk value. The threading processing parameter adjustment module is used to adjust the threading processing parameters according to the corrugated forming quality risk value. The threading processing parameters include the target value of the threading motor torque, the threading motor speed control curve, and the control parameters of the proportional-integral-derivative controller. The control parameters include the proportional gain, integral time, and derivative gain. The threading process execution module is used to execute the threading process according to the threading processing parameters; The early warning information generation module is used to generate early warning information based on the plasticity risk value and the corrugation forming quality risk value after the threading process is performed.

[0007] The embodiments of this application include at least the following beneficial effects: First, the assembly cable manufacturing process is divided into processes, namely welding, corrugation forming, and threading. Then, a risk assessment is performed on the welding process to calculate the plasticity risk value. Based on the plasticity risk value, the corrugation processing parameters are adjusted. Then, the corrugation forming process is executed based on the corrugation processing parameters. Based on the plasticity risk value, a risk assessment is performed on the corrugation forming process to calculate the corrugation forming quality risk value. Based on the corrugation forming quality risk value, the threading processing parameters are adjusted, and the threading process is executed. Based on the plasticity risk value and the corrugation forming quality risk value, early warning information is generated. Thus, the processing parameters of different processes can be adjusted by combining the plasticity risk value and the corrugation forming quality risk value to achieve manufacturing process control and improve accuracy and product quality.

[0008] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description and the drawings. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below.

[0010] Figure 1 This is a flowchart of an intelligent control method for the assembly cable manufacturing process according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an intelligent control system for the assembly cable manufacturing process according to an embodiment of the present invention. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments.

[0012] In related technologies, prefabricated cables play a crucial role in specialized communication and power transmission fields in modern industrial production due to their unique performance. The manufacturing process of these cables typically involves multiple continuous and closely interconnected steps, such as welding stainless steel strips into tubes, corrugating, and inserting the cable core. To ensure high product quality and production efficiency, existing systems strive to maintain production indicators within a preset ideal range by real-time monitoring and adjustment of various process parameters. However, with the increasing market demand for small-batch, multi-specification customized products, production lines need to frequently switch product specifications. This switching means that adjustments to parameters in upstream processes can trigger a series of unpredictable chain reactions in downstream processes, affecting product quality, production stability, and control accuracy.

[0013] For example, in the fields of specialized communications or power transmission, prefabricated cables are widely used due to their excellent mechanical protection and electromagnetic shielding performance. Their production process typically involves several continuous and tightly interconnected key steps. First, stainless steel strips of a specific width are continuously rolled into a cylindrical shape, and high-frequency or laser welding is performed at the joints to form a continuous, sealed stainless steel tube. Next, this smooth stainless steel tube enters a corrugated forming device, where a series of precisely controlled forming wheels create spiral or annular corrugations on its surface. This not only increases the cable's flexibility but also enhances its compressive strength. Finally, pre-manufactured optical fibers or cable cores are threaded through one end of the stainless steel corrugated tube under precise tension control, ultimately forming the finished prefabricated cable. To ensure product quality and production efficiency, existing systems deploy sensors at each process stage to collect real-time operational information such as welding current, voltage, steel strip feed speed, forming wheel speed, pressure, and the torque of the threading motor. Based on this information, the control center adjusts the actuators at each stage to maintain production indicators within the set standard range, thereby achieving stable automated production. This system performs exceptionally well when handling continuous production tasks of large batches of single-specification products.

[0014] However, changing market demands posed new challenges to this stable production model. Customers began demanding more small-batch, multi-specification customized products, such as special cables with different outer diameters, corrugation depths, or even different thicknesses or grades of stainless steel strip. This required the production line to have the ability to quickly switch production specifications. When a production task switched from one specification to another, the entire control system needed to reset a series of parameters. Problems began to emerge precisely during these frequent switchovers. For example, when the production line had just completed a batch of cables using 0.3 mm thick steel strip, and the next order required 0.35 mm thick steel strip, the operator would update this specification in the control system. The control logic of the welding process would react immediately, automatically increasing the welding power to ensure that the thicker steel strip could be fully welded. This was a perfectly correct local adjustment that ensured the mechanical strength and airtightness of the weld, avoiding the most basic quality problems of the product.

[0015] However, this adjustment triggered a series of unforeseen chain reactions on the production line. Due to the increased welding power, the temperature of the weld and its surrounding area was significantly higher than when producing the previous specification. This extra heat did not dissipate immediately after welding but was transferred downstream as the steel pipe continued to move forward. By the time this hotter section of pipe reached the corrugating process, its material state had undergone subtle but crucial changes. In metalworking, temperature is a critical factor affecting material plasticity. Higher temperatures result in lower yield strength, but also better ductility and plasticity in stainless steel. The control system for the corrugating process, with parameters such as the forming wheel's depth and rotation speed, is set based on the material's mechanical properties at standard room temperature. It cannot detect that the section of pipe to be processed is "hot." Therefore, when the forming wheel applies preset pressure to this "softer" section of pipe, the actual deformation exceeds expectations. Corrugations originally designed to form a 5mm pitch may now be pressed deeper, resulting in a pitch shortened to 4.8mm, affecting product quality.

[0016] The embodiments of this application will be explained in detail below with reference to the accompanying drawings: Figure 1 This is an optional flowchart of an intelligent control method for the assembly cable manufacturing process provided in this application embodiment. Figure 1 The method may include, but is not limited to, steps S101 to S107.

[0017] Step S101: Divide the assembly cable manufacturing process into processes, resulting in welding, corrugation forming, and threading processes; Step S102: After performing the welding process, conduct a risk assessment of the welding process and calculate the plasticity risk value; Step S103: Adjust the corrugation processing parameters according to the plasticity risk value. The corrugation processing parameters include the pressing depth and rotation speed of the forming wheel. Step S104: Perform the corrugation forming process according to the corrugation processing parameters, and conduct a risk assessment of the corrugation forming process based on the plasticity risk value, and calculate the corrugation forming quality risk value. Step S105: Adjust the threading processing parameters according to the corrugated forming quality risk value. The threading processing parameters include the target value of the threading motor torque, the threading motor speed control curve, and the control parameters of the proportional-integral-derivative controller. The control parameters include the proportional gain, integral time, and derivative gain. Step S106: Perform the threading process according to the threading parameters; Step S107: After performing the threading process, generate early warning information based on the plasticity risk value and the corrugation forming quality risk value.

[0018] Steps S101 to S107 shown in the embodiments of this application can combine the plasticity risk value and the corrugation forming quality risk value to adjust the processing parameters of different processes, so as to achieve manufacturing process control and improve accuracy and product quality.

[0019] In some embodiments, steps S101-S107 can first divide the assembly cable manufacturing process into three steps: welding, corrugation forming, and threading. These steps can be defined by expert experience; for example, based on the production process flow chart, welding stainless steel strips into tubes can be defined as the welding step, pressing steel tubes into corrugations as the corrugation forming step, and threading the cable cores into the corrugated tubes as the threading step. Alternatively, analysis can be performed using automated tools, such as process mining techniques, to analyze event logs in historical production data and automatically identify different process boundaries. It is understood that assembly cables refer to cable products assembled from multiple components (such as steel tubes and cable cores) through specific processes.

[0020] After the welding process, a risk assessment is conducted to calculate the plasticity risk value. For example, an infrared thermometer can be placed near the welding area to acquire real-time temperature data of the steel pipe. Simultaneously, by combining parameters such as the welding equipment's current, voltage, and speed, as well as the steel pipe's material and thickness, a pre-established physical model or machine learning model is used to predict the temperature distribution in the welding area and the downstream corrugated forming area. Based on the predicted temperature and the material's temperature-plasticity curve, the plasticity risk value of the steel pipe entering the corrugated forming process is calculated.

[0021] Then, based on the plasticity risk value, the corrugating processing parameters are adjusted. These parameters include the pressing depth and rotational speed of the forming wheel. For example, if the calculated plasticity risk value is high, indicating that the steel pipe is more prone to deformation at the current temperature, the pressing depth of the forming wheel can be reduced accordingly to avoid excessive deformation. Simultaneously, the rotational speed of the forming wheel can be appropriately adjusted to match the steel pipe's travel speed, ensuring the stability of the corrugating process. This adjustment can be achieved through a preset lookup table, where different pressing depths and rotational speeds are adjusted according to different plasticity risk value ranges.

[0022] Next, based on the corrugation processing parameters, the corrugation forming process is executed. A risk assessment is then conducted on the corrugation forming process based on the plasticity risk value, and the corrugation forming quality risk value is calculated. For example, after corrugation forming, the corrugation pitch and corrugation depth of the corrugated pipe can be measured in real time using a laser displacement sensor or machine vision system. The measured values ​​are compared with the target values ​​to calculate the pitch deviation and depth deviation. Combining the plasticity risk value, as well as information such as the operating status of the forming wheel, the current steel pipe temperature, and the ambient temperature, a comprehensive evaluation model is used to calculate the corrugation forming quality risk value. This model can be a rule-based expert system or a trained neural network model.

[0023] Based on the corrugated forming quality risk value, the threading processing parameters are adjusted. These parameters include the target torque value of the threading motor, the speed control curve of the threading motor, and the control parameters of the proportional-integral-derivative (PID) controller, including proportional gain, integral time, and derivative gain. For example, a high corrugated forming quality risk value indicates a potential large deviation in the geometric dimensions of the corrugated pipe, leading to fluctuations in threading resistance. In this case, the target torque value of the threading motor can be appropriately reduced to decrease the tension on the cable core and prevent damage. Simultaneously, the speed control curve of the threading motor can be adjusted to be smoother, reducing drastic speed fluctuations. Furthermore, the control parameters of the PID controller can be adjusted; for example, appropriately decreasing the proportional gain and increasing the integral time, to improve the robustness of the system and reduce overreaction to resistance fluctuations.

[0024] Finally, the threading process is executed according to the threading parameters. After the threading process, an early warning message is generated based on the plasticity risk value and the corrugation forming quality risk value. For example, if the plasticity risk value or the corrugation forming quality risk value exceeds a preset risk threshold, the system will trigger an early warning. The preset risk threshold can be set through expert experience. The early warning message can include the warning level (e.g., minor, moderate, severe), the affected process (e.g., welding, corrugation forming, threading), the potential cause (e.g., excessively high welding temperature, worn forming wheel, abnormal material batch), and intervention measures (e.g., checking welding parameters, adjusting the forming wheel, changing materials). This information can be displayed on the operator interface and relevant personnel can be alerted through audible and visual alarms, SMS notifications, etc.

[0025] This embodiment effectively addresses the challenges faced by traditional control systems when switching between multiple specifications by introducing a cross-process risk assessment and parameter linkage adjustment mechanism in the prefabricated cable manufacturing process. Specifically, the manufacturing process is first divided into three core processes: welding, corrugation forming, and threading. After the welding process is executed, the system immediately performs a risk assessment and calculates a plasticity risk value. This plasticity risk value is a key indicator measuring the degree of plasticity change of the steel pipe under the current welding heat effect, and can predict the "softness" or "hardness" of the steel pipe when it enters the corrugation forming process. Subsequently, the system intelligently adjusts the corrugation processing parameters, including the pressing depth and rotation speed of the forming wheel, based on the calculated plasticity risk value. For example, when the plasticity risk value is high, indicating that the steel pipe becomes softer at high temperatures, the system will correspondingly reduce the pressing depth of the forming wheel to avoid excessive deformation and adjust the rotation speed to adapt to the material properties. This proactive parameter adjustment allows the corrugation forming process to adapt to the actual state of the upstream welding process, thereby effectively avoiding deviations in corrugated geometric dimensions caused by changes in material plasticity.

[0026] After the corrugating process is executed, the system reassesses the risk of the corrugating process based on the plasticity risk value, calculating the corrugating quality risk value. This risk value comprehensively considers the impact of material plasticity changes on the corrugating quality, as well as deviations in the actual corrugated geometry. Based on this corrugating quality risk value, the system further adjusts the threading parameters, including the target torque value of the threading motor, the speed control curve of the threading motor, and the control parameters of the proportional-integral-derivative controller. For example, if the corrugating quality risk value is high, the system will appropriately reduce the target torque value of the threading motor and adjust the speed control curve and controller parameters to cope with possible fluctuations in threading resistance and ensure the uniformity of cable core tension within the corrugated tube. Finally, after the threading process is completed, the system generates detailed early warning information by combining the plasticity risk value and the corrugating quality risk value. This early warning information not only identifies potential quality problems but also provides information on affected processes, potential causes, and intervention measures, providing timely and accurate decision support for operators.

[0027] Through the above technical solution, this embodiment introduces plasticity risk values ​​and corrugation forming quality risk values ​​to achieve quantitative perception of the upstream process status and prediction of its impact on downstream processes. The plasticity risk value acts as a bridge between the welding and corrugation forming processes, enabling the corrugation forming process to adaptively adjust parameters based on the actual plasticity of the steel pipe, thereby avoiding quality problems caused by changes in material properties. Similarly, the corrugation forming quality risk value acts as a bridge between the corrugation forming and threading processes, enabling the threading process to anticipate and address challenges arising from geometric deviations in the corrugated pipe, ensuring the quality of cable core insertion. This forward-looking, cross-process linkage control significantly improves the robustness and adaptability of the entire manufacturing process, effectively solving the challenges faced by traditional control systems when switching between multiple specifications, and avoiding the gradual accumulation and amplification of quality problems. Therefore, this embodiment can significantly improve the manufacturing quality and production stability of assembled cables, and is particularly suitable for small-batch, multi-specification customized production scenarios, demonstrating significant technological advancement and practical value.

[0028] In some embodiments, step S102 involves a risk assessment of the welding process and calculation of the plasticity risk value, which may include, but is not limited to, the following steps: Obtain steel pipe property information, current steel pipe temperature, and welding parameters for the welding process. Welding parameters include welding current, welding voltage, and welding speed. Steel pipe property information includes thickness, type, specific heat capacity, density, thermal conductivity, and steel pipe geometric dimensions. Calculate the instantaneous heat input at the weld point based on the welding parameters and welding thermal efficiency; Based on the steel pipe properties and instantaneous heat input, the average temperature rise in the corrugated forming area is calculated using a transient heat transfer model. The plasticity risk value is calculated based on the average temperature rise, the current steel pipe temperature, and the target temperature for corrugated forming.

[0029] In some embodiments, the steel pipe's property information, current steel pipe temperature, and welding parameters for the welding process can be obtained first. The steel pipe's property information includes thickness, type, specific heat capacity, density, thermal conductivity, and geometric dimensions. This property information is crucial for accurately simulating the heat conduction process. The welding parameters include welding current, welding voltage, and welding speed, which directly affect the energy input during the welding process. The current steel pipe temperature provides the initial thermal state for evaluation.

[0030] Then, based on the welding parameters and welding thermal efficiency, the instantaneous heat input at the weld point is calculated. Instantaneous heat input is a key indicator of welding energy density, determining the degree of heating of the material in the welding area. Based on the steel pipe properties and the instantaneous heat input, the average temperature rise in the corrugated forming area is calculated using a transient heat transfer model. The transient heat transfer model considers the thermophysical properties, geometry, and dynamic changes of the heat source of the material, thus simulating the heat transfer process inside the steel pipe. The average temperature rise can be calculated using the transient heat transfer model.

[0031] Then, based on the average temperature rise, the current steel pipe temperature, and the target temperature for corrugated forming, a plasticity risk value is calculated. The plasticity risk value reflects the likelihood of plastic deformation or damage to the steel pipe during subsequent corrugated forming, providing a basis for subsequent parameter adjustments. For example, the current steel pipe temperature and the target temperature for corrugated forming can be subtracted to calculate the temperature deviation. The temperature deviation and the average temperature rise can then be weighted and summed to obtain the plasticity risk value.

[0032] This embodiment, by systematically acquiring and analyzing key parameters of the welding process and the inherent properties of the steel pipe, and combining this with a thermodynamic model, quantifies the impact of the welding process on the plastic state of the steel pipe material. Specifically, by acquiring steel pipe property information and welding parameters, accurate input data is provided for subsequent heat input calculations and heat transfer models. The calculation of instantaneous heat input ensures precise control of welding energy. The transient heat transfer model simulates the diffusion and accumulation of heat in the steel pipe, thereby predicting the temperature changes in the corrugated forming area. Finally, by comparing this temperature information with the target temperature, the potential plasticity risks that the steel pipe may face during corrugated forming after welding can be objectively assessed. This quantitative assessment based on a physical model transforms the risk assessment of the welding process from an empirical judgment to a scientific prediction based on data and models.

[0033] Through the above technical solution, this embodiment enables a refined and quantifiable risk assessment process for the welding procedure. By incorporating steel pipe property information, instantaneous heat input calculation, and a transient heat transfer model, this embodiment can more accurately predict the temperature state of the steel pipe in the corrugated forming area after welding, thereby calculating a more reliable plasticity risk value. This precise risk assessment helps to promptly identify potential material plasticity problems, providing a scientific basis for adjusting subsequent corrugated processing parameters, effectively avoiding material damage or product quality degradation caused by welding heat, and significantly improving the manufacturing quality and production efficiency of assembled cables.

[0034] In some embodiments, in step S104, a risk assessment is performed on the corrugated forming process based on the plasticity risk value, and the corrugated forming quality risk value is calculated. This may include, but is not limited to, the following steps: Step S201: Obtain the corrugation pitch and corrugation depth of the corrugated pipe after corrugation forming; Step S202: Calculate the pitch deviation based on the corrugated pitch and the target machining pitch; Step S203: Calculate the depth deviation based on the ripple depth and the target machining depth; Step S204: Calculate the corrugated forming quality risk value based on the plasticity risk value, pitch deviation, and depth deviation.

[0035] In some embodiments, the corrugation pitch and corrugation depth of the corrugated pipe after corrugation forming can be obtained first. The corrugation pitch refers to the distance between two adjacent crests or troughs of the corrugated pipe, and the corrugation depth refers to the vertical distance between the crests and troughs of the corrugated pipe. These geometric parameters are key indicators for evaluating the forming quality of the corrugated pipe.

[0036] Then, based on the corrugated pitch and the target machining pitch, the pitch deviation is calculated. The obtained corrugated pitch can be compared with the preset target machining pitch to calculate the pitch deviation. The pitch deviation reflects the difference between the actual corrugated pitch and the ideal pitch.

[0037] Next, the depth deviation is calculated based on the corrugation depth and the target processing depth. The obtained corrugation depth can be compared with the preset target processing depth to calculate the depth deviation. The depth deviation reflects the difference between the actual corrugation depth and the ideal depth. These deviation values ​​are important quantitative indicators for evaluating the quality of corrugation forming.

[0038] Finally, the corrugated forming quality risk value is calculated based on the plasticity risk value, pitch deviation, and depth deviation. The plasticity risk value reflects the potential plastic deformation risk of the material after the welding process, while the pitch deviation and depth deviation directly reflect the geometric accuracy of the corrugated forming process. By comprehensively considering these factors, a more comprehensive and accurate corrugated forming quality risk value can be obtained. For example, the weighted sum of the plasticity risk value, pitch deviation, and depth deviation can be used to obtain the corrugated forming quality risk value.

[0039] This embodiment quantifies the processing accuracy of the corrugating forming process by comparing the actual geometric parameters (corrugation pitch and corrugation depth) of the corrugated pipe with target values. By combining these geometric deviations with the plasticity risk value generated by the upstream welding process, the calculation of the corrugating forming quality risk value not only considers the potential defects of the material itself but also fully takes into account the dimensional deviations that may occur during actual processing. Therefore, this scheme can more comprehensively and accurately assess the quality status of the corrugating forming process, providing more reliable data support for subsequent processing parameter adjustments and early warning information generation.

[0040] Through the above technical solution, this embodiment enables a refined assessment of the quality risks in the corrugated forming process. Specifically, by introducing the measurement of corrugation pitch and depth, along with corresponding deviation calculations, the quality risk value of corrugated forming can directly reflect the degree of conformity of the product's geometric dimensions. Simultaneously, by incorporating the plasticity risk value of the welding process, the assessment of corrugated forming quality risks is ensured not only to the processing results of the current process but also to trace the impact of upstream processes on material properties. This improves the accuracy and foresight of the risk assessment, helping to promptly identify and resolve potential quality problems and prevent defective products from flowing into subsequent processes.

[0041] In some embodiments, in step S204, calculating the corrugated forming quality risk value based on the plasticity risk value, pitch deviation, and depth deviation may include, but is not limited to, the following steps: Obtain the operating status of the forming wheel, the current temperature of the steel pipe, and the ambient temperature; The contribution of material factors is determined based on the plasticity risk value and pitch deviation; The contribution of tool factors is determined based on the operating status of the forming wheel and the depth deviation; The contribution of environmental factors is determined based on the pitch deviation, the current steel pipe temperature, and the ambient temperature. The contribution of material factors, tool factors, and environmental factors is weighted and integrated to obtain the quality risk value of corrugated forming.

[0042] In some embodiments, the operating status of the forming wheel, the current temperature of the steel pipe, and the ambient temperature can be obtained first. The operating status of the forming wheel refers to various parameters of the forming wheel during operation, such as its wear level, vibration frequency, and pressure stability. These parameters directly reflect the health and performance of the forming tool. The current temperature of the steel pipe refers to its actual temperature, which has a significant impact on the plastic deformation capacity of the steel pipe material. The ambient temperature refers to the ambient temperature of the workshop where the corrugated forming process is located. Changes in the ambient temperature may indirectly affect the temperature of the steel pipe and the operational stability of the equipment.

[0043] Then, based on the plasticity risk value and pitch deviation, the contribution of material factors is determined. The plasticity risk value reflects the plastic state of the steel pipe itself after the welding process, such as whether there is a tendency for overheating or embrittlement. Pitch deviation reflects the deformation response of the material during the corrugation forming process. By comprehensively analyzing these two parameters, the influence of the material's own characteristics on the quality risk of corrugation forming can be quantified. For example, when the plasticity risk value is high and the pitch deviation is large, it may indicate that the material itself has defects or insufficient plasticity, resulting in a higher contribution to the quality of corrugation forming.

[0044] The contribution of tool factors is then determined based on the operating status of the forming wheel and the depth deviation. The forming wheel is the tool that directly plastically deforms the steel pipe, and its operating status (such as wear, runout, and stability of the compression depth) directly affects the forming accuracy of the corrugations. The depth deviation reflects the difference between the actual effect of the forming wheel and the target effect. By evaluating these parameters, the impact of the forming tool's performance and status on the risk of corrugation forming quality can be quantified. For example, abnormal operating status of the forming wheel or a large depth deviation will lead to an increase in the contribution of tool factors.

[0045] The contribution of environmental factors is determined based on pitch deviation, current steel pipe temperature, and ambient temperature. Pitch deviation can be affected by temperature changes, and the current steel pipe temperature and ambient temperature are important environmental parameters affecting the physical properties of materials and the operational stability of equipment. Changes in these environmental factors can lead to uncertainties in the corrugation forming process. For example, drastic fluctuations in ambient temperature can cause instability in the steel pipe temperature, thereby affecting its plastic deformation behavior and increasing the contribution of environmental factors.

[0046] Finally, the contributions of material factors, tool factors, and environmental factors are weighted and integrated to obtain the corrugated forming quality risk value. Different factors can be assigned different weights based on their importance to the corrugated forming quality risk, and these weighted contributions can be summed or calculated comprehensively using other mathematical models. The aim is to comprehensively and objectively assess the overall quality risk of the corrugated forming process, avoiding the one-sidedness of assessments based on a single parameter.

[0047] This embodiment refines the assessment of corrugated forming quality risk into a three-dimensional contribution analysis of material factors, tool factors, and environmental factors, and then performs a weighted fusion, thereby solving the problems of insufficient accuracy and comprehensiveness caused by relying on only a few macroscopic parameters for risk assessment. Specifically, the combination of plasticity risk value and pitch deviation can reveal the intrinsic behavior of the material in the forming process more deeply, rather than just the apparent dimensional deviation; the introduction of forming wheel running status and depth deviation makes it possible to consider the condition of the forming tool itself, thereby identifying quality problems caused by equipment failure or wear; the comprehensive consideration of pitch deviation, current steel pipe temperature, and ambient temperature can capture the potential impact of external environmental changes on forming quality. This multi-dimensional and refined risk decomposition and fusion mechanism enables the finally calculated corrugated forming quality risk value to more accurately reflect potential quality hazards in actual production, providing a more reliable basis for subsequent parameter adjustments and early warnings.

[0048] Through the above technical solution, this embodiment enables a refined and multi-dimensional assessment of corrugated forming quality risks. By introducing auxiliary information such as the forming wheel's operating status, current steel pipe temperature, and ambient temperature, and decomposing these into contributions from three levels—material, tool, and environment—and then weighted and fused, this significantly improves the accuracy and comprehensiveness of corrugated forming quality risk assessment. This more precise risk value helps the control system identify potential quality problems earlier and more accurately, thus providing a more reliable basis for subsequent adjustments to wiring parameters. This effectively avoids overall cable performance degradation or scrapping due to corrugated forming quality problems, thereby improving the manufacturing quality and production efficiency of assembled cables.

[0049] In some embodiments, in step S107, generating early warning information based on the plasticity risk value and the corrugation forming quality risk value may include, but is not limited to, the following steps: Step S301: Obtain the welding parameters for the welding process, including welding current, welding voltage and welding speed; Step S302: Preprocess the early warning assessment parameters, which include welding parameters, corrugation processing parameters, and threading processing parameters; Step S303: Identify the target risk pattern based on the risk pattern library and the preprocessed early warning assessment parameters; Step S304: Calculate the overall degree of abnormality based on the plasticity risk value and the corrugation forming quality risk value; Step S305: Extract abnormal feature combinations based on the preprocessed early warning assessment parameters; Step S306: Based on the target risk model, comprehensive anomaly degree, and combination of anomaly characteristics, extract the warning level, affected processes, potential causes, and intervention measures from the risk warning knowledge base; Step S307: Generate early warning information based on the early warning level, affected processes, potential causes, and intervention measures.

[0050] In some embodiments, welding parameters for the welding process, including welding current, welding voltage, and welding speed, can be acquired first to provide basic data for subsequent risk assessment and early warning. The early warning assessment parameters are then preprocessed to ensure data quality and consistency, providing reliable input for subsequent risk identification and assessment. These early warning assessment parameters include welding parameters, corrugation processing parameters, and threading processing parameters. The comprehensiveness of these parameters ensures integrated monitoring of the entire manufacturing process. Preprocessing may include, but is not limited to, steps such as integrity verification, missing data imputation, format standardization, noise reduction, and time alignment.

[0051] Then, based on the risk pattern library and the pre-processed early warning assessment parameters, the target risk pattern is identified. The risk pattern library stores feature patterns related to different production anomalies. By matching the current pre-processed parameters with the patterns in the library, the specific risk type that may correspond to the current production state can be determined. Simultaneously, based on the plasticity risk value and the corrugated forming quality risk value, the overall anomaly degree is calculated. The overall anomaly degree is a quantitative assessment of the deviation of the current production state from the normal level, combining the risk status of the two key processes, welding and corrugated forming, to provide an overview of the overall risk.

[0052] Then, based on the preprocessed early warning assessment parameters, combinations of abnormal features are extracted. These combinations of abnormal features are a comprehensive description of the abnormal behavior in the current production data, such as periodic fluctuations, trend drifts, and sudden spikes. These features help to more accurately locate problems.

[0053] Finally, based on the target risk pattern, the overall degree of anomaly, and the combination of anomaly characteristics, the warning level, affected processes, potential causes, and intervention measures are extracted from the risk warning knowledge base. The risk warning knowledge base is a database containing rich experience and rules; it can provide targeted warning information and solutions based on the identified risk patterns, degree of anomaly, and specific characteristics. Furthermore, it generates warning information based on the warning level, affected processes, potential causes, and intervention measures to facilitate timely corrective action.

[0054] This embodiment systematically integrates key parameters from welding, corrugating, and threading processes, and combines them with plasticity risk values ​​and corrugating quality risk values ​​to construct a multi-dimensional, multi-level early warning information generation mechanism. Specifically, acquiring welding parameters provides a starting point for the entire risk assessment chain. Preprocessing the early warning assessment parameters ensures data accuracy and usability, avoiding misjudgments due to data quality issues. Identifying target risk patterns based on a risk pattern library allows the system to associate current anomalies with known risk types, thus providing more targeted early warnings. Calculating the comprehensive anomaly degree quantifies the overall risk level, providing a basis for decision-making. Extracting anomaly feature combinations further refines the manifestation of anomalies, facilitating in-depth analysis of the root causes of problems. Finally, through a risk early warning knowledge base, the identified risk patterns, anomaly degrees, and feature combinations are transformed into specific early warning levels, affected processes, potential causes, and intervention measures, thereby realizing the transformation from data to intelligent decision-making and providing comprehensive risk management and control capabilities for the prefabricated cable manufacturing process.

[0055] Through the above technical solution, this embodiment can achieve early and accurate warning of potential risks in the manufacturing process of assembled cables. Specifically, the accuracy of the warning is ensured by comprehensively acquiring and preprocessing multi-source parameters. By introducing a risk pattern library and a risk warning knowledge base, the warning information not only points out existing problems but also provides specific risk pattern identification, anomaly degree quantification, potential cause analysis, and feasible intervention measures, greatly improving the practicality and guidance of the warning information. Therefore, operators can quickly locate problems, understand the nature of risks, and take effective countermeasures based on detailed warning information, thereby effectively reducing scrap rates and downtime in the production process, and improving production efficiency and product quality.

[0056] In some embodiments, the preprocessing of the early warning assessment parameters in step S302 may include, but is not limited to, the following steps: The integrity of the early warning assessment parameters is verified, and the integrity verification results are obtained. Based on the integrity verification results, missing data filling is performed on the early warning assessment parameters; The format of the early warning assessment parameters after missing data imputation is standardized. The standardized early warning evaluation parameters are denoised to remove noise. The denoised early warning assessment parameters are time-aligned to ensure consistent data timing.

[0057] In some embodiments, the original early warning assessment parameters may have problems such as missing data, inconsistent formats, noise interference, and disordered timing. If these problems are not effectively addressed, they will seriously affect the accuracy and reliability of subsequent risk pattern recognition, comprehensive anomaly degree calculation, and anomaly feature extraction, thereby leading to inaccurate or false alarms in the generated early warning information.

[0058] Therefore, the integrity of the early warning assessment parameters can be verified first to obtain the integrity verification results. Integrity verification refers to checking the collected early warning assessment parameters to ensure that all necessary data fields exist and are not corrupted. For example, it can be checked whether each parameter has the expected data type and non-null values. Its purpose is to identify and mark missing or abnormal parts in the data, providing a basis for subsequent data filling.

[0059] Then, based on the integrity verification results, missing data imputation is performed on the early warning assessment parameters. When the integrity verification results indicate the presence of missing data, appropriate algorithms or strategies can be used to supplement this missing data. For example, mean imputation, median imputation, mode imputation, interpolation methods (such as linear interpolation and spline interpolation), or prediction imputation based on machine learning models (such as K-nearest neighbors and regression models) can be used. The purpose is to restore data integrity and avoid analytical bias or model failure due to missing data.

[0060] Next, the early warning assessment parameters after missing data imputation are standardized in format. This involves converting the parameters into a unified format and unit. For example, all temperature data can be standardized to degrees Celsius, all timestamps to ISO 8601 format, or data with different units can be normalized or standardized. The purpose is to eliminate data format differences between different data sources or sensors, ensuring data consistency and comparability, and facilitating subsequent algorithm processing.

[0061] The standardized early warning assessment parameters undergo denoising to remove noise. This can be achieved by filtering or smoothing the standardized parameters to remove random noise or abnormal fluctuations in the data. For example, methods such as moving average, Gaussian filtering, wavelet transform, or Kalman filtering can be used. The aim is to improve the signal-to-noise ratio of the data, enabling it to more accurately reflect the actual physical process or system state and reducing the interference of noise on the risk assessment results.

[0062] Finally, the denoised early warning assessment parameters are time-aligned to ensure data consistency. Timestamp calibration and synchronization of the denoised parameters ensure that data collected by different sensors or systems remain consistent across time. For example, data can be resampled or interpolated based on a unified time reference to ensure all relevant parameters are comparable at the same point in time. The aim is to guarantee data consistency, providing accurate input for time-series-based risk pattern recognition and anomaly analysis.

[0063] This embodiment effectively addresses potential issues with the integrity, consistency, accuracy, and timeliness of raw data by systematically preprocessing the early warning assessment parameters. Specifically, integrity verification first identifies data defects, laying the foundation for subsequent processing; missing data imputation restores data integrity through intelligent algorithms, preventing analysis interruptions or errors caused by incomplete data; format standardization unifies data representation, eliminating compatibility issues arising from heterogeneous data sources; noise reduction filters out interfering information, enabling the data to more accurately reflect the actual state of the production process; and finally, time alignment ensures the synchronization of all relevant parameters over time, which is crucial for analyzing the temporal relationships between multiple variables and identifying complex risk patterns. This preprocessing allows subsequent risk pattern identification, comprehensive anomaly calculation, and anomaly feature extraction to be performed based on high-quality, highly reliable data, thereby significantly improving the accuracy and timeliness of early warning information.

[0064] To illustrate this technical solution more clearly, a specific example is used below. Assume that during the assembly cable manufacturing process, early warning evaluation parameters (including welding current, forming wheel speed, and threading motor torque) collected from welding equipment, corrugated forming equipment, and threading equipment are transmitted to the intelligent control system. First, the system performs an integrity check on these parameters and finds that the threading motor torque data is missing for a certain time period. Based on the integrity check result, the system uses linear interpolation to fill in the missing threading motor torque data. Next, the system performs format standardization processing on the filled data, for example, unifying all current values ​​to amperes and speeds to revolutions per minute. Subsequently, to eliminate random noise generated during sensor acquisition, the system applies a moving average filter to the standardized data for noise reduction. Finally, since the sampling frequencies of different devices may differ, the system performs time alignment processing on the denoised data, ensuring that all parameters have corresponding data records at fixed time points every second through resampling, thus ensuring data time sequence consistency. After this series of preprocessing steps, the original data, which had issues such as missing data, inconsistent formats, noise, and time-series problems, was transformed into a high-quality, standardized dataset that can be directly used for risk assessment and early warning generation.

[0065] Through the above technical solution, this embodiment significantly enhances the early warning capability of the intelligent control system in the prefabricated cable manufacturing process. This embodiment introduces a series of refined data preprocessing steps, including integrity verification, missing data imputation, format standardization, noise reduction, and time alignment, ensuring that the early warning assessment parameters input to the risk assessment module have high integrity, high consistency, high accuracy, and good temporal synchronization. This not only effectively avoids false alarms or missed alarms caused by data quality issues but also provides a solid and reliable data foundation for subsequent identification of target risk patterns based on the risk pattern library, calculation of comprehensive anomaly degree, and extraction of anomaly feature combinations. This results in more accurate and timely early warning information, enabling more effective guidance for intervention and optimization in the production process, reducing production risks and product defect rates.

[0066] In some embodiments, step S303, identifying the target risk pattern based on the risk pattern library and the preprocessed early warning assessment parameters, may include, but is not limited to, the following steps: Obtain product specification information; Based on the product specification information, select the target time series feature extraction strategy from the time series feature extraction strategy library; Based on the target time series feature extraction strategy, time series features are extracted from the preprocessed early warning assessment parameters to obtain time series features, which include data length, data frequency and time series pattern. The time-series features are matched with a risk pattern library to identify target risk patterns.

[0067] In some embodiments, product specification information may be obtained first. Product specification information refers to the specific technical parameters and design requirements of the assembled cable to be manufactured, such as the cable diameter, material type, insulation thickness, conductor cross-sectional area, and expected electrical performance. This information is crucial for understanding specific risk modes that may arise during the cable manufacturing process.

[0068] Then, based on the product specifications, a target time-series feature extraction strategy is selected from the time-series feature extraction strategy library. The time-series feature extraction strategy library refers to a pre-defined collection of algorithms used to extract specific patterns or features from time-series data. For example, this library may contain multiple algorithms for detecting periodic fluctuations, trend drifts, sudden spikes, or specific frequency components. Based on the current product specifications, the most suitable algorithm or method for the current manufacturing scenario and risk identification needs can be selected from the time-series feature extraction strategy library as the target time-series feature extraction strategy.

[0069] Next, based on the target time-series feature extraction strategy, time-series features are extracted from the preprocessed early warning assessment parameters to obtain time-series features, which include data length, data frequency, and time-series pattern. Time-series features refer to the regular information extracted from the preprocessed early warning assessment parameters that characterizes the data's changes over time. Specifically, data length refers to the total number of sample points or the time span of the analyzed time series data; data frequency refers to the rate of data sampling or recording, such as the number of samples collected per second; and time-series pattern encompasses various structural patterns present in the data, such as upward trends, downward trends, periodic fluctuations, random noise, or specific event sequences.

[0070] Finally, the time-series features are matched with a risk pattern library to identify the target risk pattern. The risk pattern library is a database that stores characteristic patterns of known risk events or abnormal states. Each risk pattern typically contains a specific set of time-series feature descriptions. When the extracted time-series features highly match a pattern in the library, the corresponding target risk pattern can be identified.

[0071] This embodiment leverages product specification information to optimize the subsequent time-series feature extraction process. Based on this information, the system intelligently selects the most suitable target time-series feature extraction strategy from a strategy library, considering the current product and potential risk type. Subsequently, this strategy is used to extract time-series features from the preprocessed warning assessment parameters, yielding precise time-series features including data length, data frequency, and time-series patterns. Finally, these extracted time-series features are matched against pre-stored known risk patterns in a risk pattern library, accurately identifying specific target risk patterns that may exist in the current manufacturing process. This method ensures the accuracy and specificity of risk identification, avoiding false positives or false negatives that may result from blindly applying general feature extraction methods.

[0072] Through the above technical solution, this embodiment can significantly improve the accuracy and efficiency of risk pattern recognition. By introducing product specification information and dynamically selecting temporal feature extraction strategies, the system can more accurately capture abnormal patterns related to specific products, thereby avoiding the limitations of general models in complex and ever-changing manufacturing environments. This customized feature extraction and matching mechanism enables the system to identify potential manufacturing risks earlier and more accurately, providing a solid foundation for subsequent early warning information generation and intervention measures, thus effectively ensuring the manufacturing quality and production efficiency of assembled cables.

[0073] In some embodiments, step S304, calculating the overall degree of abnormality based on the plasticity risk value and the corrugation forming quality risk value, may include, but is not limited to, the following steps: Acquire historical risk data and current production parameters. Historical risk data includes historical plasticity risk data and historical corrugated forming quality risk data. Current production parameters include product specification information, material batches, and production line load. Adjust the risk fluctuation range based on historical risk data and current production parameters; By comparing the plasticity risk value with the risk fluctuation range, the degree of welding abnormality can be identified; By comparing the quality risk value of corrugated forming with the risk fluctuation range, the degree of abnormality in corrugated forming can be identified. The degree of welding abnormality and the degree of corrugation forming abnormality are weighted and combined to calculate the overall degree of abnormality.

[0074] In some embodiments, since the production environment and material properties may change dynamically, if the calculation is made directly based solely on the current plasticity risk value and corrugated molding quality risk value, it may not be able to fully take into account the experience accumulated from historical data and the impact of current production parameters (such as product specification information, material batches, and production line load) on risk assessment. As a result, the calculated comprehensive degree of anomaly may not be accurate enough and may not be able to effectively guide the generation of early warning information.

[0075] To this end, historical risk data and current production parameters can be obtained first. Historical risk data refers to plasticity risk data and corrugated forming quality risk data accumulated over past production cycles. This data reflects the historical performance of material plasticity changes and corrugated forming quality under different production conditions. Current production parameters include product specifications, material batches, and production line load. These parameters directly affect the characteristics and potential risks of the current production process. For example, different cable models, different batches of raw materials, and varying production line loads can all significantly impact the risk levels of the welding and corrugated forming processes. Obtaining this data aims to provide comprehensive background information and dynamic reference for subsequent risk assessments.

[0076] Then, based on historical risk data and current production parameters, the risk fluctuation range is adjusted. This risk fluctuation range refers to the reasonable range within which the plasticity risk value and the corrugated forming quality risk value may fluctuate under normal production conditions. By combining historical data, a baseline fluctuation range can be established; then, by combining current production parameters, such as when producing specific specifications of products or using specific batches of materials, this baseline fluctuation range can be dynamically corrected to obtain the risk fluctuation range, making it more closely reflect the current actual production situation. The purpose is to make the risk assessment baseline more flexible and accurate, avoiding misjudgments that may result from using fixed thresholds.

[0077] Next, the plasticity risk value is compared with the risk fluctuation range to identify the degree of welding abnormality. Specifically, if the plasticity risk value exceeds the adjusted risk fluctuation range, it indicates that there may be an abnormality in the welding process; the greater the deviation from the range, the higher the degree of welding abnormality. Then, the corrugated forming quality risk value is compared with the risk fluctuation range to identify the degree of corrugated forming abnormality. The current corrugated forming quality risk value can be compared with the adjusted risk fluctuation range to identify the degree of corrugated forming abnormality. This helps to quantify the degree of risk deviation for each process.

[0078] Finally, the severity of welding and corrugating anomalies is weighted and fused to calculate the overall anomaly level. Different weights can be assigned to the welding and corrugating processes based on their importance in the overall cable manufacturing process, their impact on the final product quality, and their risk sensitivity as shown in historical data. For example, if the welding process has a greater impact on the overall cable performance, it can be given a higher weight. This weighted fusion yields a comprehensive risk indicator that fully reflects the current production status, aiming to provide a unified and instructive assessment of the anomaly level.

[0079] This embodiment addresses the potential static and one-sidedness issues in assessing the overall degree of anomaly by introducing historical risk data and current production parameters, and dynamically adjusting the risk fluctuation range accordingly. Specifically, historical risk data provides insights into the long-term stability and volatility of the production process, allowing risk assessment to move beyond instantaneous data and incorporate past experience. The introduction of current production parameters enables risk assessment to adapt to changes in the production environment in real time. For example, the normal risk fluctuation range may differ for different product specifications or material batches; dynamic adjustment avoids misjudging normal fluctuations as anomalies or ignoring potential anomalies. By comparing the plasticity risk value and the corrugated forming quality risk value with this dynamically adjusted risk fluctuation range, the actual degree of anomaly in each process can be identified more accurately, avoiding the limitations of fixed thresholds. Finally, weighted fusion of these anomaly levels ensures that the calculation of the overall anomaly level comprehensively and selectively reflects the risk status of the entire manufacturing process, providing a more reliable and refined basis for subsequent early warning information generation.

[0080] To illustrate this technical solution more clearly, a specific example is used below. Suppose a prefabricated cable manufacturer is producing a batch of a specific type of cable with high requirements for material plasticity. In traditional risk assessments, the current plasticity risk value and corrugated forming quality risk value might only be compared with preset fixed thresholds. This embodiment first acquires historical production data for this cable type, including historical plasticity risk data and historical corrugated forming quality risk data, as well as current production parameters, such as the current batch of steel pipe material used and the production line load. Specifically, if historical data shows that the plasticity risk value of this cable type, under a specific material batch, typically fluctuates within a relatively high range, it is still within the normal range. Simultaneously, if the current production line load is high, it may have a slight impact on the corrugated forming quality. Based on this historical data and current parameters, the system dynamically adjusts the risk fluctuation range of the plasticity risk value and the corrugated forming quality risk value. For example, the upper limit of normal fluctuation for the plasticity risk value may be appropriately widened, while the normal fluctuation range for the corrugated forming quality risk value may be slightly tightened.

[0081] Subsequently, when the actual measured plasticity risk value and corrugated forming quality risk value occur, they are compared with these dynamically adjusted risk fluctuation ranges. For example, if the current plasticity risk value is slightly higher than the traditional fixed threshold but still within the normal fluctuation range after dynamic adjustment, the identified degree of welding anomaly may be low. Conversely, if the corrugated forming quality risk value only slightly exceeds the dynamically adjusted tightening range, it may be identified as having a certain degree of corrugated forming anomaly. Finally, these identified welding anomaly and corrugated forming anomaly degrees are weighted and fused according to preset weights to calculate a more accurate and comprehensive anomaly degree that conforms to the current production situation. This method can avoid false alarms caused by fixed thresholds, and at the same time, it can more sensitively capture subtle anomalies that may occur under specific production conditions, thereby improving the effectiveness of early warning.

[0082] Through the above technical solution, this embodiment enables a more accurate and adaptable assessment of the overall anomaly level in the prefabricated cable manufacturing process. This embodiment fully considers the dynamic and complex nature of the production process, integrating historical data and real-time production parameters to ensure that risk assessment is no longer an isolated, instantaneous judgment, but a comprehensive analysis based on rich contextual information. This effectively avoids false alarms or missed alarms caused by fixed thresholds or single-indicator assessments, significantly improving the accuracy and timeliness of risk warnings. This refined calculation of the overall anomaly level provides a more reliable basis for generating subsequent warning information, thereby helping production managers to promptly identify and intervene in potential quality problems or production risks, ensuring the manufacturing quality and production efficiency of prefabricated cables.

[0083] In some embodiments, step S305, extracting abnormal feature combinations based on the preprocessed early warning evaluation parameters, may include, but is not limited to, the following steps: Periodic fluctuation analysis was performed on the preprocessed early warning assessment parameters to obtain periodic fluctuation characteristics; Trend drift analysis was performed on the preprocessed early warning assessment parameters to obtain trend drift characteristics; Sudden spike analysis was performed on the preprocessed early warning assessment parameters to obtain the characteristics of sudden spikes; By combining periodic fluctuation features, trend drift features, and sudden spike features, an abnormal feature combination is obtained.

[0084] In some embodiments, periodic fluctuation analysis can be performed on the preprocessed early warning assessment parameters to obtain periodic fluctuation characteristics. Specific signal processing or data analysis methods can be used to identify repetitive and regular patterns of change in the data. For example, techniques such as Fourier transform, wavelet analysis, or autocorrelation analysis can be used to reveal the periodic behavior of the data over time. The resulting periodic fluctuation characteristics may include, but are not limited to, parameters such as fluctuation amplitude, frequency, and phase, which can quantify the intensity and characteristics of periodic changes in the data.

[0085] Then, trend drift analysis is performed on the preprocessed early warning assessment parameters to obtain trend drift characteristics. Statistical or machine learning methods can be used to detect slow, continuous upward or downward trends in data over time. For example, moving averages, linear regression, exponential smoothing, or Kalman filtering can be used to capture long-term trends in the data. The resulting trend drift characteristics can include the slope, intercept, and drift magnitude of the trend, reflecting the gradual changes in the system state.

[0086] Next, a sudden spike analysis is performed on the preprocessed early warning assessment parameters to obtain sudden spike characteristics. Short-lived, drastic outliers or spikes in the data can be identified using anomaly detection algorithms or threshold judgment methods. For example, statistical process control (SPC) charts, distance-based anomaly detection algorithms (such as Local Anomaly Factor (LOF)), density-based anomaly detection algorithms (such as DBSCAN), or simple threshold comparison methods can be used to detect transient anomalies in the data. The resulting sudden spike characteristics can include the spike's amplitude, duration, and frequency of occurrence; these characteristics indicate sudden events in the system.

[0087] Finally, the periodic fluctuation features, trend drift features, and sudden spike features are concatenated to obtain anomaly feature combinations. These three different types of features can be integrated to form a more comprehensive, multi-dimensional anomaly feature vector or combination. This concatenation can be achieved by simply connecting the feature vectors, or through more complex feature fusion techniques to ensure effective synergy between different features.

[0088] This embodiment analyzes preprocessed early warning assessment parameters by decomposing them into three basic anomaly modes: periodic fluctuations, trend drifts, and sudden spikes. This allows for the capture of potential anomalies in the prefabricated cable manufacturing process across different time scales and manifestations. Periodic fluctuation analysis helps identify regular anomalies caused by equipment wear, periodic environmental changes, or repetitive operations; trend drift analysis focuses on detecting long-term, gradual anomalies caused by material aging, slow changes in process parameters, or sensor drift; and sudden spike analysis can quickly respond to instantaneous anomalies caused by transient failures, sudden impacts, or operational errors. This multi-dimensional and refined feature extraction enables the resulting combination of anomaly features to more comprehensively and accurately reflect the true anomaly state of the manufacturing process, providing a solid data foundation for subsequent risk pattern identification and early warning information generation.

[0089] Through the above technical solution, this embodiment can comprehensively capture abnormal information in the early warning assessment parameters from multiple dimensions. Specifically, through periodic fluctuation analysis, regular anomalies caused by equipment wear and periodic environmental changes can be effectively identified; through trend drift analysis, long-term deviations caused by material aging and slow changes in process parameters can be accurately detected; and through sudden spike analysis, instantaneous anomalies caused by transient faults and sudden impacts can be quickly detected. This multi-dimensional feature extraction method enables the combination of abnormal features to more comprehensively and meticulously reflect various potential risk patterns in the prefabricated cable manufacturing process, thereby providing richer and more accurate data support for subsequent target risk pattern identification, comprehensive anomaly degree calculation, and early warning information generation, significantly improving the diagnostic accuracy and reliability of the early warning system.

[0090] The beneficial effects of implementing the embodiments of the present invention include: First, the assembly cable manufacturing process is divided into processes, namely welding, corrugation forming, and threading. Then, a risk assessment is performed on the welding process to calculate the plasticity risk value. Based on the plasticity risk value, the corrugation processing parameters are adjusted. Then, the corrugation forming process is executed based on the corrugation processing parameters. Based on the plasticity risk value, a risk assessment is performed on the corrugation forming process to calculate the corrugation forming quality risk value. Based on the corrugation forming quality risk value, the threading processing parameters are adjusted, and the threading process is executed. Based on the plasticity risk value and the corrugation forming quality risk value, early warning information is generated. Thus, the processing parameters of different processes can be adjusted by combining the plasticity risk value and the corrugation forming quality risk value to achieve manufacturing process control and improve accuracy and product quality.

[0091] like Figure 2 As shown, this embodiment of the invention also provides an intelligent control system for the assembly cable manufacturing process, including: The process division module 401 is used to divide the assembly cable manufacturing process into processes, namely welding process, corrugation forming process and wire threading process. The welding risk assessment module 402 is used to assess the risk of the welding process after the welding process is performed and to calculate the plasticity risk value. The corrugated processing parameter adjustment module 403 is used to adjust the corrugated processing parameters according to the plasticity risk value. The corrugated processing parameters include the pressing depth and rotation speed of the forming wheel. The corrugated forming risk assessment module 404 is used to perform the corrugated forming process according to the corrugated processing parameters, and to perform a risk assessment on the corrugated forming process according to the plasticity risk value, and to calculate the corrugated forming quality risk value. The threading processing parameter adjustment module 405 is used to adjust the threading processing parameters according to the corrugated forming quality risk value. The threading processing parameters include the target value of the threading motor torque, the threading motor speed control curve, and the control parameters of the proportional-integral-derivative controller. The control parameters include the proportional gain, integral time, and derivative gain. The threading process execution module 406 is used to execute the threading process according to the threading processing parameters; The early warning information generation module 407 is used to generate early warning information based on the plasticity risk value and the corrugation forming quality risk value after the threading process is performed.

[0092] The content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0093] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

Claims

1. A method for intelligent control of the prefabricated cable manufacturing process, characterized in that, Includes the following steps: The manufacturing process of prefabricated cables is divided into three steps: welding, corrugation forming, and threading. After the welding process is performed, a risk assessment is conducted on the welding process, and the plasticity risk value is calculated. Based on the plasticity risk value, adjust the corrugation processing parameters, including the pressing depth and rotation speed of the forming wheel; According to the corrugated processing parameters, a corrugated forming process is performed, and a risk assessment is conducted on the corrugated forming process based on the plasticity risk value to calculate the corrugated forming quality risk value. Based on the corrugated forming quality risk value, the threading processing parameters are adjusted. The threading processing parameters include the target value of the threading motor torque, the threading motor speed control curve, and the control parameters of the proportional-integral-derivative controller, which include the proportional gain, integral time, and derivative gain. Perform the threading process according to the threading parameters; After the threading process is performed, an early warning message is generated based on the plasticity risk value and the corrugation forming quality risk value.

2. The method according to claim 1, characterized in that, The risk assessment of the welding process and the calculation of the plasticity risk value include: The steel pipe property information, the current steel pipe temperature, and the welding parameters of the welding process are obtained. The welding parameters include welding current, welding voltage, and welding speed. The steel pipe property information includes thickness, model, specific heat capacity, density, thermal conductivity, and steel pipe geometric dimensions. Calculate the instantaneous heat input of the weld point based on the welding parameters and welding thermal efficiency; Based on the steel pipe property information and the instantaneous heat input, the average temperature rise in the corrugated forming area is calculated using a transient heat transfer model. The plasticity risk value is calculated based on the average temperature rise, the current steel pipe temperature, and the target temperature for corrugated forming.

3. The method according to claim 1, characterized in that, The step of conducting a risk assessment of the corrugated forming process based on the plasticity risk value and calculating the corrugated forming quality risk value includes: Obtain the corrugation pitch and corrugation depth of the corrugated pipe after corrugation forming; Calculate the pitch deviation based on the corrugated pitch and the target machining pitch; Calculate the depth deviation based on the corrugation depth and the target machining depth; The corrugated forming quality risk value is calculated based on the plasticity risk value, the pitch deviation, and the depth deviation.

4. The method according to claim 3, characterized in that, The calculation of the corrugated forming quality risk value based on the plasticity risk value, the pitch deviation, and the depth deviation includes: Obtain the operating status of the forming wheel, the current temperature of the steel pipe, and the ambient temperature; The contribution of material factors is determined based on the plasticity risk value and the pitch deviation. The contribution of tool factors is determined based on the operating state of the forming wheel and the depth deviation. The contribution of environmental factors is determined based on the pitch deviation, the current steel pipe temperature, and the ambient temperature. The contribution of the material factor, the contribution of the tool factor, and the contribution of the environmental factor are weighted and integrated to obtain the corrugated forming quality risk value.

5. The method according to claim 1, characterized in that, The step of generating early warning information based on the plasticity risk value and the corrugation forming quality risk value includes: Obtain the welding parameters for the welding process, including welding current, welding voltage, and welding speed; The early warning assessment parameters are preprocessed, including the welding parameters, the corrugation processing parameters, and the threading processing parameters. Identify target risk patterns based on the risk pattern library and pre-processed early warning assessment parameters; Calculate the overall degree of abnormality based on the plasticity risk value and the corrugation forming quality risk value; Based on the preprocessed early warning assessment parameters, extract combinations of abnormal features; Based on the target risk pattern, the comprehensive anomaly level, and the combination of anomaly characteristics, the warning level, affected processes, potential causes, and intervention measures are extracted from the risk warning knowledge base. The warning information is generated based on the warning level, affected processes, potential causes, and intervention measures.

6. The method according to claim 5, characterized in that, The preprocessing of the early warning assessment parameters includes: The integrity of the early warning assessment parameters is verified to obtain the integrity verification result; Based on the integrity verification results, the missing data of the early warning assessment parameters is filled in. The format of the early warning assessment parameters after missing data imputation is standardized. The standardized early warning evaluation parameters are denoised to remove noise. The denoised early warning assessment parameters are time-aligned to ensure consistent data timing.

7. The method according to claim 5, characterized in that, The step of identifying target risk patterns based on the risk pattern library and preprocessed early warning assessment parameters includes: Obtain product specification information; Based on the product specification information, a target time-series feature extraction strategy is selected from the time-series feature extraction strategy library; According to the target time-series feature extraction strategy, time-series features are extracted from the preprocessed early warning evaluation parameters to obtain time-series features, which include data length, data frequency and time-series pattern. The time-series features are matched with the risk pattern library to identify the target risk pattern.

8. The method according to claim 5, characterized in that, The calculation of the overall anomaly degree based on the plasticity risk value and the corrugation forming quality risk value includes: Acquire historical risk data and current production parameters. The historical risk data includes historical plasticity risk data and historical corrugated forming quality risk data. The current production parameters include product specification information, material batch, and production line load. Adjust the risk fluctuation range based on the historical risk data and the current production parameters; The degree of welding abnormality is identified by comparing the plasticity risk value with the risk fluctuation range. The degree of abnormality in corrugated forming is identified by comparing the corrugated forming quality risk value with the risk fluctuation range. The degree of welding abnormality and the degree of corrugation forming abnormality are weighted and fused together to calculate the overall degree of abnormality.

9. The method according to claim 5, characterized in that, The step of extracting abnormal feature combinations based on the preprocessed early warning assessment parameters includes: Periodic fluctuation analysis was performed on the preprocessed early warning assessment parameters to obtain periodic fluctuation characteristics; Trend drift analysis was performed on the preprocessed early warning assessment parameters to obtain trend drift characteristics; Sudden spike analysis was performed on the preprocessed early warning assessment parameters to obtain the characteristics of sudden spikes; The abnormal feature combination is obtained by concatenating the periodic fluctuation feature, the trend drift feature, and the sudden spike feature.

10. An intelligent control system for an assembled cable manufacturing process, characterized in that, include: The process division module is used to divide the assembly cable manufacturing process into processes, namely welding process, corrugation forming process and wire threading process. The welding risk assessment module is used to assess the risk of the welding process after it is performed and to calculate the plasticity risk value. The corrugated processing parameter adjustment module is used to adjust the corrugated processing parameters according to the plasticity risk value. The corrugated processing parameters include the pressing depth and rotation speed of the forming wheel. The corrugated forming risk assessment module is used to execute the corrugated forming process according to the corrugated processing parameters, and to perform a risk assessment on the corrugated forming process according to the plasticity risk value, and to calculate the corrugated forming quality risk value. The threading processing parameter adjustment module is used to adjust the threading processing parameters according to the corrugated forming quality risk value. The threading processing parameters include the target value of the threading motor torque, the threading motor speed control curve, and the control parameters of the proportional-integral-derivative controller. The control parameters include the proportional gain, integral time, and derivative gain. The threading process execution module is used to execute the threading process according to the threading processing parameters; The early warning information generation module is used to generate early warning information based on the plasticity risk value and the corrugation forming quality risk value after the threading process is performed.

Images