A smart power control system for busbar production

Abstract

This invention discloses an intelligent power control system for busbar production, relating to the fields of power supply and distribution technology. It includes: a sensing layer for capturing power data and operating parameters, which acquires real-time information on power data and equipment operating parameters through high-precision sensors; a central control platform that receives, processes, integrates, and stores data from the sensing layer, and controls the power grid and equipment; and a scheduling model that obtains the processing time windows for each process, determines overlapping time windows, calculates the power grid load status within those overlapping time windows, and calculates the optimal scheduling state for power allocation and equipment operating parameters for each process within the overlapping time windows, combined with the production status. Through the collaborative work of sensors, the power system, and equipment, this intelligent power control system can perceive the real-time operating status of the power grid and equipment, and optimize and regulate the equipment based on a preset scheduling model and real-time data.

Description

Technical Field

[0001] This invention relates to the field of power supply and distribution technology, specifically to an intelligent power control system for busbar production. Background Technology

[0002] The overall structure of a busbar trunking system is a multi-layered, modular system. It must meet the demands of high current and safe transmission while also considering mechanical strength, thermal management, and environmental requirements. The conductor, as the core component for transmitting electrical energy, determines the busbar's transmission capacity. The busbar trunking system typically incorporates dedicated insulation materials or isolation devices. It also includes various supports, trunking connectors, seals, and joints. Under high current loads, conductors are prone to temperature rise; therefore, some busbar trunking structures incorporate heat sinks, ventilation holes, or other heat dissipation solutions. Depending on the application and requirements, busbar trunking can be broadly categorized into enclosed and open types. Enclosed structures emphasize safety and protection, suitable for high-safety-level environments; open structures facilitate heat dissipation and maintenance, and are generally used in environments with good thermal control.

[0003] Publication No. CN113922498B discloses a busbar trunking remote control system and a busbar trunking connector, belonging to the field of power distribution equipment. The busbar trunking remote control system includes a terminal and a remote control end. The terminal includes a processor I, a monitoring module, a spring-loaded module, a relay, and a communication module I. The monitoring module is used to monitor the internal status of the busbar trunking in real time; the spring-loaded module and the relay are used to control the on / off state of the power supply to the busbar trunking. The remote control end includes a processor II, a storage module, an operation module, and a communication module II. The storage module is used to store data for the processor II to read; the operation module is used for user operation to send commands to the processor II; the communication module II and the communication module I realize the data and command transmission between the terminal and the remote control end. By cooperating with the remote control end and the terminal, the on / off state of the circuit power supply can be controlled to meet the needs of users in different application scenarios.

[0004] In the production process of busbar trunking, a continuous and stable power supply must be ensured in every key link, from raw material pretreatment, rolling, forming to welding and assembly. Fluctuations in power can lead to local temperature fluctuations and unstable welding arcs, resulting in defects in the production process of busbar trunking. In addition, the processing speed of each process is inconsistent during the production process. When multiple high-power devices operate at the same time, it will affect the grid load, cause voltage fluctuations, and thus affect the stability of equipment operation. Summary of the Invention

[0005] One of the objectives of this invention is to provide an intelligent power control system for busbar production, which controls the power system of the entire busbar during the production process, realizes power dispatch, and avoids the problem of power fluctuation caused by multiple high-power devices operating at high or full power at the same time.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] An intelligent power control system for busbar trunking production includes:

[0008] The sensing layer is used to capture power data and operating parameters. The sensing layer acquires real-time information on power data and equipment operating parameters through high-precision sensors.

[0009] The data processing layer includes a central control platform and a database. The central control platform receives data from the sensing layer, processes, integrates, and stores it. The central control platform controls the power grid and equipment.

[0010] The scheduling model obtains the processing time window for each process, determines the overlapping time window and calculates the power grid load status within the overlapping time window, and calculates the optimal scheduling state of power allocation and equipment operating parameters for each process within the overlapping time window in combination with the production status.

[0011] The communication network layer connects the sensing layer and the data processing layer, transmitting sensor data to the central control platform.

[0012] The execution layer receives instructions from the central control platform and uses automated devices to control and regulate equipment and power distribution in real time.

[0013] In one or more embodiments of the present invention, a high-precision sensor outputs an analog signal, which is then conditioned to reduce noise interference and nonlinear errors. The sensing layer converts the adjusted analog signal into digital information through analog-to-digital conversion, and acquires information from multiple sensors simultaneously through a multiplexer.

[0014] In one or more embodiments of the present invention, the communication network layer adopts a hybrid topology, integrates wired and wireless transmission technologies, and performs dual-link backup. During data transmission, a verification algorithm is used to identify and correct transmission errors, and data encryption is used to prevent data from being stolen and tampered with.

[0015] In one or more embodiments of the present invention, the central control platform receives high-precision power data and equipment operating parameters transmitted from the sensing layer in real time, and simplifies the data after preprocessing.

[0016] The central control platform integrates data from various sensors, fuses and processes multi-dimensional data to form a comprehensive profile of the system's operating status. This profile is based on time, determining the changes in power data and equipment operating parameters within a time window, identifying the upper limit of the stable load of the power grid system, and matching the power load within the time window with the equipment's operating status.

[0017] In one or more embodiments of the present invention, the data simplification steps after preprocessing are as follows:

[0018] High-precision sensors collect the characteristic parameters they monitor within a fixed time window, forming a continuous data stream to generate a status profile.

[0019] The status profile uses time as the horizontal axis and feature parameters as the vertical axis to reflect the changing trends of power parameters or equipment operating status monitored by the high-precision sensor.

[0020] Based on the steps the sensors take in the production line, the data from each sensor is associated with the process to determine the corresponding production stage of the sensor.

[0021] In the process, the production status curve is divided into the processing stage and the standby stage. The production status curve is combined with the status profile to determine the processing data and standby data.

[0022] Historical data is used to identify stable characteristic parameter values ​​in standby mode as a reference benchmark, and standby data in the reference benchmark is removed.

[0023] By integrating the status profiles generated by all sensors within the same time window, a comprehensive system operation status profile is formed, reflecting the dynamic operating conditions of the entire production line or power grid.

[0024] In one or more embodiments of the present invention, the changes in characteristic parameters within a time window are predicted and calculated by combining existing state profiles and process production status:

[0025] The processing time windows of each process are uniformly divided to determine the overlapping time windows of multiple processes, that is, the working status of the equipment within the same time period.

[0026] By combining status profiles, the instantaneous changes in power load are statistically analyzed, and the critical value or stability upper limit for load matching between each process is determined.

[0027] A time series model is constructed using historical data, and the feature parameters extracted within each time window are organized into a multivariate sequence.

[0028] Feature fusion of sensor data captures the overall dynamic changes and periodic characteristics;

[0029] A time series forecasting model is used to predict the trends of power load and equipment parameter changes within each time window.

[0030] In one or more embodiments of the present invention, the steps for determining the overlap time window and calculating the power grid load status within the overlap window are as follows:

[0031] Determine the start and end times of the time window, obtain the characteristic parameters collected by the sensor in each process within the time window and the state profile of the predicted parameters based on the characteristic parameters, and identify the processing stage and standby stage of the characteristic parameters.

[0032] By comparing the processing time windows of each process, the intersection of multiple processes being in the processing state at the same time is obtained, i.e., the overlapping time window.

[0033] Real-time statistics and analysis are performed on the power consumption, load fluctuations, and peak load of the entire system within the overlapping time window. The grid load value within the overlapping time window is calculated and compared with the upper limit of the grid load in the most stable state. If it exceeds the upper limit, the overlapping time window is recorded as a high load; if it does not exceed the upper limit, the overlapping time window is recorded as stable and removed from the scheduling model.

[0034] In one or more embodiments of the present invention, optimal scheduling calculations are performed in conjunction with production status:

[0035] Obtain the production status within the high-load overlap time window, and match the power load within the overlap time window with the power demand of each process;

[0036] Under the premise of ensuring the stability of the power grid load, an optimization algorithm is used to calculate the optimal power allocation scheme and equipment operating parameters for each process.

[0037] The optimal power distribution scheme and equipment operating parameters are determined based on their impact on production.

[0038] In one or more embodiments of the present invention, the scheduling model needs to match the available power of the entire system within this overlapping window with the power demand of each process according to the actual production status of each process. The scheduling problem is modeled as a constrained optimization problem, with the power allocation of each process as a variable, the objective function constructed as the production impact value, and the objective being to minimize the overall production impact value.

[0039] In one or more embodiments of the present invention, the execution layer adjusts the equipment and power distribution according to the optimal power distribution scheme and equipment operating parameters.

[0040] Through the above technical solution, the present invention has the following beneficial effects:

[0041] 1. This application utilizes the collaborative work of sensors, power systems, and equipment to enable the intelligent power control system to perceive the real-time operating status of the power grid and equipment. Based on a preset scheduling model and real-time data, it optimizes and regulates the equipment to ensure a stable and efficient power supply in complex and ever-changing production environments, thereby improving product quality, reducing energy consumption, and ensuring production safety.

[0042] 2. By generating state profiles and constructing fluctuation curves that change over time, the data is divided into two main states: processing and standby. This not only improves data processing efficiency but also extracts key information from massive amounts of data that is truly helpful in judging system status and optimizing scheduling. This provides a solid data foundation for the real-time monitoring, early warning, and dynamic control of intelligent power control systems.

[0043] 3. The scheduling model constructs a closed-loop control mechanism based on real-time production and grid status through time window analysis, dynamic load calculation, and multi-device collaborative optimization. This mechanism ensures both the continuity and quality of production and the stable operation of the power grid.

[0044] Other features and advantages of the invention will be set forth in the description which follows, 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 written description and the accompanying drawings. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of the intelligent power control system of the present invention. Detailed Implementation

[0046] The following describes several embodiments of the present invention with reference to the accompanying drawings. For clarity, many practical details will be described in the following description. However, it should be understood that these practical details are not intended to limit the invention. That is, in some embodiments of the invention, these practical details are not essential. And features of different embodiments may be interchanged if feasible.

[0047] Unless otherwise defined, all terms used herein (including technical and scientific terms) have their ordinary meanings, which are understandable to those skilled in the art. Furthermore, the definitions of the foregoing terms in commonly used dictionaries should be interpreted in the context of this specification as having the meaning consistent with the relevant field of this invention. Unless specifically defined, these terms will not be construed as having idealized or overly formal meanings.

[0048] See Figure 1As shown, the present invention provides an intelligent power control system for busbar production, which controls the power system of the entire busbar during the production process, realizes power dispatch, and avoids the problem of power fluctuation caused by multiple high-power devices operating at high or full power at the same time.

[0049] Intelligent power control systems include:

[0050] The sensing layer is used to capture power data and operating parameters. The sensing layer acquires real-time information on power data and equipment operating parameters through high-precision sensors.

[0051] The data processing layer includes a central control platform and a database. The central control platform receives data from the sensing layer, processes, integrates, and stores it. The central control platform controls the power grid and equipment.

[0052] The scheduling model obtains the processing time window for each process, determines the overlapping time window and calculates the power grid load status within the overlapping time window, and calculates the optimal scheduling state of power allocation and equipment operating parameters for each process within the overlapping time window in combination with the production status.

[0053] The communication network layer connects the sensing layer and the data processing layer, transmitting sensor data to the central control platform.

[0054] The execution layer receives instructions from the central control platform and uses automated devices to control and regulate equipment and power distribution in real time.

[0055] In one feasible approach, a scheduling model is used to achieve dynamic balancing of the power grid load, ensuring that each process operates under optimal power allocation, determining the upper limit of the most stable state of the entire power grid load, and determining the power status in each time window, thereby avoiding equipment failures and production interruptions caused by power overload.

[0056] When the power status of each time window exceeds the upper limit of the most stable grid load, the operating status of the equipment within that time window is determined. Since the equipment does not need to operate at high power or full power at all times while it is in continuous operation, scheduling and optimizing the operating status of the equipment can reduce the peak load of the grid and maintain the stability of the grid operation.

[0057] In one embodiment, a high-precision sensor outputs an analog signal, which is then conditioned to reduce noise interference and nonlinear errors. The sensing layer converts the adjusted analog signal into digital information via analog-to-digital conversion, and a multiplexer simultaneously acquires information from multiple sensors.

[0058] In one feasible approach, the type of high-precision sensor is determined based on the power data to be monitored and the equipment operating parameters, and a redundant design is employed to avoid monitoring failure due to the failure of a single sensor.

[0059] The perception layer can accurately and in real time capture power parameters and equipment operating status during the process, providing a reliable foundation and data support for lower-level data processing, intelligent decision-making and automatic control.

[0060] In one embodiment, the communication network layer adopts a hybrid topology, integrating wired and wireless transmission technologies and performing dual-link backup. During data transmission, a verification algorithm is used to identify and correct transmission errors, and data encryption is used to prevent data from being stolen and tampered with.

[0061] In one feasible approach, the communication network layer securely, quickly, and accurately transmits the high-precision data acquired by the perception layer to the central control platform, enabling the data processing layer to perform analysis, scheduling, and control based on real-time data, thereby achieving intelligent management and dynamic optimization of the entire power system.

[0062] In one embodiment, the central control platform receives high-precision power data and equipment operating parameters transmitted from the sensing layer in real time, and simplifies the data after preprocessing.

[0063] The central control platform integrates data from various sensors, fuses and processes multi-dimensional data to form a comprehensive profile of the system's operating status. This profile is based on time, determining the changes in power data and equipment operating parameters within a time window, identifying the upper limit of the stable load of the power grid system, and matching the power load within the time window with the equipment's operating status.

[0064] In one feasible approach, data from various sensors are integrated and matched with the power load and equipment operating status within a time window. Intelligent algorithms are used to predict future load change trends and determine whether the stable load limit of the power grid system will be reached under normal operating conditions within that time window.

[0065] To further reduce the computational burden on the central control platform, data is simplified through status profiling, key feature parameters are extracted, redundant information is reduced, and data processing efficiency is improved. Furthermore, while ensuring accurate scheduling of power distribution and equipment operation status, the response speed of the central control platform is accelerated.

[0066] In one embodiment, the data simplification steps after preprocessing are as follows:

[0067] High-precision sensors collect the characteristic parameters they monitor within a fixed time window, forming a continuous data stream to generate a status profile.

[0068] The status profile uses time as the horizontal axis and feature parameters as the vertical axis to reflect the changing trends of power parameters or equipment operating status monitored by the high-precision sensor.

[0069] Based on the steps the sensors take in the production line, the data from each sensor is associated with the process to determine the corresponding production stage of the sensor.

[0070] In the process, the production status curve is divided into the processing stage and the standby stage. The production status curve is combined with the status profile to determine the processing data and standby data.

[0071] Historical data is used to identify stable characteristic parameter values ​​in standby mode as a reference benchmark, and standby data in the reference benchmark is removed.

[0072] By integrating the status profiles generated by all sensors within the same time window, a comprehensive system operation status profile is formed, reflecting the dynamic operating conditions of the entire production line or power grid.

[0073] In one feasible approach, the bulky data acquired by sensors is simplified by profiling the system's operational status, thereby improving the data processing efficiency of the central control platform. For the production process, the production status is divided into processing stage and standby stage, and the data characteristics of each stage are accurately identified.

[0074] For example, taking the welding of busbar trunking as an example, in the automated welding process, the laser welding process is the processing stage, while the cooling of the laser welding equipment and the transportation process of the busbar trunking are the standby stage. The processing stage and the standby stage are clearly separated, and when simplifying the data, the data that affects the stability of the power grid is retained.

[0075] In another embodiment, the judgment is made based on the fluctuation of feature parameters in the state profile:

[0076] Processing curve: The values ​​fluctuate greatly, reflecting the dynamic changes during equipment startup, operation, and processing.

[0077] Standby curve: The value is stable and represents the baseline parameters when the device is in a static or low-load state.

[0078] During the data simplification process, data that is in standby mode (i.e., unrelated to production and processing) and noisy data that is unrelated to core characteristic parameters are removed to reduce the total amount of data. At the same time, it is ensured that subsequent decisions are based only on data that has a critical impact on power load and equipment status.

[0079] In one embodiment, the changes in characteristic parameters within a time window are predicted and calculated by combining existing state profiles and process production status:

[0080] The processing time windows of each process are uniformly divided to determine the overlapping time windows of multiple processes, that is, the working status of the equipment within the same time period.

[0081] By combining status profiles, the instantaneous changes in power load are statistically analyzed, and the critical value or stability upper limit for load matching between each process is determined.

[0082] A time series model is constructed using historical data, and the feature parameters extracted within each time window are organized into a multivariate sequence.

[0083] Feature fusion of sensor data captures the overall dynamic changes and periodic characteristics;

[0084] A time series forecasting model is used to predict the trends of power load and equipment parameter changes within each time window.

[0085] In one feasible approach, by predicting the changes in power load and equipment parameters over a period of time, it is possible to determine whether the power load may exceed the stable upper limit or whether the equipment may be overloaded during that period. This serves as the basis for the scheduling model to allocate power to each process and adjust equipment operating parameters through overlapping time windows.

[0086] Furthermore, since the power load of the equipment is basically fixed during the processing and standby phases, the total power load within the time window can be obtained simply by considering the duration of the processing and standby phases. By combining the processing and standby phases with the state profile in the form of production state curves, the power load corresponding to each time node within the time window can be determined.

[0087] In one embodiment, the steps for determining the overlap time window and calculating the grid load status within the overlap window are as follows:

[0088] Determine the start and end times of the time window, obtain the characteristic parameters collected by the sensor in each process within the time window and the state profile of the predicted parameters based on the characteristic parameters, and identify the processing stage and standby stage of the characteristic parameters.

[0089] By comparing the processing time windows of each process, the intersection of multiple processes being in the processing state at the same time is obtained, i.e., the overlapping time window.

[0090] Real-time statistics and analysis are performed on the power consumption, load fluctuations, and peak load of the entire system within the overlapping time window. The grid load value within the overlapping time window is calculated and compared with the upper limit of the grid load in the most stable state. If it exceeds the upper limit, the overlapping time window is recorded as a high load; if it does not exceed the upper limit, the overlapping time window is recorded as stable and removed from the scheduling model.

[0091] In one feasible approach, overlapping time windows are determined and filtered. Overlapping time windows that do not exceed the upper limit are eliminated, while those that exceed the upper limit are retained. For overlapping time windows that exceed the upper limit, power allocation and equipment operating parameters are readjusted to ensure that the system can maintain stable operation under peak load and avoid power fluctuations affecting processing quality.

[0092] In one embodiment, optimal scheduling is calculated based on production status:

[0093] Obtain the production status within the high-load overlap time window, and match the power load within the overlap time window with the power demand of each process;

[0094] Under the premise of ensuring the stability of the power grid load, an optimization algorithm is used to calculate the optimal power allocation scheme and equipment operating parameters for each process.

[0095] The optimal power distribution scheme and equipment operating parameters are determined based on their impact on production.

[0096] In one feasible approach, the production impact value is determined based on changes in the production state; that is, the smaller the impact of the optimal power distribution scheme and equipment operating parameters on the production state, the smaller the production impact value, and the greater the impact on the production state, the greater the production impact value.

[0097] The scheduling model constructs a closed-loop control mechanism based on real-time production and grid status through time window analysis, dynamic load calculation, and multi-device collaborative optimization. This mechanism ensures both the continuity and quality of production and the stable operation of the power grid.

[0098] In one embodiment, the scheduling model needs to match the available power of the entire system within this overlapping window with the power demand of each process based on the actual production status of each process. The scheduling problem is modeled as a constrained optimization problem, with the power allocation of each process as a variable, and the objective function is constructed as the production impact value. The goal is to minimize the overall production impact value.

[0099] In one embodiment, the objective function is:

[0100]

[0101] Where, x i y represents the power allocation for the i-th process within the overlapping window. i This indicates the key operating parameters (process speed or temperature) of the corresponding equipment, while Impact i It is based on the production impact value function (empirical function or curve obtained by fitting historical data) to represent the impact on production efficiency, product quality or delivery time when equipment parameters deviate from the ideal state.

[0102] Total grid load constraint: The total power allocated to all processes cannot exceed the grid's stable load limit within this window.

[0103] Minimum power requirement constraint for each process: The power allocation for each process must meet the basic processing requirements to ensure that production does not stop due to insufficient power.

[0104] Equipment operating range constraints: The operating parameters of each piece of equipment (such as machine speed, temperature, etc.) can only change within a certain safe range.

[0105] The constraints include:

[0106]

[0107] x i ≥ximin, x i ≤ximax y i ∈ category i;

[0108] N represents the total number of processes involved in the scheduling. The indices i from 1 to N represent each individual process.

[0109] P max This represents the maximum stable power load allowed by the power grid within the overlapping time window, which is the upper limit of the total power allocation of the entire system during that time period. This constraint ensures that the total allocated power will not exceed the upper limit of the grid's safe load.

[0110] ximin and ximax represent the minimum and maximum power allocation values ​​allowed for the i-th process, respectively.

[0111] ximin is the minimum power required to ensure the basic processing requirements of this process.

[0112] ximax is the maximum power allowed by the equipment or process, preventing equipment malfunctions or product quality problems due to overload.

[0113] y i ∈ category i represents the operating parameters of the i-th process.

[0114] y i The value must be taken from a predefined allowed domain or set, which defines the acceptable range of operating parameters for the equipment in this process under safe and stable conditions. For example, y i If the value represents a temperature parameter, it must vary within the temperature range specified by the manufacturer and the process requirements.

[0115] Under the condition that all constraints are met (total power does not exceed P) max Under the premise that the power allocation of each process is within its allowable range and the equipment operating parameters are within a reasonable range, by selecting an appropriate x iand y i This minimizes the total production impact of all processes, which means minimizing the overall production cost or negative impact.

[0116] In one embodiment, the execution layer adjusts the equipment and power distribution based on the optimal power distribution scheme and equipment operating parameters.

[0117] Although the present invention has been disclosed in conjunction with the above embodiments, it is not intended to limit the present invention. Any person skilled in the art can make various modifications and refinements without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention should be defined by the appended claims.

Claims

1. An intelligent power control system for busbar trunking production, characterized in that, include: The sensing layer is used to capture power data and operating parameters. The sensing layer acquires real-time information on power data and equipment operating parameters through high-precision sensors. The data processing layer includes a central control platform and a database. The central control platform receives data from the sensing layer, processes, integrates, and stores it. The central control platform controls the power grid and equipment. The scheduling model obtains the processing time window for each process, determines the overlapping time window and calculates the power grid load status within the overlapping time window, and calculates the optimal scheduling state of power allocation and equipment operating parameters for each process within the overlapping time window in combination with the production status. The communication network layer connects the sensing layer and the data processing layer, transmitting sensor data to the central control platform. The execution layer receives instructions from the central control platform and uses automated devices to control and regulate equipment and power distribution in real time. The central control platform receives high-precision power data and equipment operating parameters transmitted from the sensing layer in real time, and simplifies the data after preprocessing. The central control platform integrates data from various sensors, fuses and processes multi-dimensional data to form a comprehensive system operation status profile. The status profile is established based on time, determines the changes in power data and equipment operating parameters within a time window, determines the upper limit of stable load of the power grid system, and matches the power load within the time window with the equipment operation status. The data simplification steps after preprocessing are as follows: High-precision sensors collect the characteristic parameters they monitor within a fixed time window, forming a continuous data stream to generate a status profile. The status profile uses time as the horizontal axis and feature parameters as the vertical axis to reflect the changing trends of power parameters or equipment operating status monitored by the high-precision sensor. Based on the steps the sensors take in the production line, the data from each sensor is associated with the process to determine the corresponding production stage of the sensor. In the process, the production status curve is divided into the processing stage and the standby stage. The production status curve is combined with the status profile to determine the processing data and standby data. Historical data is used to identify stable characteristic parameter values ​​in standby mode as a reference benchmark, and standby data in the reference benchmark is removed. By integrating the status profiles generated by all sensors within the same time window, a comprehensive system operation status profile is formed, reflecting the dynamic operating conditions of the entire production line or power grid.

2. The intelligent power control system for busbar production according to claim 1, characterized in that, The high-precision sensor outputs an analog signal, which is then conditioned to reduce noise interference and nonlinear errors. The sensing layer converts the adjusted analog signal into digital information through analog-to-digital conversion, and acquires information from multiple sensors simultaneously through a multiplexer.

3. The intelligent power control system for busbar production according to claim 2, characterized in that, The communication network layer adopts a hybrid topology, integrating wired and wireless transmission technologies and implementing dual-link backup. During data transmission, verification algorithms are used to identify and correct transmission errors, and data encryption is employed to prevent data theft and tampering.

4. The intelligent power control system for busbar production according to claim 3, characterized in that, Based on existing status profiles and process production status, predictive calculations are performed on the changes in feature parameters within the time window: The processing time windows of each process are uniformly divided to determine the overlapping time windows of multiple processes, that is, the working status of the equipment within the same time period. By combining status profiles, the instantaneous changes in power load are statistically analyzed, and the critical value or stability upper limit for load matching between each process is determined. A time series model is constructed using historical data, and the feature parameters extracted within each time window are organized into a multivariate sequence. Feature fusion of sensor data captures the overall dynamic changes and periodic characteristics; A time series forecasting model is used to predict the trends of power load and equipment parameter changes within each time window.

5. The intelligent power control system for busbar production according to claim 4, characterized in that, The steps for determining the overlap time window and calculating the power grid load status within the overlap window are as follows: Determine the start and end times of the time window, obtain the characteristic parameters collected by the sensor in each process within the time window and the state profile of the predicted parameters based on the characteristic parameters, and identify the processing stage and standby stage of the characteristic parameters. By comparing the processing time windows of each process, the intersection of multiple processes being in the processing state at the same time is obtained, i.e., the overlapping time window. Real-time statistics and analysis are performed on the power consumption, load fluctuations, and peak load of the entire system within the overlapping time window. The grid load value within the overlapping time window is calculated and compared with the upper limit of the grid load in the most stable state. If it exceeds the upper limit, the overlapping time window is recorded as a high load; if it does not exceed the upper limit, the overlapping time window is recorded as stable and removed from the scheduling model.

6. The intelligent power control system for busbar production according to claim 5, characterized in that, Optimal scheduling calculations are performed based on production status: Obtain the production status within the high-load overlap time window, and match the power load within the overlap time window with the power demand of each process; Under the premise of ensuring the stability of the power grid load, an optimization algorithm is used to calculate the optimal power allocation scheme and equipment operating parameters for each process. The optimal power distribution scheme and equipment operating parameters are determined based on their impact on production.

7. The intelligent power control system for busbar production according to claim 6, characterized in that, The scheduling model needs to match the available power of the entire system within this overlapping window with the power demand of each process based on the actual production status of each process. The scheduling problem is modeled as a constrained optimization problem, with the power allocation of each process as a variable, and the objective function constructed as the production impact value. The goal is to minimize the overall production impact value.

8. The intelligent power control system for busbar production according to claim 7, characterized in that, The execution layer adjusts the equipment and power distribution based on the optimal power distribution scheme and equipment operating parameters.

Images