Intelligent reconfigurable modular smelting control method and system

Abstract

The embodiment of the invention provides an intelligent reconfigurable modular smelting control method and system, and belongs to the technical field of metallurgical industry automation. The system comprises a central controller module used for module identification and control strategy generation; the independent process module comprises an embedded identity recognition chip sub-module and an intelligent regulator sub-module; the embedded identity recognition chip sub-module is used for storing a module unique identifier, a process parameter range and compatibility data; the intelligent regulator sub-module is used for receiving an instruction of the central controller module and dynamically regulating power, temperature and pressure parameters; the distributed communication network module is used for monitoring data streams among the modules on line; and the digital twin prediction engine module is used for integrating the online operation data of the physical equipment and the virtual simulation model, predicting the abnormal event of the equipment through dynamic comparison, and generating a maintenance instruction queue. According to the invention, rapid switching of the modules and temperature fluctuation control are realized, non-planned shutdown is reduced, and the smelting level is improved.

Description

Technical Field

[0001] This application relates to the field of automation technology in the metallurgical industry, and in particular to an intelligent, reconfigurable, modular smelting control method and system. Background Technology

[0002] In the metallurgical industry, traditional smelting systems generally employ fixed equipment layouts and rigid control architectures. Existing smelting equipment lacks modular reconfiguration capabilities; most equipment uses integrated designs or limited modular combinations, severely restricting production line flexibility. When multiple modules operate collaboratively, traditional systems employ a master-slave control mode, resulting in significant efficiency losses. Data silos are prevalent, with each module operating independently, leading to synchronization delays of 8-12 seconds for key parameters (such as molten pool temperature and pressure). This delay not only affects production efficiency but can also cause serious safety hazards. Current equipment health management relies primarily on periodic inspections and reactive maintenance, a passive approach that leads to frequent unplanned downtime. Therefore, traditional smelting systems have deficiencies in dynamic module reconfiguration, intelligent collaborative control, and predictive maintenance. Summary of the Invention

[0003] The main objective of this application is to provide an intelligent, reconfigurable, modular smelting control method and system.

[0004] The technical solution adopted in this invention is:

[0005] On one hand, embodiments of the present invention provide an intelligent reconfigurable modular smelting control system, which includes a central controller module, an independent process module, a distributed communication network module, and a digital twin prediction engine module.

[0006] The central controller module is responsible for module identification and control strategy generation.

[0007] The independent process module includes an embedded identity recognition chip sub-module and an intelligent regulator sub-module;

[0008] The embedded identity recognition chip sub-module is used to store the module's unique identifier, process parameter range, and compatibility data.

[0009] The intelligent regulator submodule is used to receive instructions from the central controller module and dynamically adjust power, temperature, and pressure parameters.

[0010] The distributed communication network module is used for online monitoring of data flow between modules;

[0011] The digital twin prediction engine module is used to integrate online operating data of physical equipment with virtual simulation models, predict abnormal events of equipment through dynamic comparison, and generate a maintenance instruction queue.

[0012] Furthermore, the central controller module includes a radio frequency identification scanning unit, a one-click reconstruction interface, an adaptive fuzzy PID controller submodule, and a control scheme generator submodule;

[0013] The radio frequency identification scanning unit is used to automatically identify the type of the connected independent process module;

[0014] The one-click reconfiguration interface is used to provide a smelting process template library and load parameter configuration sets;

[0015] The adaptive fuzzy PID controller submodule is used to dynamically adjust the weights of the control parameters;

[0016] The control scheme generator submodule is used to generate control strategies based on the module function code.

[0017] Furthermore, the adaptive fuzzy PID controller submodule uses the following formula when dynamically adjusting the control parameter weights:

[0018]

[0019] Among them, K p (t) represents the dynamically adjusted PID proportional term coefficient; K p0 α is the preset basic proportional coefficient; α is the temperature fluctuation correction factor; |ΔT| is the absolute deviation between the target temperature and the actual temperature during smelting.

[0020] Furthermore, the independent process module also includes a plug-and-play protocol interface;

[0021] The plug-and-play protocol interface is used to complete registration, parameter matching, and control loop initialization after the access module is connected.

[0022] Furthermore, the distributed communication network module includes a topology reconstruction protocol, a data flow monitoring unit, and an anomaly self-healing mechanism;

[0023] The topology reconfiguration protocol is used to automatically reallocate tasks when modules are added or removed;

[0024] The data stream monitoring unit is used to monitor the communication status between modules online.

[0025] The anomaly self-healing mechanism is used to migrate the tasks of the faulty module to the backup module and call the digital twin model to generate a set of compensation parameters.

[0026] Furthermore, the digital twin prediction engine module includes a health assessment unit, a lifespan prediction unit, and a strategy verification unit;

[0027] The health assessment unit is used to calculate the equipment health index and monitor the equipment degradation status;

[0028] The lifetime prediction unit is used to analyze time-series degradation data;

[0029] The strategy verification unit is used to perform Monte Carlo simulation in a virtual environment to verify the feasibility of the control strategy.

[0030] Furthermore, the formula used by the health assessment unit when calculating the equipment health index includes:

[0031]

[0032] Where HIS stands for Health Index; n represents the total number of key performance parameters; w i S is the weighting coefficient for the i-th key performance parameter; current,i S represents the current measured value of the i-th key performance parameter; initial,i This is the initial baseline value for the i-th key performance parameter.

[0033] On the other hand, embodiments of the present invention also provide an intelligent reconfigurable modular smelting control method, for implementation through the intelligent reconfigurable modular smelting control system as described above, the method comprising the following steps:

[0034] Intelligent and reconfigurable modular smelting control is achieved through a central controller module, independent process modules, distributed communication network modules, and digital twin prediction engine modules.

[0035] On the other hand, embodiments of the present invention also provide an intelligent reconfigurable modular smelting control device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the intelligent reconfigurable modular smelting control method as described above.

[0036] On the other hand, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions for causing a computer to execute the intelligent reconfigurable modular smelting control method as described above.

[0037] The embodiments of this application include at least the following beneficial effects: This application provides an intelligent, reconfigurable, modular smelting control method and system. The invention includes a central controller module responsible for module identification and control strategy generation; independent process modules, including an embedded identification chip submodule and an intelligent regulator submodule; the embedded identification chip submodule stores the module's unique identifier, process parameter range, and compatibility data; the intelligent regulator submodule receives instructions from the central controller module and dynamically adjusts power, temperature, and pressure parameters; a distributed communication network module monitors data flow between modules online; and a digital twin prediction engine module integrates online operating data of physical equipment with a virtual simulation model, predicts equipment anomalies through dynamic comparison, and generates a maintenance instruction queue. This invention achieves rapid module switching, temperature fluctuation control, and reduced unplanned downtime, thereby improving the level of smelting. Attached Figure Description

[0038] Figure 1 This is a schematic diagram of the intelligent reconfigurable modular smelting control system provided in an embodiment of the present invention;

[0039] Figure 2 This is a schematic diagram illustrating the module composition and functions of the intelligent reconfigurable modular smelting control system provided in an embodiment of the present invention.

[0040] Figure 3 This is a schematic diagram of the rapid module reconfiguration process provided in an embodiment of the present invention;

[0041] Figure 4 This is a schematic diagram of the temperature fluctuation control mechanism provided in an embodiment of the present invention;

[0042] Figure 5 This is a schematic diagram of the predictive maintenance process provided in an embodiment of the present invention. Detailed Implementation

[0043] 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. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0044] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0045] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0047] This invention provides an intelligent, reconfigurable, modular smelting control system. The system includes a central controller module, multiple independent process modules, a distributed communication network module, and a digital twin prediction engine module. The central controller module automatically scans and identifies the types of independent process modules using radio frequency identification (RFID) and generates an adapted control scheme. Each independent process module has a built-in embedded identification chip submodule and an intelligent regulator submodule, supporting plug-and-play protocols and completing parameter matching and control loop initialization within 30 seconds. The distributed communication network module monitors the data flow in real time and triggers a topology reconfiguration protocol to dynamically allocate tasks. The digital twin prediction engine module integrates real-time data and a virtual simulation model, predicts the remaining lifespan (RUL) of the equipment through an LSTM network, and generates maintenance instructions. This invention solves the problems of low module reconfiguration efficiency, lagging collaborative control, and passive maintenance in traditional systems, achieving rapid module switching, temperature fluctuation control (±5℃), and a 60% reduction in unplanned downtime, significantly improving the flexibility and intelligence of smelting production.

[0048] The embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0049] On one hand, embodiments of the present invention provide an intelligent, reconfigurable, modular smelting control system, with reference to... Figure 1 and Figure 2 The intelligent and reconfigurable modular smelting control system includes a central controller module, an independent process module, a distributed communication network module, and a digital twin prediction engine module.

[0050] The central controller module is responsible for module identification and control strategy generation;

[0051] The independent process module includes an embedded identity recognition chip sub-module and an intelligent regulator sub-module;

[0052] The embedded identity recognition chip submodule is used to store the module's unique identifier, process parameter range, and compatibility data.

[0053] The intelligent regulator submodule is used to receive instructions from the central controller module and dynamically adjust power, temperature, and pressure parameters;

[0054] The distributed communication network module is used for online monitoring of data flow between modules;

[0055] The digital twin prediction engine module integrates online operating data of physical equipment with virtual simulation models, predicts abnormal events of equipment through dynamic comparison, and generates a maintenance instruction queue.

[0056] The central controller module disclosed in this embodiment of the invention includes a radio frequency identification scanning unit, a one-click reconstruction interface, an adaptive fuzzy PID controller submodule, and a control scheme generator submodule;

[0057] The radio frequency identification (RFID) scanning unit is used to automatically identify the type of the connected independent process module;

[0058] The one-click reconfiguration interface is used to provide a smelting process template library and load parameter configuration sets;

[0059] The adaptive fuzzy PID controller submodule is used to dynamically adjust the weights of control parameters;

[0060] The control scheme generator submodule is used to generate control strategies based on the module's functional code.

[0061] As an optional implementation, the RFID scanning unit of this embodiment of the invention can automatically identify the type of independent process module accessed, such as a melting process module or a refining process module. The RFID scanning unit reads parameters from the embedded identification chip submodule of the independent process module, such as temperature range and power limit.

[0062] The one-click reconfiguration interface of this invention has a built-in preset process template library (melting, electrolysis, alloying templates). After the user selects a template, the corresponding module is automatically activated and the parameter configuration set is loaded.

[0063] The adaptive fuzzy PID controller submodule of this invention can dynamically adjust the control parameter weights (such as PID gain) and ensure temperature fluctuation ≤ ±5℃ by correcting the real-time temperature difference in response to the correction factor.

[0064] The control scheme generator of this invention generates adapted control logic (such as heating curves and pressure thresholds) based on the module function code.

[0065] The adaptive fuzzy PID controller submodule disclosed in this invention uses the following formula when dynamically adjusting the control parameter weights:

[0066]

[0067] Among them, K p (t) represents the dynamically adjusted PID proportional term coefficient; K p0 α is the preset basic proportional coefficient; α is the temperature fluctuation correction factor; |ΔT| is the absolute deviation between the target temperature and the actual temperature during smelting.

[0068] The independent process module disclosed in this embodiment of the invention also includes a plug-and-play protocol interface;

[0069] The plug-and-play protocol interface is used to complete registration, parameter matching, and control loop initialization after the module is connected.

[0070] The distributed communication network module disclosed in this invention includes a topology reconstruction protocol, a data flow monitoring unit, and an anomaly self-healing mechanism;

[0071] Topology reconfiguration protocols are used to automatically reallocate tasks when modules are added or removed;

[0072] The data flow monitoring unit is used to monitor the communication status between modules online;

[0073] The anomaly self-healing mechanism is used to migrate the tasks of the faulty module to the backup module and call the digital twin model to generate a set of compensation parameters.

[0074] As an optional implementation, the distributed communication network module of this embodiment of the invention enables efficient data interaction between modules and dynamic system reconfiguration. The topology reconfiguration protocol can automatically reallocate tasks when modules are added or removed, for example, assigning current control after adding an electrolysis module. The topology reconfiguration protocol can also avoid the synchronization delay of the traditional master-slave mode (reducing it from 8-12 seconds to milliseconds).

[0075] The data flow monitoring unit can monitor the communication status between modules in real time, such as data transmission delay and packet loss rate.

[0076] The anomaly self-healing mechanism can migrate the tasks of the faulty module to the backup module (e.g., switch to the redundant module when the temperature sensor fails); and call the digital twin to generate compensation parameters (such as the pressure compensation coefficient).

[0077] The digital twin prediction engine module disclosed in this embodiment of the invention includes a health assessment unit, a lifespan prediction unit, and a strategy verification unit;

[0078] The health assessment unit is used to calculate the equipment health index and monitor the equipment's degradation status;

[0079] The lifetime prediction unit is used to analyze time-series degradation data;

[0080] The strategy verification unit is used to perform Monte Carlo simulations in a virtual environment to verify the feasibility of control strategies.

[0081] The health assessment unit disclosed in this embodiment of the invention uses the following formula when calculating the equipment health index:

[0082]

[0083] Where HIS stands for Health Index; n represents the total number of key performance parameters; w i S is the weighting coefficient for the i-th key performance parameter; current,i S represents the current measured value of the i-th key performance parameter; initial,i This is the initial baseline value for the i-th key performance parameter.

[0084] In some embodiments, key performance parameters include temperature, vibration, energy consumption, etc.

[0085] As an optional implementation, this embodiment of the invention utilizes radio frequency identification (RFID) and a topology reconfiguration protocol to achieve rapid module identification and self-organizing communication networks. The adaptive fuzzy PID controller submodule dynamically adjusts control parameters based on the process coupling degree of the current module combination. The digital twin prediction engine module integrates real-time operating data of the physical equipment with a virtual simulation model, dynamically compares and predicts abnormal equipment events, and generates a maintenance instruction queue.

[0086] Traditional smelting systems suffer from serious deficiencies in dynamic module reconfiguration, intelligent collaborative control, and predictive maintenance. Specifically, these deficiencies manifest as a lack of plug-and-play module capabilities, insufficient adaptive communication networks, rigid control strategies, and lagging equipment health management. This invention addresses these problems through technologies such as radio frequency identification (RFID) and topology reconfiguration protocols, intelligent regulators, adaptive fuzzy PID controllers, and digital twin predictive engines.

[0087] The intelligent, reconfigurable, modular smelting control system of this invention includes: a central controller module with a built-in radio frequency identification (RFID) scanning unit for automatically identifying the types of connected process modules and generating an appropriate control scheme based on the module's function code; multiple independent process modules, each equipped with an embedded identification chip submodule that stores the module's unique functional identifier, process parameter range, and compatibility data; and an intelligent regulator submodule configured to receive command signals from the central controller and dynamically adjust output power, temperature, and pressure parameters; a distributed communication network module that monitors the data flow between modules in real time and triggers a topology reconfiguration protocol when modules are added or removed, automatically reallocating control tasks; and a digital twin prediction engine module that integrates real-time operating data of physical equipment with a virtual simulation model, predicts abnormal equipment events through dynamic comparison, and generates a maintenance command queue.

[0088] For example, the central controller module automatically identifies the type of connected process modules using a radio frequency identification (RFID) scanning unit and generates an appropriate control scheme based on the module's function code. The embedded identification chip submodule of each independent process module stores the module's unique functional identifier, process parameter range, and compatibility data. The intelligent regulator submodule of each independent process module receives command signals from the central controller module and dynamically adjusts output power, temperature, and pressure parameters. The distributed communication network module monitors the data flow between modules in real time, triggering a topology reconfiguration protocol when modules are added or removed, automatically reallocating control tasks. The digital twin prediction engine module predicts equipment anomalies through dynamic comparison and generates a maintenance command queue.

[0089] The technical solution of this application achieves rapid module identification and self-organizing communication networks through radio frequency identification (RFID) and topology reconfiguration protocols. The adaptive fuzzy PID controller submodule dynamically adjusts control parameters based on the process coupling degree of the current module combination, ensuring that system temperature fluctuations do not exceed ±5℃, thus solving the problem of rigid control strategies. The digital twin prediction engine module predicts equipment anomaly events through dynamic comparison and generates a maintenance instruction queue, effectively addressing the shortcomings of traditional smelting systems in terms of dynamic module reconfiguration, intelligent collaborative control, and predictive maintenance.

[0090] As an optional implementation, this embodiment of the invention also proposes that the central controller module is equipped with a one-click reconfiguration interface of a preset smelting process template library, including smelting, refining, and alloying templates. After the user selects a template, the corresponding module is automatically activated and the parameter configuration set is loaded.

[0091] The digital twin prediction engine module includes a health assessment unit, a lifespan prediction unit, and a strategy verification unit. The health assessment unit calculates the Health Index (HIS) based on historical equipment operating data, using the following formula:

[0092]

[0093] Where HIS stands for Health Index; n represents the total number of key performance parameters; w i S is the weighting coefficient for the i-th key performance parameter; current,i S represents the current measured value of the i-th key performance parameter; initial,i This is the initial baseline value for the i-th key performance parameter.

[0094] The lifetime prediction unit uses a Long Short-Term Memory (LSTM) network to process temporal degradation data and outputs a probability distribution of the remaining lifetime (RUL). The policy verification unit performs Monte Carlo simulation of the control policy in a virtual environment, and synchronizes it to the physical device after successful verification.

[0095] The technical solution of this application utilizes a one-click reconfiguration interface of a pre-set smelting process template library. This allows the system to automatically activate the corresponding process module and load its parameter configuration set after the user selects a specific smelting process template, greatly improving operational convenience and efficiency. The central controller module can quickly switch and configure different smelting modules according to different process requirements, reducing the complexity and error rate of manual operation.

[0096] The health assessment unit calculates the current health index (HIS) of the equipment based on its historical operating data, enabling real-time monitoring of its operational status. The lifespan prediction unit utilizes a Long Short-Term Memory (LSTM) network to process the equipment's temporal degradation data, accurately predicting the equipment's remaining useful life (RUL) and providing a scientific basis for maintenance and replacement. The strategy verification unit ensures the safety and effectiveness of the formulated control strategies in practical applications through Monte Carlo simulations of the control strategies in a virtual environment.

[0097] The health assessment unit can be implemented by collecting key performance parameters of the equipment under different operating conditions and calculating a health index through weighted summation. The lifespan prediction unit can train a long short-term memory network model to identify temporal patterns of equipment degradation, thereby predicting the remaining lifespan of the equipment. The strategy verification unit can simulate various possible operating scenarios in a virtual simulation environment, verifying the reliability and effectiveness of the control strategy through extensive Monte Carlo simulations.

[0098] Therefore, the technical solution provided in this application not only improves the operational efficiency and flexibility of the smelting system, but also achieves equipment health monitoring and lifespan prediction through a digital twin prediction engine, further ensuring the stability and safety of the system. Compared with traditional technologies, the solution in this application has significant advantages in terms of rapid module switching, automatic parameter configuration, equipment status monitoring, and control strategy verification.

[0099] As an optional implementation, this embodiment of the invention also proposes that: the access and registration of independent process modules are achieved through a plug-and-play protocol interface. After the identification chip of the new module sends a registration request to the central controller module, parameter matching and control loop initialization are completed within 30 seconds. The central controller module has a built-in adaptive fuzzy PID controller submodule, which dynamically adjusts the control parameter weights according to the process coupling degree of the current module combination, satisfying: Where α is the temperature fluctuation correction factor and ΔT is the real-time temperature difference, used to maintain the system temperature fluctuation within ±5℃.

[0100] This application employs a plug-and-play protocol interface, enabling new modules to complete registration and initialization within 30 seconds, achieving rapid module access and configuration. In this way, the system can identify new modules and complete parameter matching and control loop initialization in the shortest possible time, greatly improving system flexibility and response speed.

[0101] The application of the adaptive fuzzy PID controller submodule allows control parameters to be dynamically adjusted based on the process coupling degree of the current module combination. The control parameter weights are adjusted in real time according to temperature fluctuations to ensure that system temperature fluctuations do not exceed ±5℃. This dynamic adjustment mechanism ensures the stability and accuracy of the system under different module combinations.

[0102] This application solves the problems of slow module access and registration and rigid control strategies in traditional smelting systems by combining a plug-and-play protocol interface and an adaptive fuzzy PID controller submodule. Compared with the prior art, the embodiments of this invention significantly improve the modular reconfiguration capability and control strategy flexibility of the system, ensuring efficient and stable operation of the system under different process conditions.

[0103] As an optional implementation, this application also proposes: configuring a multi-objective optimizer in the system, establishing a dynamic programming model to solve for the optimal production strategy, with the objective function being: min(0.6C) energy +0.4C time The constraints include: Q quality ≥99%, T equipment ≤T max In the formula, C energy Energy consumption cost; C time For time cost; Q quality Product quality pass rate; T equipment The actual temperature of the equipment; T max This is the upper limit of the equipment's safe temperature. When the distributed communication network triggers the anomaly self-healing mechanism, the following actions are taken: a) migrate the tasks of the faulty module to the backup module; b) call the digital twin model to generate a set of compensation parameters, including temperature gradient compensation ΔT. c and pressure compensation coefficient β p .

[0104] The solution presented in this application primarily addresses the technical challenges of production strategy optimization and fault self-healing in smelting systems. By introducing a multi-objective optimizer, the system can find the optimal balance between energy consumption and production time, ensuring optimized production efficiency and reduced costs while meeting quality requirements and equipment temperature limits. Furthermore, the anomaly self-healing mechanism of the distributed communication network enhances the system's robustness and reliability, reducing production downtime caused by module failures.

[0105] A multi-objective optimizer can be implemented using a dynamic programming model. The optimizer dynamically adjusts the production strategy based on real-time process parameters and production demands. The objective function combines energy and time costs, and the weights can be adjusted according to specific production needs. Constraints ensure the final product quality and equipment operational safety. Furthermore, an anomaly self-healing mechanism monitors module status in real time; when a fault is detected, it automatically migrates the task to a backup module, ensuring the continuity and stability of the production process. Simultaneously, a set of compensation parameters generated by the digital twin model is used to adjust the system's control parameters to maintain production process stability.

[0106] Therefore, this invention significantly improves the production efficiency and reliability of the smelting system by introducing multi-objective optimization and anomaly self-healing mechanisms. This technical solution not only addresses the shortcomings of traditional smelting systems in dynamic reconfiguration and fault handling, but also achieves more efficient production management and more stable operation through intelligent optimization and self-healing capabilities.

[0107] As an optional implementation, the digital twin prediction engine module of this invention plays a crucial role in the anomaly self-healing process. By monitoring equipment operating data in real time and dynamically comparing it with the virtual simulation model, the digital twin prediction engine module can quickly identify abnormal events and generate corresponding maintenance instructions. Therefore, the system can rapidly adjust its control strategy when a fault occurs, ensuring the stability and efficiency of the production process.

[0108] As an optional implementation, the multi-objective optimizer can employ improved genetic algorithms or particle swarm optimization algorithms to enhance solution efficiency. The optimizer can further improve the accuracy and stability of the optimization results by adaptively adjusting algorithm parameters. Simultaneously, the digital twin model can integrate more equipment operation data, enhancing its prediction accuracy and response speed.

[0109] Through the aforementioned technical means, this invention has achieved significant progress in realizing intelligent control and optimization of modular smelting systems. Compared with traditional technologies, the embodiments of this invention can more efficiently solve problems such as module identification, communication network adaptation, control strategy optimization, and equipment health management, thereby significantly improving the system's flexibility, stability, and production efficiency.

[0110] On the other hand, embodiments of the present invention also provide an intelligent reconfigurable modular smelting control method, which is implemented through the aforementioned intelligent reconfigurable modular smelting control system. The method includes the following steps:

[0111] Intelligent and reconfigurable modular smelting control is achieved through a central controller module, independent process modules, distributed communication network modules, and digital twin prediction engine modules.

[0112] As an optional implementation, the module rapid reconfiguration process of this embodiment of the invention refers to... Figure 3 When a new independent process module is connected to the system, the central controller module automatically scans and identifies the module's type and function code using RFID, generating a suitable control scheme. After the new module sends a registration request, the system completes parameter matching and initializes the control loop within 30 seconds. Simultaneously, the distributed communication network module monitors data flow changes in real time, triggering a topology reconfiguration protocol to dynamically allocate tasks, achieving collaborative control between modules. The entire process requires no manual intervention, significantly improving reconfiguration efficiency and system flexibility.

[0113] As an optional implementation, the temperature fluctuation control mechanism of this embodiment of the invention refers to... Figure 4 The temperature fluctuation control mechanism is implemented through an adaptive fuzzy PID controller submodule: the system monitors temperature data in real time and analyzes fluctuations, dynamically adjusting the PID parameter weights (such as proportional gain) according to the current process coupling degree; the optimized control strategy is verified by digital twin and then synchronized to the physical equipment to ensure that temperature fluctuations are stable within ±5℃. The entire process forms a closed-loop feedback, effectively suppressing overshoot and maintaining system stability.

[0114] As an optional implementation, the predictive maintenance process of this embodiment of the invention refers to... Figure 5 The system achieves closed-loop management through a digital twin prediction engine module: the health assessment unit collects equipment operation data in real time and calculates the Health Index (HIS) to assess the current status; the lifespan prediction unit uses an LSTM network to analyze time-series degradation data and predict the remaining useful life (RUL) and failure probability; the strategy verification unit verifies the reliability of the maintenance strategy through Monte Carlo simulation, and after confirmation, synchronizes it to the physical equipment for execution. This process reduces unplanned downtime by 60%, realizing a shift from "reactive maintenance" to "proactive prevention."

[0115] On the other hand, embodiments of the present invention also provide an intelligent reconfigurable modular smelting control device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the intelligent reconfigurable modular smelting control method described above.

[0116] The processor and memory can be connected via a bus or other means. Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, which can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0117] On the other hand, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the aforementioned intelligent reconfigurable modular smelting control method.

[0118] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0119] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. An intelligent, reconfigurable, modular smelting control system, characterized in that, The intelligent, reconfigurable, modular smelting control system includes a central controller module, an independent process module, a distributed communication network module, and a digital twin prediction engine module. The central controller module is responsible for module identification and control strategy generation. The independent process module includes an embedded identity recognition chip sub-module and an intelligent regulator sub-module; The embedded identity recognition chip sub-module is used to store the module's unique identifier, process parameter range, and compatibility data. The intelligent regulator submodule is used to receive instructions from the central controller module and dynamically adjust power, temperature, and pressure parameters. The distributed communication network module is used for online monitoring of data flow between modules; The digital twin prediction engine module is used to integrate online operating data of physical equipment with virtual simulation models, predict abnormal events of equipment through dynamic comparison, and generate a maintenance instruction queue.

2. The intelligent reconfigurable modular smelting control system according to claim 1, characterized in that, The central controller module includes an RFID scanning unit, a one-key reconstruction interface, an adaptive fuzzy PID controller submodule, and a control scheme generator submodule. The radio frequency identification scanning unit is used to automatically identify the type of the connected independent process module; The one-click reconfiguration interface is used to provide a smelting process template library and load parameter configuration sets; The adaptive fuzzy PID controller submodule is used to dynamically adjust the weights of the control parameters; The control scheme generator submodule is used to generate control strategies based on the module function code.

3. The intelligent reconfigurable modular smelting control system according to claim 2, characterized in that, The formulas used by the adaptive fuzzy PID controller submodule when dynamically adjusting the control parameter weights include: Among them, K p (t) represents the dynamically adjusted PID proportional term coefficient; K p0 α is the preset basic proportional coefficient; α is the temperature fluctuation correction factor; |ΔT| is the absolute deviation between the target temperature and the actual temperature during smelting.

4. The intelligent reconfigurable modular smelting control system according to claim 1, characterized in that, The independent process module also includes a plug-and-play protocol interface; The plug-and-play protocol interface is used to complete registration, parameter matching, and control loop initialization after the access module is connected.

5. The intelligent reconfigurable modular smelting control system according to claim 1, characterized in that, The distributed communication network module includes a topology reconstruction protocol, a data flow monitoring unit, and an anomaly self-healing mechanism. The topology reconfiguration protocol is used to automatically reallocate tasks when modules are added or removed; The data stream monitoring unit is used to monitor the communication status between modules online. The anomaly self-healing mechanism is used to migrate the tasks of the faulty module to the backup module and call the digital twin model to generate a set of compensation parameters.

6. The intelligent reconfigurable modular smelting control system according to claim 1, characterized in that, The digital twin prediction engine module includes a health assessment unit, a lifespan prediction unit, and a strategy verification unit. The health assessment unit is used to calculate the equipment health index and monitor the equipment degradation status; The lifetime prediction unit is used to analyze time-series degradation data; The strategy verification unit is used to perform Monte Carlo simulation in a virtual environment to verify the feasibility of the control strategy.

7. The intelligent reconfigurable modular smelting control system according to claim 6, characterized in that, The formula used by the health assessment unit to calculate the equipment health index includes: Where HIS stands for Health Index; n represents the total number of key performance parameters; w i S is the weighting coefficient for the i-th key performance parameter; current,i S represents the current measured value of the i-th key performance parameter; initial,i This is the initial baseline value for the i-th key performance parameter.

8. A smart, reconfigurable, modular smelting control method, implemented using a smart, reconfigurable, modular smelting control system as described in any one of claims 1 to 7, characterized in that, The method includes the following steps: Intelligent and reconfigurable modular smelting control is achieved through a central controller module, independent process modules, distributed communication network modules, and digital twin prediction engine modules.

9. A smart, reconfigurable, modular smelting control device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the intelligent reconfigurable modular smelting control method as described in claim 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the intelligent reconfigurable modular smelting control method as described in claim 8.

Images