Hydrogen metallurgy control system, equipment, storage medium and method

Abstract

The invention relates to the field of metallurgy, and discloses a hydrogen metallurgy control system, equipment, a storage medium and a method. The system comprises a digital twin platform; the sensor modules are arranged at different parameter detection positions in the metallurgical reactor; the edge calculation module is in communication connection with the corresponding sensor modules and the digital twin platform, and the edge calculation module comprises a plurality of edge nodes in communication connection with the corresponding sensor modules and a preset parameter prediction model; wherein the plurality of edge nodes are in communication connection through the ring network module, and the ring network module is used for controlling different edge calculation modules to communicate with each other in at least two different communication delay durations. And a signal instruction generated by the digital twin platform is transmitted to the metallurgical reactor through the ring network module at any communication delay duration. According to the system provided by the embodiment of the invention, various parameters in the metallurgical reactor can be dynamically coupled, and the control delay of the metallurgical reactor is greatly reduced.

Description

Technical Field

[0001] This invention relates to the field of metallurgy, and more particularly to a hydrogen metallurgical control system, equipment, storage medium, and method. Background Technology

[0002] Driven by carbon emission control strategies, the steel industry, as the largest carbon emitter among industrial sectors, urgently needs to achieve deep decarbonization through technological innovation. Currently, hydrogen metallurgy technology uses hydrogen energy to replace traditional coke / coal as a reducing agent in steel production. Compared to the traditional method of using coke / coal as a reducing agent, hydrogen energy can directly reduce carbon emissions by 40% to 90%, becoming one of the important directions for the green transformation of the steel industry.

[0003] However, hydrogen metallurgy technology involves metallurgical reactions using a high proportion of flammable, explosive, and toxic gases under high temperature and high pressure conditions. Its production process is complex, the coordination and control of multiple processes is difficult, and the safety risks are high, making management and control challenging.

[0004] In existing technologies, digital twin platform technology is typically applied to the hydrogen metallurgical production process to achieve real-time monitoring and safety control of the hydrogen metallurgical production line. However, existing digital twin platforms have the following problems: 1. Due to the complex physicochemical field involving gas, liquid, solid, high temperature, high pressure, and multiple components in the hydrogen metallurgical production process, the existing digital twin platform cannot dynamically couple various parameters, resulting in excessive errors between the calculated parameters and the actual production parameters.

[0005] 2. Existing digital twin platforms rely on centralized data processing in the cloud, with control loop delays of several seconds, which cannot meet the millisecond-level safety response requirements of hydrogen metallurgy. In the event of sudden conditions such as hydrogen leakage or local overheating, the excessively high control response delay leads to a significant increase in production safety risks.

[0006] 3. Existing digital twin platforms only aim to improve production efficiency and cannot achieve a balance between production efficiency, safety risks, production costs and low carbon emissions. Summary of the Invention

[0007] This invention provides a hydrogen metallurgical control system, equipment, storage medium, and method to solve at least one of the above-mentioned problems.

[0008] In a first aspect, embodiments of the present invention provide a hydrogen metallurgical control system, comprising: a digital twin platform; multiple sensor modules disposed at different parameter detection locations in a metallurgical reactor; and an edge computing module communicatively connected to the corresponding sensor modules and the digital twin platform. The edge computing module includes multiple edge nodes communicatively connected to the corresponding sensor modules and a preset parameter prediction model. The parameter prediction model is used to generate corresponding parameter adjustment results based on the operating parameters transmitted by the corresponding sensor modules. The multiple edge nodes are communicatively connected by a ring network module, which controls communication between different edge computing modules at at least two different communication delay durations. Signal commands generated by the digital twin platform are transmitted to the metallurgical reactor through the ring network module at any communication delay duration.

[0009] The hydrogen metallurgical control system provided in this embodiment of the invention can dynamically couple multiple collected operating parameters to generate accurate parameter adjustment results. At the same time, it realizes communication between edge computing modules through a ring network module and precisely controls the communication delay, so that when the digital twin platform sends instructions, the instructions can be quickly transmitted to the metallurgical reactor and start execution, thereby reducing control response delay.

[0010] Optionally, the edge computing module is used to: input the acquired operating parameters into the parameter prediction model, so that the parameter prediction model generates risk detection results for the metallurgical reactor based on the operating parameters and preset constraint values; and optimize the preset constraint values ​​into dynamic constraint values ​​based on the risk detection results, so that the parameter prediction model generates optimized risk detection results for the metallurgical reactor, wherein the operating parameters include the fatigue coefficient and temperature uniformity coefficient of the metallurgical reactor, and the parameter prediction model calculates the dynamic constraint values ​​based on the fatigue coefficient and temperature uniformity coefficient.

[0011] Optionally, the digital twin platform includes a local control module and a cloud control module. The local control module is communicatively connected to the cloud control module and to multiple edge nodes, enabling the cloud control module to send instructions to any edge computing module through the local control module.

[0012] Optionally, the hydrogen metallurgical control system also includes multiple gateway modules. The gateway modules are used to connect the edge computing module and the sensor module to communicate using the corresponding network protocol, and to send the data transmitted by the edge computing module or the sensor module to the sensor module or the edge computing module after preprocessing it.

[0013] Optionally, the ring network module includes a communication delay unit and a time synchronization unit. Different edge computing modules, as well as the digital twin platform and the edge computing modules, are connected through the communication delay unit and the time synchronization unit. The communication delay unit is used to control the communication between different edge computing modules and between the digital twin platform and the edge computing modules to be carried out with at least two different communication delay durations. The time synchronization unit is used to synchronize the clock sources between different edge computing modules and between the digital twin platform and the edge computing modules.

[0014] Optionally, the sensor module includes a data acquisition unit and a preprocessing unit. The data acquisition unit and the preprocessing unit are communicatively connected. The data acquisition unit is used to acquire the raw parameters of the corresponding parameter detection position, and the preprocessing unit is used to acquire the raw parameters and preprocess the raw parameters to generate operating parameters.

[0015] Optionally, the hydrogen metallurgical control system also includes a data display module, which is connected in communication with the digital twin platform. The data display module is used to display the operating parameters and parameter adjustment results of each parameter detection location in the metallurgical reactor.

[0016] Secondly, embodiments of the present invention provide a method for constructing a parameter prediction model. The parameter prediction model is applied to a metallurgical control system in any of the foregoing embodiments of the first aspect of the present invention. The method for constructing the parameter prediction model includes: acquiring the operating parameters and external environmental parameters of each parameter detection location in the metallurgical reactor; constructing a multi-objective loss function framework based on the number of types of operating parameters; and inputting the external environmental parameters and operating parameters into the multi-objective loss function framework to generate a parameter prediction model.

[0017] The parameter prediction model construction method provided in this embodiment of the invention can dynamically couple multiple collected operating parameters, so that when the parameter prediction model is applied to the metallurgical control system, the metallurgical control system can generate accurate parameter adjustment results based on the multiple collected operating parameters.

[0018] Optionally, the types of operating parameters include at least two of the following: input material consumption, output product discharge, reactant concentration in the metallurgical reactor, gas flow rate in the metallurgical reactor, energy consumption in the metallurgical reactor, and operating time of the metallurgical reactor.

[0019] Optionally, the steps of constructing a multi-objective loss function framework based on the number of types of operating parameters include: obtaining the weight coefficient of each type of operating parameter based on the number of types of operating parameters; and constructing a multi-objective loss function framework based on the number of types of operating parameters and the weight coefficient of each type of operating parameter.

[0020] Optionally, the step of obtaining the weight coefficient of each type of operating parameter based on the number of types of operating parameters includes: obtaining initial weight values ​​and constructing an initial framework based on the number of types of operating parameters; inputting the operating parameters and the initial weight values ​​of each type of operating parameter into the initial framework to obtain the initial total loss value; adjusting the initial weight values ​​of each type of operating parameter, calculating the optimized total loss value, until the minimum total loss value is obtained among multiple optimized total loss values, and using the optimized weight value corresponding to the minimum total loss value as the weight coefficient.

[0021] Thirdly, embodiments of the present invention provide a hydrogen metallurgical control device, comprising: a processor and a memory, wherein the memory stores instructions; the processor invokes the instructions in the memory to cause the processor to execute the parameter prediction model construction method of any of the foregoing embodiments of the second aspect of the present invention.

[0022] The processor of the hydrogen metallurgical control device provided in this embodiment of the invention executes the parameter prediction model construction method of any of the foregoing embodiments of the first aspect of the invention by calling instructions in the memory. It can dynamically couple multiple collected operating parameters, so that when the parameter prediction model is applied to the metallurgical control system, the metallurgical control system can generate accurate parameter adjustment results based on the multiple collected operating parameters.

[0023] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing instructions that, when executed by a processor, implement a method for constructing a parameter prediction model according to any of the foregoing embodiments of the second aspect of the present invention.

[0024] The instructions stored in the computer-readable storage medium provided in the embodiments of the present invention can be called by a processor and executed by the parameter prediction model construction method of any of the foregoing embodiments of the first aspect of the present invention, which dynamically couples multiple collected operating parameters, so that when the parameter prediction model is applied to the metallurgical control system, the metallurgical control system can generate accurate parameter adjustment results based on the multiple collected operating parameters. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0026] Figure 1 This is a structural block diagram of the first embodiment of the metallurgical control system of the present invention; Figure 2A flowchart illustrating the process of generating optimized risk detection results for the edge computing module in the first embodiment of the metallurgical control system of the present invention. Figure 3 A flowchart illustrating the process of generating optimized risk detection results by the edge computing module in the first embodiment of the metallurgical control system of the present invention. Figure 4 This is a structural block diagram of a second embodiment of the metallurgical control system of the present invention; Figure 5 This is a schematic diagram of the structural block of the second embodiment of the metallurgical control system of the present invention; Figure 6 This is a structural block diagram of the ring network module in the second embodiment of the metallurgical control system of the present invention; Figure 7 This is a structural block diagram of the sensor module in the second embodiment of the metallurgical control system of the present invention; Figure 8 This is a schematic diagram of the structure in the second embodiment of the metallurgical control system of the present invention; Figure 9 This is a flowchart of one embodiment of the method for constructing the parameter prediction model of the present invention; Figure 10 This is a flowchart illustrating one embodiment of the method for constructing the parameter prediction model of the present invention. Figure 11 This is a flowchart of step S120 in one embodiment of the method for constructing the parameter prediction model of the present invention; Figure 12 This is a flowchart of step S121 in one embodiment of the method for constructing the parameter prediction model of the present invention; Figure 13 This is a structural block diagram of one embodiment of the hydrogen metallurgical control equipment of the present invention.

[0027] Explanation of icon numbers: 110 - Digital Twin Platform; 111 - Local Control Module; 112 - Cloud Control Module; 120 - Sensor module; 121 - Data acquisition unit; 122 - Preprocessing unit; 130 - Edge computing module; 131 - Edge node; 140 - Ring network module; 141 - Communication delay unit; 142 - Time synchronization unit; 150-Gateway Module; 160 - Data display module; 200-Metallurgical reactor; 301 - Processor; 302 - Memory; 303 - Communication interface; 304 - Bus. Detailed Implementation

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0029] It should be noted that all directional indications in the embodiments of the present invention, such as up, down, left, right, front, back, etc., are only used to explain the relative positional relationship and movement of the components in a specific posture as shown in the attached figure. If the specific posture changes, the directional indication will also change accordingly.

[0030] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0031] like Figure 1 As shown, in the first embodiment of the present invention, the hydrogen metallurgical control system includes: a digital twin platform 110, multiple sensor modules 120 disposed at different parameter detection positions in the metallurgical reactor 200, and an edge computing module 130 communicatively connected to the corresponding sensor modules 120 and the digital twin platform 110.

[0032] The edge computing module 130 includes multiple edge nodes 131 that are communicatively connected to the corresponding sensor module 120, and a preset parameter prediction model. The parameter prediction model is used to generate corresponding parameter adjustment results based on the operating parameters transmitted by the corresponding sensor module 120.

[0033] Multiple edge nodes 131 are connected by a ring network module 140. The ring network module 140 is used to control the communication between different edge nodes 131 with at least two different communication delay durations. The signal commands generated by the digital twin platform 110 are transmitted to the metallurgical reactor 200 through the ring network module 140 with any communication delay duration.

[0034] In this embodiment of the invention, the sensor module 120 is used to detect the operating parameters of the corresponding position of the metallurgical reactor 200 and transmit the operating parameters to the corresponding edge node 131. The edge computing module 130 can receive and process the operating parameters transmitted by the corresponding sensor module 120 through the parameter prediction model to generate the corresponding parameter adjustment results, so as to realize the detection and feedback control of the production process of the metallurgical reactor 200.

[0035] like Figure 7 As shown, specifically, the sensor module 120 includes a data acquisition unit 121 and a preprocessing unit 122. The data acquisition unit 121 and the preprocessing unit 122 are communicatively connected. The data acquisition unit 121 is used to acquire the raw parameters of the corresponding parameter detection position, and the preprocessing unit 122 is used to acquire the raw parameters and preprocess the raw parameters to generate operating parameters.

[0036] The preprocessing unit 122 can convert the raw data into a standardized format, clean the data by filtering invalid values ​​(such as NULL values ​​and abnormal values) and filling in default values, and then use the template engine to define the output structure, perform standardized format conversion, and finally output unified interface data.

[0037] The hydrogen metallurgical control system also includes various types of databases such as MySQL, PostgreSQL, Oracle, and MongoDB. The data acquisition unit 121 is connected to each database and is used to store the acquired operating parameters in the database.

[0038] The ring network module 140 used to realize communication between edge nodes 131 includes three communication delay durations: a first delay duration of 1ms, a second delay duration of 5ms, and a third delay duration of 10ms. The signal commands include real-time control signals, process detection signals, and non-real-time signals.

[0039] In the hydrogen metallurgical process, when sudden conditions such as hydrogen leakage or local overheating occur, it is necessary to respond quickly to real-time control signals within milliseconds, such as rapidly controlling valve switches or temperature equipment. The corresponding real-time control signals are transmitted using the first delay duration.

[0040] For the detection of process signals such as hydrogen concentration and pressure in the metallurgical reactor 200, the response time requirement is lower than that for real-time control signals, so a second delay duration can be used for transmission.

[0041] For non-real-time signals where real-time requirements are not high, such as those requiring the generation of historical reports corresponding to historical production data and historical equipment parameters of the metallurgical reactor 200, a third delay duration can be used for transmission.

[0042] In this way, the ring network module 140 can allocate corresponding communication delay durations for communication data with different real-time requirements, so that communication data that requires real-time response operations can be transmitted as soon as possible, thereby greatly reducing communication latency.

[0043] Specifically, the ring network module 140 adopts a ring topology and the IEEE 802.1CB redundant transmission protocol. When a transmission link between edge nodes 131 fails, it can automatically switch to the redundant path to ensure that there will be no long-term communication delay.

[0044] The hydrogen metallurgical control system provided in this embodiment of the invention can dynamically couple multiple collected operating parameters to generate accurate parameter adjustment results. At the same time, the ring network module 140 enables communication between edge nodes 131 and precisely controls the communication delay, so that when the digital twin platform 110 sends an instruction, the instruction can be quickly transmitted to the metallurgical reactor 200 and start execution, thereby reducing the control response delay.

[0045] In some embodiments, parameter detection locations include the material inlet and material outlet of the metallurgical reactor 200, the interior of the processing device for processing materials, and the interior of the conveying device for conveying materials.

[0046] In this embodiment, by setting a sensor module 120 at the corresponding parameter detection position, the sensor module 120 is able to detect the corresponding operating parameters at that position.

[0047] The operating parameters include the input material consumption, output product discharge, reactant concentration in the metallurgical reactor 200, gas flow rate in the metallurgical reactor 200, energy consumption of the metallurgical reactor 200, and operating time of the metallurgical reactor 200. They may also include the gas pressure in the metallurgical reactor 200, temperature information of the metallurgical reactor 200, and vibration spectrum information.

[0048] For example, the input material consumption can be the amount of hydrogen gas input, the output product emission can be the amount of steel produced and the amount of carbon emissions, the reactant concentration can be the hydrogen concentration in the metallurgical reactor 200, the gas flow rate in the metallurgical reactor 200 can be the hydrogen flow rate and the air flow rate in the metallurgical reactor 200, the energy consumption of the metallurgical reactor 200 can be the power consumption of the metallurgical reactor 200, and the operating time of the metallurgical reactor 200 is used to obtain the fatigue coefficient of the metallurgical reactor 200.

[0049] like Figure 2As shown, in some embodiments, the edge computing module 130 is used to: input the acquired operating parameters into the parameter prediction model, so that the parameter prediction model generates the risk detection result of the metallurgical reactor 200 based on the operating parameters and preset constraint values, and optimize the preset constraint values ​​into dynamic constraint values ​​based on the risk detection results, so that the parameter prediction model generates the optimized risk detection result of the metallurgical reactor 200.

[0050] The operating parameters include the fatigue coefficient and temperature uniformity coefficient of the metallurgical reactor 200. The parameter prediction model calculates dynamic constraint values ​​based on the fatigue coefficient and temperature uniformity coefficient. The fatigue coefficient and temperature uniformity coefficient of the metallurgical reactor 200 are obtained through the temperature information and operating time of the metallurgical reactor 200.

[0051] like Figure 3 As shown, in this embodiment, the safety boundary of the preset constraint value is optimized. After the model identifies the risk in the simulation, it uses the optimization algorithm to feed back and construct a multi-objective optimization structure (i.e., simultaneously maintaining the maximum efficiency, minimum cost, and minimum safety risk in metallurgy), so that the metallurgical system simulated by the model will not approach the critical boundary.

[0052] By setting boundary thresholds using various operating parameters, the edge computing module 130 can predict the probability of overpressure risk in real time during the operation of the metallurgical reactor 200. When the threshold is approached, an early warning is triggered and risk location is provided. The module also dynamically reconstructs the preset constraint values ​​of the parameter prediction model, converting the preset constraint value P into a dynamic constraint value. This enables the reconstruction and real-time updating of constraint conditions (i.e., the initial constraint condition is: P < preset constraint value, and the reconstructed constraint condition is: Pmax = basic pressure of metallurgical reactor 200 + 0.1η(1-Rt)), where η is the fatigue coefficient of metallurgical reactor 200 and Rt is the temperature uniformity coefficient). This allows the prediction results of the edge computing module 130 to continuously approach the optimal safety boundary, maximizing production efficiency while ensuring safety, thereby achieving the goal of reducing risk and ensuring safe and efficient production.

[0053] Meanwhile, by incorporating various production parameters into the parameter prediction model of the edge computing module 130, multi-objective collaborative optimization is achieved, thereby improving hydrogen utilization, reducing carbon emissions, extending the life cycle of the metallurgical reactor 200, and providing timely early warning when the corresponding components of the metallurgical reactor 200 are aging.

[0054] Figure 4 This is a structural block diagram of a second embodiment of the metallurgical control system of the present invention. Some parts of the structure of the second embodiment are the same as those of the first embodiment; the differences between the two will be described below, while the similarities will not be detailed further.

[0055] like Figure 4As shown, in the second embodiment of the present invention, the digital twin platform 110 includes a local control module 111 and a cloud control module 112. The local control module 111 is communicatively connected to the cloud control module 112, and the local control module 111 is communicatively connected to multiple edge nodes 131, so that the cloud control module 112 can send instructions to any edge node 131 through the local control module 111.

[0056] Furthermore, such as Figure 5 As shown, in the second embodiment of the present invention, the sensor module 120 can be an intelligent sensing terminal integrating an NPU (Neural Processing Unit) to perform raw data preprocessing, such as threshold judgment and data compression. The intelligent sensing terminal includes a gas composition monitoring device, a solid material composition analyzer, an intelligent thermal imaging system, and a multimodal leak detection instrument to achieve corresponding data acquisition and data processing.

[0057] In this embodiment, the local control module 111 is communicatively connected to the cloud control module 112, and the local control module 111 is also communicatively connected to multiple edge nodes 131. This enables the local control module 111 to send instructions to the corresponding modules locally to complete data processing and closed-loop control, and to upload non-real-time historical data to the cloud control module 112 according to the instructions of the cloud control module 112, thus taking into account the low latency, high reliability and operational flexibility of end-to-end data transmission.

[0058] In some embodiments, the hydrogen metallurgical control system further includes multiple gateway modules 150. The gateway modules 150 are used to connect the edge computing module 130 and the sensor module 120 via corresponding network protocols, and to preprocess the data transmitted by the edge computing module 130 or the sensor module 120 before sending it to the sensor module 120 or the edge computing module 130. Specifically, they preprocess the data transmitted by the edge computing module 130 before sending it to the sensor module 120 to adjust the operating parameters corresponding to that location, or preprocess the data transmitted by the sensor module 120 before sending it to the edge computing module 130.

[0059] In this embodiment, the gateway module 150 is an FPGA (Field-Programmable Gate Array) gateway to achieve high-speed transmission and filtering of various types of data, intercept invalid data at the edge computing module 130, and improve the efficiency of effective information transmission.

[0060] like Figure 6As shown, in some embodiments, the ring network module 140 includes a communication delay unit 141 and a time synchronization unit 142. Different edge nodes 131 and the digital twin platform 110 are connected to the edge nodes 131 through the communication delay unit 141 and the time synchronization unit 142.

[0061] The communication delay unit 141 is used to control communication between different edge nodes 131 and between the digital twin platform 110 and the edge nodes 131 with at least two different communication delay durations. The time synchronization unit 142 is used to synchronize the clock sources between different edge nodes 131 and between the digital twin platform 110 and the edge nodes 131.

[0062] In this embodiment, the communication delay unit 141 is used to preset different communication delay durations and control the corresponding signal commands to communicate with the corresponding communication delay duration. The time synchronization unit 142 includes DS-TT (terminal-side converter) and NW-TT (network-side converter) to realize clock source coordination between TSN GM (root clock) and 5G GM, enabling network topology to be configured among edge nodes 131 and achieving automatic unified scheduling control.

[0063] In some embodiments, the hydrogen metallurgical control system further includes a data display module 160, which is communicatively connected to the digital twin platform 110. The data display module 160 is used to display the operating parameters and parameter adjustment results of each parameter detection location in the metallurgical reactor 200.

[0064] In this embodiment, the data display module 160 can display the operating parameters of the material inlet, material outlet, the interior of the processing device for processing materials, the interior of the conveying device for conveying materials, and other devices or parts in the metallurgical reactor 200. For example, it can display the input material consumption, output product discharge, reactant concentration, airflow velocity, energy consumption, and operating time of the metallurgical reactor 200. It can also include the gas pressure, temperature, and vibration spectrum information of the metallurgical reactor 200. It is also used to display historical reports corresponding to historical production data and historical equipment parameters of the metallurgical reactor 200, as well as the optimized risk detection results of the metallurgical reactor 200.

[0065] When a safety risk occurs in the metallurgical reactor 200, the user can determine the location and specific circumstances of the safety risk based on the optimized risk detection results displayed by the data display module 160, and send instructions through the digital twin platform 110 to control the corresponding valve switch or temperature equipment operation to eliminate the safety risk in a timely manner.

[0066] In some embodiments, the data display module 160 can also reflect the execution status of the metallurgical task in real time based on the operating parameters and parameter adjustment results of each parameter detection position in the metallurgical reactor 200, so as to respond quickly in case of abnormality.

[0067] The hydrogen metallurgy control system restricts the scope of operation through fine-grained access control. For long-running tasks, it can design a checkpoint mechanism to support recovery from breakpoints after interruption, improving execution efficiency. It also generates tokens to verify user identity, assigns a unique key to each client, and uses AES / RSA encryption algorithms to encrypt data. It adds SQL injection and XSS protection measures to ensure the security of data interfaces. Furthermore, it can monitor service status, performance indicators, and anomalies in real time, realize automatic alarms and fault self-healing, record operation logs and user behavior, and use the ELK (Elasticsearch + Logstash + Kibana) log management and analysis platform to centrally store and analyze logs.

[0068] In this embodiment, the hydrogen metallurgical control system can achieve the following functions: (1) Comprehensive display of the entire factory The display interface of the data display module 160, such as the 3D digital twin platform, displays real-time dynamic information such as relevant operating parameters, parameter adjustment results, optimized risk detection results, and historical reports. It also provides entry menus for various business functions and displays the overall factory layout and detailed equipment models.

[0069] (2) Comprehensive display of metallurgical workshop The display interface of the data display module 160 enables energy management and logistics management, and provides a comparative display of 3D models and real-time data to enhance the intuitive display effect. At the same time, it embeds analysis reports, which can display relevant operating information, as well as related analysis reports and historical reports (such as equipment operation analysis reports) when the user selects a node object.

[0070] (3) Monitoring of metallurgical production processes A three-dimensional factory is formed in the display interface of the data display module 160. The structure is divided into regions, equipment and other categories in a tree structure. Users can click on any node to switch the viewpoint to locate the specified target and display the relevant node's operating data, report information and other content.

[0071] (4) Intelligent operation and maintenance of metallurgical equipment In the display interface of the data display module 160, clicking on the relevant equipment in the displayed 3D model can display asset information related to the equipment (including engineering drawings, design specifications, inspection records and other documents, including work orders, work tasks, engineering attributes and other information).

[0072] (5) Security control In the 3D scene of the data display module 160, hazards are classified according to their level of danger, and emergency supplies location and emergency plans are provided. Each device is mapped to a different camera address, establishing a mapping relationship between the device and the monitoring system access address. The corresponding video monitoring link is displayed on the device information display interface, allowing users to open the corresponding video monitoring to create a real-time display of the device's on-site status.

[0073] (6) Early warning alarm The 160-level data display module enables equipment alarms within a 3D factory environment. When equipment malfunctions in the hydrogen metallurgy control system, an alarm is triggered in the visual environment, and the production system can be remotely controlled to confirm the anomaly, generate work orders, and assign personnel for handling. The system automatically records key steps in the processing, creating a traceable anomaly handling archive. Simultaneously, the hydrogen metallurgy control system can mine historical anomaly data to extract best practices for equipment maintenance and provide early warnings of potential equipment failures, shifting from reactive response to proactive prevention, thereby improving overall production efficiency and equipment reliability.

[0074] The present invention also proposes a method for constructing a parameter prediction model, which is applied to the metallurgical control system of any of the foregoing embodiments of the present invention.

[0075] like Figure 9 As shown, the method for constructing the parameter prediction model in this embodiment of the invention includes steps S110 to S130.

[0076] In step S110, the operating parameters and external environmental parameters of each parameter detection location in the metallurgical reactor are obtained.

[0077] In some alternative embodiments, the types of operating parameters include at least two of the following: input material consumption, output product discharge, reactant concentration in the metallurgical reactor, gas flow rate in the metallurgical reactor, energy consumption of the metallurgical reactor, and operating time of the metallurgical reactor.

[0078] External environmental parameters include air pressure, ambient temperature, and ambient humidity outside the metallurgical reactor.

[0079] In step S120, a multi-objective loss function framework is constructed based on the number of types of running parameters.

[0080] like Figure 11 As shown, in some optional embodiments, step S120 includes steps S121 to S122.

[0081] In step S121, the weight coefficient of each type of operating parameter is obtained based on the number of types of operating parameters.

[0082] In step S122, a multi-objective loss function framework is constructed based on the number of types of operating parameters and the weight coefficient of each type of operating parameter.

[0083] In this embodiment, the carbon emissions, hydrogen consumption, energy consumption, and operating time of the metallurgical reactor in the hydrogen metallurgical process are used. Based on the operating time of the metallurgical reactor, the remaining service life of the metallurgical reactor can be obtained. Through the above operating parameters, a multi-objective loss function framework is constructed to obtain a parameter prediction model, thereby achieving accurate simulation and prediction of the hydrogen metallurgical process.

[0084] like Figure 12 As shown, step S121 further includes steps S1211 to S1213.

[0085] In step S1211, based on the number of types of running parameters, the initial weight values ​​are obtained and the initial framework is constructed.

[0086] In step S1212, the operating parameters and the initial weight value of each operating parameter are input into the initial frame to obtain the initial total loss value.

[0087] In step S1213, the initial weight value of each running parameter is adjusted, and the optimized total loss value is calculated until the minimum total loss value is obtained among multiple optimized total loss values. The optimized weight value corresponding to the minimum total loss value is used as the weight coefficient.

[0088] In this embodiment, the function of the multi-objective loss function framework can be obtained as follows: ; in, , , , These are the weighting coefficients for the corresponding operating parameters. To obtain Minimum total loss value.

[0089] By adjusting the weight coefficients of the corresponding operating parameters, the minimum total loss value is obtained, thereby constructing a multi-objective loss function framework. This allows the operating parameters of the metallurgical reactor to be adjusted based on the parameter adjustment results generated by the constructed parameter prediction model, keeping the production efficiency of the metallurgical reactor in the hydrogen metallurgical process close to its maximum value and maximizing production efficiency.

[0090] In step S130, external environmental parameters and operating parameters are input into the multi-objective loss function framework to generate a parameter prediction model.

[0091] In this embodiment, by inputting the operating parameters inside the metallurgical reactor and the external environmental parameters outside the metallurgical reactor into the parameter prediction model, the parameter prediction model can integrate the operating conditions of various parts inside the metallurgical reactor and the external environmental conditions to generate more accurate parameter adjustment results.

[0092] like Figure 8 and Figure 10 As shown, this embodiment uses the quantized TensorRT (TensorRuntime) model to compress the obtained LSTM parameter prediction model to <5MB, so that the model inference latency is controlled within 3ms.

[0093] To achieve synergistic optimization of multiple objectives such as carbon emission intensity, hydrogen consumption per unit, equipment lifespan, and energy consumption, this invention applies the constructed parameter prediction model to the hydrogen metallurgical control system, forming a four-layer decoupled architecture of "sensing-modeling-decision-scheduling".

[0094] Specifically, the perception layer is used to build parameter prediction models based on various operating parameters, the modeling layer is used to build a multi-objective loss function framework, the decision layer is used to generate corresponding parameter adjustment results based on the constructed parameter prediction models, and the scheduling layer is used to seamlessly connect the generated parameter adjustment results with the actual production system (such as the shift scheduling system and the gas scheduling system), while calling the parameter adjustment results to achieve hourly production scheduling adjustments and resource control, and to provide feedback on the load status of key components of the metallurgical reactor, thereby achieving continuous optimization and fine-tuning of the metallurgical equipment.

[0095] The method for constructing a parameter prediction model provided in this embodiment of the invention includes: obtaining the operating parameters and external environmental parameters at each parameter detection location in the metallurgical reactor; constructing a multi-objective loss function framework based on the number of types of operating parameters; and inputting the external environmental parameters and operating parameters into the multi-objective loss function framework to generate a parameter prediction model.

[0096] The parameter prediction model construction method provided in this embodiment of the invention can dynamically couple multiple collected operating parameters, so that when the parameter prediction model is applied to the metallurgical control system, the metallurgical control system can generate accurate parameter adjustment results based on the multiple collected operating parameters.

[0097] In addition to the above method embodiments, the present invention also provides, for example, Figure 13 The hydrogen metallurgical control device shown includes a processor 301 and a memory 302, wherein the memory 302 stores instructions; the processor 301 calls the instructions in the memory 302 to cause the processor 301 to execute the parameter prediction model construction method of any of the foregoing embodiments of the present invention.

[0098] The method for constructing the parameter prediction model in the above embodiment includes: obtaining the operating parameters and external environmental parameters at each parameter detection location in the metallurgical reactor; constructing a multi-objective loss function framework based on the number of types of operating parameters; and inputting the external environmental parameters and operating parameters into the multi-objective loss function framework to generate a parameter prediction model.

[0099] The hydrogen metallurgical control equipment provided in this embodiment of the invention can dynamically couple multiple collected operating parameters by implementing the above-mentioned parameter prediction model construction method. This enables the metallurgical control system to generate accurate parameter adjustment results based on the collected multiple operating parameters when the parameter prediction model is applied to the metallurgical control system.

[0100] Furthermore, the hydrogen metallurgical control device provided in this embodiment of the invention may also include a communication interface 303 and a bus 304, with the processor 301, memory 302 and communication interface 303 electrically connected via the bus 304.

[0101] The memory 302 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 303 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc. The bus 304 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 13 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0102] Processor 301 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 301 or by instructions in software form. Processor 301 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a readily available storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 302. The processor 301 reads the information from memory 302 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0103] This invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of the above-described method for constructing a parameter prediction model.

[0104] The computer-readable storage medium provided in this embodiment of the invention stores data and computer-executable instructions for the construction method of the above-mentioned parameter prediction model. The construction method of the above-mentioned parameter prediction model includes: obtaining the operating parameters and external environmental parameters of each parameter detection location in the metallurgical reactor; constructing a multi-objective loss function framework based on the number of types of operating parameters; and inputting the external environmental parameters and operating parameters into the multi-objective loss function framework to generate a parameter prediction model.

[0105] The computer-readable storage medium provided in this embodiment of the invention implements the above-described method for constructing the parameter prediction model, which enables dynamic coupling of multiple collected operating parameters. This allows the metallurgical control system to generate accurate parameter adjustment results based on the collected operating parameters when the parameter prediction model is applied to the metallurgical control system.

[0106] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0107] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0108] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A hydrogen metallurgical control system, characterized in that, The system includes: Digital twin platform; Multiple sensor modules are installed at different parameter detection locations within the metallurgical reactor; and An edge computing module is communicatively connected to the corresponding sensor module and the digital twin platform. The edge computing module includes multiple edge nodes communicatively connected to the corresponding sensor module and a preset parameter prediction model. The parameter prediction model is used to generate corresponding parameter adjustment results based on the operating parameters transmitted by the corresponding sensor module. The multiple edge nodes are connected by a ring network module, which controls the communication between different edge computing modules with at least two different communication delay durations. The signal commands generated by the digital twin platform are transmitted to the metallurgical reactor through the ring network module with any of the communication delay durations.

2. The hydrogen metallurgical control system according to claim 1, characterized in that, The edge computing module is used for: The acquired operating parameters are input into the parameter prediction model, so that the parameter prediction model generates the risk detection result of the metallurgical reactor based on the operating parameters and preset constraint values. as well as Based on the risk detection results, the preset constraint values ​​are optimized into dynamic constraint values, enabling the parameter prediction model to generate optimized risk detection results for the metallurgical reactor. The operating parameters include the fatigue coefficient and temperature uniformity coefficient of the metallurgical reactor, and the parameter prediction model calculates the dynamic constraint value based on the fatigue coefficient and the temperature uniformity coefficient.

3. The hydrogen metallurgical control system according to claim 1, characterized in that, The digital twin platform includes a local control module and a cloud control module. The local control module is communicatively connected to the cloud control module and to multiple edge nodes, enabling the cloud control module to send instructions to any of the edge computing modules through the local control module.

4. The hydrogen metallurgical control system according to claim 1, characterized in that, The hydrogen metallurgical control system also includes multiple gateway modules. The gateway modules are used to connect the edge computing module and the sensor module to communicate using corresponding network protocols, and to send the data transmitted by the edge computing module or the sensor module to the sensor module or the edge computing module after preprocessing the data.

5. The hydrogen metallurgical control system according to claim 1, characterized in that, The ring network module includes a communication delay unit and a time synchronization unit. Different edge computing modules and the digital twin platform communicate with each other through the communication delay unit and the time synchronization unit. The communication delay unit is used to control the communication between different edge computing modules and between the digital twin platform and the edge computing modules to be at least two different communication delay durations. The time synchronization unit is used to synchronize the clock sources between different edge computing modules and between the digital twin platform and the edge computing modules.

6. The hydrogen metallurgical control system according to claim 1, characterized in that, The sensor module includes a data acquisition unit and a preprocessing unit. The data acquisition unit is communicatively connected to the preprocessing unit. The data acquisition unit is used to acquire the raw parameters corresponding to the parameter detection position. The preprocessing unit is used to acquire the raw parameters and preprocess the raw parameters to generate the operating parameters.

7. The hydrogen metallurgical control system according to claim 1, characterized in that, The hydrogen metallurgical control system also includes a data display module, which is communicatively connected to the digital twin platform. The data display module is used to display the operating parameters and parameter adjustment results of each parameter detection location in the metallurgical reactor.

8. A method for constructing a parameter prediction model, characterized in that, The parameter prediction model is applied to the metallurgical control system as described in any one of claims 1 to 7, and the method includes: The operating parameters and external environmental parameters of each parameter detection location in the metallurgical reactor are obtained; Based on the number of types of the aforementioned operating parameters, a multi-objective loss function framework is constructed; The external environment parameters and the operating parameters are input into the multi-objective loss function framework to generate the parameter prediction model.

9. The method for constructing a parameter prediction model according to claim 8, characterized in that, The types of operating parameters include at least two of the following: The input parameters are: material consumption, output product discharge, reactant concentration in the metallurgical reactor, gas flow rate in the metallurgical reactor, energy consumption of the metallurgical reactor, and operating time of the metallurgical reactor.

10. The method for constructing the parameter prediction model according to claim 8, characterized in that, The steps for constructing a multi-objective loss function framework based on the number of types of operating parameters include: Based on the number of types of the operating parameters, obtain the weight coefficient of the operating parameter for each type; The multi-objective loss function framework is constructed based on the number of types of operating parameters and the weight coefficient of each type of operating parameter.

11. The method for constructing the parameter prediction model according to claim 10, characterized in that, The step of obtaining the weight coefficient of the operating parameter for each category based on the number of categories of the operating parameters includes: Based on the number of types of the operating parameters, obtain the initial weight values ​​and construct the initial framework; Input the operating parameters and the initial weight value of each operating parameter into the initial framework to obtain the initial total loss value; Adjust the initial weight value of each of the aforementioned operating parameters, calculate the optimized total loss value, until the minimum total loss value is obtained among multiple optimized total loss values, and use the optimized weight value corresponding to the minimum total loss value as the weight coefficient.

12. A hydrogen metallurgical control device, characterized in that, The hydrogen metallurgical control device includes: a processor and a memory, wherein the memory stores instructions; The processor invokes the instructions in the memory to enable the hydrogen metallurgical control device to implement the method for constructing the parameter prediction model as described in any one of claims 8 to 11.

13. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the method for constructing the parameter prediction model as described in any one of claims 8 to 11.

Images