Control method and device of circulating fluidized bed unit, electronic equipment and storage medium

Abstract

The present disclosure discloses a control method and device of a circulating fluidized bed unit, an electronic device and a storage medium. Since the control instruction is generated based on the preset control model and the real-time operation data of the unit, the model parameters are continuously iteratively updated through online operation data to dynamically adapt to the working condition changes, and the multi-objective optimization is carried out in a wide parameter space combined with the load changes to adjust the model operation strategy, fully responding to the strong nonlinearity and time characteristics of the circulating fluidized bed system. Therefore, the technical problem that the existing control method cannot adapt to the frequent fluctuations of coal quality, large range changes of load and multi-variable strong coupling working conditions due to the use of fixed parameter model or rules and the insufficient consideration of the strong nonlinearity and time variability of the system can be solved. The technical effects of improving the dynamic adaptability and control precision of the circulating fluidized bed unit control, enhancing the response capability of the unit to complex working conditions, ensuring the stable and efficient operation of the unit under various working conditions, and further improving the reliability of power supply are achieved.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a control method and apparatus, electronic equipment and storage medium for a circulating fluidized bed unit. Background Technology

[0002] As an important type of unit in the thermal power generation field, the stable and efficient operation of circulating fluidized bed units is crucial for ensuring power supply. With the development of industrial automation and intelligent technologies, related technologies have constructed control systems for key processes such as boiler combustion and steam temperature through the synergy of traditional PID control, advanced control algorithms, and artificial intelligence-assisted analysis techniques.

[0003] Existing control methods directly adopt control strategies based on fixed parameter models or rules, without fully considering the strong nonlinearity and time-varying nature of circulating fluidized bed systems caused by frequent fluctuations in coal quality, large-scale changes in load, and strong coupling of multiple variables. Summary of the Invention

[0004] This disclosure provides a control method, apparatus, electronic device, and storage medium for a circulating fluidized bed unit.

[0005] According to a first aspect of this disclosure, a control method for a circulating fluidized bed unit is provided, comprising:

[0006] Control commands are generated based on a preset control model and the real-time operating data of the unit, and the control commands are output to the corresponding control loop of the unit. The online operating data of the unit is collected, and the parameters of the preset control model are continuously updated through the online operating data to achieve dynamic adaptation to changes in the unit's operating conditions. Based on the load changes of the unit, multi-objective optimization is performed within a wide parameter space, and the operation strategy of the preset control model is dynamically adjusted according to the optimization results.

[0007] Optionally, before generating control commands based on a preset control model and the unit's real-time operating data, the method includes: Data modeling is performed on the analog parameters of the entire circulating fluidized bed unit system. Meanwhile, key variables that are difficult to measure directly in the unit are inferred through multimodal modeling and parameter soft measurement technology, and the inferred variables are incorporated into the construction process of the preset control model.

[0008] Optionally, the analog parameters include temperature parameters, pressure parameters, and flow rate parameters; the multimodal modeling method includes at least one of statistical analysis, Fourier transform, and Laplace transform.

[0009] Optionally, the preset control model is constructed by fusing neural network algorithms and reinforcement learning algorithms.

[0010] Optionally, the changes in operating conditions include fluctuations in coal quality and changes in load.

[0011] Optionally, the step of performing multi-objective optimization within a wide parameter space based on the load changes of the unit, and dynamically adjusting the operating strategy of the preset control model based on the optimization results, includes: Multi-objective comprehensive optimization of the unit is performed within a wide parameter space to form a dynamic operating domain that matches different operating conditions of the unit, and the dynamic changes of the unit in a wide load range are adapted based on the dynamic operating domain.

[0012] Optionally, the method further includes: For group control scenarios involving multiple similar devices, models are established based on the control curves, device characteristics, and actual operating status of each device. Based on the modeling results of each device, control commands are assigned to the multiple similar devices to achieve optimal energy consumption control for a single device.

[0013] According to a second aspect of this disclosure, a control device for a circulating fluidized bed unit is provided, comprising: The output unit is used to generate control commands based on a preset control model and the real-time operating data of the unit, and output the control commands to the corresponding control loop of the unit; An adaptation unit is used to collect online operating data of the unit and continuously update the parameters of the preset control model through the online operating data to achieve dynamic adaptation to changes in the unit's operating conditions. The adjustment unit is used to perform multi-objective optimization within a wide parameter space based on the load changes of the unit, and dynamically adjust the operation strategy of the preset control model based on the optimization results.

[0014] Optionally, the device includes: The modeling unit is used to perform data modeling of the analog parameters of the entire circulating fluidized bed unit before the output unit generates control commands based on the preset control model and the real-time operating data of the unit. The inference unit is used to simultaneously infer key variables in the unit that are difficult to measure directly through multimodal modeling and parameter soft measurement technology, and incorporate the inferred variables into the construction process of the preset control model.

[0015] Optionally, the analog parameters include temperature parameters, pressure parameters, and flow rate parameters; the multimodal modeling method includes at least one of statistical analysis, Fourier transform, and Laplace transform.

[0016] Optionally, the preset control model is constructed by fusing neural network algorithms and reinforcement learning algorithms.

[0017] Optionally, the changes in operating conditions include fluctuations in coal quality and changes in load.

[0018] Optionally, the adjustment unit is further configured to: Multi-objective comprehensive optimization of the unit is performed within a wide parameter space to form a dynamic operating domain that matches different operating conditions of the unit, and the dynamic changes of the unit in a wide load range are adapted based on the dynamic operating domain.

[0019] Optionally, the device further includes: Establish a unit to build a model for group control scenarios with multiple similar devices, based on the control curve, device characteristics and actual operating status of each device; The control unit is used to assign control commands to the multiple similar devices based on the modeling results of each device, so as to achieve optimal energy consumption control of a single device.

[0020] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0021] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0022] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0023] The control method, device, electronic equipment, and storage medium for circulating fluidized bed (CFB) units disclosed herein generate control commands based on a preset control model and real-time operating data of the unit. They dynamically adapt to changes in operating conditions by continuously updating model parameters through online operating data. Simultaneously, they perform multi-objective optimization and adjust model operating strategies across a wide parameter space in conjunction with load changes. This effectively addresses the strong nonlinearity and time characteristics of the CFB system. Therefore, it solves the technical problems of existing control methods that fail to adapt to frequent coal quality fluctuations, large-scale load changes, and strongly coupled multivariate operating conditions due to the use of fixed parameter models or rules and insufficient consideration of the system's strong nonlinearity and time-varying nature. This achieves the technical effect of improving the dynamic adaptability and control accuracy of CFB unit control, enhancing the unit's ability to cope with complex operating conditions, ensuring stable and efficient operation of the unit under various operating conditions, and ultimately improving the reliability of power supply.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0025] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 A schematic flowchart illustrating a control method for a circulating fluidized bed unit provided in an embodiment of this disclosure; Figure 2 A schematic diagram of the structure of a control device for a circulating fluidized bed unit provided in an embodiment of this disclosure; Figure 3 A schematic diagram of the structure of a control device for a circulating fluidized bed unit provided in an embodiment of this disclosure; Figure 4 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0026] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0027] The following description, with reference to the accompanying drawings, outlines a control method, apparatus, electronic device, and storage medium for a circulating fluidized bed unit according to embodiments of the present disclosure.

[0028] Figure 1This is a schematic flowchart illustrating a control method for a circulating fluidized bed unit provided in an embodiment of this disclosure.

[0029] like Figure 1 As shown, the method includes the following steps: Step 101: Generate control commands based on the preset control model and the real-time operating data of the unit, and output the control commands to the control loop corresponding to the unit; During actual operation, the generating unit continuously collects real-time operational data from all stages of the process. This data provides a clear and comprehensive picture of the unit's current operating status and forms the crucial data foundation for generating control commands. After establishing the preset control model and effectively collecting the unit's real-time operational data, the collected data is fully input into the model. The model then performs comprehensive analysis and calculations on the input data based on its built-in core computational logic. Simultaneously, it generates matching control commands based on the unit's actual operational and control requirements. These commands precisely address various specific control needs of the unit's operation and possess a high degree of adaptability to the unit's current operational status.

[0030] After the control commands are generated, they are directly output to the corresponding control loop of the unit. As the core execution link for the unit to achieve operation regulation, the control loop can directly receive control commands and perform precise regulation of each operation link of the unit according to the specific content of the commands. This allows the regulatory intent of the control commands to directly affect the actual operation of the unit, realizing the direct implementation of control commands from generation to execution. It effectively connects model calculation with the actual control links of the unit, enabling the unit's operation regulation to make a fast and accurate response based on the real-time operating status, effectively improving the timeliness and accuracy of unit control, and fully adapting to the actual operation regulation needs of the unit.

[0031] Step 102: Collect the online operating data of the unit, and continuously update the parameters of the preset control model through the online operating data to achieve dynamic adaptation to changes in the unit's operating conditions; After completing the collection of online operation data, the collected data is transmitted to the preset control model in real time. The model uses its built-in algorithm logic to systematically analyze and calculate the input online operation data, accurately extract key feature information that reflects changes in the unit's operating conditions, and then continuously update and adjust its parameters based on this key feature information.

[0032] The parameter updates of the preset control model are not simply single-dimensional numerical modifications, but rather comprehensive dynamic optimizations based on the actual changing trends of the unit's operating conditions. This ensures that all parameters of the model remain highly matched with the actual operating state of the unit, thereby achieving dynamic adaptation to changes in the unit's operating conditions.

[0033] This parameter-based continuous update method, which relies on online operational data, allows the preset control model to overcome the adaptation limitations imposed by fixed parameters. When various changes occur in the unit's operating conditions, the model can quickly adjust its own parameters, always maintaining a precise adaptation to the unit's operating status. This ensures that the control commands subsequently generated by the model continuously meet the unit's real-time operational needs, significantly improving the adaptability and accuracy of unit control and guaranteeing stable and efficient operation of the unit under different operating conditions.

[0034] Step 103: Based on the load changes of the unit, perform multi-objective optimization within a wide parameter space, and dynamically adjust the operation strategy of the preset control model based on the optimization results.

[0035] Based on the acquired unit load changes, multi-objective optimization is conducted within a wide parameter space. This wide parameter space covers the variation range of various core operating parameters such as temperature, pressure, and flow rate during unit operation, and can fully adapt to the parameter change requirements under different load conditions. The multi-objective optimization process revolves around the core control requirements of unit operation, comprehensively considering multiple objectives such as unit operation stability, energy consumption control, and parameter compliance, and performing coordinated calculations. Through systematic optimization analysis, the optimal solution that fits the current load conditions is obtained, forming the corresponding optimization result.

[0036] After obtaining accurate optimization results, the operating strategy of the preset control model is dynamically adjusted directly based on these results. The model's control logic, parameter matching methods, and command generation rules are optimized according to the actual load changes, ensuring that the operating strategy of the preset control model remains highly adapted to the unit's current load state. This multi-objective optimization and dynamic adjustment method based on load changes allows the preset control model to accurately match the unit's load variation requirements, avoiding the insufficient adaptability problems caused by fixed operating strategies. It significantly improves the model's control adaptability under different load conditions, ensuring that the unit can achieve optimal operation across multiple dimensions in various load change scenarios, effectively improving the overall operating efficiency and control accuracy of the unit.

[0037] In some embodiments, before generating control commands based on a preset control model and the unit's real-time operating data, the method includes: Data modeling is performed on the analog parameters of the entire circulating fluidized bed unit system. Meanwhile, key variables that are difficult to measure directly in the unit are inferred through multimodal modeling and parameter soft measurement technology, and the inferred variables are incorporated into the construction process of the preset control model.

[0038] When constructing a preset control model adapted to the circulating fluidized bed unit, comprehensive numerical modeling of the analog parameters of the entire unit system is first carried out. The analog parameters of the entire unit system cover various core dimensions such as temperature, pressure, and flow rate during operation. Full-dimensional data modeling of these parameters can achieve complete coverage of the operating parameters of the entire unit system, providing a comprehensive and solid parameter data foundation for model construction. This effectively overcomes the problem of limited modeling quantity in traditional modeling methods, significantly improves the model's coverage of unit operating parameters and the accuracy of data modeling, and provides core data support for the efficient construction of the preset control model.

[0039] While completing the modeling of analog parameters for the entire system, the inference of key variables of the unit is carried out by relying on multimodal modeling and parameter soft measurement technology. Multimodal modeling integrates various modeling logics such as statistical analysis, Fourier transform, and Laplace transform. Combined with the technical advantages of parameter soft measurement technology, it can perform accurate data analysis and numerical inference for key variables that are difficult to measure directly during unit operation, accurately uncover the actual values ​​and variation patterns of such key variables, and make up for the shortcomings of direct measurement methods.

[0040] Subsequently, the key variables inferred in this way are fully incorporated into the overall construction process of the preset control model. This ensures that the parameter system of the preset control model includes both directly measurable analog parameters of the entire system and accurately inferred, difficult-to-measure key variables. This makes the model construction more comprehensive and the parameter system more complete, significantly improving the overall construction accuracy of the preset control model. It also allows the model to better match the actual operating state of the circulating fluidized bed unit, laying a solid model foundation for the accurate generation of subsequent control commands.

[0041] In some embodiments, the analog parameters include temperature parameters, pressure parameters, and flow rate parameters; the multimodal modeling method includes at least one of statistical analysis, Fourier transform, and Laplace transform.

[0042] In some embodiments, the preset control model is constructed by fusing neural network algorithms and reinforcement learning algorithms.

[0043] In some embodiments, the changes in operating conditions include fluctuations in coal quality and changes in load.

[0044] In some embodiments, the step of performing multi-objective optimization within a wide parameter space based on the load changes of the unit, and dynamically adjusting the operating strategy of the preset control model based on the optimization results, includes: Multi-objective comprehensive optimization of the unit is performed within a wide parameter space to form a dynamic operating domain that matches different operating conditions of the unit, and the dynamic changes of the unit in a wide load range are adapted based on the dynamic operating domain.

[0045] In the process of performing multi-objective optimization and dynamically adjusting the preset control model operation strategy in a wide parameter space based on the load changes of the unit, the multi-objective comprehensive optimization work of the circulating fluidized bed unit is first carried out in the completed wide parameter space. This wide parameter space covers the full range of changes of various core operating parameters during the unit operation. The multi-objective comprehensive optimization is carried out in a coordinated manner around the core operating objectives such as unit operation stability, energy consumption control effect, and compliance of various parameters, and comprehensively considers the actual operating needs and various operating constraints of the unit under different load conditions.

[0046] Through comprehensive multi-objective optimization calculations across all dimensions, and by combining the actual operating characteristics and control points of different operating conditions such as unit startup, load variation, and stable operation, a dynamic operating domain is generated and formed that can accurately match different operating conditions of the unit. This dynamic operating domain is a dynamic parameter system that adapts to changes in unit operating conditions. The parameter boundaries and control ranges can be flexibly adjusted according to the actual operating status of the unit, fully meeting the actual control requirements of the unit under different operating conditions.

[0047] Based on this dynamic operating domain, the preset control model adapts to the dynamic changes of the unit's wide load range. This allows the model to quickly match the corresponding control logic and parameter configuration within the dynamic operating domain according to the real-time changes in the unit's load. This ensures that the model's operating strategy is highly compatible with any load state within the unit's wide load range, effectively solving the problem of the difficulty of adapting traditional control technologies under wide operating conditions. It also ensures the control accuracy of the unit when operating in a wide load range, allowing the unit to maintain a stable and efficient operating state under different load conditions.

[0048] In some embodiments, the method further includes: For group control scenarios involving multiple similar devices, models are established based on the control curves, device characteristics, and actual operating status of each device. Based on the modeling results of each device, control commands are assigned to the multiple similar devices to achieve optimal energy consumption control for a single device.

[0049] This control method can also be adapted to group control scenarios with multiple similar devices. In the process of group control, independent modeling is carried out for each device in the group control system. During the modeling process, the model is built strictly according to the control curve, device characteristics and actual operating status of each device. The control curve of each device reflects its unique control logic and operation adjustment law, the device characteristics determine its basic operating parameters and performance boundaries, and the actual operating status reflects the current real operating conditions of the device. The model built for a single device based on this exclusive information can accurately fit the device's own operation and control needs, so that the model of each device has exclusive adaptability. This is different from the unified modeling method in traditional group control, and ensures the accuracy of control of a single device from the modeling level.

[0050] After completing the modeling of all individual devices, the system will integrate and analyze the modeling results of each device, fully consider the operating characteristics, working condition differences and energy consumption potential of each device, and use this as the core basis to scientifically allocate control commands to multiple similar devices. The command allocation process abandons the traditional average allocation mode and realizes differentiated and precise allocation of control commands based on the modeling results of each device.

[0051] This instruction allocation method enables optimal energy consumption control of individual devices while meeting the overall control objectives of group control of multiple similar devices. It allows each device to operate in an optimal energy consumption state under its own control instructions, effectively overcoming the resource waste problem caused by the traditional average allocation mode, improving the overall energy utilization efficiency of the group control system of multiple similar devices, and ensuring that the group control system achieves the overall control objectives while taking into account the operational economy of individual devices, making the group control system more efficient and energy-saving.

[0052] Corresponding to the control method for the circulating fluidized bed unit described above, this invention also proposes a control device for the circulating fluidized bed unit. Since the device embodiments of this invention correspond to the method embodiments described above, details not disclosed in the device embodiments can be referred to in the method embodiments described above, and will not be repeated here.

[0053] Figure 2 This is a schematic diagram of the structure of a control device for a circulating fluidized bed unit provided in an embodiment of this disclosure, as shown below. Figure 2 As shown, it includes: Output unit 21 is used to generate control commands based on a preset control model and the real-time operating data of the unit, and output the control commands to the control loop corresponding to the unit; The adaptation unit 22 is used to collect the online operating data of the unit and continuously update the parameters of the preset control model through the online operating data to achieve dynamic adaptation to changes in the unit's operating conditions. The adjustment unit 23 is used to perform multi-objective optimization in a wide parameter space according to the load change of the unit, and dynamically adjust the operation strategy of the preset control model based on the optimization results.

[0054] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 3 As shown, the device includes: Modeling unit 24 is used to perform data modeling of the analog parameters of the entire circulating fluidized bed unit before the output unit generates control commands based on the preset control model and the real-time operating data of the unit. The inference unit 25 is used to simultaneously infer key variables in the unit that are difficult to measure directly through multimodal modeling and parameter soft measurement technology, and incorporate the inferred variables into the construction process of the preset control model.

[0055] Furthermore, in one possible implementation of this disclosure, the analog parameters include temperature parameters, pressure parameters, and flow rate parameters; the multimodal modeling method includes at least one of statistical analysis, Fourier transform, and Laplace transform.

[0056] Furthermore, in one possible implementation of this disclosure, the preset control model is constructed by fusing neural network algorithms and reinforcement learning algorithms.

[0057] Furthermore, in one possible implementation of the present disclosure, the changes in operating conditions include coal quality fluctuations and load variations.

[0058] Furthermore, in one possible implementation of this disclosure, the adjustment unit 23 is further configured to: Multi-objective comprehensive optimization of the unit is performed within a wide parameter space to form a dynamic operating domain that matches different operating conditions of the unit, and the dynamic changes of the unit in a wide load range are adapted based on the dynamic operating domain.

[0059] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 3 As shown, the device further includes: Unit 26 is established to create models for group control scenarios involving multiple similar devices, based on the control curves, device characteristics, and actual operating status of each device. The control unit 27 is used to assign control commands to the multiple similar devices according to the modeling results of each device, so as to achieve optimal energy consumption control of a single device.

[0060] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of the embodiments of this disclosure, and the principle is the same. Therefore, the embodiments of this disclosure are not limited thereto.

[0061] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0062] Figure 4A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0063] like Figure 4 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 402 or a computer program loaded from storage unit 408 into RAM (Random Access Memory) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. I / O (Input / Output) interface 405 is also connected to bus 404.

[0064] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0065] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the control methods for a circulating fluidized bed unit. For example, in some embodiments, the control methods for a circulating fluidized bed unit can be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the aforementioned control method for the circulating fluidized bed unit by any other suitable means (e.g., by means of firmware).

[0066] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0067] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0068] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0069] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0070] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0071] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0072] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0073] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0074] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A control method for a circulating fluidized bed unit, characterized in that, include: Control commands are generated based on a preset control model and the real-time operating data of the unit, and the control commands are output to the corresponding control loop of the unit. The online operating data of the unit is collected, and the parameters of the preset control model are continuously updated through the online operating data to achieve dynamic adaptation to changes in the unit's operating conditions. Based on the load changes of the unit, multi-objective optimization is performed within a wide parameter space, and the operation strategy of the preset control model is dynamically adjusted according to the optimization results.

2. The method according to claim 1, characterized in that, Before generating control commands based on a preset control model and the unit's real-time operating data, the method includes: Data modeling of analog parameters for the entire circulating fluidized bed unit system; Meanwhile, key variables that are difficult to measure directly in the unit are inferred through multimodal modeling and parameter soft measurement technology, and the inferred variables are incorporated into the construction process of the preset control model.

3. The method according to claim 2, characterized in that, The analog parameters include temperature, pressure, and flow rate parameters; the multimodal modeling method includes at least one of statistical analysis, Fourier transform, and Laplace transform.

4. The method according to claim 1, characterized in that, The preset control model is constructed by fusing neural network algorithms and reinforcement learning algorithms.

5. The method according to claim 1, characterized in that, The changes in operating conditions include fluctuations in coal quality and changes in load.

6. The method according to claim 1, characterized in that, The step of performing multi-objective optimization within a wide parameter space based on the load changes of the unit, and dynamically adjusting the operating strategy of the preset control model based on the optimization results, includes: Multi-objective comprehensive optimization of the unit is performed within a wide parameter space to form a dynamic operating domain that matches different operating conditions of the unit, and the dynamic changes of the unit in a wide load range are adapted based on the dynamic operating domain.

7. The method according to claim 1, characterized in that, The method further includes: For group control scenarios involving multiple similar devices, models are established based on the control curves, device characteristics, and actual operating status of each device. Based on the modeling results of each device, control commands are assigned to the multiple similar devices to achieve optimal energy consumption control for a single device.

8. A control device for a circulating fluidized bed unit, characterized in that, include: The output unit is used to generate control commands based on a preset control model and the real-time operating data of the unit, and output the control commands to the corresponding control loop of the unit; An adaptation unit is used to collect online operating data of the unit and continuously update the parameters of the preset control model through the online operating data to achieve dynamic adaptation to changes in the unit's operating conditions. The adjustment unit is used to perform multi-objective optimization within a wide parameter space based on the load changes of the unit, and dynamically adjust the operation strategy of the preset control model based on the optimization results.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

Images