Power plant water production system data processing and optimal scheduling method

Abstract

The invention discloses a power plant water production system data processing and optimal scheduling method comprising the following steps: obtaining key parameters in a power plant water production process, and carrying out combined filtering on the key parameters; performing feature extraction and fusion on the key parameters after combined filtering by using a convolutional neural network; based on the data after feature extraction and fusion, establishing a mathematical model for optimal distribution of the water production system of the power plant; and forming an optimal scheduling scheme according to a calculation result of the mathematical model and transmitting an optimal scheduling instruction. According to the method, a comprehensive filtering technology combining parameter adaptive Kalman filtering and dynamic mean filtering is introduced, so that errors in the data acquisition and transmission process are effectively reduced, and the processing precision of key data is remarkably improved; the optimal control scheme can be automatically generated through model calculation and an optimization algorithm, control instructions are transmitted in real time, intelligent and self-adaptive control over the water production system is achieved, the operation efficiency of the system is improved, and energy consumption and operation cost are remarkably reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing and scheduling, and in particular to a data processing and optimal scheduling method for a water production system of a power plant. Background Art

[0002] Data processing and optimal scheduling in power plant water production systems are key factors in ensuring stable system operation, improving efficiency and reducing costs. However, existing water production systems face many challenges in these aspects, which limits their full performance.

[0003] First, in terms of data processing, the existing system has the problem of insufficient accuracy. Due to errors in the data collection and transmission process, coupled with the limitations of the data processing algorithm itself, the monitoring and control of key data such as water quality parameters, flow, and pressure are not accurate enough, which not only affects the stability and efficiency of the water production system, but may also lead to waste of resources and increased costs. In addition, the lack of real-time data processing is also a significant problem. Complex algorithms and data transmission delays make it impossible for the system to respond to water quality changes or failures in a timely manner, reducing reliability and safety. At the same time, the water production system involves multiple subsystems and data sources. The data formats, units, and accuracy of different sources are different, which increases the difficulty of integration and makes it difficult to form a unified view, which is not conducive to overall optimization and control.

[0004] Secondly, in terms of optimal control, the current water production system is characterized by insufficient flexibility. The control strategy based on fixed mathematical models and parameter settings is difficult to adjust quickly when the working conditions change, which can easily lead to performance degradation or frequent failures. The problems of high energy consumption and low efficiency are also prominent, especially when the cooling effect is poor in summer and antifreeze measures increase energy consumption in winter, which further increases the operating cost. The application of intelligent control means is relatively lagging. Although the development of artificial intelligence technology has made it possible for real-time monitoring, fault prediction and adaptive control, the progress in this field is still limited. The degree of system optimization is also insufficient, especially in terms of sewage discharge rate optimization and condensate treatment. There is a lack of systematic methods and technologies, which restricts the improvement of overall performance. In addition, pollutants such as wastewater, waste gas and solid waste may be generated during the operation of the water production system. If improperly handled, it will cause pollution to the environment, and the existing environmental protection measures need to be improved. The complexity of the equipment and the difficulty of maintenance also lead to high maintenance costs. The lack of intelligent and remote monitoring means requires maintenance personnel to conduct frequent on-site inspections and repairs, which increases manpower and material costs.

[0005] In order to meet the above challenges, it is urgent to develop a new data processing and optimal scheduling method for power plant water production systems, which has higher data processing accuracy and real-time performance, and achieves energy saving, consumption reduction and environmental protection through flexible and intelligent control strategies. Summary of the invention

[0006] In view of the above existing problems, the present invention is proposed.

[0007] Therefore, the present invention provides a method for data processing and optimal scheduling of a power plant water production system to solve the problem that the existing water production system has many deficiencies in data processing accuracy, real-time performance, integration capability, control strategy flexibility, energy efficiency, intelligence level, system optimization degree, environmental protection and maintenance costs, which limits the overall performance and operating efficiency of the system.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0009] In a first aspect, the present invention provides a method for data processing and optimal scheduling of a water production system of a power plant, comprising: obtaining key parameters in the water production process of the power plant, and performing combined filtering on the key parameters; using a convolutional neural network to perform feature extraction and fusion on the key parameters after combined filtering; based on the data after feature extraction and fusion, establishing a mathematical model for optimal allocation of the water production system of the power plant; forming an optimal scheduling plan according to the calculation results of the mathematical model and transmitting the optimal scheduling instructions.

[0010] As a preferred solution of the power plant water system data processing and optimal scheduling method of the present invention, the combined filtering of the key parameters includes:

[0011] The current estimated value is derived from the state change of the power plant water system at the previous moment, so the state equation is expressed as:

[0012] x k =A k-1 x k-1 +B k-1 u k-1 +ω k-1

[0013] Among them, x k and x k-1 A represents the sensor transmission state variables at time k and time k-1 respectively, and is composed of the column vector of the data transmission state of each sensor. k-1 represents the system state transfer matrix, B k-1 Represents the input parameter relationship matrix, u k-1 represents the system input matrix, ω k-1 Represents the internal noise of the observed object and sets its variance to N Q , Gaussian distribution with expected value of 0; sensor measurement value z k The following relations are satisfied:

[0014] z k =H k x k +v k

[0015] Among them, H k is the sensor observation model, v k is the internal noise of the sensor and its variance is set to N R , a Gaussian distribution with an expected value of 0;

[0016] The state estimation of the current shot is calculated using the sensor data estimation results of the previous stage, where the calculation of the prediction stage is:

[0017]

[0018] in, It means using the optimal estimation result of the sensor in the previous shot to predict the state variable at the current moment. represents the system prediction estimate covariance at the current moment, P k-1 and Q k-1 They are respectively the active output and reactive output of the water-making system of the power plant;

[0019] Then calculate the covariance and Kalman gain:

[0020]

[0021] Among them, γ k is the difference between the actual measured value and the expected value, s k is the covariance matrix, K k is the optimal Kalman gain;

[0022] The calculated optimal Kalman gain is used to update the state variables and covariance estimates. The formula is expressed as:

[0023]

[0024] Among them, I is the identity matrix, and its dimension is the same as the system state matrix.

[0025] As a preferred solution of the power plant water system data processing and optimal scheduling method of the present invention, the combined filtering of the key parameters also includes:

[0026] Perform dynamic mean filtering on the key parameters after parameter adaptive Kalman filtering:

[0027]

[0028] Among them, o(k) is the sensor data output after dynamic mean filtering.

[0029] As a preferred solution of the data processing and optimal scheduling method for the power plant water system of the present invention, the feature extraction of the key parameters after the combined filtering by using a convolutional neural network includes:

[0030] Assuming the output function of the convolutional neural network is f(x), the actual output function of the deep hybrid convolutional neural network is h(x)=f(x)w n+1 (t)+x(t), where w n+1 (t) represents the weight variable of the previous stage, and x(t) is the sensor output value after each data preprocessing;

[0031] Feature extraction of sensor data is expressed as:

[0032]

[0033] in, represents the feature extraction results of various sensors, and h′ represents the partial derivative results of each point.

[0034] As a preferred solution of the power plant water system data processing and optimization scheduling method of the present invention, the method of fusing the key parameters after the combined filtering by using a convolutional neural network includes:

[0035] The energy function θ is established using the Fisher criterion and introduced into the eigenvalue fusion stage:

[0036]

[0037] in, is the similarity function, κ * is the penalty function, P is the output residual, smooth(t) represents the intra-class constraint, and h k and d k represent subfunction and distance function respectively.

[0038] As a preferred solution of the method for data processing and optimal dispatching of a water production system of a power plant described in the present invention, the method for establishing a mathematical model for optimal allocation of the water production system of a power plant includes:

[0039] The water replenishment task is allocated to n water production subsystems to minimize their total water consumption. The mathematical model for optimizing the allocation of the water production system of the power plant is established with the goal of minimizing the total water consumption in the water production process of the power plant, which is expressed as:

[0040]

[0041] Among them, Q represents the total water consumption of this water production process, A k , B k , C kis the water consumption characteristic coefficient of the kth water production subsystem, P k Represents the output of the kth water-making subsystem.

[0042] As a preferred solution of the method for data processing and optimal dispatching of a water production system of a power plant described in the present invention, the constraints of the mathematical model for optimal allocation of the water production system of a power plant include:

[0043]

[0044] in, represents the lower limit of the safe operation output of the k-th water production subsystem, It represents the lower limit of safe operation output of the kth water production subsystem.

[0045] In a second aspect, the present invention provides a data processing and optimization scheduling system for a water production system of a power plant, comprising:

[0046] A data preprocessing module is used to obtain key parameters in the water production process of the power plant and perform combined filtering on the key parameters;

[0047] A data extraction and fusion module, used for extracting and fusing features of the key parameters after the combined filtering using a convolutional neural network;

[0048] The optimization scheduling module is used to establish a mathematical model for optimizing the allocation of the water production system of the power plant based on the feature extraction and fusion data, form an optimal scheduling plan according to the calculation results of the mathematical model, and transmit the optimal scheduling instructions.

[0049] In a third aspect, the present invention provides an electronic device, comprising:

[0050] Memory and processor;

[0051] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the power plant water system data processing and optimization scheduling method are implemented.

[0052] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the power plant water system data processing and optimal scheduling method.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] ① The present invention effectively reduces the error in the data acquisition and transmission process by introducing a comprehensive filtering technology that combines the parameter adaptive Kalman filtering method with the dynamic mean filtering, and significantly improves the processing accuracy of key data such as water quality parameters, flow, and pressure. At the same time, by optimizing the data processing algorithm, reducing the computational complexity and increasing the data processing speed, the real-time monitoring and rapid response of the water production system can be achieved, and the stability and safety of the system can be enhanced;

[0055] ② The present invention uses convolutional neural networks to extract and fuse multi-sensor data, effectively solving the integration problems caused by differences in data formats, units, precision, etc. between different data sources. By establishing energy functions and introducing eigenvalue fusion technology, the seamless fusion of multi-sensor data in the water system is achieved, providing a unified and accurate data view for the overall optimization and control of the system;

[0056] ③ The present invention designs two optimal control objectives: minimum total cost (water consumption) and minimum equipment start-up and shutdown cost, and establishes corresponding mathematical models and constraints. The optimal control scheme can be automatically generated through model calculation and optimization algorithm, and control instructions can be transmitted in real time to achieve intelligent and adaptive control of the water production system, which not only improves the operating efficiency of the system, but also significantly reduces energy consumption and operating costs;

[0057] ④ The present invention applies artificial intelligence algorithms to the control of water production systems to achieve real-time monitoring, fault prediction and adaptive control of the system. By introducing intelligent algorithms, the automation and intelligence level of the system are improved, the frequency and difficulty of manual intervention are reduced, and a more convenient and efficient means of operation and maintenance is provided for operation and maintenance personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0059] Figure 1 A schematic diagram of the overall process logic of a method for data processing and optimal scheduling of a water production system in a power plant according to an embodiment of the present invention;

[0060] Figure 2 The present invention is a flowchart of a method for data processing and optimal scheduling of a water production system in a power plant according to an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0062] Example 1

[0063] Reference Figure 1-Figure 2 As an embodiment of the present invention, a method for data processing and optimal scheduling of a water production system in a power plant is provided. Figure 1 The specific steps shown include:

[0064] S100: obtaining key parameters in the water production process of the power plant and performing combined filtering on the key parameters;

[0065] S200: Use convolutional neural network to extract and fuse the key parameters after combined filtering;

[0066] S300: Based on the feature extraction and fusion data, a mathematical model for optimizing the allocation of the power plant water system is established;

[0067] S400: Form an optimal scheduling plan according to the calculation results of the mathematical model and transmit the optimal scheduling instruction.

[0068] It should be noted that ① the present invention effectively reduces the errors in the data acquisition and transmission process by introducing a comprehensive filtering technology that combines a parameter adaptive Kalman filtering method with a dynamic mean filter, and significantly improves the processing accuracy of key data such as water quality parameters, flow, and pressure. At the same time, by optimizing the data processing algorithm, reducing the computational complexity, and improving the data processing speed, it can achieve real-time monitoring and rapid response of the water production system, and enhance the stability and security of the system; ② the present invention uses a convolutional neural network to extract and fuse multi-sensor data, effectively solving the integration problems caused by differences in data format, unit, precision, etc. between different data sources. By establishing an energy function and introducing eigenvalue fusion technology, seamless fusion of multi-sensor data of the water production system is achieved, providing a unified and accurate data view for the overall optimization and control of the system; ③ the present invention designs two optimal control objectives: minimum total cost (water consumption) and minimum equipment start-up and shutdown cost, and establishes corresponding mathematical models and constraints. Through model calculation and optimization algorithm, the optimal control scheme can be automatically generated, and control instructions can be transmitted in real time to realize intelligent and adaptive control of the water production system, which not only improves the operating efficiency of the system, but also significantly reduces energy consumption and operating costs; ④ The present invention applies artificial intelligence algorithms to the control of the water production system to realize real-time monitoring, fault prediction and adaptive control of the system. Through the introduction of intelligent algorithms, the automation and intelligence level of the system are improved, the frequency and difficulty of manual intervention are reduced, and a more convenient and efficient means of operation and maintenance is provided for operation and maintenance personnel.

[0069] In the embodiments of the present application, Figure 2 The above step S100 performs comprehensive filtering on key data such as water quality parameters, flow, pressure, etc. in each water production system, including initialization parameters, design covariance estimation, sensor internal noise covariance, overall observation covariance, state prediction and calculation of disturbance noise covariance, cyclic update of state estimation and error covariance, and data mean filtering. Specifically, it includes:

[0070] The comprehensive filter can be composed of two parts: parameter adaptive Kalman filter and dynamic mean filter. The current estimated value is derived from the state change of the water system of the power plant at the previous moment, and the state equation is expressed as:

[0071] x k =A k-1 x k-1 +B k-1 u k-1 +ω k-1

[0072] Among them, x k and x k-1 A represents the sensor transmission state variables at time k and time k-1 respectively, and is composed of the column vector of the data transmission state of each sensor. k-1represents the system state transfer matrix, B k-1 Represents the input parameter relationship matrix, u k-1 represents the system input matrix, ω k-1 Represents the internal noise of the observed object and sets its variance to N Q , Gaussian distribution with expectation of 0;

[0073] Sensor measurement value z k The following relations are satisfied:

[0074] z k =H k x k +v k

[0075] Among them, H k is the sensor observation model, v k is the internal noise of the sensor and its variance is set to N R , a Gaussian distribution with an expected value of 0;

[0076] The adaptive Kalman filter can be generally divided into two stages: prediction and update. That is, the state estimation of the current shot is calculated using the sensor data estimation results of the previous stage. The calculation of the prediction stage is:

[0077]

[0078] in, It means using the optimal estimation result of the sensor in the previous shot to predict the state variable at the current moment. represents the system prediction estimate covariance at the current moment, P k-1 and Q k-1 They are respectively the active output and reactive output of the water-making system of the power plant;

[0079] Then calculate the covariance and Kalman gain:

[0080]

[0081] Among them, γ k is the difference between the actual measured value and the expected value, s k is the covariance matrix, K k is the optimal Kalman gain;

[0082] The calculated optimal Kalman gain is used to update the state variables and covariance estimates. The formula is expressed as:

[0083]

[0084] Among them, I is the identity matrix, and its dimension is the same as the system state matrix.

[0085] Furthermore, dynamic mean filtering is performed on the key parameters after the parameter adaptive Kalman filtering:

[0086]

[0087] Among them, o(k) is the sensor data output after dynamic mean filtering.

[0088] It should be noted that the above step S100 not only effectively reduces the impact of noise and outliers on data analysis, but also enhances the stability and reliability of the data, laying the foundation for the subsequent use of convolutional neural networks for feature extraction and fusion.

[0089] In the embodiment of the present application, the above step S200 uses a convolutional neural network to extract and fuse the key parameters after the combined filtering, including:

[0090] Assuming the output function of the convolutional neural network is f(x), the actual output function of the deep hybrid convolutional neural network is h(x)=f(x)w n+1 (t)+x(t), where w n+1 (t) represents the weight variable of the previous stage, and x(t) is the sensor output value after each data preprocessing;

[0091] Feature extraction of sensor data is expressed as:

[0092]

[0093] in, represents the feature extraction results of various sensors, and h′ represents the partial derivative results of each point;

[0094] Furthermore, in order to better perform data fusion, the energy function θ is established using the Fisher criterion, and the energy function is introduced into the eigenvalue fusion stage:

[0095]

[0096] in, is the similarity function, κ * is the penalty function, P is the output residual, smooth(t) represents the intra-class constraint, and h k and d k Denote sub-function and distance function respectively. The above method can realize the multi-sensor data fusion operation of water system.

[0097] It should be noted that the above step S200 can effectively capture the intrinsic connections and patterns between different key parameters through the powerful characterization ability of convolutional neural networks, achieve high abstraction and effective fusion of data features, and thus provide high-quality data support for the subsequent establishment of accurate mathematical models, so that the optimal scheduling plan formed is closer to the actual operating conditions, and improve the optimization allocation efficiency of the power plant water system and the scientific nature of the decision-making.

[0098] In the embodiment of the present application, the above step S300 establishes a mathematical model for optimizing the allocation of the water production system of the power plant based on the feature extraction and fusion data, including:

[0099] The water replenishment task is allocated to n water production subsystems to minimize their total water consumption. The mathematical model for optimizing the allocation of the water production system of the power plant is established with the goal of minimizing the total water consumption in the water production process of the power plant, which is expressed as:

[0100]

[0101] Among them, Q represents the total water consumption of this water production process, A k , B k , C k is the water consumption characteristic coefficient of the kth water production subsystem, P k Represents the output of the kth water-making subsystem.

[0102] Furthermore, according to the total water replenishment of the power plant, the following constraints can be designed for the safe operation range of the mathematical model for optimizing the allocation of the power plant water system:

[0103]

[0104] in, represents the lower limit of the safe operation output of the k-th water production subsystem, It represents the lower limit of safe operation output of the kth water production subsystem.

[0105] It should be noted that the above step S300 can not only more realistically reflect the complex dynamic relationships and internal laws in the water production process of the power plant, but also effectively deal with various uncertainties and nonlinear problems that may arise in the water production system, and provide a solid theoretical basis and technical support for achieving the optimal allocation of resources, thereby ensuring that the final scheduling plan achieves the best balance in improving water production efficiency, reducing costs and ensuring water quality safety, thereby enhancing the overall performance and competitiveness of the power plant's water production system.

[0106] In an embodiment of the present application, the above-mentioned step S400 forms an optimal scheduling plan and transmits the optimal scheduling instructions based on the calculation results of the mathematical model, thereby achieving seamless connection from data analysis to actual action, and also ensuring that the operation of the power plant water production system can closely follow the guidance of the optimization model and dynamically respond to various changing conditions, thereby significantly improving water production efficiency, resource utilization efficiency and water quality control level, while reducing operating costs and energy consumption, and ultimately enhancing the flexibility, reliability and economy of the entire water production system.

[0107] Example 2

[0108] This embodiment provides a power plant water system data processing and optimization scheduling system, including a data preprocessing module, a data extraction and fusion module, and an optimization scheduling module;

[0109] Specifically, the data preprocessing module is used to obtain key parameters in the water production process of the power plant and perform combined filtering on the key parameters;

[0110] Specifically, the data extraction and fusion module is used to perform feature extraction and fusion of key parameters after combined filtering using a convolutional neural network;

[0111] Specifically, the optimization scheduling module is used to establish a mathematical model for optimizing the allocation of the power plant water production system based on feature extraction and fusion data, form an optimal scheduling plan according to the calculation results of the mathematical model, and transmit the optimal scheduling instructions.

[0112] It should be noted that the technical solution of the system for data processing and optimal scheduling of the power plant water production system and the technical solution of the above-mentioned technical solution of the power plant water production system data processing and optimal scheduling method belong to the same concept. For the details not described in detail in the technical solution of the system for data processing and optimal scheduling of the power plant water production system in this embodiment, please refer to the description of the technical solution of the above-mentioned technical solution of the power plant water production system data processing and optimal scheduling method.

[0113] The above-mentioned unit modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above-mentioned modules.

[0114] This embodiment also provides an electronic device, which includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for data processing and optimal scheduling of a power plant water system is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0115] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method proposed in the above embodiment is implemented.

[0116] The storage medium proposed in this embodiment and the method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0117] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0118] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0119] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages.

[0120] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0123] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0124] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for data processing and optimal scheduling of a water production system in a power plant, characterized in that: include: Acquire key parameters in the water production process of the power plant, and perform combined filtering on the key parameters; Using a convolutional neural network to extract and fuse the key parameters after the combined filtering; Based on the feature extraction and fused data, a mathematical model for optimizing the allocation of the water production system of the power plant is established; An optimal scheduling scheme is formed according to the calculation results of the mathematical model and an optimal scheduling instruction is transmitted.

2. The method for data processing and optimal scheduling of a water production system in a power plant according to claim 1, characterized in that: The combined filtering of the key parameters comprises: The current estimated value is derived from the state change of the power plant water system at the previous moment, so the state equation is expressed as: x k =A k-1 x k-1 +B k-1 u k-1 +ω k-1 Among them, x k and x k-1 A represents the sensor transmission state variables at time k and time k-1 respectively, and is composed of the column vector of the data transmission state of each sensor. k-1 represents the system state transfer matrix, B k-1 Represents the input parameter relationship matrix, u k-1 represents the system input matrix, ω k-1 Represents the internal noise of the observed object and sets its variance to N Q , Gaussian distribution with expected value of 0; sensor measurement value z k The following relations are satisfied: z k =H k x k +v k Among them, H k is the sensor observation model, v k is the internal noise of the sensor and its variance is set to N R , a Gaussian distribution with an expected value of 0; The state estimation of the current shot is calculated using the sensor data estimation results of the previous stage, where the calculation of the prediction stage is: in, It means using the optimal estimation result of the sensor in the previous shot to predict the state variable at the current moment. represents the system prediction estimate covariance at the current moment, P k-1 and Q k-1 They are respectively the active output and reactive output of the water-making system of the power plant; Then calculate the covariance and Kalman gain: Among them, γ k is the difference between the actual measured value and the expected value, s k is the covariance matrix, K k is the optimal Kalman gain; The calculated optimal Kalman gain is used to update the state variables and covariance estimates. The formula is expressed as: Among them, I is the identity matrix, and its dimension is the same as the system state matrix.

3. The method for data processing and optimal scheduling of a water production system in a power plant according to claim 2, characterized in that: The combined filtering of the key parameters further comprises: Perform dynamic mean filtering on the key parameters after parameter adaptive Kalman filtering: Among them, o(k) is the sensor data output after dynamic mean filtering.

4. The method for data processing and optimal scheduling of a water production system in a power plant according to claim 3, characterized in that: The method of extracting features of the key parameters after the combined filtering by using a convolutional neural network includes: Assuming the output function of the convolutional neural network is f(x), the actual output function of the deep hybrid convolutional neural network is h(x)=f(x)w n+1 (t)+x(t), where w n+1 (t) represents the weight variable of the previous stage, and x(t) is the sensor output value after each data preprocessing; Feature extraction of sensor data is expressed as: in, represents the feature extraction results of various sensors, and h′ represents the partial derivative results of each point.

5. The method for data processing and optimal scheduling of a water production system in a power plant according to claim 4, characterized in that: The step of fusing the key parameters after the combined filtering by using a convolutional neural network includes: The energy function θ is established using the Fisher criterion and introduced into the eigenvalue fusion stage: in, is the similarity function, κ * is the penalty function, P is the output residual, smooth(t) represents the intra-class constraint, and h k and d k represent subfunction and distance function respectively.

6. The method for data processing and optimal scheduling of a water production system in a power plant according to claim 5, characterized in that: The mathematical model for optimizing the distribution of the water production system of the power plant includes: The water replenishment task is allocated to n water production subsystems to minimize their total water consumption. The mathematical model for optimizing the allocation of the water production system of the power plant is established with the goal of minimizing the total water consumption in the water production process of the power plant, which is expressed as: Among them, Q represents the total water consumption of this water production process, A k , B k , C k is the water consumption characteristic coefficient of the kth water production subsystem, P k Represents the output of the kth water-making subsystem.

7. The method for data processing and optimal scheduling of a water production system in a power plant according to claim 6, characterized in that: The constraints of the mathematical model for optimizing the allocation of the water production system of the power plant include: in, represents the lower limit of the safe operation output of the k-th water production subsystem, It represents the lower limit of safe operation output of the kth water production subsystem.

8. A system using the power plant water system data processing and optimization scheduling method as claimed in any one of claims 1 to 7, characterized in that: include: A data preprocessing module is used to obtain key parameters in the water production process of the power plant and perform combined filtering on the key parameters; A data extraction and fusion module, used for extracting and fusing features of the key parameters after the combined filtering using a convolutional neural network; The optimization scheduling module is used to establish a mathematical model for optimizing the allocation of the water production system of the power plant based on the feature extraction and fusion data, form an optimal scheduling plan according to the calculation results of the mathematical model, and transmit the optimal scheduling instructions.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the power plant water system data processing and optimal scheduling method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the power plant water system data processing and optimal scheduling method as described in any one of claims 1 to 7.

Images