Power plant water network leakage prediction method and system based on dynamic water balance and ARIMA model

Abstract

The invention provides a power plant water network leakage prediction method and system based on dynamic water balance and an ARIMA model, and the method comprises the steps: carrying out the dynamic water balance calculation based on a collected first real-time operation parameter of a power plant water network, and recognizing a water amount imbalance region in an electric field water network; performing multi-level analysis on the basis of the obtained instantaneous operation parameters of the key nodes in the power plant water network and the water quantity imbalance region, and determining leakage points; an ARIMA prediction model is constructed based on the obtained historical operation parameters of the power plant water network, and the first real-time operation parameters are adopted for training; and predicting the power plant water network based on the trained ARIMA prediction model to obtain a predicted leakage amount. According to the method, automation and intellectualization of leakage prediction are realized, the safety risk caused by manual inspection is greatly reduced, the management level and the operation efficiency of a power plant water network are remarkably improved, and a powerful guarantee is provided for safe and stable operation of a power plant.

Description

Technical Field

[0001] The present invention belongs to the technical field of water network leakage monitoring and prediction, and in particular to a method and system for predicting water network leakage in a power plant based on dynamic water balance and ARIMA model. Background Art

[0002] In the daily operation of a power plant, the water network system undertakes important tasks such as cooling and transportation. Its stable operation is crucial to the overall production of the power plant. During operation, the water network is prone to leakage due to factors such as pipe materials, geology, and installation, which restricts the effective use of water resources and the efficient operation of the power plant.

[0003] In response to water network leakage, the traditional leakage detection method relies on manual inspections and regular inspections. Manual inspections often require staff to check one by one along the long water network pipes. Due to the wide distribution range and complex environment of the water network system, and the large number of pipes, valves, water pumps and other equipment contained in the water network system, it not only consumes a lot of manpower, material resources and time, but also is difficult to be comprehensive and detailed. Although regular inspections can detect leakage problems to a certain extent, due to the limitations of the inspection cycle, it is difficult to capture the occurrence of leakage in time. This lagging detection method makes it impossible to detect the leakage area in a timely and accurate manner, resulting in a large amount of water resources being lost unknowingly. In the long run, it will not only cause serious waste of water resources and increase the operating costs of power plants, but may also cause more serious safety accidents because the leakage problem cannot be solved in time, affecting the safe production of power plants. Summary of the Invention

[0004] In order to solve the problems of low timeliness and high safety risks of manual inspections and regular testing of existing water network leakage, the present invention provides a power plant water network leakage prediction method and system based on dynamic water balance and ARIMA model, thereby improving the operational safety and water resource utilization efficiency of the power plant water network.

[0005] To achieve the above object, the present invention provides the following technical solutions: The present invention proposes a method for predicting water network leakage in a power plant based on dynamic water balance and ARIMA model, which includes the following steps: Performing dynamic water balance calculation based on the collected first real-time operating parameters of the power plant water network to identify water imbalance areas in the power plant water network; Based on the instantaneous operating parameters of key nodes in the power plant water network and the water imbalance areas, multi-level analysis is carried out to determine the leakage points; Building an ARIMA prediction model based on the acquired historical operating parameters of the power plant water network and training it using the first real-time operating parameters; The power plant water network is predicted based on the trained ARIMA prediction model to obtain the predicted leakage.

[0006] Preferably, the dynamic water balance calculation is performed based on the first real-time operating parameter collected from the power plant water network, including: The power plant water network is divided into several sub-areas according to the physical topology, and each sub-area contains several nodes; Collecting first real-time operating parameters of a plurality of nodes to obtain a preprocessing data set; Calculating a water volume change value in the power plant water network based on the pre-processed flow data in each of the sub-areas; Based on the water volume change value, abnormal sub-areas and normal sub-areas in the plurality of sub-areas are determined; The water volume in the sub-area is calculated based on the preprocessed data set, and the water volume in the sub-area of the normal area is compared with the water volume in the sub-area of the abnormal area. The abnormal areas corresponding to the water volume differences exceeding the preset difference range are screened out and recorded as water imbalance areas.

[0007] Preferably, the first real-time operating parameter includes flow data and pressure data.

[0008] Preferably, a multi-level analysis is performed based on the acquired instantaneous operating parameters of key nodes in the power plant water network and the water imbalance area to determine the leakage point, including: Acquire first instantaneous operating parameters of key nodes in the water imbalance area; Calculating an average instantaneous loss based on the first instantaneous operating parameter using a dynamic water balance calculation model; Compare the average instantaneous loss with a preset first expected value range. If the average instantaneous loss exceeds the first expected value range, mark the key node and the nodes on the same pipeline as the key node as abnormal points. Obtain the second instantaneous operating parameters of the abnormal point; Based on the second instantaneous operating parameter, the second instantaneous loss amount of the abnormal point is calculated, and the second instantaneous loss amount is compared with the preset second expected value range. If the second instantaneous loss amount exceeds the first expected value range, the node is marked as a leakage point.

[0009] Preferably, an ARIMA prediction model is constructed based on the acquired historical operating parameters of the power plant water network, including: Obtain historical data of the power plant water network and process the historical data set; After sorting the data points in the historical data set based on the time series, performing unit root test and difference processing to obtain a stationary data set; Draw the autocorrelation function graph and partial autocorrelation function graph of the stationary data set, obtain the truncation and tailing characteristics of the autocorrelation function graph and partial autocorrelation function graph, and determine the autoregressive order and sliding average order; Based on the autoregressive order and the sliding average order, multiple ARIMA models are fitted, and the information criterion value and Bayesian information criterion value of each ARIMA model are calculated. The ARIMA model with the smallest information criterion value or the smallest Bayesian information criterion value is selected as the optimal model to create an ARIMA forecasting model.

[0010] Preferably, the training ARIMA prediction model is:

[0011] in, is the predicted leakage amount, is a constant term, is the autoregressive coefficient, is the sliding average coefficient, is the error term.

[0012] Preferably, the power plant water network is predicted based on the trained ARIMA prediction model, including: The historical parameters of the leakage point are obtained, and the historical parameters are input into the trained ARIMA prediction model for prediction to obtain the predicted leakage amount of the power plant water network within the expected time.

[0013] The present invention provides a power plant water network leakage prediction system based on dynamic water balance and ARIMA model, and applies a power plant water network leakage prediction method based on dynamic water balance and ARIMA model, including: The acquisition module is configured to: acquire first real-time operating parameters of the power plant water network and obtain second operating parameters of key nodes in the power plant water network; The dynamic water balance processing module is configured to: calculate the actual leakage amount based on the node pressure data in the water imbalance area; The multi-level analysis module is configured to: perform multi-level analysis based on the second operating parameters of key nodes in the power plant water network and the water imbalance area to determine the leakage point; A model building module is configured to: build an ARIMA forecasting model and train it using the historical operating parameters of the power plant water network and the first real-time operating parameters; The prediction module is configured to: predict the power plant water network based on the trained ARIMA prediction model to obtain the predicted leakage amount; The output module is configured to output the predicted leakage amount.

[0014] The present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable in the processor. When the processor executes the computer program, the processor implements the steps of a method for predicting water network leakage in a power plant based on dynamic water balance and an ARIMA model.

[0015] The present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the computer program implements the steps of a method for predicting water network leakage in a power plant based on dynamic water balance and ARIMA model.

[0016] Compared with the prior art, the present invention has the following beneficial technical effects: The present invention provides a power plant water network leakage prediction method based on dynamic water balance and ARIMA model. The method performs dynamic water balance calculation by real-time collection of the first operating parameters of the power plant water network, accurately identifies water imbalance areas, and uses the instantaneous operating parameters of key nodes and the water imbalance areas for multi-level analysis to quickly determine leakage points, thereby significantly improving the accuracy and efficiency of leakage positioning. By constructing an ARIMA prediction model based on historical operating parameters and training it with real-time operating parameters, the model can accurately predict the future leakage of the power plant water network, thereby realizing the automation and intelligence of leakage prediction, greatly reducing the safety risks brought about by manual inspections, significantly improving the management level and operating efficiency of the power plant water network, and providing a strong guarantee for the safe and stable operation of the power plant.

[0017] Furthermore, this method divides the power plant water network into several sub-areas according to the physical topology, each of which contains several nodes. By collecting the real-time operating parameters of these nodes, a preprocessed data set is obtained. Based on the preprocessed flow data in each sub-area, the water volume change value in the power plant water network is calculated, and then abnormal sub-areas and normal sub-areas are determined. By comparing the water volume in the sub-areas of the normal and abnormal areas, abnormal areas corresponding to water volume differences exceeding the preset difference range are screened out and recorded as water imbalance areas. This achieves rapid positioning and accurate identification of water imbalance areas. An ARIMA prediction model is constructed using historical operating parameters and trained using real-time operating parameters, enabling the model to accurately predict future leakage in the power plant water network, improving the accuracy and efficiency of leakage prediction.

[0018] Furthermore, this method obtains the first instantaneous operating parameters of key nodes in the water imbalance area, calculates the average instantaneous loss using a dynamic water balance calculation model, and compares this with a preset first expected value range. If the average instantaneous loss exceeds the first expected value range, the key node and the nodes on the same pipeline are marked as outliers. The second instantaneous operating parameters of the outlier point are then obtained, and the second instantaneous loss of the outlier point is calculated and compared with a preset second expected value range. If the second instantaneous loss exceeds the expected value range, the node is marked as a leakage point. This achieves precise positioning and rapid identification of leakage points, significantly improving the efficiency and accuracy of leakage detection.

[0019] Furthermore, this method forms a high-quality historical data set by comprehensively acquiring and carefully processing historical data, ensuring the integrity and accuracy of the data, sorting the data in time series, performing unit root tests and difference processing on the data to obtain a stationary data set, eliminating trend and seasonal factors in the data, making the data more analyzable, and accurately obtaining truncation and tailing characteristics by drawing autocorrelation function graphs and partial autocorrelation function graphs, thereby scientifically determining the autoregressive order and sliding average order, providing key parameters for model construction, fitting multiple ARIMA models and calculating the information criterion value and Bayesian information criterion value, selecting the optimal model, and ensuring the rationality and effectiveness of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of a flow chart of a method for predicting water network leakage in a power plant based on dynamic water balance and ARIMA model provided by the present invention; Figure 2 A schematic diagram of a computer device provided in accordance with an embodiment of the present invention; Figure 3 The block diagram of a chip provided according to one embodiment of the present invention is shown. DETAILED DESCRIPTION

[0021] Hereinafter, only certain exemplary embodiments are briefly described. As will be appreciated by those skilled in the art, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and description are to be considered as illustrative in nature and not restrictive.

[0022] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0023] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0024] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0025] This paper proposes a method for predicting water network leakage in power plants based on dynamic water balance and ARIMA model. Figure 1 As shown, the following steps are included: Performing dynamic water balance calculation based on the collected first real-time operating parameters of the power plant water network to identify water imbalance areas in the power plant water network; Specifically, the power plant water network is divided into several sub-areas according to the physical topology, each sub-area includes several nodes, and collection sensors, such as flow sensors and pressure sensors, are arranged on each node; the collection sensors arranged in the power plant water network perform real-time collection to obtain first real-time operating parameters, and multi-channel redundant collection technology is used during the collection process to ensure data reliability, wherein the first real-time operating parameters include flow data and pressure data; Preprocess the first real-time operating parameter to ensure data integrity, that is, eliminate noise from the flow data, pressure data, and temperature data using Kalman filtering, and then use linear interpolation to fill in short-term missing data (<5 seconds) in the denoised flow data and pressure data to obtain a preprocessed data set; The mean value method is used to calculate the average pressure value of the power plant water network based on the pressure data in the preprocessing data set. The dynamic water balance calculation model is used to calculate the leakage through the flow data and the average pressure value. .

[0026] The dynamic water balance calculation model is:

[0027] in, is the water inlet flow rate, is the water flow rate, is the average pressure value.

[0028] The leakage Compare with the preset loss range. If the leakage If the loss exceeds the preset range, it means there is leakage in the power plant water network; The water volume change value in the power plant water network is calculated by pre-processing the flow data in each sub-area , the specific calculation process is:

[0029] in, Indicates the change in water volume in the sub-area at time t (unit: m 3 ), is the water inlet flow rate (unit: m 3 / s), is the water flow rate (unit: m 3 / s), is the actual water loss in the power plant water network (unit: m 3 / s).

[0030] A change curve map is drawn by plotting the change value ΔV(t) of the water volume in the sub-region within a preset time period to obtain a water volume change curve of the sub-region, and the water volume change curve of the sub-region is analyzed. For example, if the water volume change curve of the sub-region is stable, that is, as time goes by, the water volume change curve of the sub-region fluctuates within a preset change range, then the node is marked as a normal sub-region; if the water volume change curve of the sub-region is initially high and gradually decreases as time goes by, or as time goes by, the water volume change curve fluctuates within a preset change range, then the sub-region is marked as an abnormal sub-region; Obtain the flow data collected at the key nodes in each sub-area, and calculate the water volume in the sub-area through the flow data ; The specific calculation process is:

[0031] in, is the amount of water in the sub-region, is the flow rate at the joint point in the sub-region, is the time interval.

[0032] By dividing the amount of water in the sub-area marked as normal area The amount of water in the sub-area marked as anomaly Compare and obtain the water volume difference, compare the water volume difference with the preset difference range, and screen out the abnormal areas where the water volume difference exceeds the preset difference range, and record them as water volume imbalance areas.

[0033] Based on the instantaneous operating parameters of key nodes in the power plant water network and the water imbalance areas, multi-level analysis is carried out to determine the leakage points; Specifically, the position of the key node in the water imbalance area is obtained, and the first instantaneous operating parameter of the key node is obtained, that is, the first instantaneous flow and the first instantaneous pressure of the key node are obtained, and the first instantaneous flow and the first instantaneous pressure are respectively calculated by the mean method to obtain the average instantaneous flow and the average instantaneous pressure of the key node. The average instantaneous flow and the average instantaneous pressure are passed through the dynamic water balance calculation model to calculate the average instantaneous loss of the key node, and the average instantaneous loss is compared with a preset first expected value range. If the average instantaneous loss exceeds the first expected value range, the key node and the nodes on the same pipeline as the key node are marked as abnormal points; Obtain the second instantaneous operating parameters of the abnormal point, that is, obtain the second instantaneous flow and second instantaneous pressure of the abnormal point, calculate the second instantaneous loss of the abnormal point through the dynamic water balance calculation model, and compare the second instantaneous loss with the preset second expected value range. If the second instantaneous loss exceeds the first expected value range, mark the node as a leakage point.

[0034] Building an ARIMA prediction model based on the acquired historical operating parameters of the power plant water network and training it using the first real-time operating parameters; Specifically, historical data of the power plant water network is obtained, and a historical data set is processed, namely, the historical flow data and historical pressure data of the power plant water network. The quartiles of the historical flow data and the historical pressure data are calculated respectively, and the data exceeding 1.5 times the interquartile range is marked as the first outlier. The means of the historical flow data and the historical pressure data are calculated respectively to obtain the historical flow mean and the historical pressure mean. The standardized distance between the historical flow mean and the historical flow data points is calculated, and the standardized distance between the historical pressure mean and the historical pressure data points is calculated. The historical flow data points and the historical pressure data points exceeding the preset standardized distance range are marked as the second outlier. The second outlier and the first outlier are deleted, and the interpolation method is used to fill in the gaps to obtain the historical flow data set and the historical pressure data set.

[0035] The data points in the historical flow data set and the historical pressure data set are sorted based on the time series to obtain the historical time series flow data set and the historical time series pressure data set. The historical time series flow data set and the historical time series pressure data set are subjected to a unit root test to determine whether the data is stationary. If it is stationary, it is retained. If it is not stationary, it is subjected to difference processing to obtain a stationary data set. Draw the autocorrelation function graph and the partial autocorrelation function graph of the stationary data set, obtain the truncation and tailing characteristics of the autocorrelation function graph and the partial autocorrelation function graph, that is, obtain the order when the autocorrelation function graph and the partial autocorrelation function graph rapidly decay to near zero, and determine the autoregressive order and the sliding average order; Multiple ARIMA models are obtained by fitting the autoregressive order and the moving average order, and the information criterion value and Bayesian information criterion value of each ARIMA model are calculated. The ARIMA model with the smallest information criterion value or Bayesian information criterion value is selected as the best model to create an ARIMA forecasting model. The pre-processed first real-time operating parameters are input into the ARIMA forecasting model for multiple iterations, and the parameters of the forecasting model are estimated and adjusted through maximum likelihood estimation to train the ARIMA forecasting model.

[0036] The ARIMA forecast model is trained as:

[0037] in, is the predicted leakage amount, is a constant term, is the autoregressive coefficient, is the sliding average coefficient, is the error term.

[0038] The power plant water network is predicted based on the trained ARIMA prediction model to obtain the predicted leakage.

[0039] The historical parameters of the leakage points in the power plant water network, namely the historical flow rate and historical pressure of the leakage points, are obtained. The historical flow rate and historical pressure of the leakage points are input into the trained ARIMA prediction model for prediction, and the predicted leakage amount of the power plant water network within the expected time is obtained.

[0040] Combine the predicted leakage with the real-time monitoring data Compare and calculate the error value. If the error exceeds the set threshold τ, a warning is sent The present invention also proposes a power plant water network leakage prediction system based on dynamic water balance and ARIMA model, and applies a power plant water network leakage prediction method based on dynamic water balance and ARIMA model, including: The acquisition module is configured to: acquire first real-time operating parameters of the power plant water network and obtain second operating parameters of key nodes in the power plant water network; The dynamic water balance processing module is configured to: calculate the actual leakage amount based on the node pressure data in the water imbalance area; The multi-level analysis module is configured to: perform multi-level analysis based on the second operating parameters of key nodes in the power plant water network and the water imbalance area to determine the leakage point; A model building module is configured to: build an ARIMA forecasting model and train it using the historical operating parameters of the power plant water network and the first real-time operating parameters; The prediction module is configured to: predict the power plant water network based on the trained ARIMA prediction model to obtain a predicted value; The output module is configured to output a predicted value.

[0041] It also includes an alarm module, which is configured to: compare the predicted leakage amount with the real-time monitoring data, calculate the error value, and generate an alarm message if the error value exceeds the set threshold τ.

[0042] In another embodiment of the present invention, a terminal device is provided, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of a multimodal electricity price analysis method, including: Based on the first real-time operating parameters collected from the power plant water network, dynamic water balance calculation is performed to identify water imbalance areas in the power plant water network; based on the acquired instantaneous operating parameters of key nodes in the power plant water network and the water imbalance areas, a multi-level analysis is performed to determine leakage points; based on the acquired historical operating parameters of the power plant water network, an ARIMA prediction model is constructed and trained using the first real-time operating parameters; based on the trained ARIMA prediction model, the power plant water network is predicted to obtain a predicted leakage amount.

[0043] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in a terminal device, used to store programs and data. It is understood that the computer-readable storage medium herein may include both built-in storage media in the terminal device and, of course, extended storage media supported by the terminal device. The computer-readable storage medium provides storage space, which stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for being loaded and executed by a processor. These instructions may be one or more computer programs (including program code). It should be noted that the computer-readable storage medium herein may be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage device.

[0044] The processor may load and execute one or more instructions stored in a computer-readable storage medium to implement the corresponding steps of the method for quality control of water saturation results data from well logging interpretation in the above embodiment. The processor may load and execute the following steps: Based on the first real-time operating parameters collected from the power plant water network, dynamic water balance calculation is performed to identify water imbalance areas in the power plant water network; based on the acquired instantaneous operating parameters of key nodes in the power plant water network and the water imbalance areas, a multi-level analysis is performed to determine leakage points; based on the acquired historical operating parameters of the power plant water network, an ARIMA prediction model is constructed and trained using the first real-time operating parameters; based on the trained ARIMA prediction model, the power plant water network is predicted to obtain a predicted leakage amount.

[0045] See also Figure 2The terminal device is a computer device. Computer device 60 in this embodiment includes: a processor 61, a memory 62, and a computer program 63 stored in memory 62 and executable by processor 61. When executed by processor 61, computer program 63 implements the method for calculating fluid composition in a reservoir-stimulated wellbore according to the embodiment. To avoid repetition, this description is omitted here. Alternatively, when executed by processor 61, computer program 63 implements the functions of various models / units in the system for calculating fluid composition in a reservoir-stimulated wellbore according to the embodiment. To avoid repetition, this description is omitted here.

[0046] The computer device 60 may be a desktop computer, a notebook computer, a PDA, a cloud server, or other computing devices. The computer device 60 may include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art will appreciate that Figure 2 This is only an example of the computer device 60 and does not constitute a limitation of the computer device 60. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0047] The processor 61 may be a central processing unit (CPU), other general-purpose processors, central processing units (CPUs), graphics processors (GPUs), digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), other programmable logic devices, discrete gate or transistor logic devices, quantum computing-based data processing logic, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0048] The memory 62 may be an internal storage unit of the computer device 60, such as a hard disk or memory of the computer device 60. The memory 62 may also be an external storage device of the computer device 60, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 60.

[0049] Furthermore, the memory 62 may include both an internal storage unit of the computer device 60 and an external storage device. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 may also be used to temporarily store data that has been output or is about to be output.

[0050] Any reference to memory, database, or other media used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0051] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0052] See also Figure 3 The terminal device is a chip. The chip 600 of this embodiment includes a processor 622, which may be one or more, and a memory 632 for storing a computer program executable by the processor 622. The computer program stored in the memory 632 may include one or more modules, each corresponding to a set of instructions. In addition, the processor 622 may be configured to execute the computer program to perform the above-mentioned generalizable monocular absolute depth map estimation method.

[0053] In addition, the chip 600 may further include a power supply component 626 and a communication component 650. The power supply component 626 may be configured to perform power management of the chip 600, and the communication component 650 may be configured to implement communication, such as wired or wireless communication, of the chip 600. In addition, the chip 600 may further include an input / output interface 658. The chip 600 may operate based on an operating system stored in the memory 632.

[0054] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, from all points of view, the embodiments should be regarded as illustrative and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and range of equivalents of the claims are included in the present invention. Any reference signs in the claims should not be construed as limiting the claim to which they relate.

[0055] In addition, it should be understood that although this specification describes the embodiments, not every embodiment contains only one independent technical solution. This description is for clarity only. Those skilled in the art should consider the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only for the purpose of illustrating the technical concept of the present invention and cannot be used to limit the scope of protection of the present invention. Any changes made based on the technical solution in accordance with the technical concept proposed by the present invention fall within the scope of protection of the claims of the present invention.

Claims

1. A method for predicting water network leakage in power plants based on dynamic water balance and ARIMA model, characterized in that: The following steps are involved: Performing dynamic water balance calculation based on the collected first real-time operating parameters of the power plant water network to identify water imbalance areas in the power plant water network; Based on the instantaneous operating parameters of key nodes in the power plant water network and the water imbalance areas, multi-level analysis is carried out to determine the leakage points; Building an ARIMA prediction model based on the acquired historical operating parameters of the power plant water network and training it using the first real-time operating parameters; The power plant water network is predicted based on the trained ARIMA prediction model to obtain the predicted leakage.

2. The method for predicting water network leakage in a power plant based on dynamic water balance and ARIMA model according to claim 1, characterized in that: Based on the collected first real-time operating parameters of the power plant water network, dynamic water balance calculation is performed, including: The power plant water network is divided into several sub-areas according to the physical topology, and each sub-area contains several nodes; Collecting first real-time operating parameters of a plurality of nodes to obtain a preprocessing data set; Calculating a water volume change value in the power plant water network based on the pre-processed flow data in each of the sub-areas; Based on the water volume change value, abnormal sub-areas and normal sub-areas in the plurality of sub-areas are determined; The water volume in the sub-area is calculated based on the preprocessed data set, and the water volume in the sub-area of the normal area is compared with the water volume in the sub-area of the abnormal area. The abnormal areas corresponding to the water volume differences exceeding the preset difference range are screened out and recorded as water imbalance areas.

3. The method for predicting water network leakage in a power plant based on dynamic water balance and ARIMA model according to claim 2, characterized in that: The first real-time operating parameter includes flow data and pressure data.

4. The method for predicting water network leakage in a power plant based on dynamic water balance and ARIMA model according to claim 1, characterized in that: Based on the acquired instantaneous operating parameters of key nodes in the power plant water network and the water imbalance areas, a multi-level analysis is conducted to identify leakage points, including: Obtaining first instantaneous operating parameters of key nodes in the water imbalance area; Calculating an average instantaneous loss based on the first instantaneous operating parameter using a dynamic water balance calculation model; Compare the average instantaneous loss with a preset first expected value range. If the average instantaneous loss exceeds the first expected value range, mark the key node and the nodes on the same pipeline as the key node as abnormal points. Obtain the second instantaneous operating parameters of the abnormal point; Based on the second instantaneous operating parameter, the second instantaneous loss amount of the abnormal point is calculated, and the second instantaneous loss amount is compared with the preset second expected value range. If the second instantaneous loss amount exceeds the first expected value range, the node is marked as a leakage point.

5. The method for predicting water network leakage in a power plant based on dynamic water balance and ARIMA model according to claim 1, characterized in that: An ARIMA forecasting model is constructed based on the historical operating parameters of the power plant water network, including: Obtain historical data of the power plant water network and process the historical data set; After sorting the data points in the historical data set based on the time series, performing unit root test and difference processing to obtain a stationary data set; Draw the autocorrelation function graph and partial autocorrelation function graph of the stationary data set, obtain the truncation and tailing characteristics of the autocorrelation function graph and partial autocorrelation function graph, and determine the autoregressive order and sliding average order; Based on the autoregressive order and the sliding average order, multiple ARIMA models are fitted, and the information criterion value and Bayesian information criterion value of each ARIMA model are calculated. The ARIMA model with the smallest information criterion value or the smallest Bayesian information criterion value is selected as the optimal model to create an ARIMA forecasting model.

6. The method for predicting water network leakage in a power plant based on dynamic water balance and ARIMA model according to claim 5, characterized in that: The training ARIMA forecasting model is: in, is the predicted leakage amount, is a constant term, is the autoregressive coefficient, is the sliding average coefficient, is the error term.

7. The method for predicting water network leakage in a power plant based on dynamic water balance and ARIMA model according to claim 6, characterized in that: The trained ARIMA forecasting model is used to forecast the power plant water network, including: The historical parameters of the leakage point are obtained, and the historical parameters are input into the trained ARIMA prediction model for prediction to obtain the predicted leakage amount of the power plant water network within the expected time.

8. A power plant water network leakage prediction system based on dynamic water balance and ARIMA model, applying the power plant water network leakage prediction method based on dynamic water balance and ARIMA model according to any one of claims 1 to 7, characterized in that: include: The acquisition module is configured to: acquire first real-time operating parameters of the power plant water network and obtain second operating parameters of key nodes in the power plant water network; The dynamic water balance processing module is configured to: calculate the actual leakage amount based on the node pressure data in the water imbalance area; The multi-level analysis module is configured to: perform multi-level analysis based on the second operating parameters of key nodes in the power plant water network and the water imbalance area to determine the leakage point; A model building module is configured to: build an ARIMA forecasting model and train it using the historical operating parameters of the power plant water network and the first real-time operating parameters; The prediction module is configured to: predict the power plant water network based on the trained ARIMA prediction model to obtain the predicted leakage amount; The output module is configured to output the predicted leakage amount.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable in the processor, wherein when the processor executes the computer program, the method implements the steps of a method for predicting water network leakage in a power plant based on dynamic water balance and ARIMA model as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of a power plant water network leakage prediction method based on dynamic water balance and ARIMA model according to any one of claims 1 to 7 are implemented.

Images