Hydraulic power plant operation emergency disposal process optimization method and system based on artificial intelligence

Abstract

The invention discloses a hydraulic power plant operation emergency disposal process optimization method and system based on artificial intelligence, and relates to the technical field of intelligent hydraulic power plant operation management and emergency response optimization, and the method comprises the steps: collecting the data of a hydraulic power plant in real time, carrying out the preprocessing of the collected data, building and training an artificial intelligence model through the preprocessed data, and carrying out the optimization of the hydraulic power plant operation emergency disposal process. An anomaly detection model is constructed and trained by using a deep learning technology, anomaly detection is performed by using the anomaly detection model, an emergency scheme is recommended for a fault by using a reinforcement learning algorithm, emergency disposal measures are automatically executed, and the scheme is dynamically adjusted according to a real-time monitoring result. The problems that traditional data processing and model accuracy is low, anomaly detection is not timely, and emergency disposal efficiency is low can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent hydropower plant operation management and emergency response optimization, and in particular to an artificial intelligence-based hydropower plant operation emergency response process optimization method and system. Background Art

[0002] With the continuous growth of energy demand and the increasing complexity of power systems, the operational safety and efficiency of hydropower plants have become the focus of industry attention. In the field of hydropower plant operation management, related technologies have undergone a transformation from traditional manual monitoring to computer-aided systems. In recent years, the development of artificial intelligence technology has provided new possibilities for hydropower plant operation monitoring and emergency response. Existing technologies can achieve real-time monitoring of key parameters of hydropower plants through the integration of sensors and monitoring systems, and indicate potential risks through preset threshold alarm systems.

[0003] However, the existing emergency response technologies for hydropower plant operations have shortcomings. First, traditional data processing methods often rely on simple statistical analysis and threshold judgment, which makes it difficult to deal with complex nonlinear problems that arise in the operation of hydropower plants. Secondly, the current anomaly detection model lacks in-depth mining of time series data, resulting in insufficient accuracy and real-time performance of anomaly identification. In addition, existing emergency response systems usually rely on preset rules and the experience of operators, lack flexibility and adaptability, and are difficult to provide optimal emergency plans for different fault conditions. In our invention, by collecting and preprocessing data from hydropower plants in real time, combined with deep learning and reinforcement learning techniques, the accuracy of anomaly detection and the intelligence level of emergency response can be significantly improved, thereby improving the efficiency and effectiveness of emergency response while ensuring the safe operation of hydropower plants. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an artificial intelligence-based method and system for optimizing the emergency response process of a hydropower plant, which can solve the problems of low accuracy of traditional data processing and models, untimely anomaly detection and low efficiency of emergency response.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions, a method for optimizing the emergency response process of a hydropower plant based on artificial intelligence, comprising:

[0007] The data of the first hydropower plant is collected in real time, and the data of the first hydropower plant is preprocessed to build and train the second model; the output data of the third optimization model is used to optimize the second model, and the output data of the second model is used to build the fourth detection model, and the fourth detection model is used to detect the operation status of the hydropower plant; the fourth detection model is used to output the fifth fault detection data and recommend emergency plans, and emergency disposal measures are automatically executed, and the plan is dynamically adjusted according to the real-time monitoring results.

[0008] As a preferred solution of the artificial intelligence-based hydropower plant operation emergency response process optimization method described in the present invention, the collection of the first hydropower plant data includes real-time collection of equipment status data, environmental parameters, historical fault information, operation logs, power grid data and communication system data.

[0009] As a preferred solution of the artificial intelligence-based hydropower plant operation emergency response process optimization method of the present invention, wherein: the preprocessing of the first hydropower plant data includes cleaning, normalizing, standardizing, feature extraction, data conversion and outlier processing of the collected data;

[0010] The preprocessing includes cleaning, normalizing, standardizing, feature extraction, data conversion and outlier processing of the collected data;

[0011] The normalization formula is:

[0012]

[0013] Among them, X is the original eigenvalue, X min is the minimum value of the feature, X max is the maximum value of the feature, X norm is the normalized eigenvalue;

[0014] The standardized formula is:

[0015]

[0016] Among them, X std is the standardized eigenvalue, X is the original eigenvalue, μ is the mean of the feature, and σ is the standard deviation of the feature;

[0017] The outlier processing formula is:

[0018]

[0019] Among them, y is the linear interpolation result, y1 and y2 are two adjacent data points, and x, x1 and x2 are the positions of the corresponding data points.

[0020] As a preferred solution of the method for optimizing the emergency response process of hydropower plant operation based on artificial intelligence described in the present invention, wherein: the construction and training of the second model includes defining the model structure, training the artificial intelligence model using the loss function and the gradient descent algorithm, optimizing the artificial intelligence model using the deep learning model, and the artificial intelligence model is called the second model; the model structure includes an input layer, a hidden layer, an output layer and an activation function.

[0021] As a preferred solution of the artificial intelligence-based hydropower plant operation emergency response process optimization method described in the present invention, wherein: the use of the third optimization model output data to optimize the second model includes optimizing the artificial intelligence model using a deep learning model.

[0022] As a preferred solution of the artificial intelligence-based hydropower plant operation emergency response process optimization method described in the present invention, the use of the fourth detection model to detect the operation status of the hydropower plant includes using CNN convolution operations to construct an anomaly detection function to detect anomalies.

[0023] The CNN convolution operation formula is:

[0024]

[0025] Among them, C kl is the feature map after convolution, W fg is the convolution kernel weight, I kl is the input image, p is the bias term, and o is the convolution kernel size.

[0026] The reinforcement learning algorithm includes using the reinforcement learning algorithm to recommend emergency plans for faults.

[0027] The fault calculation formula is:

[0028]

[0029] Among them, H is the comprehensive index of fault calculation, r is the fault feature vector, s is the parameter vector in the reinforcement learning algorithm, v is the sensitivity coefficient of the fault feature difference, w is the adjustment parameter of the normalized exponential function, R is the time range of fault calculation, V is the number of fault features, G is the complex information filtering function, and f τ is the τth fault feature, f ω is the ωth fault feature, and e is the base of the natural logarithm.

[0030] When H<10, the hydropower plant equipment is in a minor fault; when 10≤H<50, the hydropower plant equipment is in a moderate fault; when H≥50, the hydropower plant equipment is in a serious fault.

[0031] The method of using the fourth detection model to output the fifth fault detection data and recommend an emergency plan includes using a reinforcement learning algorithm to recommend an emergency plan for the fault, automatically executing emergency handling measures, and dynamically adjusting the plan based on real-time monitoring results.

[0032] As a preferred solution of the artificial intelligence-based hydropower plant operation emergency disposal process optimization system described in the present invention, it is characterized by comprising a data acquisition and preprocessing module, an artificial intelligence model construction and training module, an anomaly detection model construction and training module, and an emergency disposal plan recommendation and execution module;

[0033] The data acquisition and preprocessing module is used to collect data from the hydropower plant in real time, process the collected data, and provide reliable input for model training;

[0034] The artificial intelligence model construction and training module is used to construct and train artificial intelligence models to predict the operating status of the hydropower plant and provide fault warnings;

[0035] The anomaly detection model construction and training module is used to construct an anomaly detection function through CNN convolution operation, train the anomaly detection model, and perform anomaly detection using the trained model;

[0036] The emergency response plan recommendation and execution module is used to recommend emergency plans for faults through a reinforcement learning algorithm, automatically execute emergency response measures, and dynamically adjust plans based on real-time monitoring results.

[0037] As a preferred solution of the artificial intelligence-based hydropower plant operation emergency response process optimization system described in the present invention, it is characterized in that it includes: starting a data acquisition module to collect various data of the hydropower plant in real time, and transmitting the data to a data preprocessing module for cleaning, normalization and standardization; storing the processed data in a database, extracting the processed data by an artificial intelligence model construction and training module, training prediction and fault warning models, and training the anomaly detection model construction and training module on the data set, and identifying abnormal conditions in the hydropower plant; the deep learning model optimization module optimizes the artificial intelligence model; in the real-time monitoring stage, the data acquisition module continues to collect new data, and after the data preprocessing module processes the data, the anomaly detection module monitors the abnormal conditions in real time. If an abnormality is detected, an alarm is immediately triggered, and the information is passed to the emergency response plan recommendation and execution module. The module recommends an emergency plan based on a reinforcement learning algorithm, and automatically executes it after manual review, while monitoring the power plant status and dynamically adjusting the plan based on feedback, and feeding back the results of the emergency response to the model training and optimization module to form a closed-loop feedback mechanism.

[0038] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of a method for optimizing the emergency response process of a hydropower plant operation based on artificial intelligence are implemented.

[0039] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a method for optimizing the emergency response process of a hydropower plant operation based on artificial intelligence are implemented.

[0040] Beneficial effects of the present invention: The method of the present invention ensures data quality and availability by real-time collection of multi-source heterogeneous data of the hydropower plant and efficient preprocessing, and then uses the artificial intelligence model to conduct in-depth analysis and high-precision prediction of the operating status of the hydropower plant, significantly improving the accuracy of data analysis and model prediction. At the same time, combined with the anomaly detection model constructed by deep learning technology, the present invention can monitor and accurately identify potential abnormal situations in real time, effectively improving the early warning capability of the hydropower plant. In addition, by recommending emergency plans through reinforcement learning algorithms and automatically executing emergency disposal measures, the present invention can quickly provide optimal or near-optimal emergency response strategies when a fault occurs, greatly speeding up the fault handling speed and improving the efficiency of emergency response. Most importantly, the present invention can dynamically adjust the emergency plan according to the real-time monitoring results, ensuring the flexibility and adaptability of the emergency disposal measures, and effectively responding to the changing operating conditions. In general, the present invention not only ensures the safe and stable operation of the hydropower plant, reduces safety accidents and economic losses caused by faults, but also improves the overall operation and maintenance management level of the hydropower plant, and provides solid technical support for the long-term sustainable development of the hydropower plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] 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.

[0042] Figure 1 A schematic flow chart of a method for optimizing the emergency response process of a hydropower plant operation based on artificial intelligence provided by one embodiment of the present invention.

[0043] Figure 2 A system solution flow chart of an artificial intelligence-based hydropower plant operation emergency response process optimization system provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0044] 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.

[0045] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0046] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0047] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0048] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the 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 direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0049] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0050] Example 1, reference Figure 1 , which is the first embodiment of the present invention, and provides an optimization method for emergency response process of hydropower plant operation based on artificial intelligence, including:

[0051] S1: Collect data from the hydropower plant in real time, pre-process the collected data, and use the pre-processed data to build and train the artificial intelligence model.

[0052] Furthermore, the data collected from the hydropower plant includes real-time collection of equipment status data, environmental parameters, historical fault information, operation logs, power grid data, and communication system data;

[0053] The equipment status data includes the output power, voltage, current and frequency of the generator set, the turbine speed, head pressure and flow, the transformer temperature, oil level and insulation resistance, gate opening, water level and reservoir water storage capacity; the environmental parameters include air temperature, humidity, wind speed, wind direction, seismic waves, geological activities, water quality components, water temperature and dissolved oxygen; the historical fault information includes equipment failure time, fault type, maintenance measures, tripping and overload; the operation log includes the operator's power on and off, adjustment settings, maintenance and inspection activities; the power grid data includes power grid load data, power grid power supply quality parameters and power grid dispatch instructions; the communication system data includes signal strength, transmission delay, data transmission and reception status.

[0054] Furthermore, the preprocessing includes cleaning, normalizing, standardizing, feature extraction, data conversion and outlier processing of the collected data;

[0055] The normalization formula is:

[0056]

[0057] Among them, X is the original eigenvalue, X min is the minimum value of the feature, X max is the maximum value of the feature, X norm is the normalized eigenvalue;

[0058] The standardized formula is:

[0059]

[0060] Among them, X std is the standardized eigenvalue, X is the original eigenvalue, μ is the mean of the feature, and σ is the standard deviation of the feature;

[0061] The outlier processing formula is:

[0062]

[0063] Among them, y is the linear interpolation result, y1 and y2 are two adjacent data points, and x, x1 and x2 are the positions of the corresponding data points.

[0064] It should be noted that the construction and training of the artificial intelligence model includes defining the model structure, training the artificial intelligence model using the loss function and the gradient descent algorithm, and optimizing the artificial intelligence model using the deep learning model;

[0065] The model structure includes an input layer, a hidden layer, an output layer, and an activation function; the hidden layer includes a CNN convolution operation and an LSTM unit; the formula for the output layer is:

[0066] Y = W·h + b

[0067] where Y is the output result, W is the output layer weight, h is the hidden layer output, and b is the output layer bias;

[0068] The formula for the activation function is:

[0069] f(a) = max(0, a)

[0070] where f(a) is the activation function output and a is the input value;

[0071] The formula for the loss function is:

[0072]

[0073] where L is the loss function value, Z i is the true value, is the predicted value, and N is the number of samples;

[0074] The formula for the gradient descent algorithm is:

[0075]

[0076] where W b+1 is the updated weight, W b is the current weight, α is the learning rate, is the gradient of the loss function with respect to the weight.

[0077] S2: Use deep learning technology to construct and train an anomaly detection model, and use the anomaly detection model to perform anomaly detection.

[0078] E(q) is the data outlier. When 0 < E(q) ≤ 0.5, it indicates a low degree of data anomaly, which can be ignored and the current device operating state can continue; when 0.5 < E(q) ≤ 1, it indicates a high degree of data anomaly and an emergency plan needs to be called urgently.

[0079] S3: Use the reinforcement learning algorithm to recommend an emergency plan for faults, automatically execute emergency disposal measures, and dynamically adjust the plan according to the real-time monitoring results.

[0080] Further, the reinforcement learning algorithm includes using the reinforcement learning algorithm to recommend emergency plans for faults;

[0081] Furthermore, the dynamic adjustment plan includes using a reinforcement learning algorithm to recommend emergency plans for faults, automatically executing emergency response measures, and dynamically adjusting the plan based on real-time monitoring results.

[0082] 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.

[0083] Example 2, reference Figure 1 , which is an embodiment of the present invention, provides an optimization method for the emergency response process of a hydropower plant based on artificial intelligence. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0084] S1: Collect data from the hydropower plant in real time, pre-process the collected data, and use the pre-processed data to build and train the artificial intelligence model;

[0085] Furthermore, the data collected from the hydropower plant includes real-time collection of equipment status data, environmental parameters, historical fault information, operation logs, power grid data, and communication system data;

[0086] Furthermore, the preprocessing includes cleaning, normalizing, standardizing, feature extraction, data conversion and outlier processing of the collected data;

[0087] It should be noted that the construction and training of the artificial intelligence model includes defining the model structure, training the artificial intelligence model using the loss function and gradient descent algorithm, and optimizing the artificial intelligence model using the deep learning model;

[0088] The model structure includes an input layer, a hidden layer, an output layer and an activation function; the hidden layer includes a CNN convolution operation and an LSTM unit.

[0089] S2: Use deep learning technology to build and train anomaly detection models, and use the anomaly detection models to perform anomaly detection.

[0090] The anomaly detection model includes using CNN convolution operation to construct an anomaly detection function to detect anomalies;

[0091] The CNN convolution operation formula is:

[0092]

[0093] Among them, C kl is the feature map after convolution, W fg is the convolution kernel weight, I kl is the input image, p is the bias term, and o is the convolution kernel size.

[0094] S3: Use reinforcement learning algorithms to recommend emergency plans for faults, automatically execute emergency response measures, and dynamically adjust plans based on real-time monitoring results.

[0095] Further, the reinforcement learning algorithm includes using the reinforcement learning algorithm to recommend emergency plans for faults;

[0096] The fault calculation formula is:

[0097]

[0098] Among them, H is the comprehensive index of fault calculation, r is the fault feature vector, s is the parameter vector in the reinforcement learning algorithm, v is the sensitivity coefficient of the fault feature difference, w is the adjustment parameter of the normalized exponential function, R is the time range of fault calculation, V is the number of fault features, G is the complex information filtering function, and f τ is the τth fault feature, f ω is the ωth fault feature, e is the base of the natural logarithm;

[0099] When H<10, the hydropower plant equipment is in a minor fault; when 10≤H<50, the hydropower plant equipment is in a moderate fault; when H≥50, the hydropower plant equipment is in a serious fault.

[0100] Furthermore, the dynamic adjustment scheme includes using a reinforcement learning algorithm to recommend emergency plans for faults, automatically executing emergency response measures, and dynamically adjusting the plan based on real-time monitoring results;

[0101] The recommended emergency plan for faults includes: when the AI ​​system detects a minor fault signal, it triggers the minor fault handling process, increases the monitoring frequency of the fault area, tracks the fault development in real time, conducts a detailed analysis of the fault data, predicts the fault development trend, and arranges regular maintenance teams to troubleshoot and maintain the fault during non-peak hours; when the AI ​​system detects a medium fault signal, it triggers the medium fault handling process, adjusts the operating parameters of the hydropower plant, reduces the power generation load, isolates the faulty part, and dispatches a professional maintenance team to handle the fault; when the AI ​​system detects a serious fault signal, it immediately activates the emergency response mechanism, immediately stops the operation of the hydropower plant, starts the personnel evacuation plan, and organizes a team composed of senior management, technical experts and emergency response personnel to quickly make decisions and implement emergency plans.

[0102] 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.

[0103] Embodiment 3, the third embodiment of the present invention, is different from the first two embodiments in that:

[0104] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0105] 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.

[0106] 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.

[0107] 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 A step that specifies a function in one or more boxes.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] Example 4, reference Figure 2 , which is the fourth embodiment of the present invention, provides an artificial intelligence-based hydropower plant operation emergency response process optimization system, including a data acquisition and preprocessing module 100, an artificial intelligence model construction and training module 200, an anomaly detection model construction and training module 300, and an emergency response plan recommendation and execution module 400.

[0112] The data collection and preprocessing module 100 is used to collect data from the hydropower plant in real time, process the collected data, and provide reliable input for model training.

[0113] The artificial intelligence model construction and training module 200 is used to construct and train an artificial intelligence model to predict the operating status of a hydropower plant and warn of faults.

[0114] The anomaly detection model construction and training module 300 is used to construct an anomaly detection function through CNN convolution operation, train the anomaly detection model, and perform anomaly detection using the trained model.

[0115] The emergency response plan recommendation and execution module 400 is used to recommend emergency plans for faults through a reinforcement learning algorithm, automatically execute emergency response measures, and dynamically adjust plans based on real-time monitoring results.

[0116] The data acquisition module 100 is started to collect various data of the hydropower plant in real time, and the data is transmitted to the data preprocessing module for cleaning, normalization and standardization; the processed data is stored in the database, and the processed data is extracted by the artificial intelligence model construction and training module 200 to train the prediction and fault warning model. The anomaly detection model construction and training module 300 is trained on the data set and identifies abnormal conditions in the hydropower plant; the deep learning model optimization module optimizes the artificial intelligence model; in the real-time monitoring stage, the data acquisition module 100 continues to collect new data. After the data preprocessing module processes the data, the anomaly detection module 300 monitors the abnormal conditions in real time. If an abnormality is detected, an alarm is triggered immediately, and the information is passed to the emergency response plan recommendation and execution module 400. The module recommends emergency plans based on the reinforcement learning algorithm, and automatically executes them after manual review. At the same time, it monitors the power plant status and dynamically adjusts the plan based on feedback, and feeds back the results of the emergency response to the model training and optimization module to form a closed-loop feedback mechanism.

[0117] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. 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.

Claims

1. An artificial intelligence-based optimization method for emergency response process in hydropower plants, characterized by: include, Collect data from the first hydropower plant in real time, pre-process the data from the first hydropower plant, and build and train a second model; Optimizing the second model using the output data of the third optimization model, constructing a fourth detection model using the output data of the second model, and detecting the operation of the hydropower plant using the fourth detection model; The fourth detection model is used to output the fifth fault detection data and recommend an emergency plan, and emergency disposal measures are automatically executed, and the plan is dynamically adjusted according to the real-time monitoring results.

2. The method for optimizing the emergency response process of a hydropower plant based on artificial intelligence according to claim 1, characterized in that: The collecting of the first hydropower plant data includes real-time collection of equipment status data, environmental parameters, historical fault information, operation logs, power grid data and communication system data.

3. The method for optimizing the emergency response process of a hydropower plant based on artificial intelligence as claimed in claim 2, characterized in that: The preprocessing of the first hydropower plant data includes cleaning, normalizing, standardizing, feature extraction, data conversion and outlier processing of the collected data; The preprocessing includes cleaning, normalizing, standardizing, feature extraction, data conversion and outlier processing of the collected data; The normalization formula is: Among them, X is the original eigenvalue, X min is the minimum value of the feature, X max is the maximum value of the feature, X norm is the normalized eigenvalue; The standardized formula is: Among them, X std is the standardized eigenvalue, X is the original eigenvalue, μ is the mean of the feature, and σ is the standard deviation of the feature; The outlier processing formula is: Among them, y is the linear interpolation result, y1 and y2 are two adjacent data points, and x, x1 and x2 are the positions of the corresponding data points.

4. The method for optimizing the emergency response process of a hydropower plant operation based on artificial intelligence as claimed in claim 3 is characterized by: The constructing and training of the second model includes defining a model structure, training the artificial intelligence model using a loss function and a gradient descent algorithm, and optimizing the artificial intelligence model using a deep learning model. The artificial intelligence model is called the second model; the model structure includes an input layer, a hidden layer, an output layer, and an activation function.

5. The method for optimizing the emergency response process of a hydropower plant operation based on artificial intelligence according to claim 4, characterized in that: The method of optimizing the second model using the output data of the third optimization model includes optimizing the artificial intelligence model using a deep learning model.

6. The method for optimizing the emergency response process of a hydropower plant operation based on artificial intelligence according to claim 5, characterized in that: The use of the fourth detection model to detect the operation of the hydropower plant includes using a CNN convolution operation to construct an anomaly detection function to detect anomalies; The CNN convolution operation formula is: Among them, C kl is the feature map after convolution, W fg is the convolution kernel weight, I kl is the input image, p is the bias term, and o is the convolution kernel size; The reinforcement learning algorithm includes using the reinforcement learning algorithm to recommend emergency plans for faults; The fault calculation formula is: Among them, H is the comprehensive index of fault calculation, r is the fault feature vector, s is the parameter vector in the reinforcement learning algorithm, v is the sensitivity coefficient of the fault feature difference, w is the adjustment parameter of the normalized exponential function, R is the time range of fault calculation, V is the number of fault features, G is the complex information filtering function, and f τ is the τth fault feature, f ω is the ωth fault feature, e is the base of the natural logarithm; When H<10, the hydropower plant equipment is in a minor fault; when 10≤H<50, the hydropower plant equipment is in a moderate fault; when H≥50, the hydropower plant equipment is in a serious fault; The method of using the fourth detection model to output the fifth fault detection data and recommend an emergency plan includes using a reinforcement learning algorithm to recommend an emergency plan for the fault, automatically executing emergency handling measures, and dynamically adjusting the plan based on real-time monitoring results.

7. A system using the artificial intelligence-based hydropower plant operation emergency response process optimization method as described in any one of claims 1 to 6, characterized in that: It includes data collection and preprocessing module, artificial intelligence model building and training module, anomaly detection model building and training module, and emergency response plan recommendation and execution module; The data acquisition and preprocessing module is used to collect data from the hydropower plant in real time, process the collected data, and provide reliable input for model training; The artificial intelligence model construction and training module is used to construct and train artificial intelligence models to predict the operating status of the hydropower plant and provide fault warnings; The anomaly detection model construction and training module is used to construct an anomaly detection function through CNN convolution operation, train the anomaly detection model, and perform anomaly detection using the trained model; The emergency response plan recommendation and execution module is used to recommend emergency plans for faults through a reinforcement learning algorithm, automatically execute emergency response measures, and dynamically adjust plans based on real-time monitoring results.

8. A system using the artificial intelligence-based hydropower plant operation emergency response process optimization method as described in any one of claims 1 to 6, characterized in that: Including, starting the data acquisition module, collecting various data of the hydropower plant in real time, and transmitting the data to the data preprocessing module for cleaning, normalization and standardization; The processed data is stored in the database. The processed data is extracted by the artificial intelligence model building and training module to train the prediction and fault warning models. The anomaly detection model building and training module is trained on the data set and identifies abnormal conditions in the hydropower plant; The deep learning model optimization module optimizes the artificial intelligence model; During the real-time monitoring stage, the data acquisition module continues to collect new data. After the data preprocessing module processes the data, the anomaly detection model monitors abnormal situations in real time. If an anomaly is detected, an alarm is triggered immediately and the information is passed to the emergency response plan recommendation and execution module. The module recommends emergency plans based on the reinforcement learning algorithm, which are automatically executed after manual review. At the same time, it monitors the power plant status and dynamically adjusts the plan based on feedback, and feeds back the results of the emergency response to the model training and optimization module to form a closed-loop feedback mechanism.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images