Environmental anomaly monitoring and warning method and system for smart power plant

Abstract

The invention provides an environment abnormity monitoring and warning method and system for a smart power plant, and relates to the technical field of abnormity monitoring. Determining a power plant environment anomaly region and a region environment anomaly recognition result; obtaining a first coefficient of the environmental anomaly risk; obtaining a second coefficient of the environmental anomaly risk; based on the first weight of the environmental anomaly risk and the second weight of the environmental anomaly risk, performing weighted calculation on the first coefficient of the environmental anomaly risk and the second coefficient of the environmental anomaly risk to obtain an environmental anomaly risk detection coefficient; and generating an environment abnormity early warning signal. According to the invention, the technical problem in the prior art that a power plant cannot respond in time when an abnormal condition occurs due to the fact that the potential influence on other regions is difficult to evaluate according to the abnormality of one region due to the lack of an effective abnormality propagation prediction mechanism can be solved; the technical effects of improving the response speed and the early warning accuracy of the power plant to the environment abnormity and reducing the accident risk are achieved.

Description

Technical Field

[0001] The present application relates to the field of abnormal monitoring technology, and in particular to an environmental abnormality monitoring and alarm method and system for a smart power plant. Background Art

[0002] In the modern power production process, environmental monitoring and abnormal management have become an important part of ensuring the safe and efficient operation of power plants. In recent years, with the rapid development of Internet of Things technology and big data analysis, intelligent monitoring systems have gradually been applied to the power industry. These systems use sensor networks to collect environmental data in real time and evaluate the environmental status through data analysis technology.

[0003] However, the current intelligent monitoring system still has some shortcomings. For example, the algorithm models of existing technologies in anomaly detection and risk prediction are mostly static models, lacking an effective anomaly propagation prediction mechanism, making it difficult to evaluate the potential impact of anomalies in one area on other areas, resulting in power plants failing to respond in time when abnormal situations occur, which may cause safety hazards. Summary of the invention

[0004] The purpose of this application is to provide an environmental anomaly monitoring and alarm method and system for a smart power plant, so as to solve the technical problem in the prior art that due to the lack of an effective anomaly propagation prediction mechanism, it is difficult to evaluate the potential impact of anomalies in one area on other areas, resulting in the power plant failing to respond in time when an abnormal situation occurs.

[0005] In view of the above problems, the present application provides an environmental abnormality monitoring and alarm method and system for a smart power plant.

[0006] In the first aspect, the present application provides an environmental anomaly monitoring and alarm method for a smart power plant, which is implemented by an environmental anomaly monitoring and alarm system for a smart power plant, wherein the environmental anomaly monitoring and alarm method for a smart power plant includes: performing real-time environmental monitoring of various areas of the power plant according to a sensor unit to obtain a power plant environmental monitoring data set; based on a power plant environmental anomaly depth constraint table, performing anomaly detection according to the power plant environmental monitoring data set to determine the power plant environmental anomaly area and regional environmental anomaly identification results; based on a bidirectional gated loop unit, identifying the power plant environmental anomaly area according to the regional environmental anomaly identification results An environmental anomaly risk prediction is performed in the abnormal area to obtain a first environmental anomaly risk coefficient; based on the environmental anomaly area of ​​the power plant and the environmental anomaly identification result of the area, an environmental anomaly propagation prediction is performed on the power plant to obtain a second environmental anomaly risk coefficient; based on the first environmental anomaly risk weight and the second environmental anomaly risk weight, the first environmental anomaly risk coefficient and the second environmental anomaly risk coefficient are weighted to obtain an environmental anomaly risk detection coefficient; it is determined whether the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold; if the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold, an environmental anomaly warning signal is generated.

[0007] In the second aspect, the present application also provides an environmental anomaly monitoring and alarm system for a smart power plant, which is used to execute an environmental anomaly monitoring and alarm method for a smart power plant as described in the first aspect, wherein the environmental anomaly monitoring and alarm system for a smart power plant includes: a real-time environmental monitoring module, which is used to perform real-time environmental monitoring of various areas of the power plant according to the sensor unit to obtain a power plant environmental monitoring data set; an anomaly detection module, which is used to perform anomaly detection based on the power plant environmental anomaly depth constraint table and the power plant environmental monitoring data set to determine the power plant environmental anomaly area and the regional environmental anomaly identification results; an anomaly risk prediction module, which is used to perform environmental anomaly detection on the power plant environmental anomaly area based on the bidirectional gated loop unit according to the regional environmental anomaly identification results. Risk prediction, obtaining a first environmental anomaly risk coefficient; an environmental anomaly propagation prediction module, used to predict the environmental anomaly propagation of the power plant based on the environmental anomaly area of ​​the power plant and the regional environmental anomaly identification results, and obtain a second environmental anomaly risk coefficient; a risk weighting module, used to perform weighted calculation on the first environmental anomaly risk coefficient and the second environmental anomaly risk coefficient based on the first environmental anomaly risk weight and the second environmental anomaly risk weight, and obtain an environmental anomaly risk detection coefficient; a risk judgment module, used to judge whether the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold; an abnormal warning module, used to generate an environmental anomaly warning signal if the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold.

[0008] In the third aspect, the present application also provides an electronic device, comprising: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the environmental abnormality monitoring and alarm method for a smart power plant as described in any one of the above-mentioned first aspects.

[0009] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed, the steps of the method for environmental abnormality monitoring and alarm of a smart power plant described in any one of the first aspects are implemented.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages: According to the sensor unit, real-time environmental monitoring is performed on various areas of the power plant to obtain a power plant environmental monitoring data set; based on the power plant environmental anomaly depth constraint table, anomaly detection is performed according to the power plant environmental monitoring data set to determine the power plant environmental anomaly area and the regional environmental anomaly identification result; based on the bidirectional gated loop unit, environmental anomaly risk prediction is performed on the power plant environmental anomaly area according to the regional environmental anomaly identification result to obtain a first environmental anomaly risk coefficient; based on the power plant environmental anomaly area and the regional environmental anomaly identification result, environmental anomaly propagation prediction is performed on the power plant to obtain a second environmental anomaly risk coefficient; based on the environmental anomaly area of ​​the power plant and the regional environmental anomaly identification result, the first environmental anomaly risk coefficient and the second environmental anomaly risk coefficient are weightedly calculated to obtain an environmental anomaly risk detection coefficient; it is determined whether the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold; if the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold, an environmental anomaly warning signal is generated. Through the sensor unit, each area of ​​the power plant is monitored in real time, and the environmental anomaly risk prediction and environmental anomaly propagation prediction are made based on the monitoring data. The environmental risk detection coefficient is then weighted and calculated and compared with the detection threshold to ensure that a warning signal is generated in time when the risk exceeds the threshold, thereby achieving the technical effect of improving the power plant's response speed to environmental anomalies and the accuracy of warnings, and reducing accident risks.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 A flowchart of an abnormal environment monitoring and alarm method for a smart power plant is provided for this application; Figure 2 A schematic diagram of the structure of an abnormal environment monitoring and alarm system for a smart power plant is provided for this application; Figure 3 This is a schematic diagram of the structure of an exemplary electronic device of the present application.

[0014] Description of reference numerals: Real-time environment monitoring module 11, anomaly detection module 12, anomaly risk prediction module 13, environmental anomaly propagation prediction module 14, risk weighting module 15, risk judgment module 16, anomaly warning module 17, bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 305. DETAILED DESCRIPTION

[0015] This application provides an environmental anomaly monitoring and alarm method and system for a smart power plant, which solves the technical problem in the prior art that the lack of an effective abnormal propagation prediction mechanism makes it difficult to evaluate the potential impact of an abnormality in one area on other areas, resulting in the power plant failing to respond in time when an abnormal situation occurs. The sensor unit monitors each area of ​​the power plant in real time, and predicts the environmental anomaly risk and environmental anomaly propagation based on the monitoring data. The environmental risk detection coefficient is then weighted and calculated, and compared with the detection threshold to ensure that an early warning signal is generated in time when the risk exceeds the threshold, thereby achieving the technical effect of improving the power plant's response speed to environmental anomalies and the accuracy of early warnings, and reducing accident risks.

[0016] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0017] For example, please refer to the attached Figure 1 The present application provides an abnormal environment monitoring and alarm method for a smart power plant, wherein the abnormal environment monitoring and alarm method for a smart power plant is applied to an abnormal environment monitoring and alarm system for a smart power plant, and the abnormal environment monitoring and alarm method for a smart power plant specifically includes the following steps: Step 1: Perform real-time environmental monitoring of various areas of the power plant based on the sensor units to obtain a power plant environmental monitoring data set.

[0018] Specifically, sensor units are deployed in various key areas of the power plant to achieve real-time monitoring of the environment. They can monitor a variety of environmental parameters, including temperature, humidity, air quality, noise level, and vibration. The real-time data collected by the sensor units are aggregated and formed into a complete power plant environmental monitoring data set, aiming to provide a comprehensive environmental status assessment. For example, sensor units may record the temperature of the generator room, the carbon dioxide concentration in the control room, the noise level in the substation, etc. in different areas of the power plant (such as the generator room, control room, and substation).

[0019] Step 2: Based on the power plant environment anomaly depth constraint table, perform anomaly detection according to the power plant environment monitoring data set to determine the power plant environment anomaly area and regional environment anomaly identification results.

[0020] Specifically, the power plant environmental anomaly depth constraint table is a predefined standard used to evaluate the normal range of different environmental parameters and their degree of abnormality. The various parameters in the power plant environmental monitoring data set are compared with the power plant environmental anomaly depth constraint table, and the environmental anomaly depth coefficient of each area is calculated to identify the power plant environmental anomaly area and the regional environmental anomaly identification results. For example, the data collected by the sensor unit include the temperature of the generator room is 35°C (exceeding the normal range of 30°C), the humidity is 70% (the normal range should be 40%-60%), and the carbon dioxide concentration in the control room is 800 ppm (exceeding the normal threshold of 600 ppm). According to the environmental anomaly depth constraint table, the abnormal depth coefficients corresponding to these parameters will be calculated, and the abnormal depth coefficient of the generator room is 2, and the abnormal depth coefficient of the control room is 1.5. By comparing these coefficients with the thresholds specified in the constraint table, the algorithm determines that both the generator room and the control room are identified as environmental anomaly areas, and generates the corresponding regional environmental anomaly identification results.

[0021] Step three: Based on the bidirectional gated cycle unit, the environmental anomaly risk of the power plant environmental anomaly area is predicted according to the regional environmental anomaly identification result to obtain the first environmental anomaly risk coefficient.

[0022] Specifically, the bidirectional gated recurrent unit is a deep learning model that is particularly suitable for processing time series data and can effectively capture the dynamic characteristics of environmental parameters changing over time. First, the regional environmental anomaly recognition results are used to construct an input data set, including the previously identified anomaly type, anomaly depth coefficient, and related environmental monitoring data (such as temperature, humidity, gas concentration, etc.). The input data is fed into the bidirectional gated recurrent unit for training and prediction. The bidirectional characteristics of the bidirectional gated recurrent unit allow it to consider both past and future data sequences at the same time, thereby capturing a more comprehensive time dependency. In the model training phase, supervised learning is performed using historical environmental anomaly data and its corresponding risk record set, with the goal of minimizing the gap between the predicted environmental anomaly risk and the actual risk. The regional environmental anomaly recognition results are input into the trained bidirectional gated recurrent unit to predict the environmental anomaly risk and obtain the first environmental anomaly risk coefficient. The first environmental anomaly risk coefficient not only provides an important basis for the safety management of the power plant, but also provides data support for subsequent risk assessment and decision support, ensuring the safety and efficiency of the power plant during operation.

[0023] Step 4: Based on the power plant environmental anomaly area and the regional environmental anomaly identification results, the environmental anomaly propagation prediction of the power plant is performed to obtain a second environmental anomaly risk coefficient.

[0024] Specifically, the prediction of environmental anomaly propagation aims to assess the risk that environmental anomalies may spread inside and around the power plant. First, based on the basic data set of the power plant, a detailed power plant model is constructed, which covers key information such as various areas of the power plant, equipment layout, and environmental parameters. This model helps to simulate the propagation path of abnormal conditions. For example, assuming that a temperature anomaly (35°C) occurs in the first area of ​​the power plant, and this area has a close physical connection with the adjacent areas, the model will predict the probability that the abnormal state may spread to the surrounding areas by calculating environmental factors and connection strength. Next, based on the regional environmental anomaly identification results, the power plant model is simulated for environmental anomaly propagation, and the propagation process of the abnormal state within the power plant is analyzed. It is assumed that the simulation results show that under the temperature anomaly state in the first area, the probability that the anomaly may spread to the second area within one hour is 60%, and the probability of spreading to the third area is 30%. This simulation result will form the environmental anomaly propagation simulation result. Based on these simulation results, the propagation risk is predicted for each predetermined propagation area of ​​the power plant. At this time, the propagation risk coefficient of each area is calculated. For example, the propagation risk coefficient of the second area may be 0.6 (60% propagation probability), while the propagation risk coefficient of the third area may be 0.3 (30% propagation probability). Finally, the central value of these propagation risk coefficients is calculated as the second coefficient of environmental abnormality risk. Through this series of steps, the power plant can more comprehensively assess the potential impact of environmental abnormalities and take timely measures to prevent the further spread of abnormal conditions, thereby ensuring the safe and stable operation of the power plant.

[0025] Step 5: Based on the first weight of the environmental abnormality risk and the second weight of the environmental abnormality risk, weighted calculation is performed on the first coefficient of the environmental abnormality risk and the second coefficient of the environmental abnormality risk to obtain the environmental abnormality risk detection coefficient.

[0026] Specifically, in the final stage of the environmental abnormality risk assessment, it is necessary to perform weighted calculation on the first environmental abnormality risk coefficient and the second environmental abnormality risk coefficient to obtain a comprehensive environmental abnormality risk detection coefficient. This coefficient is intended to comprehensively reflect the current environmental risk level faced by the power plant. Specifically, the professional and technical personnel in this field shall determine the first weight of environmental abnormality risk and the second weight of environmental abnormality risk by the coefficient of variation method in combination with practical experience or by collecting historical risk data. According to the first weight of environmental abnormality risk and the second weight of environmental abnormality risk, the first environmental abnormality risk coefficient and the second environmental abnormality risk coefficient are weightedly calculated to obtain the environmental abnormality risk detection coefficient, and finally the environmental abnormality risk detection coefficient is obtained, which provides an important reference for the power plant management to take timely measures to deal with potential risks, thereby ensuring the safe and stable operation of the power plant.

[0027] Step 6: Determine whether the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold.

[0028] Specifically, after the calculation of the environmental anomaly risk detection coefficient is completed, a key judgment will be made, that is, to determine whether the environmental anomaly risk detection coefficient is greater than or equal to the preset environmental anomaly detection threshold. The environmental anomaly detection threshold is a pre-set standard used to assess whether the current environmental risk level has reached a level that requires an emergency response. This threshold is usually determined based on historical data analysis, industry standards, and expert opinions to ensure that it can effectively distinguish between normal operation and potential dangerous conditions.

[0029] Step 7: If the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold, an environmental anomaly warning signal is generated.

[0030] Specifically, if the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold, an environmental anomaly warning signal will be generated. The content of the environmental anomaly warning signal may include a specific abnormal area to facilitate management to make quick decisions and take corresponding measures.

[0031] Further, step 2 of this application includes: According to the power plant environmental monitoring data set, the first area environmental monitoring data corresponding to the first area of ​​the power plant is extracted; based on the first area environmental monitoring data, anomaly detection is performed to obtain a first area environmental anomaly recognition result; according to the first area environmental anomaly recognition result, anomaly depth evaluation is performed to obtain a first environment anomaly depth coefficient; based on the power plant environmental anomaly depth constraint table, the first area environmental anomaly depth threshold corresponding to the first area of ​​the power plant is matched; it is determined whether the first environment anomaly depth coefficient is greater than or equal to the first area environmental anomaly depth threshold; if the first environment anomaly depth coefficient is greater than or equal to the first area environmental anomaly depth threshold, the first area of ​​the power plant is added to the power plant environmental anomaly area, and the first area environmental anomaly recognition result is added to the area environmental anomaly recognition result.

[0032] Furthermore, the present application also includes the following steps: Based on the first area of ​​the power plant, real-time operation task parameters are collected to obtain the operation tasks of the first area; based on the operation tasks of the first area, a health environment prediction is performed on the first area of ​​the power plant to establish a health environment matrix for the first area; based on the environmental monitoring data of the first area, matrix processing is performed to generate an environmental monitoring matrix for the first area; based on the health environment matrix of the first area, anomalies are identified on the environmental monitoring matrix of the first area to generate an environmental anomaly identification result for the first area.

[0033] Furthermore, the present application also includes the following steps: Load multiple regional health environment record groups for the first area of ​​the power plant, wherein each regional health environment record group includes historical regional operation tasks and historical regional health environment information corresponding to the first area of ​​the power plant; based on the first regional operation tasks, perform twin identification on each historical regional operation task in the multiple regional health environment record groups to obtain multiple task twin coefficients; based on the multiple task twin coefficients, select health environment samples for the multiple regional health environment record groups according to task twin thresholds to establish a first regional health environment prediction space; perform central trend analysis based on the first regional health environment prediction space to generate the first regional health environment matrix.

[0034] Specifically, the data of any area is extracted from the power plant environmental monitoring data set and recorded as the first area environmental monitoring data of the first area of ​​the power plant, including multiple indicators such as temperature, humidity, vibration and harmful gas concentration. Subsequently, anomaly detection is performed based on the first area environmental monitoring data to generate the environmental anomaly recognition result of the first area. The specific steps of anomaly detection are as follows: In the first area of ​​the power plant, the real-time operation task parameters are collected through sensors. The real-time operation task parameters include information such as the operating load of the equipment, maintenance cycle, and operation frequency. These data will be integrated into the first area operation task. For example, assuming that in a certain task, the operating load of the generator is 85%, the maintenance cycle is once every 500 hours, and the operation frequency is 2 times per hour, this information is then used to predict the health environment of the first area, and then establish the first area health environment matrix. The first area health environment matrix is ​​a structured data set that reflects the expected environmental state of the first area of ​​the power plant under different working conditions. Through the analysis of historical data, the matrix can provide environmental health prediction results under the current operation task. For example, assuming that according to historical records, the ideal temperature range of the first area under the same load should be 28°C to 32°C. Based on this information, the constructed health environment matrix will include multiple parameters and their corresponding ideal states. At the same time, matrix processing is performed based on the environmental monitoring data of the first area to generate the first area environmental monitoring matrix, recording real-time environmental parameters, such as temperature of 30°C, humidity of 50%, and vibration of 0.2 g. Next, the relationship between the first-area health environment matrix and the first-area environmental monitoring matrix is ​​used to conduct anomaly identification analysis. By comparing the two, it is determined whether the indicators in the first-area environmental monitoring matrix are within the ideal range of the first-area health environment matrix. In this way, the first-area environmental anomaly identification result is generated, ensuring comprehensive monitoring and timely response to the environment of each area of ​​the power plant, and promoting safe operation.

[0035] Among them, the steps of predicting the health environment of the first area of ​​the power plant based on the first area operation task and establishing the health environment matrix of the first area include: loading multiple regional health environment record groups of the first area of ​​the power plant, each regional health environment record group contains historical regional operation tasks and historical regional health environment information of the area, and these data include environmental parameters under different operation tasks, such as temperature, humidity and equipment status, etc., aiming to provide a basis for subsequent health environment analysis. Next, based on the first area operation task, each historical area operation task is twin-identified. Twin identification is a method for comparing the first area operation task with the historical area operation task to evaluate their similarity and calculate the task twin coefficient of each historical operation task. For example, if the similarity between the first area operation task and the historical area operation task is 0.85, the twin coefficient of the task is 0.85. By performing this calculation on each historical area operation task, multiple task twin coefficients are obtained. Among them, the similarity calculation can be calculated using existing methods such as deviation comparison and cosine similarity. The task twin threshold is pre-set by professionals in this field to select healthy environment samples from multiple regional health environment record groups. Only those records whose task twin coefficients are greater than or equal to the threshold can be regarded as valid healthy environment samples and added to the first regional health environment prediction space. For example, assuming that there are three tasks with twin coefficients of 0.9, 0.8, and 0.6 in the historical records, only the health environment information of the first two tasks will be included in the prediction space.

[0036] Finally, a central tendency analysis is performed based on the healthy environment prediction space of the first region, and the central tendency indicators of various parameters, such as the mean, standard deviation, and maximum value, are calculated. For example, if the samples contained in the healthy environment prediction space of the first region show that the temperatures under similar operating conditions in the past were 28°C, 29°C, 30°C, 31°C, and 32°C, respectively, then the average temperature of the region is 30°C, and other parameters are processed in a similar manner to obtain their central tendency characteristics. The central tendency indicators are summarized to form a healthy environment matrix for the first region, which will contain the predicted values ​​of various environmental parameters and their corresponding normal ranges to reflect the healthy environment status of the first region under the current operating conditions. For example, the generated healthy environment matrix may show that the predicted value of temperature is 30°C (normal range 28°C to 32°C), the predicted value of humidity is 55% (normal range 40% to 60%), and the predicted value of vibration value is 0.2 g (normal range 0.1 g to 0.3 g). Thus, the healthy environment matrix of the first region is generated, which can effectively reflect the environmental change trend of the first region in the future and provide support for the management and decision-making of the power plant.

[0037] After obtaining the first-region environmental anomaly identification result, the next step is to conduct an anomaly depth evaluation on the first-region environmental anomaly identification result to determine the first-region environmental anomaly depth coefficient. The first-region environmental anomaly depth coefficient is used to quantify the degree of anomaly identified and help evaluate its potential impact on the safe operation of the power plant. Specifically, the professional and technical personnel in this field can pre-set an anomaly depth coefficient table corresponding to different anomaly identification results, and then input the first-region environmental anomaly identification result for matching to determine the first-region environmental anomaly depth coefficient.

[0038] Next, the power plant environmental anomaly depth constraint table is searched to match the environmental anomaly depth threshold of the area. By comparison, it is determined whether the first environmental anomaly depth coefficient is greater than or equal to the environmental anomaly depth threshold. If so, the first area of ​​the power plant is marked as an environmental anomaly area, and the environmental anomaly identification result of the first area is added to the environmental anomaly identification result of the area, ensuring the timely identification of potential safety hazards and providing an important basis for subsequent risk assessment and response measures.

[0039] Further, step three of this application includes: Based on the abnormal environment area of ​​the power plant, risk record retrieval is performed to obtain a regional environmental anomaly identification record set and an environmental anomaly risk record set; the bidirectional gated recurrent unit is supervised and trained with the regional environmental anomaly identification record set as input information and the environmental anomaly risk record set as output information, and when the number of training times meets the training number constraint, the environmental anomaly risk prediction loss coefficient is obtained; it is determined whether the environmental anomaly risk prediction loss coefficient is less than the environmental anomaly risk prediction loss threshold; if the environmental anomaly risk prediction loss coefficient is less than the environmental anomaly risk prediction loss threshold, an environmental anomaly risk prediction channel is generated; the regional environmental anomaly identification result is input into the environmental anomaly risk prediction channel to generate the first environmental anomaly risk coefficient.

[0040] Specifically, when predicting environmental anomaly risks, it is first necessary to retrieve risk records based on the environmental anomaly areas of the power plant. This process aims to extract relevant information from historical data to obtain regional environmental anomaly identification record sets and environmental anomaly risk record sets. The regional environmental anomaly identification record sets contain various environmental anomalies and their characteristics identified in past monitoring, while the environmental anomaly risk record sets contain the corresponding risk assessment results. Next, the bidirectional gated recurrent unit is supervised and trained with the regional environmental anomaly identification record set as input information and the environmental anomaly risk record set as output information. The training process of the model matches the input data with the output results, aiming to make the prediction results closer to the actual risk value by adjusting the model parameters. For example, assuming that there are 10 regional environmental anomaly identification records corresponding to their environmental risks in the training data set, the model will be gradually optimized during the training process to reduce the prediction error. When the number of training times meets the preset training times constraint, the environmental anomaly risk prediction loss coefficient is calculated, which is used to measure the prediction accuracy of the model. For example, if the loss coefficient is 0.05 and the set environmental anomaly risk prediction loss threshold is 0.1, then the coefficient is significantly less than the threshold, indicating that the model has good prediction ability. In this case, an environmental anomaly risk prediction channel will be generated to allow subsequent real-time data input. Then, the regional environmental anomaly identification results are input into the channel to generate the first environmental anomaly risk coefficient. As a result, the power plant can efficiently identify potential environmental risks and enhance the accuracy of early warning of abnormal situations.

[0041] Further, step 4 of this application includes: A power plant model is constructed based on the power plant basic data set of the power plant; based on the environmental anomaly area of ​​the power plant, an environmental anomaly propagation simulation is performed on the power plant model according to the environmental anomaly identification result of the area to obtain an environmental anomaly propagation simulation result; based on the environmental anomaly propagation simulation result, a propagation risk prediction is performed on each predetermined propagation area of ​​the power plant to obtain a plurality of environmental anomaly propagation risk coefficients; and a concentrated value of the plurality of environmental anomaly propagation risk coefficients is calculated to generate the second environmental anomaly risk coefficient.

[0042] Specifically, when predicting the propagation of environmental anomalies in power plants, it is first necessary to build a detailed power plant model based on the basic data set of the power plant. The power plant model contains information such as the various areas of the power plant, equipment configuration, environmental parameters, and connection relationships, and can fully understand the operating environment of the power plant and the mutual influence between equipment. For example, the power plant model may include the temperature, humidity, gas concentration of multiple areas and their interconnected pipeline networks. Next, based on the abnormal environmental areas of the power plant, the power plant model is simulated for the propagation of environmental anomalies according to the results of regional environmental anomaly identification. Assuming that temperature anomalies (35°C) and humidity anomalies (75%) are identified in the first area, the propagation process of abnormal states within the power plant is simulated by calculating the physical connectivity and similarity of environmental conditions between different areas. For example, the power plant model shows that in the case of temperature anomalies, the probability of the anomaly propagating to the second area within one hour is 70%, while the probability of propagating to the third area is 40%. After completing the propagation simulation, the propagation risk prediction is performed for each predetermined propagation area of ​​the power plant according to the results of the environmental anomaly propagation simulation. Each predetermined propagation area refers to the area in the power plant other than the environmental anomaly area of ​​the power plant. For example, the propagation risk coefficient of the second area is 0.7 (70% propagation probability), while the propagation risk coefficient of the third area is 0.4 (40% propagation probability), and the propagation risk coefficient of the fourth area is 0.2 (20% propagation probability). These risk coefficients reflect the risk levels faced by different areas under the current abnormal state. Finally, the central value of multiple environmental anomaly propagation risk coefficients is calculated to generate the second environmental anomaly risk coefficient. For example, assuming that the risk coefficients of the three predetermined propagation areas are 0.7, 0.4, and 0.2, respectively, the central value will be (0.7+0.4+0.2) / =0.433. This second environmental anomaly risk coefficient represents the overall environmental anomaly propagation risk level of the power plant under the current conditions. As a result, the power plant can comprehensively assess the potential impact of environmental anomalies on operations, which is convenient for timely early warning.

[0043] Furthermore, the present application also includes the following steps: Based on the environmental abnormality propagation simulation results, the risk of spread probability is predicted for each predetermined propagation area to obtain a plurality of regional spread probability risk coefficients; based on the environmental abnormality propagation simulation results, the risk of spread impact is predicted for each predetermined propagation area to obtain a plurality of regional spread impact risk coefficients; based on the propagation risk prediction weight condition, the plurality of regional spread probability risk coefficients and the plurality of regional spread impact risk coefficients are weighted respectively to generate the plurality of environmental abnormality propagation risk coefficients.

[0044] Specifically, according to the results of the simulation of the propagation of environmental anomalies, the spread probability risk prediction is performed for each predetermined propagation area to obtain the spread probability risk coefficients of multiple areas. The spread probability risk coefficient reflects the probability that the environmental anomaly may affect the surrounding areas under abnormal conditions. For example, assuming that the simulation results show that the probability of the temperature anomaly in the first area spreading to the second area is 80%, the probability of spreading to the third area is 50%, and the probability of spreading to the fourth area is 30%. Therefore, the spread probability risk coefficients obtained are 0.8, 0.5 and 0.3. Next, based on the same results of the simulation of the propagation of environmental anomalies, the spread impact risk prediction is performed for each predetermined propagation area to obtain the spread impact risk coefficients of multiple areas. The spread impact risk coefficient represents the actual impact of the abnormal state on the surrounding areas. For example, in the second area, the temperature anomaly may cause the equipment to overheat and affect the operation, and its spread impact risk coefficient is 0.9; in the third area, the impact is relatively small, which may be 0.4; and in the fourth area, the impact is even smaller, only 0.2, which means that under the current conditions, there are significant differences in the degree of impact on different areas. Finally, based on the propagation risk prediction weight condition, the obtained multiple regional spread probability risk coefficients and spread impact risk coefficients are weighted to generate multiple environmental anomaly propagation risk coefficients, where the weights of multiple regional spread probability risk coefficients and spread impact risk coefficients are set by professional and technical personnel in this field based on experience, for example, all are set to 0.5. Through these steps, the power plant can comprehensively assess the propagation risk of environmental anomalies, understand the potential impact of anomalies on the surrounding environment, and thus ensure the accuracy of anomaly warnings.

[0045] In summary, the environmental abnormality monitoring and alarm method of a smart power plant provided by this application has the following technical effects: According to the sensor unit, real-time environmental monitoring is performed on various areas of the power plant to obtain a power plant environmental monitoring data set; based on the power plant environmental anomaly depth constraint table, anomaly detection is performed according to the power plant environmental monitoring data set to determine the power plant environmental anomaly area and the regional environmental anomaly identification result; based on the bidirectional gated loop unit, environmental anomaly risk prediction is performed on the power plant environmental anomaly area according to the regional environmental anomaly identification result to obtain a first environmental anomaly risk coefficient; based on the power plant environmental anomaly area and the regional environmental anomaly identification result, environmental anomaly propagation prediction is performed on the power plant to obtain a second environmental anomaly risk coefficient; based on the environmental anomaly area of ​​the power plant and the regional environmental anomaly identification result, the first environmental anomaly risk coefficient and the second environmental anomaly risk coefficient are weightedly calculated to obtain an environmental anomaly risk detection coefficient; it is determined whether the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold; if the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold, an environmental anomaly warning signal is generated. Through the sensor unit, each area of ​​the power plant is monitored in real time, and the environmental anomaly risk prediction and environmental anomaly propagation prediction are made based on the monitoring data. The environmental risk detection coefficient is then weighted and calculated and compared with the detection threshold to ensure that a warning signal is generated in time when the risk exceeds the threshold, thereby achieving the technical effect of improving the power plant's response speed to environmental anomalies and the accuracy of warnings, and reducing accident risks.

[0046] Embodiment 2: Based on the same inventive concept as the method for monitoring and warning an abnormal environment of a smart power plant in the aforementioned embodiment, the present application also provides an abnormal environment monitoring and warning system for a smart power plant, as shown in the attached Figure 2 , the environmental abnormality monitoring and alarm system of a smart power plant comprises: The real-time environment monitoring module 11 is used to perform real-time environment monitoring on various areas of the power plant according to the sensor units to obtain a power plant environment monitoring data set.

[0047] The anomaly detection module 12 is used to perform anomaly detection based on the power plant environment anomaly depth constraint table and the power plant environment monitoring data set to determine the power plant environment anomaly area and regional environment anomaly identification results.

[0048] The abnormal risk prediction module 13 is used to predict the environmental abnormality risk of the abnormal area of ​​the power plant environment based on the bidirectional gated cycle unit according to the regional environmental abnormality identification result, and obtain the first environmental abnormality risk coefficient.

[0049] The environmental anomaly propagation prediction module 14 is used to predict the environmental anomaly propagation of the power plant based on the environmental anomaly area of ​​the power plant and the regional environmental anomaly identification result, and obtain a second environmental anomaly risk coefficient.

[0050] The risk weighting module 15 is used to perform weighted calculation on the first environmental abnormality risk coefficient and the second environmental abnormality risk coefficient based on the first environmental abnormality risk weight and the second environmental abnormality risk weight to obtain the environmental abnormality risk detection coefficient.

[0051] The risk judgment module 16 is used to judge whether the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold.

[0052] The abnormality warning module 17 is used to generate an environmental abnormality warning signal if the environmental abnormality risk detection coefficient is greater than / equal to the environmental abnormality detection threshold.

[0053] Furthermore, the abnormality detection module 12 in the environmental abnormality monitoring and alarm system of the smart power plant is also used for: According to the power plant environmental monitoring data set, the first area environmental monitoring data corresponding to the first area of ​​the power plant is extracted; based on the first area environmental monitoring data, anomaly detection is performed to obtain a first area environmental anomaly recognition result; according to the first area environmental anomaly recognition result, anomaly depth evaluation is performed to obtain a first environment anomaly depth coefficient; based on the power plant environmental anomaly depth constraint table, the first area environmental anomaly depth threshold corresponding to the first area of ​​the power plant is matched; it is determined whether the first environment anomaly depth coefficient is greater than or equal to the first area environmental anomaly depth threshold; if the first environment anomaly depth coefficient is greater than or equal to the first area environmental anomaly depth threshold, the first area of ​​the power plant is added to the power plant environmental anomaly area, and the first area environmental anomaly recognition result is added to the area environmental anomaly recognition result.

[0054] Furthermore, the abnormality detection module 12 in the environmental abnormality monitoring and alarm system of the smart power plant is also used for: Based on the first area of ​​the power plant, real-time operation task parameters are collected to obtain the operation tasks of the first area; based on the operation tasks of the first area, a health environment prediction is performed on the first area of ​​the power plant to establish a health environment matrix for the first area; based on the environmental monitoring data of the first area, matrix processing is performed to generate an environmental monitoring matrix for the first area; based on the health environment matrix of the first area, anomalies are identified on the environmental monitoring matrix of the first area to generate an environmental anomaly identification result for the first area.

[0055] Furthermore, the abnormality detection module 12 in the environmental abnormality monitoring and alarm system of the smart power plant is also used for: Load multiple regional health environment record groups for the first area of ​​the power plant, wherein each regional health environment record group includes historical regional operation tasks and historical regional health environment information corresponding to the first area of ​​the power plant; based on the first regional operation tasks, perform twin identification on each historical regional operation task in the multiple regional health environment record groups to obtain multiple task twin coefficients; based on the multiple task twin coefficients, select health environment samples for the multiple regional health environment record groups according to task twin thresholds to establish a first regional health environment prediction space; perform central trend analysis based on the first regional health environment prediction space to generate the first regional health environment matrix.

[0056] Furthermore, the abnormal risk prediction module 13 in the abnormal environment monitoring and alarm system of the smart power plant is also used for: Based on the abnormal environment area of ​​the power plant, risk record retrieval is performed to obtain a regional environmental anomaly identification record set and an environmental anomaly risk record set; the bidirectional gated recurrent unit is supervised and trained with the regional environmental anomaly identification record set as input information and the environmental anomaly risk record set as output information, and when the number of training times meets the training number constraint, the environmental anomaly risk prediction loss coefficient is obtained; it is determined whether the environmental anomaly risk prediction loss coefficient is less than the environmental anomaly risk prediction loss threshold; if the environmental anomaly risk prediction loss coefficient is less than the environmental anomaly risk prediction loss threshold, an environmental anomaly risk prediction channel is generated; the regional environmental anomaly identification result is input into the environmental anomaly risk prediction channel to generate the first environmental anomaly risk coefficient.

[0057] Furthermore, the environmental anomaly propagation prediction module 14 in the environmental anomaly monitoring and alarm system of the smart power plant is also used for: A power plant model is constructed based on the power plant basic data set of the power plant; based on the environmental anomaly area of ​​the power plant, an environmental anomaly propagation simulation is performed on the power plant model according to the environmental anomaly identification result of the area to obtain an environmental anomaly propagation simulation result; based on the environmental anomaly propagation simulation result, a propagation risk prediction is performed on each predetermined propagation area of ​​the power plant to obtain a plurality of environmental anomaly propagation risk coefficients; and a concentrated value of the plurality of environmental anomaly propagation risk coefficients is calculated to generate the second environmental anomaly risk coefficient.

[0058] Furthermore, the environmental anomaly propagation prediction module 14 in the environmental anomaly monitoring and alarm system of the smart power plant is also used for: Based on the environmental abnormality propagation simulation results, the risk of spread probability is predicted for each predetermined propagation area to obtain a plurality of regional spread probability risk coefficients; based on the environmental abnormality propagation simulation results, the risk of spread impact is predicted for each predetermined propagation area to obtain a plurality of regional spread impact risk coefficients; based on the propagation risk prediction weight condition, the plurality of regional spread probability risk coefficients and the plurality of regional spread impact risk coefficients are weighted respectively to generate the plurality of environmental abnormality propagation risk coefficients.

[0059] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The environmental anomaly monitoring and alarm method and specific examples of a smart power plant in Example 1 are also applicable to an environmental anomaly monitoring and alarm system of a smart power plant in this embodiment. Through the above detailed description of the environmental anomaly monitoring and alarm method of a smart power plant, those skilled in the art can clearly know the environmental anomaly monitoring and alarm system of a smart power plant in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0060] Embodiment three, based on the inventive concept of an environmental abnormality monitoring and alarm method for a smart power plant in the aforementioned embodiment one, the present application also provides an electronic device, comprising: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the environmental abnormality monitoring and alarm method for a smart power plant described in any one of the aforementioned embodiments one.

[0061] Attached Figure 3 This is a schematic diagram of the structure of an exemplary electronic device of this application. Figure 3In the embodiment, the bus architecture is represented by bus 300, which may include any number of interconnected buses and bridges, and bus 300 connects various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, namely a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 may be used to store data used by processor 302 when performing operations.

[0062] Embodiment 4, based on the same inventive concept as the environmental abnormality monitoring and alarm method for a smart power plant in the aforementioned embodiment 1, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, the steps of the environmental abnormality monitoring and alarm method for a smart power plant described in any one of the aforementioned embodiments 1 are implemented.

[0063] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0064] 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 belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for monitoring and warning abnormal environment in a smart power plant, characterized in that: The method for monitoring and warning abnormal environment of a smart power plant comprises: Perform real-time environmental monitoring of various areas of the power plant based on sensor units to obtain a power plant environmental monitoring data set; Based on the power plant environment anomaly depth constraint table, anomaly detection is performed according to the power plant environment monitoring data set to determine the power plant environment anomaly area and regional environment anomaly identification results; Based on the bidirectional gated cycle unit, predict the environmental abnormality risk of the power plant environmental abnormality area according to the regional environmental abnormality identification result to obtain the first environmental abnormality risk coefficient; Based on the power plant environmental anomaly area and the regional environmental anomaly identification result, the environmental anomaly propagation prediction of the power plant is performed to obtain a second environmental anomaly risk coefficient; Based on the first weight of the environmental abnormality risk and the second weight of the environmental abnormality risk, weighted calculation is performed on the first coefficient of the environmental abnormality risk and the second coefficient of the environmental abnormality risk to obtain an environmental abnormality risk detection coefficient; Determine whether the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold; If the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold, an environmental anomaly warning signal is generated.

2. The method for monitoring and warning abnormal environment of a smart power plant according to claim 1, characterized in that: Based on the power plant environment anomaly depth constraint table, anomaly detection is performed according to the power plant environment monitoring data set to determine the power plant environment anomaly area and regional environment anomaly identification results, including: Extracting first area environmental monitoring data corresponding to a first area of ​​the power plant according to the power plant environmental monitoring data set; Perform anomaly detection based on the first regional environmental monitoring data to obtain a first regional environmental anomaly identification result; Perform an abnormal depth evaluation based on the first regional environmental abnormality recognition result to obtain a first environmental abnormal depth coefficient; Based on the power plant environmental abnormality depth constraint table, matching a first area environmental abnormality depth threshold corresponding to the first area of ​​the power plant; Determining whether the first environmental abnormality depth coefficient is greater than or equal to the first regional environmental abnormality depth threshold; If the first environmental anomaly depth coefficient is greater than or equal to the first regional environmental anomaly depth threshold, the first region of the power plant is added to the power plant environmental anomaly region, and the first regional environmental anomaly identification result is added to the regional environmental anomaly identification result.

3. The method for monitoring and warning abnormal environment of a smart power plant according to claim 2, characterized in that: Performing anomaly detection based on the first regional environmental monitoring data to obtain an anomaly recognition result of the first regional environment includes: Based on the first area of ​​the power plant, real-time operation task parameter collection is performed to obtain the first area operation task; Performing a health environment prediction for the first area of ​​the power plant based on the first area operation task, and establishing a health environment matrix for the first area; Performing matrix processing based on the first regional environmental monitoring data to generate a first regional environmental monitoring matrix; Based on the first-region health environment matrix, anomalies of the first-region environment monitoring matrix are identified to generate an anomaly identification result of the first-region environment.

4. The method for monitoring and warning abnormal environment of a smart power plant according to claim 3, characterized in that: Performing a health environment prediction for the first area of ​​the power plant based on the first area operation task, and establishing a health environment matrix for the first area, including: Loading a plurality of regional health environment record groups of the first region of the power plant, wherein each regional health environment record group includes historical regional operation tasks and historical regional health environment information corresponding to the first region of the power plant; Based on the first regional operation task, twin identification is performed on each historical regional operation task in the plurality of regional health environment record groups to obtain a plurality of task twin coefficients; Based on the multiple task twin coefficients, selecting healthy environment samples from the multiple regional health environment record groups according to the task twin threshold, and establishing a first regional health environment prediction space; A central trend analysis is performed based on the first regional health environment prediction space to generate the first regional health environment matrix.

5. The method for monitoring and warning abnormal environment of a smart power plant according to claim 1, characterized in that: Based on the bidirectional gated cycle unit, the environmental anomaly risk of the power plant environmental anomaly area is predicted according to the regional environmental anomaly identification result to obtain the first environmental anomaly risk coefficient, including: Perform risk record retrieval based on the abnormal environment area of ​​the power plant to obtain a regional environmental anomaly identification record set and an environmental anomaly risk record set; Taking the regional environmental anomaly identification record set as input information and the environmental anomaly risk record set as output information, the bidirectional gated recurrent unit is supervised trained, and when the number of training times meets the training number constraint, the environmental anomaly risk prediction loss coefficient is obtained; Determining whether the environmental abnormality risk predicted loss coefficient is less than the environmental abnormality risk predicted loss threshold; If the environmental abnormality risk prediction loss coefficient is less than the environmental abnormality risk prediction loss threshold, generating an environmental abnormality risk prediction channel; The regional environmental anomaly identification result is input into the environmental anomaly risk prediction channel to generate the first environmental anomaly risk coefficient.

6. The method for monitoring and warning abnormal environment of a smart power plant according to claim 1, characterized in that: Based on the power plant environmental anomaly area and the regional environmental anomaly identification result, the environmental anomaly propagation prediction of the power plant is performed to obtain a second environmental anomaly risk coefficient, including: Building a power plant model based on a power plant basic data set of the power plant; Based on the power plant environmental anomaly area, performing environmental anomaly propagation simulation on the power plant model according to the regional environmental anomaly identification result to obtain an environmental anomaly propagation simulation result; Based on the environmental anomaly propagation simulation result, a propagation risk prediction is performed on each predetermined propagation area of ​​the power plant to obtain a plurality of environmental anomaly propagation risk coefficients; The centralized value of the plurality of environmental anomaly propagation risk coefficients is calculated to generate the second environmental anomaly risk coefficient.

7. The method for monitoring and warning abnormal environment of a smart power plant according to claim 6, characterized in that: Based on the environmental anomaly propagation simulation result, a propagation risk prediction is performed on each predetermined propagation area of ​​the power plant to obtain a plurality of environmental anomaly propagation risk coefficients, including: Based on the environmental anomaly propagation simulation result, predicting the risk of spreading probability for each predetermined propagation area to obtain a plurality of regional spreading probability risk coefficients; Based on the environmental anomaly propagation simulation result, predicting the impact risk of each predetermined propagation area to obtain multiple regional impact risk coefficients; Based on the propagation risk prediction weight condition, the multiple regional spread probability risk coefficients and the multiple regional spread impact risk coefficients are weighted respectively to generate the multiple environmental abnormality propagation risk coefficients.

8. An environmental abnormality monitoring and alarm system for a smart power plant, characterized in that: The steps for implementing the method for monitoring and warning an abnormal environment of a smart power plant according to any one of claims 1 to 7, wherein the method comprises: A real-time environmental monitoring module is used to perform real-time environmental monitoring of various areas of the power plant based on sensor units to obtain a power plant environmental monitoring data set; An anomaly detection module, used to perform anomaly detection based on the power plant environment anomaly depth constraint table and the power plant environment monitoring data set, and determine the power plant environment anomaly area and regional environment anomaly identification results; An abnormal risk prediction module is used to predict the environmental abnormality risk of the abnormal area of ​​the power plant environment based on the bidirectional gated cycle unit according to the regional environmental abnormality identification result, and obtain a first environmental abnormality risk coefficient; An environmental anomaly propagation prediction module is used to predict the environmental anomaly propagation of the power plant based on the environmental anomaly area of ​​the power plant and the regional environmental anomaly identification result, and obtain a second environmental anomaly risk coefficient; A risk weighting module, configured to perform weighted calculation on the first environmental abnormality risk coefficient and the second environmental abnormality risk coefficient based on the first environmental abnormality risk weight and the second environmental abnormality risk weight to obtain an environmental abnormality risk detection coefficient; A risk judgment module is used to judge whether the environmental anomaly risk detection coefficient is greater than / equal to the environmental anomaly detection threshold; The abnormality warning module is used to generate an environmental abnormality warning signal if the environmental abnormality risk detection coefficient is greater than / equal to the environmental abnormality detection threshold.

9. An electronic device, comprising: at least one processor; a memory communicatively coupled to the at least one processor; In which, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the environmental abnormality monitoring and alarm method of a smart power plant 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, which, when executed, implements the steps of the environmental abnormality monitoring and alarm method for a smart power plant as described in any one of claims 1 to 7.

Images