Transformer substation environment disaster real-time monitoring and early warning system

Abstract

The invention relates to the technical field of transformer substation environment monitoring, and discloses a transformer substation environment disaster real-time monitoring and early warning system, which comprises a data acquisition module used for regularly acquiring environment parameters and image data of a key area of a transformer substation; the environment parameter imaging module is used for converting the acquired data into an image form; and the image fusion module is used for superposing the parameter image and the real-time image to generate a fused image and visually displaying the environment condition of the transformer substation. And the data analysis module is responsible for analyzing an environment parameter change trend and detecting abnormal data. And the risk assessment module constructs a risk assessment model, and assesses a disaster risk level in combination with a data analysis result and a linear regression algorithm. And the early warning issuing module automatically issues early warning information according to the risk level. The system integrates the functions of environmental monitoring, image display, data analysis and early warning release, provides powerful guarantee for safe and stable operation of the transformer substation, and effectively deals with the influence of various natural disasters and environmental factors.

Description

Technical Field

[0001] The present invention relates to the technical field of substation environment monitoring, and in particular to a real-time monitoring and early warning system for substation environmental disasters. Background Art

[0002] With the rapid development of the power industry, substations, as an important part of the power system, play a vital role in ensuring power supply through safe and stable operation. However, the environment in which substations are located is complex and changeable, and is often affected by various natural disasters and environmental factors, such as extreme weather, geological disasters, equipment overheating, etc. These factors may pose a serious threat to the normal operation of substations. In recent years, with the rapid development of technologies such as the Internet of Things, big data, and artificial intelligence, substation environmental monitoring technology has also made significant progress. However, most of the existing substation environmental monitoring systems focus on the monitoring of a single environmental parameter, lack comprehensive analysis and graphical display of environmental parameters, and are difficult to intuitively reflect the overall status of the substation environment. At the same time, the existing system also has deficiencies in environmental disaster risk assessment and early warning, and cannot accurately assess the disaster risk level and issue early warning information in a timely manner.

[0003] Therefore, there is an urgent need for a real-time monitoring and early warning system for substation environmental disasters that can monitor the environmental parameters and image data of key areas of substations in real time, display the environmental parameters in images, and combine data analysis, risk assessment, and early warning release functions. This system can comprehensively improve the real-time and accuracy of substation environmental monitoring, and provide a strong guarantee for the safe and stable operation of substations. Summary of the invention

[0004] The purpose of the present invention is to provide a real-time monitoring and early warning system for environmental disasters in a substation to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a real-time monitoring and early warning system for environmental disasters in a substation, the system comprising: Data acquisition module, used to regularly collect environmental parameters and image data of key areas of the substation; The environmental parameter imaging module is used to convert the collected environmental parameters into an image form and generate a parameter distribution image; An image fusion module is used to superimpose the parameter distribution image with the real-time image of the key area to generate a fused image, and the fused image is used to simultaneously display the actual physical space of the substation and the distribution status of its environmental parameters; The data analysis module includes an environmental parameter change trend analysis unit and an anomaly detection unit, which are responsible for analyzing the change gradient of environmental parameters and detecting abnormal data respectively; A risk assessment module is used to construct a risk assessment model, which combines the output of the data analysis module and a linear regression algorithm to assess the risk level of environmental disasters in the substation; The early warning release module automatically releases corresponding early warning information according to the risk level obtained by the risk assessment module.

[0006] Preferably, the step of generating a parameter distribution image by the environmental parameter imaging module comprises: S101: receiving environmental parameter data transmitted by a data acquisition module, including a set of temperature, humidity, and air pressure values ​​at each measurement point in a key area; S102: preprocessing the received environmental parameter data, including data cleaning, denoising and normalization; S103: Using a color mapping algorithm, convert the normalized environmental parameter values ​​into corresponding color values ​​to generate a color mapping table; the color mapping uses a linear interpolation algorithm, and its calculation formula is as follows: in, is the normalized environmental parameter value, and are the minimum and maximum color values ​​in the color map, respectively. is the calculated color value; S104: constructing a three-dimensional grid model according to the physical layout of the key area and the location information of the measurement points, and mapping the environmental parameter value and the corresponding color value of each measurement point to the corresponding position of the grid model; S105: Using image rendering technology, the three-dimensional mesh model and the color mapping thereon are converted into a two-dimensional image form to generate a parameter distribution image.

[0007] Preferably, the step of generating a fused image by the image fusion module comprises: S201: receiving a parameter distribution image transmitted by an environmental parameter imaging module; S202: simultaneously receiving the real-time image of the key area transmitted by the data acquisition module; S203: preprocessing the parameter distribution image and the real-time image, including image size adjustment and contrast enhancement; S204: Using an image fusion algorithm, superimposing the preprocessed parameter distribution image on the real-time image to generate a fused image; the image fusion algorithm uses a weighted average method, and its calculation formula is: in, is the fused image, is the parameter distribution image, For real-time images, is the weighting coefficient, and its value range is [0, 1]; S205: Post-processing the generated fused image, including image smoothing and edge enhancement, to eliminate fusion artifacts.

[0008] Preferably, the image smoothing adopts Gaussian filtering algorithm, and the edge enhancement adopts Laplace operator.

[0009] Preferably, the implementation steps of the environmental parameter change trend analysis unit include: S301: Acquire environmental parameters of key areas of the substation collected regularly by a data collection module; S302: For each environmental parameter, calculate the first-order difference of its time series, the formula is: Δy(t) = y(t) - y(t-1), where y(t) is the environmental parameter value at time t, y(t-1) is the environmental parameter value at time t-1, and Δy(t) represents the change gradient of the environmental parameter at time t; S303: Generate a change trend of the environmental parameter over time according to the calculated change gradient.

[0010] Preferably, the abnormality detection unit in the data analysis module uses a threshold determination method to detect abnormal data of environmental parameters, and when the environmental parameters exceed a preset threshold range, they are marked as abnormal data.

[0011] Preferably, the implementation steps of the risk assessment module include: S401: receiving environmental parameter change trend data and anomaly detection data output by a data analysis module; S402: Setting risk assessment indicators, including the absolute value of the gradient of environmental parameters, the frequency of abnormal data, and the severity of abnormal data; S403: Construct a risk assessment model using a linear regression algorithm, with the formula: Y = βX + ε, where Y represents the risk level, X represents the risk assessment indicator vector, β is the regression coefficient vector, and ε is the error term; S404: Calculate the risk level of the substation environmental disaster according to the risk assessment model.

[0012] Preferably, when training the risk assessment model, the risk assessment module calculates the loss between the model output and the true label through a forward propagation algorithm, and the loss function adopts a cross entropy loss function; its formula is: Where N is the sample size, is the true label of the i-th sample, is the predicted probability of the ith sample; The gradient of the loss function with respect to the model parameters is calculated through the back-propagation algorithm, and the model parameters are updated using the gradient descent algorithm.

[0013] Preferably, the risk level output by the risk assessment module is divided into four levels: low risk, medium risk, high risk, and extremely high risk, and each level corresponds to a different early warning information release strategy.

[0014] Preferably, the warning release module automatically selects a corresponding warning information release method according to the risk level output by the risk assessment module, including SMS notification, email notification, sound and light alarm and voice alarm.

[0015] Compared with the prior art, the present invention has the following beneficial effects: Real-time monitoring and comprehensive perception: The system collects environmental parameters and image data of key areas of the substation regularly through the data acquisition module, realizing real-time monitoring and comprehensive perception of the substation environment. This helps to timely discover and deal with potential environmental disaster risks and ensure the safe and stable operation of the substation.

[0016] Environmental parameter visualization: The environmental parameter visualization module converts the collected environmental parameters into images and generates parameter distribution images. This visualization method makes the environmental parameters more intuitive and easy to understand, which helps operation and maintenance personnel quickly understand the overall status of the substation environment.

[0017] Fusion images improve judgment accuracy: The image fusion module superimposes the parameter distribution image with the real-time image of the key area to generate a fusion image. This fusion image simultaneously displays the actual physical space of the substation and the distribution of its environmental parameters, providing operation and maintenance personnel with more comprehensive and accurate information, which helps to improve their judgment accuracy on environmental disasters.

[0018] Data analysis and anomaly detection: The data analysis module includes an environmental parameter change trend analysis unit and an anomaly detection unit, which can analyze the change gradient of environmental parameters and detect abnormal data. This helps to timely discover abnormal changes in environmental parameters and provide strong support for risk assessment and early warning release.

[0019] Accurately assess the disaster risk level: The risk assessment module builds a risk assessment model, combines the output of the data analysis module and the linear regression algorithm to assess the risk level of environmental disasters in substations. This assessment method is more scientific and accurate, which helps operation and maintenance personnel take corresponding measures in a timely manner to reduce the impact of environmental disasters on substations.

[0020] Automatically release early warning information: The early warning release module automatically releases corresponding early warning information according to the risk level obtained by the risk assessment module. This helps operation and maintenance personnel respond to environmental disaster risks in a timely manner and ensure the safe and stable operation of the substation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a working principle diagram of a real-time monitoring and early warning system for environmental disasters in a substation according to the present invention; Figure 2 A diagram showing the working steps of the environmental parameter imaging module from receiving data to generating parameter distribution images; Figure 3 A diagram of the working steps of the image fusion module from receiving images to generating the final fused image. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] See also Figure 1-3 The present invention provides a technical solution: a real-time monitoring and early warning system for environmental disasters in a substation, the system comprising: Data acquisition module: The data acquisition module is the foundation of the system and is responsible for regularly collecting environmental parameters and image data of key areas of the substation. Environmental parameters include but are not limited to temperature, humidity, wind speed, air pressure, etc. These parameters are obtained in real time through sensors. At the same time, the module is also equipped with a high-definition camera to capture real-time images of key areas. The data acquisition module automatically collects data at preset time intervals, such as every minute or every hour, and sends the data to the subsequent processing module.

[0024] Environmental parameter visualization module: The environmental parameter visualization module receives the environmental parameter data sent by the data acquisition module and converts the data into image form through a specific algorithm. For example, temperature data can be mapped to pixels of different colors to generate a temperature distribution image; similarly, parameters such as humidity and wind speed can also be converted into corresponding images. These parameter distribution images can intuitively display the distribution of environmental parameters in key areas of the substation.

[0025] Image fusion module: The image fusion module superimposes the parameter distribution image generated by the environmental parameter visualization module with the real-time image of the key area captured by the data acquisition module. Through image fusion technology, the parameter distribution image is superimposed on the real-time image as a transparent layer to generate a fused image. The fused image can simultaneously display the actual physical space of the substation and its environmental parameter distribution status, providing more comprehensive environmental information for operation and maintenance personnel.

[0026] Data analysis module: The data analysis module includes an environmental parameter change trend analysis unit and an anomaly detection unit. The change trend analysis unit is responsible for time series analysis of the collected environmental parameter data, calculating the parameter change gradient, and predicting future change trends. The anomaly detection unit detects anomalies in the data by setting thresholds or using machine learning algorithms to promptly identify potential environmental problems.

[0027] Risk Assessment Module: The risk assessment module constructs a risk assessment model, combines the output of the data analysis module and the linear regression algorithm, and evaluates the risk level of environmental disasters in substations. The model comprehensively considers the changing trends, abnormal conditions and historical data of multiple environmental parameters, and calculates the risk level through the algorithm. The risk level can be divided into low, medium, high and very high levels, providing a basis for the issuance of early warnings.

[0028] Early warning release module: The early warning release module automatically releases corresponding early warning information according to the risk level obtained by the risk assessment module. Early warning information can be sent to operation and maintenance personnel or relevant management departments through SMS, email, APP push and other methods. At the same time, the system can also integrate early warning information into the monitoring system of the substation to realize real-time display and processing of early warning information.

[0029] The present invention will be further described below in conjunction with Examples 1 to 3: Embodiment 1: The steps for the environmental parameter visualization module to generate parameter distribution images are as follows: S101: receiving environmental parameter data transmitted by the data acquisition module The environmental parameter visualization module first receives the environmental parameter data transmitted by the data acquisition module. These data include the temperature, humidity, and air pressure values ​​of each measurement point in the key area. The data acquisition module collects these data regularly at preset time intervals and ensures the accuracy and integrity of the data.

[0030] S102: Preprocessing the received environmental parameter data After receiving the environmental parameter data, the environmental parameter visualization module preprocesses the data. The preprocessing steps include data cleaning, denoising and normalization. Data cleaning is used to remove abnormal values ​​and erroneous values ​​in the data to ensure the accuracy of the data. Denoising reduces noise interference in the data through filtering algorithms and other means. Normalization maps environmental parameter values ​​of different ranges to a standard range, such as between 0 and 1, for subsequent color mapping processing.

[0031] S103: Using a color mapping algorithm, convert the normalized environmental parameter value into a corresponding color value After preprocessing is completed, the environmental parameter visualization module uses a color mapping algorithm to convert the normalized environmental parameter values ​​into corresponding color values. Color mapping uses a linear interpolation algorithm, and its calculation formula is as follows: in, is the normalized environmental parameter value, and are the minimum and maximum color values ​​in the color map, respectively. is the calculated color value.

[0032] Through this formula, the environmental parameter visualization module can map the environmental parameter value of each measurement point to a specific color value and generate a color mapping table. In this way, different environmental parameter values ​​correspond to different colors, which is convenient for subsequent visualization.

[0033] S104: Construct a 3D grid model based on the physical layout of the key areas and the location information of the measurement points The environmental parameter visualization module constructs a 3D grid model based on the physical layout of the key areas and the location information of the measurement points. This model can accurately reflect the physical space of the key areas and the distribution of the measurement points. Then, the module maps the environmental parameter value and the corresponding color value of each measurement point to the corresponding position of the grid model. In this way, each point on the grid model represents a measurement point and has a corresponding environmental parameter value and color value.

[0034] S105: Use image rendering technology to convert the 3D mesh model and its color mapping into a 2D image Finally, the environmental parameter visualization module uses image rendering technology to convert the 3D grid model and its color mapping into a 2D image. This 2D image is the parameter distribution image, which can intuitively display the distribution of environmental parameters in key areas. Through this image, operation and maintenance personnel can clearly see the differences and change trends of environmental parameters in different areas, providing strong support for subsequent environmental monitoring and early warning.

[0035] The steps of the image fusion module to generate a fused image: S201: receiving the parameter distribution image transmitted by the environmental parameter visualization module The image fusion module first receives the parameter distribution image transmitted by the environmental parameter visualization module. This image shows the distribution of environmental parameters in key areas, such as the spatial distribution of temperature, humidity, air pressure, etc. The parameter distribution image is represented in the form of color mapping, and different colors represent different environmental parameter values.

[0036] S202: receiving the real-time image of the key area transmitted by the data acquisition module The image fusion module also receives real-time images of key areas transmitted by the data acquisition module. This image is a real-time picture captured by a high-definition camera, showing the actual physical space of the key areas of the substation. The real-time image provides intuitive information about the substation equipment, layout and surrounding environment.

[0037] S203: Preprocessing the parameter distribution image and the real-time image After receiving the parameter distribution image and the real-time image, the image fusion module preprocesses the two images. The preprocessing steps include image resizing and contrast enhancement. Image resizing is to ensure that the two images have the same resolution and size for subsequent image fusion processing. Contrast enhancement is to improve the clarity and visibility of the image, making the fused image easier to observe and analyze.

[0038] S204: Using an image fusion algorithm, the preprocessed parameter distribution image is superimposed on the real-time image After the preprocessing is completed, the image fusion module uses an image fusion algorithm to superimpose the preprocessed parameter distribution image on the real-time image. The image fusion algorithm used in this embodiment is a weighted average method, and its calculation formula is: in, is the fused image, is the parameter distribution image, For real-time images, is the weighting coefficient, and its value range is [0, 1].

[0039] By adjusting the value of the weighting coefficient α, the proportion and transparency of the parameter distribution image and the real-time image in the fused image can be controlled. When α is close to 1, the fused image mainly presents the information of the parameter distribution image; when α is close to 0, the fused image mainly presents the information of the real-time image. By reasonably selecting the value of α, a fused image that contains both the environmental parameter distribution information and the details of the real-time image can be generated.

[0040] S205: Post-processing the generated fused image Finally, the image fusion module performs post-processing on the generated fused image to eliminate artifacts and unevenness that may occur during the fusion process. The post-processing steps include image smoothing and edge enhancement. Image smoothing reduces noise and jaggedness in the image through filtering algorithms and other means, making the image smoother and more natural. Edge enhancement enhances the edge information in the image, improves the clarity and contrast of the image, and makes the device and environmental features in the fused image more prominent and easier to identify.

[0041] Embodiment 2: The implementation steps of the environmental parameter change trend analysis unit include: S301: Obtaining environmental parameters of key areas of the substation collected regularly by the data collection module The environmental parameter change trend analysis unit first obtains the environmental parameters of the key areas of the substation collected regularly by the data acquisition module. These environmental parameters include but are not limited to temperature, humidity, air pressure, etc., which reflect the real-time environmental conditions of the key areas of the substation.

[0042] S302: For each environmental parameter, calculate the first-order difference of its time series The environmental parameter change trend analysis unit calculates the first-order difference of the time series for each environmental parameter. The calculation formula of the first-order difference is: Δy(t) = y(t) - y(t-1), where y(t) is the environmental parameter value at time t, y(t-1) is the environmental parameter value at time t-1, and Δy(t) represents the change gradient of the environmental parameter at time t. By calculating the first-order difference, the rate of change of the environmental parameter over time can be obtained, thereby reflecting its change trend.

[0043] S303: Generate the change trend of environmental parameters over time based on the calculated change gradient The environmental parameter change trend analysis unit generates the change trend of the environmental parameters over time based on the calculated change gradient. This can be achieved by drawing a time series graph of the change gradient, which can clearly show the changes of environmental parameters in different time periods, thereby providing intuitive information on environmental parameter changes to operation and maintenance personnel.

[0044] The implementation steps of the risk assessment module include: S401: receiving environmental parameter change trend data and anomaly detection data output by the data analysis module The risk assessment module first receives the environmental parameter change trend data and anomaly detection data output by the data analysis module. These data are the basis of risk assessment and reflect the dynamic changes and anomalies of environmental parameters in key areas of the substation.

[0045] S402: Setting risk assessment indicators The risk assessment module sets risk assessment indicators. These indicators include the absolute value of the change gradient of environmental parameters, the frequency of abnormal data, and the severity of abnormal data. The absolute value of the change gradient reflects the severity of the change of environmental parameters, while the frequency and severity of abnormal data reflect the abnormal conditions of environmental parameters.

[0046] S403: Build a risk assessment model The risk assessment module constructs a risk assessment model. In this embodiment, a linear regression algorithm is used to construct the model, and the formula is: Y = βX + ε, where Y represents the risk level, X represents the risk assessment indicator vector, β is the regression coefficient vector, and ε is the error term. Through the linear regression algorithm, a mapping relationship between risk assessment indicators and risk levels can be established.

[0047] S404: Calculate the risk level of substation environmental disasters based on the risk assessment model The risk assessment module calculates the risk level of substation environmental disasters based on the risk assessment model. This can be done by inputting risk assessment indicators into the model to obtain the corresponding risk level output. The risk level can be used to assess the potential risk of substation environmental disasters and provide decision support for operation and maintenance personnel.

[0048] When training the risk assessment model, the risk assessment module uses the forward propagation algorithm to calculate the loss between the model output and the true label. The loss function uses the cross entropy loss function, and its formula is: Where N is the sample size, is the true label of the i-th sample, is the predicted probability of the ith sample.

[0049] Then, the risk assessment module calculates the gradient of the loss function with respect to the model parameters through the back propagation algorithm, and uses the gradient descent algorithm to update the model parameters. By continuously iterating and optimizing the model parameters, the model can more accurately predict the risk level of substation environmental disasters.

[0050] Embodiment 3: The abnormality detection unit is responsible for detecting abnormal data of environmental parameters. It uses a threshold determination method for detection, and the specific steps are as follows: Preset threshold ranges for environmental parameters. According to the actual operation of the substation and the historical data of environmental parameters, set a reasonable threshold range for each environmental parameter, including upper and lower limits.

[0051] Real-time monitoring of environmental parameters. The data acquisition module regularly collects environmental parameters in key areas of the substation, such as temperature, humidity, air pressure, etc.

[0052] Determine whether the environmental parameter exceeds the threshold range. Compare the real-time monitored environmental parameter with the preset threshold range. If the value of the environmental parameter exceeds the upper limit or is lower than the lower limit, it is determined to be abnormal data.

[0053] Mark abnormal data. Mark the data that is determined to be abnormal for subsequent data analysis and processing.

[0054] The risk assessment module is responsible for assessing the risk level of environmental disasters in substations based on the environmental parameter change trend data and anomaly detection data output by the data analysis module. The implementation steps are as follows: Receive data. The risk assessment module receives the environmental parameter change trend data and anomaly detection data output by the data analysis module as the basis for risk assessment.

[0055] Set risk assessment indicators. According to the changing trends of environmental parameters and the situation of abnormal data, set risk assessment indicators, such as the absolute value of the gradient of environmental parameters, the frequency and severity of abnormal data, etc.

[0056] Calculate the risk level based on the risk assessment indicators.

[0057] Output risk level. The risk level calculated by the risk assessment model is divided into four levels: low risk, medium risk, high risk, and extremely high risk. Each level corresponds to a different early warning information release strategy, so that operation and maintenance personnel can take corresponding measures according to the risk level.

[0058] The warning release module is responsible for automatically selecting the corresponding warning information release method based on the risk level output by the risk assessment module, and promptly conveying the warning information to the operation and maintenance personnel. The implementation steps are as follows: Receive risk level. The early warning release module receives the risk level information output by the risk assessment module.

[0059] Determine the risk level. Determine the current risk level based on the received risk level information.

[0060] Select the method for issuing warning information. According to the risk level, the corresponding method for issuing warning information will be automatically selected. For example, for low risk level, you can choose email notification; for medium risk level, you can choose SMS notification; for high risk and extremely high risk level, you can choose to issue warning information in multiple ways at the same time, such as sound and light alarm and voice alarm.

[0061] Release warning information. Through the selected warning information release method, the warning information will be promptly conveyed to the operation and maintenance personnel so that they can take corresponding response measures to ensure the safe operation of the substation.

[0062] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0063] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A real-time monitoring and early warning system for environmental disasters in a substation, characterized in that: The system comprises: Data acquisition module, used to regularly collect environmental parameters and image data of key areas of the substation; The environmental parameter imaging module is used to convert the collected environmental parameters into an image form and generate a parameter distribution image; An image fusion module is used to superimpose the parameter distribution image with the real-time image of the key area to generate a fused image, and the fused image is used to simultaneously display the actual physical space of the substation and the distribution status of its environmental parameters; The data analysis module includes an environmental parameter change trend analysis unit and an anomaly detection unit, which are responsible for analyzing the change gradient of environmental parameters and detecting abnormal data respectively; A risk assessment module is used to construct a risk assessment model, which combines the output of the data analysis module and a linear regression algorithm to assess the risk level of environmental disasters in the substation; The early warning release module automatically releases corresponding early warning information according to the risk level obtained by the risk assessment module.

2. A substation environmental disaster real-time monitoring and early warning system according to claim 1, characterized in that: The step of generating a parameter distribution image by the environmental parameter imaging module comprises: S101: receiving environmental parameter data transmitted by a data acquisition module, including a set of temperature, humidity, and air pressure values ​​at each measurement point in a key area; S102: preprocessing the received environmental parameter data, including data cleaning, denoising and normalization; S103: Using a color mapping algorithm, convert the normalized environmental parameter values ​​into corresponding color values ​​to generate a color mapping table; the color mapping uses a linear interpolation algorithm, and its calculation formula is as follows: in, is the normalized environmental parameter value, and are the minimum and maximum color values ​​in the color map, respectively. is the calculated color value; S104: constructing a three-dimensional grid model according to the physical layout of the key area and the location information of the measurement points, and mapping the environmental parameter value and the corresponding color value of each measurement point to the corresponding position of the grid model; S105: Using image rendering technology, the three-dimensional mesh model and the color mapping thereon are converted into a two-dimensional image form to generate a parameter distribution image.

3. A substation environmental disaster real-time monitoring and early warning system according to claim 2, characterized in that: The step of generating a fused image by the image fusion module comprises: S201: receiving a parameter distribution image transmitted by an environmental parameter imaging module; S202: simultaneously receiving the real-time image of the key area transmitted by the data acquisition module; S203: preprocessing the parameter distribution image and the real-time image, including image size adjustment and contrast enhancement; S204: Using an image fusion algorithm, superimposing the preprocessed parameter distribution image on the real-time image to generate a fused image; the image fusion algorithm uses a weighted average method, and its calculation formula is: in, is the fused image, is the parameter distribution image, For real-time images, is the weighting coefficient, and its value range is [0, 1]; S205: Post-processing the generated fused image, including image smoothing and edge enhancement, to eliminate fusion artifacts.

4. A substation environmental disaster real-time monitoring and early warning system according to claim 3, characterized in that: The image is smoothed using a Gaussian filter algorithm, and edge enhancement is performed using a Laplace operator.

5. A real-time monitoring and early warning system for environmental disasters in a substation according to claim 1, characterized in that: The implementation steps of the environmental parameter change trend analysis unit include: S301: Acquire environmental parameters of key areas of the substation collected regularly by a data collection module; S302: For each environmental parameter, calculate the first-order difference of its time series, the formula is: Δy(t) = y(t) - y(t-1), where y(t) is the environmental parameter value at time t, y(t-1) is the environmental parameter value at time t-1, and Δy(t) represents the change gradient of the environmental parameter at time t; S303: Generate a change trend of the environmental parameter over time according to the calculated change gradient.

6. A substation environmental disaster real-time monitoring and early warning system according to claim 1, characterized in that: The abnormality detection unit in the data analysis module uses a threshold determination method to detect abnormal data of environmental parameters. When the environmental parameters exceed a preset threshold range, they are marked as abnormal data.

7. A real-time monitoring and early warning system for environmental disasters in a substation according to claim 6, characterized in that: The implementation steps of the risk assessment module include: S401: receiving environmental parameter change trend data and anomaly detection data output by a data analysis module; S402: Setting risk assessment indicators, including the absolute value of the gradient of environmental parameters, the frequency of abnormal data, and the severity of abnormal data; S403: Construct a risk assessment model using a linear regression algorithm, with the formula: Y = βX + ε, where Y represents the risk level, X represents the risk assessment indicator vector, β is the regression coefficient vector, and ε is the error term; S404: Calculate the risk level of the substation environmental disaster according to the risk assessment model.

8. A real-time monitoring and early warning system for environmental disasters in a substation according to claim 7, characterized in that: When training the risk assessment model, the risk assessment module calculates the loss between the model output and the true label through the forward propagation algorithm, and the loss function adopts the cross entropy loss function; its formula is: Where N is the sample size, is the true label of the i-th sample, is the predicted probability of the ith sample; The gradient of the loss function with respect to the model parameters is calculated through the back-propagation algorithm, and the model parameters are updated using the gradient descent algorithm.

9. A real-time monitoring and early warning system for environmental disasters in a substation according to claim 1, characterized in that: The risk level output by the risk assessment module is divided into four levels: low risk, medium risk, high risk, and extremely high risk, and each level corresponds to a different early warning information release strategy.

10. A substation environmental disaster real-time monitoring and early warning system according to claim 1, characterized in that: The warning release module automatically selects the corresponding warning information release method according to the risk level output by the risk assessment module, including SMS notification, email notification, sound and light alarm and voice alarm.

Images