Electric power field operation safety management and control method and device based on deep fusion of Internet of Things data

Abstract

The invention provides an electric power field operation safety management and control method and device based on Internet of Things data deep fusion, and the method comprises the steps: obtaining deep fusion data through an Internet of Things equipment fusion model, building a multi-dimensional time series data set based on time and space, dividing a first feature of the data set through information gain evaluation, and obtaining a second feature of the data set; normalizing the first feature to obtain a second feature, constructing a hydropower station full-dimensional data deep fusion model to obtain a data development trend of deep fusion data, judging whether the data development trend accords with standard normal distribution or not, if yes, indicating that the deep fusion data is in a stable state, and if not, indicating that the deep fusion data is in a non-stable state. And if the state distribution does not conform to the standard state distribution, indicating that the deep fusion data is abnormal, evaluating the abnormal deep fusion data, and identifying potential safety hazards and risk points. According to the method, the deep fusion data is obtained through the Internet of Things equipment fusion model, the abnormal deep fusion data is obtained, potential safety hazards and risk points are identified after evaluation, and the whole operation process is visible, known and controllable.

Description

Technical Field

[0001] The present application relates to the technical field of power operation safety management and control, and in particular, to a method and device for power on-site operation safety management and control based on deep integration of Internet of Things data. Background Art

[0002] With the increasing attention paid to renewable energy around the world, the installed capacity of new energy stations continues to grow. With the increasing attention paid to renewable energy around the world and the advancement of energy transformation, the market environment for new energy stations is improving. Although the development of new energy stations has achieved remarkable results, it still faces some challenges. At present, the laws and regulations related to safety management in the power system are constantly being improved, supervision is being strengthened, safety education and training are being strengthened, the entry threshold for enterprises is being raised, and insurance systems and credit mechanisms are being initially explored. The power industry is studying the safety organization management system and developing a safety management information system. The power system attaches great importance to safety work. Through research in recent years, relevant safety theories have been applied to safety management to a certain extent, but they cannot keep up with the needs of economic and technological development, mainly in the following aspects:

[0003] (1) Environmental factors such as climate conditions and natural disasters have a direct impact on the safety of the station;

[0004] (2) High-altitude operations are a high-risk link in the station operation process and require strict safety regulations and operating procedures;

[0005] (3) The high risk of human error in on-site operations, insufficient focus on power station data collection, weak coordination between systems within the station, weak overall analysis capabilities, and weak overall planning capabilities lead to low efficiency in hydropower on-site operations and high risks to personnel safety.

[0006] When working in collaboration at high altitudes, it is very difficult for operators to work together and communicate with each other. Traditional interaction methods such as text and gestures are not suitable for high-altitude power operations, and voice interaction is seriously affected by environmental noise.

[0007] Therefore, the prior art has the following disadvantages:

[0008] (1) Traditional on-site monitoring technology is difficult to identify and control typical behaviors, safety status, operating procedures, etc., and IoT devices, personnel qualifications, operating information, and operating steps cannot be associated.

[0009] (2) Original networked devices can only perform single identification, making it difficult to analyze and discover unsafe behaviors, unsafe states, or unsafe programs. Summary of the invention

[0010] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a method and device for safety management and control of power field operations based on deep fusion of Internet of Things data. The deep fusion data obtained by the fusion model of the Internet of Things is processed to obtain abnormal deep fusion data, and the abnormal deep fusion data is evaluated to identify potential safety hazards and risk points, so as to achieve visualization, knowability and controllability of the entire operation process.

[0011] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0012] The safety management and control method of power field operations based on deep integration of IoT data includes the following steps:

[0013] Obtain deep fusion data through the IoT device fusion model and establish a multi-dimensional time series data set based on time and space;

[0014] Using information gain evaluation to divide the first feature of the data set, and normalizing the first feature to obtain the second feature;

[0015] Construct a deep fusion model of the full-dimensional data of the hydropower station, use the second feature to obtain the data development trend of the deep fusion data, and judge whether the data development trend conforms to the standard normal distribution. If it conforms to the standard normal distribution, it means that the deep fusion data is in a stable state. If it does not conform to the standard state distribution, it means that the deep fusion data is abnormal.

[0016] Evaluate abnormal deep fusion data to identify potential safety hazards and risk points.

[0017] Furthermore, the method of using information gain evaluation to divide the characteristics of the data set is:

[0018] Calculate the data set entropy (D);

[0019] Assume that there are n samples in the data set D, of which c samples belong to category C1, d samples belong to category C2, ..., z samples belong to category Ck, then the probability of category Ck is expressed as P(Ck)=ck / n, and the calculation formula of data set entropy(D) is:

[0020] Entropy(D)=-P(C1)*log2(P(C1))-P(C2)*log2(P(C2))-..-P(Ck)*log2(P(Ck))

[0021] Calculate conditional entropy;

[0022] For each first feature A, suppose the first feature has m values, each value is a1, a2, ..., am, and a certain value ai of the first feature A contains di samples. Under the value ai of the first feature A, the number of samples of category Ck is ci. Then the conditional entropy of the first feature A for the data set D is expressed as:

[0023] ConditionalEntropy(A|D)=(d1 / n)*Entropy(D1)+(d2 / n)*Entropy(D2)+...+(dm / n)*Entropy(Dm)

[0024] Calculate information gain InformationGain(A|D);

[0025] The information gain of the first feature A for the data set D can be obtained by calculating the difference between the entropy and the conditional entropy:

[0026] InformationGain(A|D)=Entropy(D)-ConditionalEntropy(A|D).

[0027] Furthermore, the first feature is standardized by using maximum and minimum normalization, Z-score normalization method or L2 norm normalization.

[0028] Furthermore, the method of establishing the IoT device fusion model is as follows:

[0029] Develop unified communication protocols for various IoT devices;

[0030] Select a cloud platform to receive, store and process data from various IoT devices, and build a unified data interface on the cloud platform;

[0031] Conduct in-depth analysis and mining of data generated by IoT devices based on big data and artificial intelligence;

[0032] Perform data security and privacy protection, including data encryption, access control and security auditing.

[0033] Furthermore, the data of various IoT devices are obtained by:

[0034] Add IoT devices that integrate smart access control, smart tags, and smart wearables, and make intelligent transformations to existing video surveillance systems and electrical five-defense systems, and access IoT devices;

[0035] Based on various IoT devices, videos, images, texts, and data are obtained, and the qualification level, work area, work steps, and work behavior are identified through videos, images, texts, and data.

[0036] Furthermore, it also includes establishing a power site operation safety management and control model based on safety hazards and risk points. The method for establishing the power site operation safety management and control model includes:

[0037] Before the operation, the on-site environment data and equipment status data are obtained through IoT devices, and the risk assessment results are obtained based on the on-site environment data and equipment status data. Based on the risk assessment results, an abnormal handling process is established for potential safety hazards and risk points to establish safety control measures;

[0038] Monitoring during operation: Use IoT technology to monitor on-site operation conditions in real time, and combine with intelligent sensing technology to automatically identify potential safety hazards and risk points;

[0039] Exception handling: When an abnormal situation is found, the exception handling process is initiated, and corresponding emergency measures are taken according to the specific type and degree of the exception handling process;

[0040] Post-operation summary: Review and summarize the entire operation process, analyze the effectiveness and shortcomings of safety control measures to obtain summary results, and optimize the safety control process and improve control capabilities based on the summary results.

[0041] A power field operation safety control device based on deep integration of IoT data, comprising:

[0042] The data acquisition module is used to obtain deep fusion data through the IoT device fusion model and establish a multi-dimensional time series data set based on time and space;

[0043] A feature acquisition module, used to divide the first feature of the data set by using information gain evaluation, and normalize the first feature to obtain a second feature;

[0044] The anomaly acquisition module is used to build a deep fusion model of the full-dimensional data of the hydropower station, use the second feature to obtain the data development trend of the deep fusion data, and judge whether the data development trend conforms to the standard normal distribution. If it conforms to the standard normal distribution, it means that the deep fusion data is in a stable state. If it does not conform to the standard state distribution, it means that the deep fusion data is abnormal.

[0045] The safety hazard and risk identification module is used to evaluate abnormal deep fusion data and identify potential safety hazards and risk points.

[0046] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for safe control of electric power field operations based on deep integration of IoT data is implemented.

[0047] A non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the above-mentioned method for safe management and control of power field operations based on deep fusion of Internet of Things data.

[0048] A computer program product includes a computer program, which, when executed by a processor, implements the above-mentioned method for safe management and control of power field operations based on deep integration of Internet of Things data.

[0049] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0050] 1. The purpose of this invention is to develop a multi-IoT device fusion technology suitable for new energy station operation scenarios. On the one hand, it integrates IoT devices such as smart access control, smart tags, and smart wearables. On the other hand, it conducts intelligent transformation and access to existing video surveillance systems and electrical five-defense systems to build an IoT device fusion model for new energy stations.

[0051] 2. The purpose of the present invention is to study safety management and control technology based on human-machine collaboration, establish a multi-dimensional safety management and control model for new energy stations, and associate IoT devices, personnel qualifications, operation information, and operation steps with respect to key and important links and control points in the operation process of personnel in new energy stations, and set up locking logic. Based on image recognition technology, the qualification level, operation area, operation steps, and operation behavior are identified through video, images, text, data and other information, and unsafe behaviors, unsafe states, or unsafe procedures are analyzed and discovered, and early warnings are issued or the program is actively terminated, so as to make the entire operation process visible, knowable, and controllable. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0053] Figure 1 It is a flow chart of the method for safety management and control of electric power field operations based on deep integration of IoT data of the present invention.

[0054] Figure 2 This is a flow chart of the safety management and control of power field operations according to the present invention.

[0055] Figure 3 It is a schematic diagram of the power field operation safety management and control device based on the deep integration of Internet of Things data of the present invention. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0057] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known in the art are not described.

[0058] It should be understood that the present invention can be implemented in different forms and should not be interpreted as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to make the disclosure thorough and complete and to fully convey the scope of the present invention to those skilled in the art.

[0059] Example 1

[0060] Example 1 provides a method for safety management and control of power field operations based on deep integration of IoT data, such as Figure 1 and Figure 2 As shown, the following steps are included:

[0061] Obtain deep fusion data through the IoT device fusion model and establish a multi-dimensional time series data set based on time and space;

[0062] Using information gain evaluation to divide the first feature of the data set, and normalizing the first feature to obtain the second feature;

[0063] Construct a deep fusion model of the full-dimensional data of the hydropower station, use the second feature to obtain the data development trend of the deep fusion data, and judge whether the data development trend conforms to the standard normal distribution. If it conforms to the standard normal distribution, it means that the deep fusion data is in a stable state. If it does not conform to the standard state distribution, it means that the deep fusion data is abnormal.

[0064] Evaluate abnormal deep fusion data to identify potential safety hazards and risk points.

[0065] This embodiment uses the IoT device fusion model to associate IoT devices, personnel qualifications, operation information, and operation steps to obtain deep fusion data for typical behaviors, safety status, and operation processes that are difficult to identify and control with on-site monitoring technology. The data is processed to obtain abnormal deep fusion data, and the abnormal deep fusion data is evaluated to identify potential safety hazards and risk points, making the entire operation process visible, knowable, and controllable. This solves the problem that the original networked devices can only perform single identification and are difficult to analyze and discover unsafe behaviors, unsafe status, or unsafe procedures.

[0066] In this embodiment, Figure 1 and Figure 2 As shown, the method of obtaining data of various IoT devices is:

[0067] Add IoT devices that integrate smart access control, smart tags, and smart wearables, and make intelligent transformations to existing video surveillance systems and electrical five-defense systems, and access IoT devices;

[0068] Based on various IoT devices, videos, images, texts, and data are obtained, and the qualification level, work area, work steps, and work behavior are identified through videos, images, texts, and data.

[0069] Through the IoT device nodes, we can obtain deeply integrated data, establish multi-dimensional time series based on space and time, and provide effective data support for the safe operation of on-site personnel.

[0070] Integrate IoT devices such as smart access control, smart tags, and smart wearables. On the one hand, the existing video surveillance system and electrical five-protection system are intelligently transformed and connected. The transformation method is to introduce high-definition cameras, intelligent analysis software, etc. to improve the monitoring effect and intelligence level. Connect the video surveillance system with the IoT device fusion model to realize real-time transmission and storage of video data, which is convenient for remote monitoring and management. Through the IoT technology, remote monitoring and operation of equipment are realized, and the electrical five-protection system (preventing the wrong opening and closing of circuit breakers, preventing the pulling and closing of disconnecting switches with load, preventing the hanging (closing) of grounding wires (grounding switches) with power on, and preventing the closing of circuit breakers (disconnecting switches) with grounding wires (grounding switches)) is connected to the IoT device fusion model to realize real-time data sharing and collaborative work.

[0071] In this embodiment, Figure 1 and Figure 2 As shown in the figure, the method of establishing the IoT device fusion model is:

[0072] Unified communication protocol: Develop a unified communication protocol to ensure smooth communication between various IoT devices.

[0073] Cloud platform integration: Select a powerful cloud platform to receive, store and process data from various IoT devices, build a unified data interface on the cloud platform, and realize centralized management and sharing of data.

[0074] Data analysis and visualization: Use big data and artificial intelligence technologies to conduct in-depth analysis and mining of the data generated by IoT devices, extract valuable information, and use data visualization technology to display the analysis results in the form of charts, reports, etc., to facilitate managers' understanding and decision-making.

[0075] Security assurance: Fully consider the security and privacy protection of data, including data encryption, access control, security audit and other measures to ensure the security of building the IoT device fusion model.

[0076] In this embodiment, information gain evaluation is used to divide the characteristics of the data set, including the dimension of the data set, that is, the sum of the number of attributes of the data objects in the data set, the sparsity of the data set, that is, the proportion of non-zero or meaningful data items in the data set, the resolution of the data set, that is, the degree of detail of the data observation of the object in time, space or collection volume, the type and structure of the data set, etc., and the characteristics are normalized to construct a deep fusion model of the full-dimensional data of the hydropower station.

[0077] Information gain is used as an evaluation indicator. Information gain is a method used in decision tree algorithms to evaluate the importance of a feature for dividing data.

[0078] The method of using information gain evaluation to divide the features of the data set is:

[0079] Calculate the data set entropy (D);

[0080] Assume that there are n samples in the data set D, of which c samples belong to category C1, d samples belong to category C2, ..., z samples belong to category Ck, then the probability of category Ck is expressed as P(Ck)=ck / n, and the calculation formula of data set entropy(D) is:

[0081] Entropy(D)=-P(C1)*log2(P(C1))-P(C2)*log2(P(C2))-..-P(Ck)*log2(P(Ck))

[0082] Calculate conditional entropy;

[0083] For each first feature A, suppose the first feature has m values, each value is a1, a2, ..., am, and a certain value ai of the first feature A contains di samples. Under the value ai of the first feature A, the number of samples of category Ck is ci. Then the conditional entropy of the first feature A for the data set D is expressed as:

[0084] ConditionalEntropy(A|D)=(d1 / n)*Entropy(D1)+(d2 / n)*Entropy(D2)+...+(dm / n)*Entropy(Dm)

[0085] Calculate information gain InformationGain(A|D);

[0086] The information gain of the first feature A for the data set D can be obtained by calculating the difference between the entropy and the conditional entropy:

[0087] InformationGain(A|D)=Entropy(D)-ConditionalEntropy(A|D).

[0088] Normalize the features: Integrate the video data obtained by the video surveillance system, the electrical five-defense system, etc., build a deep fusion model of the full-dimensional data of the hydropower station, and normalize the features. This is an important step to improve the stability of the model and the prediction accuracy. The following are several common normalization methods:

[0089] (1) Min-Max Normalization: This normalization method is also called deviation normalization, which maps the result value to between [0,1]. The conversion function is as follows:

[0090] x'=(x-min) / (max-min)

[0091] Where x is the original data, x' is the normalized data, min is the minimum value of the data, and max is the maximum value of the data.

[0092] (2) Z-score standardization method: After data processing, it conforms to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1.

[0093] Its conversion function is:

[0094] x'=(x-μ) / σ

[0095] Where x is the original data, x' is the normalized data, μ is the mean of all sample data, and σ is the standard deviation of all sample data.

[0096] (3) L2 norm normalization: Each element in the feature vector is divided by the L2 norm of the vector.

[0097] For the second feature after normalization, a deep fusion model of the full-dimensional data of the hydropower station can be further constructed. The specific method is that the hydropower station provides full-dimensional data, and the above-mentioned feature normalization processing method is used to obtain the development trend of the data and check whether the processed data conforms to the standard normal distribution. Data that conforms to the standard normal distribution is judged to be in a stable state, and data that does not conform to the standard state distribution indicates that the monitoring data is unstable and the equipment may be abnormal. This analysis step realizes the intelligent analysis function of the data; when it is determined that the equipment is abnormal, the system alarms. This process reflects the risk warning function and realizes functions such as intelligent analysis of data and risk warning.

[0098] In this embodiment, Figure 1 and Figure 2As shown in the figure, through intelligent perception and deep integration of data, a safety risk assessment mechanism for on-site operations is proposed, and a safety management and control process for power on-site operations based on deep integration of IoT data is designed.

[0099] Using IoT technology, various data on field operations are collected, including personnel activities, equipment status, environmental parameters, etc. Then, data analysis technologies such as machine learning and deep learning are applied to perform intelligent perception and pattern recognition on the collected data to identify potential safety hazards and risk points, such as abnormal equipment status.

[0100] Based on the results of intelligent perception, combined with historical data and expert knowledge, the safety risks of on-site operations are assessed. The assessment results are expressed in quantitative indicators, such as risk level, possibility, impact, etc. These indicators are based on existing on-site operation work experience and operating standards. When the assessment results exceed the preset risk threshold, the risk warning mechanism is triggered.

[0101] This embodiment also includes establishing a safety management and control model for power field operations based on safety hazards and risk points, such as Figure 1 and Figure 2 As shown in FIG. 1 , the method for establishing a safety control model for power field operations includes:

[0102] (1) Before the operation, obtain on-site environmental data, equipment status data, etc. through IoT devices, and formulate targeted safety control measures based on risk assessment results.

[0103] (2) Monitoring during operation: Use IoT technology to monitor on-site operation conditions in real time, and combine it with intelligent sensing technology to automatically identify potential safety hazards and risk points.

[0104] (3) Exception handling: Once an abnormal situation is discovered, the exception handling process is immediately initiated and appropriate emergency measures are taken based on the specific type and severity of the abnormal situation.

[0105] (4) Post-operation summary: Review and summarize the entire operation process, analyze the effectiveness and shortcomings of safety control measures, and optimize the safety control process and improve control capabilities based on the summary results.

[0106] (5) Deeply integrate data from different IoT devices to form a complete operational data chain. Use these data chains to perform big data analysis, extract valuable information and rules, and provide decision support for security management and control.

[0107] Identify and control typical behaviors, safety status, operating procedures, etc. to achieve closed-loop control, active early warning and auxiliary support of on-site operations, realize the interconnection of personnel, equipment, environment, and business processes, improve the level of operation management, and actively prevent safety accidents.

[0108] This embodiment uses the Internet of Things technology and data fusion technology to achieve real-time data connection and data interaction between IoT devices and the smart safety service support platform of new energy stations, and realizes mobile and intelligent operations. Through the structured processing of the operation process, the basic process control of personnel operations is realized; through video monitoring and process linkage, unsafe behaviors of personnel are controlled.

[0109] Extract the causes and safety risks of safety incidents related to on-site operation tasks, identify the key links and control nodes in the operation process, such as data on personnel activities during the operation: personnel's movement trajectory, spatial coordinates and other data. If there is a problem with the extracted data, it means that there is an error in the link and an early warning is needed; Equipment status: Equipment such as impeller blades, data monitored by sensors such as rotation speed. Under normal circumstances, the changes in the equipment's monitoring data are stable, which conforms to the standard normal distribution. Instability indicates that the equipment may be abnormal. On the basis of the structured operation process, key links and control key nodes can be checked, realizing the construction of a new energy station operation process tracking model.

[0110] In summary, this embodiment has the following advantages:

[0111] 1. It can collect on-site operation data in real time and conduct comprehensive analysis and processing of these data through data fusion technology. This enables the safety management system to grasp the safety status of the operation site in real time. Once an abnormality or potential risk is found, the system can immediately issue an early warning to remind the operator to take corresponding safety measures.

[0112] 2. The present invention can realize real-time monitoring and adjustment of the operation process, thereby optimizing the operation process and reducing unnecessary operation links. At the same time, through automation and intelligent control, it can improve operation efficiency and reduce labor costs. The safety management and control system based on the deep integration of IoT data can cover all aspects and links of power field operations, realize comprehensive and systematic safety management, eliminate blind spots and dead ends in safety management, and improve the overall level of safety management.

[0113] Example 2

[0114] Embodiment 2 provides a power field operation safety management and control device based on deep integration of IoT data, such as Figure 3 As shown, including:

[0115] The data acquisition module is used to obtain deep fusion data through the IoT device fusion model and establish a multi-dimensional time series data set based on time and space;

[0116] A feature acquisition module, used to divide the first feature of the data set by using information gain evaluation, and normalize the first feature to obtain a second feature;

[0117] The anomaly acquisition module is used to build a deep fusion model of the full-dimensional data of the hydropower station, use the second feature to obtain the data development trend of the deep fusion data, and judge whether the data development trend conforms to the standard normal distribution. If it conforms to the standard normal distribution, it means that the deep fusion data is in a stable state. If it does not conform to the standard state distribution, it means that the deep fusion data is abnormal.

[0118] The safety hazard and risk identification module is used to evaluate abnormal deep fusion data and identify potential safety hazards and risk points.

[0119] Example 3

[0120] Embodiment 3 provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for safe management and control of electric power field operations based on deep integration of IoT data is implemented.

[0121] Example 4

[0122] Embodiment 4 provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for safety management and control of power field operations based on deep integration of IoT data is implemented.

[0123] Example 5

[0124] This embodiment provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, the above-mentioned power field operation safety management and control method based on deep integration of Internet of Things data is implemented.

[0125] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0126] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0127] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for safety control of power field operations based on deep integration of IoT data, characterized in that: The following steps are involved: Obtain deep fusion data through the IoT device fusion model and establish a multi-dimensional time series data set based on time and space; Using information gain evaluation to divide the first feature of the data set, and normalizing the first feature to obtain the second feature; Construct a deep fusion model of the full-dimensional data of the hydropower station, use the second feature to obtain the data development trend of the deep fusion data, and judge whether the data development trend conforms to the standard normal distribution. If it conforms to the standard normal distribution, it means that the deep fusion data is in a stable state. If it does not conform to the standard state distribution, it means that the deep fusion data is abnormal. Evaluate abnormal deep fusion data to identify potential safety hazards and risk points.

2. The method for safety management and control of electric power field operations based on deep integration of IoT data according to claim 1 is characterized in that: The method of using information gain evaluation to divide the features of the data set is: Calculate the data set entropy (D); Assume that there are n samples in the data set D, of which c samples belong to category C1, d samples belong to category C2, ..., z samples belong to category Ck, then the probability of category Ck is expressed as P(Ck)=ck / n, and the calculation formula of data set entropy(D) is: Entropy(D)=-P(C1)*log2(P(C1))-P(C2)*log2(P(C2))-..-P(Ck)*log2(P(Ck)) Calculate conditional entropy; For each first feature A, suppose the first feature has m values, each value is a1, a2, ..., am, and a certain value ai of the first feature A contains di samples. Under the value ai of the first feature A, the number of samples of category Ck is ci. Then the conditional entropy of the first feature A for the data set D is expressed as: ConditionalEntropy(A|D)=(d1 / n)*Entropy(D1)+(d2 / n)*Entropy(D2)+...+(dm / n)*Entropy(Dm) calculates information gain InformationGain(A|D); The information gain of the first feature A for the data set D can be obtained by calculating the difference between the entropy and the conditional entropy: InformationGain(A|D)=Entropy(D)-ConditionalEntropy(A|D).

3. The method for safety management and control of electric power field operations based on deep integration of IoT data according to claim 1 is characterized in that: The first feature is standardized using maximum and minimum standardization, Z-score standardization method or L2 norm normalization.

4. The method for safety management and control of electric power field operations based on deep integration of IoT data according to claim 1 is characterized in that: The method to establish the IoT device fusion model is: Develop unified communication protocols for various IoT devices; Select a cloud platform to receive, store and process data from various IoT devices, and build a unified data interface on the cloud platform; Conduct in-depth analysis and mining of data generated by IoT devices based on big data and artificial intelligence; Perform data security and privacy protection, including data encryption, access control and security auditing.

5. The method for safety management and control of electric power field operations based on deep integration of IoT data according to claim 1 is characterized in that: The methods for obtaining data from various IoT devices are: Add IoT devices that integrate smart access control, smart tags, and smart wearables, and make intelligent transformations to existing video surveillance systems and electrical five-defense systems, and access IoT devices; Based on various IoT devices, videos, images, texts, and data are obtained, and the qualification level, work area, work steps, and work behavior are identified through videos, images, texts, and data.

6. The method for safety management and control of electric power field operations based on deep integration of IoT data according to claim 1 is characterized in that: It also includes establishing a safety management and control model for power field operations based on safety hazards and risk points. The method for establishing the safety management and control model for power field operations includes: Before the operation, the on-site environment data and equipment status data are obtained through IoT devices, and the risk assessment results are obtained based on the on-site environment data and equipment status data. Based on the risk assessment results, an abnormal handling process is established for potential safety hazards and risk points to establish safety control measures; Monitoring during operation: Use IoT technology to monitor on-site operation conditions in real time, and combine with intelligent sensing technology to automatically identify potential safety hazards and risk points; Exception handling: When an abnormal situation is found, the exception handling process is initiated, and corresponding emergency measures are taken according to the specific type and degree of the exception handling process; Post-operation summary: Review and summarize the entire operation process, analyze the effectiveness and shortcomings of safety control measures to obtain summary results, and optimize the safety control process and improve control capabilities based on the summary results.

7. A power field operation safety control device based on deep integration of IoT data, characterized in that: include: The data acquisition module is used to obtain deep fusion data through the IoT device fusion model and establish a multi-dimensional time series data set based on time and space; A feature acquisition module, used to divide the first feature of the data set by using information gain evaluation, and normalize the first feature to obtain a second feature; The anomaly acquisition module is used to build a deep fusion model of the full-dimensional data of the hydropower station, use the second feature to obtain the data development trend of the deep fusion data, and judge whether the data development trend conforms to the standard normal distribution. If it conforms to the standard normal distribution, it means that the deep fusion data is in a stable state. If it does not conform to the standard state distribution, it means that the deep fusion data is abnormal. The safety hazard and risk identification module is used to evaluate abnormal deep fusion data and identify potential safety hazards and risk points.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, it implements the method for safe management and control of power field operations based on deep integration of IoT data as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the method for safety management and control of power field operations based on deep integration of Internet of Things data as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by the processor, it implements the method for safety management and control of power field operations based on deep integration of Internet of Things data as described in any one of claims 1 to 6.

Images