Transformer substation on-line monitoring system and method based on Internet of Things

Abstract

The invention discloses a transformer substation on-line monitoring system and method based on the Internet of Things, and belongs to the technical field of on-line monitoring, and the method specifically comprises the steps: collecting operation data and environment data in a transformer substation collaborative application scene, summarizing the operation data and the environment data, and obtaining transformer substation summarized data, preprocessing the summarized data of the transformer substation, including data cleaning and missing value correction, identifying abnormal conditions of the transformer substation by using a transformer substation state prediction model, classifying states of transformer substation equipment, predicting faults of the transformer substation equipment, and generating early warning information when the fault of the transformer substation equipment is detected; based on the real-time data and historical data of the substation equipment, the intelligent control strategy is utilized, the operation parameters of the substation equipment are optimized, the sudden failure and downtime of the equipment are reduced, the service life of the equipment is prolonged, the operation strategy of the substation can be improved, and the energy efficiency and the equipment utilization rate can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of online monitoring, and in particular to an online monitoring system and method for a substation based on the Internet of Things. Background Art

[0002] Existing substations are mainly operated and maintained manually. If a danger occurs, it is handled based on the experience of the operating staff. The operating efficiency is low and safety accidents are prone to occur. Therefore, multiple trainings are required and misoperation should be avoided as much as possible. Some solutions also provide unmanned operation and maintenance methods for substations, but the sensors at the power grid site are transmitted back to the main station through the optical fiber network and are encrypted. Manual data collection is used, and unmanned operation and maintenance are not possible.

[0003] For example, the Chinese patent with publication number CN115236469A discloses an unmanned substation online monitoring method, system, medium and equipment. The solution includes starting the video detection equipment in the substation to collect images; starting the infrared and ultraviolet detection equipment in the substation to collect temperature and abnormal discharge; analyzing the moving object based on the image data obtained by image collection to obtain the object's movement speed and direction; generating an abnormal discharge index based on the abnormal discharge collection data; calculating the duty index based on the abnormal discharge index, the object's movement speed, the movement direction and the temperature obtained by real-time collection; and performing online fault elimination inspection and remote update when it is determined that the duty index exceeds the preset index. The solution realizes unmanned rapid alarm and risk fault elimination through intelligent analysis of video data and infrared data, combined with artificial intelligence algorithms, and coordinated with online remote status inspection.

[0004] The defect of the above patent is that in special environments, such as thunderstorms and at night, it is impossible to accurately detect temperature and abnormal discharge. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention proposes an online monitoring system and method for substations based on the Internet of Things, which collects operating data and environmental data in substation collaborative application scenarios, and summarizes the operating data and environmental data to obtain substation summary data, and pre-processes the substation summary data, including data cleaning and correction of missing values. The substation status prediction model is used to identify abnormal conditions of the substation, classify the status of substation equipment, predict the failure of substation equipment, and generate early warning information when a substation equipment failure is detected. Based on the real-time data and historical data of the substation equipment, an intelligent control strategy is used to optimize the operating parameters of the substation equipment.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A substation online monitoring method based on the Internet of Things includes the following specific steps:

[0008] Step S1: collecting operation data and environmental data in the substation collaborative application scenario, and summarizing the operation data and environmental data to obtain substation summary data;

[0009] Step S2: preprocessing the substation summary data, including data cleaning and correction of missing values;

[0010] Step S3: using the substation status prediction model to identify abnormal conditions of the substation and classify the status of the substation equipment;

[0011] Step S4: predicting the failure of the substation equipment and generating early warning information when a failure of the substation equipment is detected;

[0012] Step S5: Based on the real-time data and historical data of the substation equipment, the operating parameters of the substation equipment are optimized using intelligent control strategies.

[0013] Specifically, the specific steps of step S3 are:

[0014] Step S301: Set the pre-processed substation summary data set to X, where X = {x1(m), x2(m), ..., x n (m)}, where x n (m) represents the mth type of data at the nth moment in the preprocessed substation summary data set;

[0015] Step S302: Calculate the short-term average value and long-term average value of the pre-processed substation summary data, and the calculation formula is:

[0016]

[0017] Among them, Dq t represents the short-term average value of the substation summary data preprocessed within time point t and the previous p-1 time points, t represents the current time point, p represents the short-term window size, and represents the length of the time period (i.e., the number of time steps) used to calculate the short-term average value, x t-i (m) represents the m-th type of data at the ti-th moment in the preprocessed substation summary data set, Cq t represents the long-term average value of the preprocessed substation summary data within time point t and the previous p-1 time points, q represents the long-term window size, and represents the length of the time period (i.e., the number of time steps) used to calculate the long-term average value;

[0018] Step S303: Calculate the standard deviation of the pre-processed substation summary data within the short-term window, and the calculation formula is:

[0019]

[0020] Among them, Ms. t represents the standard deviation of the preprocessed substation summary data within the short-term window;

[0021] Step S304: Calculate the autocorrelation value of the pre-processed substation summary data under time lag i, and the calculation formula is:

[0022]

[0023] Where Ac(i) represents the autocorrelation value of the preprocessed substation summary data at time lag i, x j (m) represents the m-th type of data at the j-th moment in the preprocessed substation summary data set, represents the average value of the mth type of data in the preprocessed substation summary data set, x j+i (m) represents the mth type of data at the j+ith moment in the preprocessed substation summary data set.

[0024] Specifically, the specific steps of step S3 also include:

[0025] Step S305: Use the trained classification machine learning model to classify the status categories of the substation equipment. The specific formula is:

[0026] y=f(Dq t , Cq t , Ms. t ,Ac(t)),

[0027] Among them, y represents the status category of the substation equipment, and the category outputs include: 0, 1 and 2. 0 means that the substation equipment is normal, 1 means that the substation equipment is subhealthy, and 2 means that the substation equipment is faulty. f() represents the trained classification machine learning model.

[0028] Specifically, the specific steps of step S4 are:

[0029] Step S401: Calculate the cumulative and characteristic of the pre-processed substation summary data at time t, and the calculation formula is:

[0030]

[0031] Among them, Lh t The accumulation and characteristics of the preprocessed substation summary data at time t;

[0032] Step S402: Calculate the exponential smoothing characteristics of the pre-processed substation summary data at time t, and the calculation formula is:

[0033] Ph t =αx t (m)+(1-α)Ph t-1 '

[0034] Among them, Ph t represents the exponential smoothing characteristics of the preprocessed substation summary data at time t, Ph t-1 represents the exponential smoothing characteristics of the preprocessed substation summary data at time t-1, α represents the smoothing parameter, which is between 0 and 1;

[0035] Step S403: Use the trained fault prediction model to predict the fault probability after κ time steps in the future. The specific formula is:

[0036] G(t+κ)=g(Dq t , Cq t , Ms. t ,Ac(t),Lh t , Ph t )'

[0037] Among them, G(t+κ) represents the predicted failure probability after κ time steps in the future, and g() represents the trained fault prediction model.

[0038] Specifically, the intelligent control strategy in step S5 includes:

[0039] Reinforcement learning is used to control and optimize the operating parameters of substation equipment. The specific formula is:

[0040] Q(s, θ)=Q(s, θ)+γ[r+η×max Q(s′, θ′)-Q(s, θ)],

[0041] Among them, Q(s, θ) represents the value of taking action θ in state S, γ represents the learning rate, r represents the immediate reward, η represents the discount factor, s′ represents the next state, θ′ represents the next action, and max represents the maximum function.

[0042] A substation online monitoring system based on the Internet of Things is used to implement an online monitoring method for a substation based on the Internet of Things, characterized by comprising: a data acquisition module, a preprocessing module, a state classification module, a fault prediction module and a control optimization module;

[0043] The data acquisition module is used to collect operation data and environmental data in the substation collaborative application scenario, and summarize the operation data and environmental data to obtain substation summary data;

[0044] The preprocessing module is used to preprocess the substation summary data, including data cleaning and correction of missing values;

[0045] The state classification module is used to identify abnormal conditions of the substation and classify the states of the substation equipment using the substation state prediction model;

[0046] The fault prediction module is used to predict the fault of the substation equipment and generate early warning information when a fault of the substation equipment is detected;

[0047] The control optimization module is used to optimize the operating parameters of the substation equipment based on the real-time data and historical data of the substation equipment using an intelligent control strategy.

[0048] Specifically, the state classification module includes a feature extraction unit and a state classification unit;

[0049] The feature extraction unit is used to extract the state features of the pre-processed substation summary data, including the short-term average value, the long-term average value, the standard deviation within the short-term window, and the autocorrelation value under the time lag i;

[0050] The state classification unit is used to classify the state categories of substation equipment according to the state features of the extracted preprocessed substation summary data using a trained classification machine learning model.

[0051] An electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of an online monitoring method for a substation based on the Internet of Things when executing the computer program.

[0052] A computer-readable storage medium stores computer instructions, which, when executed, execute the steps of a substation online monitoring method based on the Internet of Things.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] 1. The present invention proposes an online monitoring method for substations based on the Internet of Things. By utilizing the Internet of Things technology, the automatic management and control of substation equipment can be realized, reducing the errors and risks caused by human operations.

[0055] 2. The present invention proposes an online monitoring method for substations based on the Internet of Things. The system can predict possible failures of equipment through data analysis and machine learning algorithms. When an abnormality or failure is detected, the system can promptly issue an alarm message to notify maintenance personnel to handle it quickly.

[0056] 3. The present invention proposes an online monitoring method for substations based on the Internet of Things. By analyzing the equipment operation data, a preventive maintenance plan can be formulated to reduce sudden failures and downtime of equipment, extend the service life of equipment, and improve the operation strategy of the substation, thereby improving energy efficiency and equipment utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 The present invention provides a flow chart of a substation online monitoring method based on the Internet of Things;

[0058] Figure 2 An architecture diagram of a substation online monitoring system based on the Internet of Things provided by the present invention;

[0059] Figure 3 A schematic diagram of an electronic device for an online monitoring method for a substation based on the Internet of Things provided by the present invention;

[0060] Figure 4 A schematic diagram of the structure of a computer-readable storage medium for an online monitoring method for a substation based on the Internet of Things provided by the present invention. DETAILED DESCRIPTION

[0061] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, in the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside" and the like indicate the orientation or position relationship based on the orientation or position relationship shown in the accompanying drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "No. 1", "No. 2" and "No. 3" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. The present invention is further explained below in conjunction with specific embodiments.

[0062] Example 1

[0063] See also Figure 1 , an embodiment provided by the present invention: a substation online monitoring method based on the Internet of Things, comprising the following specific steps:

[0064] Step S1: The substation monitoring personnel collects the operation data and environmental data in the substation collaborative application scenario, and summarizes the operation data and environmental data to obtain substation summary data;

[0065] Step S2: preprocessing the substation summary data, including data cleaning and correction of missing values;

[0066] Step S3: using the substation status prediction model to identify abnormal conditions of the substation and classify the status of the substation equipment;

[0067] The specific steps of step S3 are:

[0068] Step S301: Set the pre-processed substation summary data set to X, where X = {x1(m), x2(m), ..., x n (m)}, where x n (m) represents the mth type of data at the nth moment in the preprocessed substation summary data set;

[0069] Step S302: Calculate the short-term average value and long-term average value of the pre-processed substation summary data, and the calculation formula is:

[0070]

[0071] Among them, Dq t represents the short-term average value of the substation summary data preprocessed within time point t and the previous p-1 time points, t represents the current time point, p represents the short-term window size, and represents the length of the time period (i.e., the number of time steps) used to calculate the short-term average value, x t-i (m) represents the m-th type of data at the ti-th moment in the preprocessed substation summary data set, Cq t represents the long-term average value of the preprocessed substation summary data within time point t and the previous p-1 time points, q represents the long-term window size, and represents the length of the time period (i.e., the number of time steps) used to calculate the long-term average value;

[0072] Short-term average value Dq t Reflects the average state of the equipment in the short term, and the long-term average value Cq t Reflects the average status of the equipment in the long term;

[0073] Step S303: Calculate the standard deviation of the pre-processed substation summary data within the short-term window, and the calculation formula is:

[0074]

[0075] Among them, Ms. t represents the standard deviation of the preprocessed substation summary data within the short-term window;

[0076] Standard deviation Ms within the short-term window t It reflects the fluctuation of the equipment in the short term, because the equipment status classification or fault prediction is based on short-term data, and the long-term data is only for reference;

[0077] Step S304: Calculate the autocorrelation value of the pre-processed substation summary data under time lag i, and the calculation formula is:

[0078]

[0079] Where Ac(i) represents the autocorrelation value of the preprocessed substation summary data at time lag i, x j (m) represents the m-th type of data at the j-th moment in the preprocessed substation summary data set, represents the average value of the mth type of data in the preprocessed substation summary data set, x j+i (m) represents the m-th type of data at the j+i-th moment in the preprocessed substation summary data set;

[0080] The autocorrelation value Ac(i) reflects the correlation of data at different time intervals and helps to discover periodic patterns;

[0081] Step S305: Use the trained classification machine learning model to classify the status categories of the substation equipment. The specific formula is:

[0082] y=f(Dq t , Cq t , Ms. t ,Ac(t)),

[0083] Among them, y represents the status category of the substation equipment, and the category outputs include: 0, 1 and 2. 0 means that the substation equipment is normal, 1 means that the substation equipment is subhealthy, and 2 means that the substation equipment is faulty. f() represents the trained classification machine learning model.

[0084] Step S4: predicting the failure of the substation equipment and generating early warning information when a failure of the substation equipment is detected;

[0085] The specific steps of step S4 are:

[0086] Step S401: Calculate the cumulative and characteristic of the pre-processed substation summary data at time t, and the calculation formula is:

[0087]

[0088] Among them, Lh t The accumulation and characteristics of the preprocessed substation summary data at time t;

[0089] Cumulative and Lh t The feature reflects the cumulative sum of data from time point 1 to the current time point t and is used to detect the cumulative change of data;

[0090] Step S402: Calculate the exponential smoothing characteristics of the pre-processed substation summary data at time t, and the calculation formula is:

[0091] Ph t =αx t (m)+(1-α)Ph t-1 '

[0092] Among them, Ph t represents the exponential smoothing characteristics of the preprocessed substation summary data at time t, Ph t-1 represents the exponential smoothing characteristics of the preprocessed substation summary data at time t-1, α represents the smoothing parameter, which is between 0 and 1;

[0093] Exponential smoothing characteristic Ph t Represents the exponentially weighted moving average of the data before and at the current time point t, which is used to smooth the data, reduce the impact of noise, and reflect trend changes;

[0094] Step S403: Use the trained fault prediction model to predict the fault probability after κ time steps in the future. The specific formula is:

[0095] G(t+κ)=g(Dq t , Cq t , Ms. t ,Ac(t),Lh t , Ph t )'

[0096] Among them, G(t+κ) represents the predicted failure probability after κ time steps in the future, and g() represents the trained fault prediction model.

[0097] Compared with the prior art, the method of the present invention is unique in feature selection and model design, and can more accurately capture equipment status changes and failure trends;

[0098] Step S5: Based on the real-time data and historical data of the substation equipment, the operating parameters of the substation equipment are optimized using intelligent control strategies.

[0099] The intelligent control strategy in step S5 includes:

[0100] Reinforcement learning is used to control and optimize the operating parameters of substation equipment. The specific formula is:

[0101] Q(s, θ)=Q(s, θ)+γ[r+η×max Q(s′, θ′)-Q(s, θ)],

[0102] Among them, Q(s, θ) represents the value of taking action θ in state s, γ represents the learning rate, r represents the immediate reward, η represents the discount factor, s′ represents the next state, θ′ represents the next action, and max represents the maximum value function.

[0103] Through the analysis of real-time and historical data, reinforcement learning is used to optimize the operating parameters of the substation to achieve intelligent control and optimization.

[0104] Example 2

[0105] See also Figure 2 , another embodiment provided by the present invention: an online monitoring system for a substation based on the Internet of Things, comprising: a data acquisition module, a preprocessing module, a state classification module, a fault prediction module and a control tuning module;

[0106] The data acquisition module is used to collect operation data and environmental data in the substation collaborative application scenario, and summarize the operation data and environmental data to obtain substation summary data;

[0107] The preprocessing module is used to preprocess the substation summary data, including data cleaning and correction of missing values;

[0108] The state classification module is used to identify abnormal conditions of the substation and classify the states of the substation equipment using the substation state prediction model;

[0109] The fault prediction module is used to predict the fault of the substation equipment and generate early warning information when a fault of the substation equipment is detected;

[0110] The control optimization module is used to optimize the operating parameters of the substation equipment based on the real-time data and historical data of the substation equipment using an intelligent control strategy.

[0111] The state classification module includes a feature extraction unit and a state classification unit;

[0112] The feature extraction unit is used to extract the state features of the pre-processed substation summary data, including the short-term average value, the long-term average value, the standard deviation within the short-term window, and the autocorrelation value under the time lag i;

[0113] The state classification unit is used to classify the state categories of substation equipment according to the state features of the extracted preprocessed substation summary data using a trained classification machine learning model.

[0114] Example 3

[0115] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3As shown, according to another aspect of the present application, an electronic device 500 is also provided. The electronic device 500 may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are executed by one or more processors, a substation online monitoring method based on the Internet of Things can be executed.

[0116] The method or system according to the embodiment of the present application can also be used by Figure 3 The electronic device architecture shown in FIG. Figure 3 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, ROM 503, RAM 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, and the like. The storage device in the electronic device 500, such as ROM 503 or hard disk 507, may store an online monitoring method for a substation based on the Internet of Things provided in the present application. An online monitoring method for a substation based on the Internet of Things may, for example, include: the substation monitoring personnel collect the operating data and environmental data under the collaborative application scenario of the substation, and summarize the operating data and environmental data to obtain the substation summary data, pre-process the substation summary data, including data cleaning and correction of missing values, use the substation status prediction model to identify abnormal conditions of the substation, classify the status of the substation equipment, predict the failure of the substation equipment, and generate early warning information when a failure of the substation equipment is detected, and optimize the operating parameters of the substation equipment based on the real-time data and historical data of the substation equipment using intelligent control strategies. Further, the electronic device 500 may also include a user interface 508. Of course, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0117] Example 4

[0118] Figure 4 Schematic diagram of a computer-readable storage medium structure provided by an embodiment of the present application. Figure 4 As shown, a computer-readable storage medium 600 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, a substation online monitoring method based on the Internet of Things according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0119] It should be understood that the methods, apparatuses, and devices of the present application can be implemented in many ways. For example, the methods, apparatuses, and devices of the present application can be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is only for illustration, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application can also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers a recording medium storing a program for executing the method according to the present application.

[0120] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0121] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A substation online monitoring method based on the Internet of Things, characterized in that: The specific steps include: Step S1: collecting operation data and environmental data in the substation collaborative application scenario, and summarizing the operation data and environmental data to obtain substation summary data; Step S2: preprocessing the substation summary data, including data cleaning and correction of missing values; Step S3: using the substation status prediction model to identify abnormal conditions of the substation and classify the status of the substation equipment; Step S4: predicting the failure of the substation equipment and generating early warning information when a failure of the substation equipment is detected; Step S5: Based on the real-time data and historical data of the substation equipment, the operating parameters of the substation equipment are optimized using intelligent control strategies.

2. The method for online monitoring of a substation based on the Internet of Things according to claim 1, characterized in that: The specific steps of step S3 are: Step S301: Set the pre-processed substation summary data set to X, where X = {x1(m), x2(m), ..., x n (m)}, where x n (m) represents the mth type of data at the nth moment in the preprocessed substation summary data set; Step S302: Calculate the short-term average value and long-term average value of the pre-processed substation summary data, and the calculation formula is: Among them, Dq t represents the short-term average value of the preprocessed substation summary data, t represents the current time point, p represents the short-term window size, and x t-i (m) represents the m-th type of data at the ti-th moment in the preprocessed substation summary data set, Cq t represents the long-term average value of the preprocessed substation summary data, and q represents the long-term window size; Step S303: Calculate the standard deviation of the pre-processed substation summary data within the short-term window, and the calculation formula is: Among them, Ms. t represents the standard deviation of the preprocessed substation summary data within the short-term window; Step S304: Calculate the autocorrelation value of the pre-processed substation summary data under the time lag ι, and the calculation formula is: Where Ac(ι) represents the autocorrelation value of the preprocessed substation summary data under time lag ι, x j (m) represents the m-th type of data at the j-th moment in the preprocessed substation summary data set, represents the average value of the mth type of data in the preprocessed substation summary data set, x j+ι (m) represents the mth type of data at the j+ιth moment in the preprocessed substation summary data set.

3. The method for online monitoring of a substation based on the Internet of Things according to claim 2, characterized in that: The specific steps of step S3 also include: Step S305: Use the trained classification machine learning model to classify the status categories of the substation equipment. The specific formula is: y=f(Dq t ,Cq t ,Ms t ,Ac(t)), Among them, y represents the status category of the substation equipment, and f() represents the trained classification machine learning model.

4. The method for online monitoring of a substation based on the Internet of Things according to claim 3, characterized in that: The specific steps of step S4 are: Step S401: Calculate the cumulative and characteristic of the pre-processed substation summary data at time t, and the calculation formula is: Among them, Lh t The accumulation and characteristics of the preprocessed substation summary data at time t; Step S402: Calculate the exponential smoothing characteristics of the pre-processed substation summary data at time t, and the calculation formula is: Ph t =αx t (m)+(1-α)Ph t-1 , Among them, Ph t represents the exponential smoothing characteristics of the preprocessed substation summary data at time t, Ph t-1 represents the exponential smoothing characteristics of the preprocessed substation summary data at time t-1, and α represents the smoothing parameter; Step S403: Use the trained fault prediction model to predict the fault probability after κ time steps in the future. The specific formula is: G(t+κ)=g(Dq t ,Cq t ,Ms t ,Ac(t),Lh t ,Ph t ), Among them, G(t+κ) represents the predicted failure probability after κ time steps in the future, and g() represents the trained fault prediction model.

5. The method for online monitoring of a substation based on the Internet of Things according to claim 4, characterized in that: The intelligent control strategy in step S5 includes: Reinforcement learning is used to control and optimize the operating parameters of substation equipment. The specific formula is: Q(s, θ)=Q(s, θ)+γ[r+η×max Q(s′, θ′)-Q(s, θ)], Among them, Q(s, θ) represents the value of taking action θ in state s, γ represents the learning rate, r represents the immediate reward, η represents the discount factor, s′ represents the next state, θ′ represents the next action, and max represents the maximum value function.

6. An online monitoring system for a substation based on the Internet of Things, used to implement an online monitoring method for a substation based on the Internet of Things as claimed in any one of claims 1 to 5, characterized in that: include: Data acquisition module, preprocessing module, state classification module, fault prediction module and control tuning module; The data acquisition module is used to collect operation data and environmental data in the substation collaborative application scenario, and summarize the operation data and environmental data to obtain substation summary data; The preprocessing module is used to preprocess the substation summary data, including data cleaning and correction of missing values; The state classification module is used to identify abnormal conditions of the substation and classify the states of the substation equipment using the substation state prediction model; The fault prediction module is used to predict the fault of the substation equipment and generate early warning information when a fault of the substation equipment is detected; The control optimization module is used to optimize the operating parameters of the substation equipment based on the real-time data and historical data of the substation equipment using an intelligent control strategy.

7. The substation online monitoring system based on the Internet of Things according to claim 6, characterized in that: The state classification module includes a feature extraction unit and a state classification unit; The feature extraction unit is used to extract the state features of the pre-processed substation summary data, including the short-term average value, the long-term average value, the standard deviation within the short-term window and the autocorrelation value under the time lag ι; The state classification unit is used to classify the state categories of substation equipment according to the state features of the extracted preprocessed substation summary data using a trained classification machine learning model.

8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the substation online monitoring method based on the Internet of Things described in any one of claims 1-5 are implemented.

9. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed, the steps of a substation online monitoring method based on the Internet of Things described in any one of claims 1-5 are executed.

Images