Circuit breaker on-off state analysis method and device, terminal equipment and storage medium
By obtaining the mechanical characteristic curve of the circuit breaker and using the random forest model to analyze it, the problem of low efficiency of circuit breaker state analysis in the existing technology is solved, and an automated circuit breaker state analysis is realized, which improves efficiency and convenience.
Patent Information
- Application Number
- CN202411313789.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-20
- Publication Date
- 2025-01-10
AI Technical Summary
The lack of effective circuit breaker state analysis methods in the prior art leads to a large amount of manual inspection and waste of human resources.
By obtaining the mechanical characteristic curve of the circuit breaker, input it into the interrupt state analysis model, extracting characteristic parameters, determining the length and state of the static arc contact, and then determining the interrupt state of the circuit breaker, and using a random forest model for training and construction.
It improves the convenience and efficiency of circuit breaker interruption status analysis, avoids manual inspection one by one, and realizes automated analysis.
Smart Images
Figure CN119293430A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power fault analysis, and in particular to a circuit breaker disconnection state analysis method, device, terminal equipment and storage medium. Background Art
[0002] The reliability of circuit breakers in power systems directly affects the safety and stability of power system operation. The existing technology lacks an effective method for analyzing the status of circuit breakers. The status of circuit breakers is mainly detected one by one through manual inspections. This circuit breaker status analysis method requires a lot of operation and maintenance and repair work, resulting in a lot of waste of human resources. Summary of the invention
[0003] The embodiments of the present invention provide a circuit breaker disconnection state analysis method, device, terminal equipment and storage medium, which can improve the convenience and efficiency of circuit breaker disconnection state analysis.
[0004] An embodiment of the present invention provides a circuit breaker disconnection state analysis method, comprising:
[0005] Obtaining a mechanical characteristic curve of the circuit breaker to be analyzed; wherein the mechanical characteristic curve includes an opening stroke curve and a closing stroke curve;
[0006] The mechanical characteristic curve is input into the breaking state analysis model, so that the breaking state analysis model extracts characteristic parameters of the mechanical characteristic curve, and determines the static arc contact length of the circuit breaker to be analyzed and the static arc contact state of the circuit breaker to be analyzed according to the characteristic parameters; wherein the characteristic parameters include: opening time, opening speed, closing time, closing speed, opening overtravel and closing distance; the static arc contact state includes: normal state, potential abnormal state, abnormal state and severe state;
[0007] The breaking state of the circuit breaker to be analyzed is determined according to the static arc contact length of the circuit breaker to be analyzed and the static arc contact state of the circuit breaker to be analyzed.
[0008] Furthermore, the construction of the breaking state analysis model includes:
[0009] Acquire a training sample data set; wherein the training sample data set includes a number of mechanical characteristic curve samples of a number of different types of circuit breakers under various working conditions; each mechanical characteristic curve sample includes: a sample static arc contact state, a sample static arc contact length, a sample opening time, a sample opening speed, a sample closing time, a sample closing speed, a sample opening overtravel, and a sample closing distance;
[0010] A random forest model is constructed, and the random forest model is trained with the training sample data set, and when the random forest model converges, a breaking state analysis model is generated.
[0011] Furthermore, the random forest model is trained with the training sample data set, including:
[0012] Performing multiple sampling with replacement on the training sample data set to obtain a number of training sample sampling sets;
[0013] For each training sample sampling set, a decision tree is constructed in the random forest model according to the training sample sampling set, and the decision tree is trained according to the training sample sampling set.
[0014] Furthermore, the obtaining of the training sample data set includes:
[0015] Get several different types of circuit breakers;
[0016] For each type of circuit breaker, multiple simulations are performed in normal state, potential abnormal state, abnormal state and severe state to obtain several mechanical characteristic curve samples in normal state, potential abnormal state, abnormal state and severe state;
[0017] A training sample data set is generated according to several mechanical characteristic curve samples of various types of circuit breakers.
[0018] Based on the above method embodiment, the present invention provides a corresponding device embodiment;
[0019] An embodiment of the present invention provides a circuit breaker disconnection state analysis device, including: a data acquisition module, a state analysis module and a state determination module;
[0020] The data acquisition module is used to acquire the mechanical characteristic curve of the circuit breaker to be analyzed; wherein the mechanical characteristic curve includes an opening stroke curve and a closing stroke curve;
[0021] The state analysis module is used to input the mechanical characteristic curve into the breaking state analysis model, so that the breaking state analysis model extracts the characteristic parameters of the mechanical characteristic curve, and determines the static arc contact length of the circuit breaker to be analyzed and the static arc contact state of the circuit breaker to be analyzed according to the characteristic parameters; wherein the characteristic parameters include: opening time, opening speed, closing time, closing speed, opening overtravel and closing distance; the static arc contact state includes: normal state, potential abnormal state, abnormal state and serious state;
[0022] The state determination module is used to determine the breaking state of the circuit breaker to be analyzed according to the static arc contact length of the circuit breaker to be analyzed and the static arc contact state of the circuit breaker to be analyzed.
[0023] Furthermore, it also includes a state analysis model building module;
[0024] The state analysis model building module is used to obtain a training sample data set; wherein the training sample data set includes a number of mechanical characteristic curve samples of different types of circuit breakers under various working conditions; each mechanical characteristic curve sample includes: a sample static arc contact state, a sample static arc contact length, a sample opening time, a sample opening speed, a sample closing time, a sample closing speed, a sample opening overtravel and a sample closing distance; a random forest model is built, and the random forest model is trained with the training sample data set, and when the random forest model converges, a breaking state analysis model is generated.
[0025] Furthermore, the random forest model is trained with the training sample data set, including:
[0026] Performing multiple sampling with replacement on the training sample data set to obtain a number of training sample sampling sets;
[0027] For each training sample sampling set, a decision tree is constructed in the random forest model according to the training sample sampling set, and the decision tree is trained according to the training sample sampling set.
[0028] Furthermore, the obtaining of the training sample data set includes:
[0029] Get several different types of circuit breakers;
[0030] For each type of circuit breaker, multiple simulations are performed in normal state, potential abnormal state, abnormal state and severe state to obtain several mechanical characteristic curve samples in normal state, potential abnormal state, abnormal state and severe state;
[0031] A training sample data set is generated according to several mechanical characteristic curve samples of various types of circuit breakers.
[0032] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, a circuit breaker disconnection state analysis method described in the above-mentioned embodiment of the invention is implemented.
[0033] Another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute a circuit breaker disconnection state analysis method described in the above-mentioned embodiment of the invention.
[0034] The following beneficial effects are achieved by implementing the present invention:
[0035] The present invention provides a circuit breaker breaking state analysis method, device, terminal equipment and storage medium. The state analysis method obtains a mechanical characteristic curve of a circuit breaker to be analyzed, inputs the mechanical characteristic curve into a breaking state analysis model, and then extracts characteristic parameters such as opening time, opening speed, closing time, closing speed, opening overtravel and closing distance of the mechanical characteristic curve through the breaking state analysis model, and then determines the static arc contact length and static arc contact state of the circuit breaker to be analyzed according to the characteristic parameters, and then determines the breaking state of the circuit breaker to be analyzed according to the static arc contact length and the static arc contact state of the circuit breaker to be analyzed. After obtaining the mechanical characteristic curve of the circuit breaker to be analyzed and combining it with the breaking state analysis model to extract the characteristic parameters of the mechanical characteristic curve of the circuit breaker to be analyzed, the static arc contact length and the static arc contact state of the circuit breaker to be analyzed are determined based on the characteristic parameters, and then the breaking state of the circuit breaker to be analyzed is determined according to the static arc contact length and the static arc contact state. This method avoids the need to detect the circuit breaker state one by one through manual inspection to determine the circuit breaker breaking state, thereby improving the convenience and efficiency of circuit breaker breaking state analysis. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Figure 1 It is a flow chart of a circuit breaker disconnection state analysis method provided by an embodiment of the present invention.
[0037] Figure 2 It is a closing stroke curve diagram provided by an embodiment of the present invention.
[0038] Figure 3 It is a structural schematic diagram of a circuit breaker disconnection state analysis device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0039] 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.
[0040] like Figure 1 As shown, a circuit breaker disconnection state analysis method provided by an embodiment of the present invention includes:
[0041] Step S1: obtaining a mechanical characteristic curve of the circuit breaker to be analyzed; wherein the mechanical characteristic curve includes an opening stroke curve and a closing stroke curve;
[0042] Step S2: inputting the mechanical characteristic curve into the breaking state analysis model, so that the breaking state analysis model extracts characteristic parameters of the mechanical characteristic curve, and determines the static arc contact length of the circuit breaker to be analyzed and the static arc contact state of the circuit breaker to be analyzed according to the characteristic parameters; wherein the characteristic parameters include: opening time, opening speed, closing time, closing speed, opening overtravel and closing distance; the static arc contact state includes: normal state, potential abnormal state, abnormal state and severe state;
[0043] Step S3: determining the breaking state of the circuit breaker to be analyzed according to the static arc contact length and the static arc contact state of the circuit breaker to be analyzed.
[0044] For step S1, a mechanical characteristic curve of the circuit breaker to be analyzed is obtained, including an opening stroke curve and a closing stroke curve of the circuit breaker to be analyzed.
[0045] For step S2, the mechanical characteristic curve obtained in step S1 is input into the breaking state analysis model, so that the breaking state analysis model extracts characteristic parameters such as opening time, opening speed, closing time, closing speed, opening overtravel and closing distance of the mechanical characteristic curve, and determines the static arc contact length and the static arc contact state of the circuit breaker to be analyzed according to the above characteristic parameters.
[0046] It should be added that by extracting the above characteristic parameters from the mechanical characteristic curve, the slight changes of the mechanical characteristic curve under different working conditions can be reflected. The mechanical characteristic curve is the displacement-time variation curve of the three-phase moving contact during the opening and closing process of the high-voltage circuit breaker within a cycle. Figure 2 The figure shows a closing stroke curve of a typical closing process. Figure 2 The data of overtravel, opening distance, stroke and just-closed point of the circuit breaker can be obtained; among them, overtravel refers to the difference in displacement of the moving and static contacts from the beginning of contact to the stable closed state during a closing process in one opening and closing action cycle of the circuit breaker; opening distance refers to the distance between the moving and static contacts in the opening state; stroke refers to the contact stroke, which is the total displacement between the starting positions of the moving contacts of the high-voltage circuit breaker after completing an opening and closing action; just-closed point is the moment when the moving and static contacts begin to contact.
[0047] In a preferred embodiment, the construction of the breaking state analysis model includes: obtaining a training sample data set; wherein the training sample data set includes several mechanical characteristic curve samples of several different types of circuit breakers under various working conditions; each mechanical characteristic curve sample includes: sample static arc contact state, sample static arc contact length, sample opening time, sample opening speed, sample closing time, sample closing speed, sample opening overtravel and sample closing distance; constructing a random forest model, training the random forest model with the training sample data set, and generating a breaking state analysis model when the random forest model converges.
[0048] Specifically, a training sample data set for training the breaking state analysis model is obtained, and the training sample data set mainly includes several mechanical characteristic curve samples obtained from multiple different types of circuit breakers under various working conditions. It should be noted that the circuit breaker types in the training sample data set must cover the types of circuit breakers to be analyzed. If the type of circuit breaker to be analyzed does not exist in the training sample data set, it is necessary to first obtain sample data of the type corresponding to the circuit breaker to be analyzed. Preferably, if a new type of circuit breaker data is added after the breaking state analysis model has been trained, a decision tree can be added to the breaking state analysis model based on the newly added data to avoid repeated training of the trained part of the breaking state analysis model, reduce computing power consumption, and increase the generalization of the model.
[0049] In a preferred embodiment, the obtaining of the training sample data set includes: obtaining a number of different types of circuit breakers; for each type of circuit breaker, performing multiple simulations in a normal state, a potential abnormal state, an abnormal state, and a severe state, respectively, to obtain a number of mechanical characteristic curve samples in a normal state, a potential abnormal state, an abnormal state, and a severe state; and generating a training sample data set according to the number of mechanical characteristic curve samples of each type of circuit breaker.
[0050] Specifically, multiple different types of circuit breakers are obtained, and simulation tests are performed on each circuit breaker to obtain training sample data. Circuit breakers of the same type and different voltage levels will show similar mechanical behavior characteristics during the opening and closing process, but the specific values and change trends may vary due to design differences, material selection and operating environment. Therefore, a circuit breaker model can be selected to represent its versatility. For the same type of circuit breaker, through the simulation test platform, the mechanical characteristic curve samples of the type of circuit breaker in normal state, potential abnormal state, abnormal state and severe state are obtained. The mechanical characteristic curve samples include opening stroke curve samples and closing stroke curve samples. For each mechanical characteristic curve sample in the simulation process, the static arc contact length and static arc contact state corresponding to the mechanical characteristic curve sample are recorded. For each type of circuit breaker, several mechanical characteristic curve samples as described in the following table can be obtained through simulation (the serial number is the mechanical characteristic curve sample number), and a training sample data set is formed according to several mechanical characteristic curve samples of each type of circuit breaker.
[0051]
[0052]
[0053] Preferably, a filtering algorithm is used to remove noise from the acquired training sample data set, a standardized formula is used to scale the eigenvalues to the same scale, and a normalization process is performed to eliminate the influence of different dimensions.
[0054] An initial random forest model is constructed and trained according to the training sample data set prepared above. When the random forest model converges, a breaking state analysis model is generated.
[0055] In a preferred embodiment, the random forest model is trained with the training sample data set, including: performing multiple sampling with replacement on the training sample data set to obtain a plurality of training sample sampling sets; for each training sample sampling set, constructing a decision tree in the random forest model according to the training sample sampling set, and training the decision tree according to the training sample sampling set.
[0056] Specifically, the random forest algorithm is used for training. The random forest algorithm belongs to the bagging method in ensemble learning. Its principle is to use the training sample data set to generate multiple decision trees, and then determine the final voting category (i.e., the output result of the model) based on the generated decision trees. When the random forest algorithm is used to construct a decision tree, it is first necessary to perform multiple samplings with replacement on the training sample data set, i.e., Bootstrap. Through multiple random samplings with replacement, several training sample sampling sets are obtained. For each training sample sampling set, a corresponding CART decision tree is constructed according to the training sample sampling set. After the construction of the CART decision trees corresponding to all training sample sampling sets is completed, a random forest model constructed by the training sample data set is generated. The random forest model is then further trained, i.e., each decision tree in the random forest model is trained.
[0057] It should be noted that decision trees are mainly learned from data and then used for classification and prediction. It is a tree structure with only one root node and multiple non-leaf nodes, where the non-leaf nodes represent the characteristics of the data set, and the leaf nodes represent a certain category. The key to decision tree learning is how to select the optimal features. By continuously dividing and building branches, it is hoped that the subsets contained in each generated branch will belong to the same category as much as possible, and finally produce a tree with strong generalization performance. Therefore, the process of creating a decision tree embodies the idea of recursion, and it will only stop when the nodes on the branch belong to the same category or the data set or attribute set is empty and cannot be divided anymore.
[0058] Exemplarily, the data of serial numbers 1-17 in the above table are used as training sample data sets and input into the random forest model, so that the model extracts the sample opening time, sample opening speed, sample closing time, sample closing speed, sample opening overtravel and sample closing distance for each mechanical characteristic curve sample, and outputs the predicted static arc contact length according to the sample opening time, sample opening speed, sample closing time, sample closing speed, sample opening overtravel and sample closing distance, and determines the error according to the predicted static arc contact length and the corresponding sample static arc contact length. When the error is too large, that is, when the random forest model is overfitting, the prediction result is adjusted according to the sample static arc contact length; when the error is small and meets the error threshold, it is considered that the random forest model has converged, and the random forest model that has completed the training at this time is the above-mentioned breaking state analysis model. Through model training, the random forest model learns the mapping relationship between the static arc contact length and characteristic parameters such as opening time, opening speed, closing time, closing speed, opening overtravel and closing distance. After completing the model training, the characteristic parameters in the mechanical characteristic curve are extracted by the breaking state analysis model. The corresponding static arc contact length can be output according to the breaking state analysis model, and then the static arc contact state can be inverted according to the static arc contact length.
[0059] For step S3, the breaking state of the circuit breaker to be analyzed is determined according to the static arc contact length and the static arc contact state of the circuit breaker to be analyzed.
[0060] Preferably, the breaking state, static arc contact length, static arc contact state and mechanical characteristic curve of the circuit breaker to be analyzed are displayed to the power system operation and maintenance personnel in a visual manner, so that the power system operation and maintenance personnel can intuitively judge the circuit breaker state and take corresponding operation and maintenance measures.
[0061] Based on the above method embodiment, the present invention provides a corresponding device embodiment.
[0062] like Figure 3 As shown, an embodiment of the present invention provides a circuit breaker disconnection state analysis device, including: a data acquisition module, a state analysis module and a state determination module;
[0063] The data acquisition module is used to acquire the mechanical characteristic curve of the circuit breaker to be analyzed; wherein the mechanical characteristic curve includes an opening stroke curve and a closing stroke curve;
[0064] The state analysis module is used to input the mechanical characteristic curve into the breaking state analysis model, so that the breaking state analysis model extracts the characteristic parameters of the mechanical characteristic curve, and determines the static arc contact length of the circuit breaker to be analyzed and the static arc contact state of the circuit breaker to be analyzed according to the characteristic parameters; wherein the characteristic parameters include: opening time, opening speed, closing time, closing speed, opening overtravel and closing distance; the static arc contact state includes: normal state, potential abnormal state, abnormal state and serious state;
[0065] The state determination module is used to determine the breaking state of the circuit breaker to be analyzed according to the static arc contact length of the circuit breaker to be analyzed and the static arc contact state of the circuit breaker to be analyzed.
[0066] In a preferred embodiment, it also includes a state analysis model building module;
[0067] The state analysis model building module is used to obtain a training sample data set; wherein the training sample data set includes a number of mechanical characteristic curve samples of different types of circuit breakers under various working conditions; each mechanical characteristic curve sample includes: a sample static arc contact state, a sample static arc contact length, a sample opening time, a sample opening speed, a sample closing time, a sample closing speed, a sample opening overtravel and a sample closing distance; a random forest model is built, and the random forest model is trained with the training sample data set, and when the random forest model converges, a breaking state analysis model is generated.
[0068] In a preferred embodiment, training the random forest model with the training sample data set includes:
[0069] Performing multiple sampling with replacement on the training sample data set to obtain a number of training sample sampling sets;
[0070] For each training sample sampling set, a decision tree is constructed in the random forest model according to the training sample sampling set, and the decision tree is trained according to the training sample sampling set.
[0071] In a preferred embodiment, the step of obtaining a training sample data set includes:
[0072] Get several different types of circuit breakers;
[0073] For each type of circuit breaker, multiple simulations are performed in normal state, potential abnormal state, abnormal state and severe state to obtain several mechanical characteristic curve samples in normal state, potential abnormal state, abnormal state and severe state;
[0074] A training sample data set is generated according to several mechanical characteristic curve samples of various types of circuit breakers.
[0075] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.
[0076] Those skilled in the art can clearly understand that for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.
[0077] Based on the above method item embodiments, the present invention provides corresponding terminal device item embodiments.
[0078] An embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, a circuit breaker disconnection state analysis method described in any one of the present invention is implemented.
[0079] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.
[0080] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.
[0081] The memory can be used to store the computer program, and the processor realizes various functions of the terminal device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med i aCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0082] Based on the above method item embodiments, the present invention provides a corresponding storage medium item embodiment.
[0083] An embodiment of the present invention provides a storage medium, wherein the storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute a circuit breaker disconnection state analysis method as described in any one of the present inventions.
[0084] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium.
[0085] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.
Claims
1. A circuit breaker breaking state analysis method, characterized in that: include: Obtaining a mechanical characteristic curve of the circuit breaker to be analyzed; wherein the mechanical characteristic curve includes an opening stroke curve and a closing stroke curve; The mechanical characteristic curve is input into the breaking state analysis model, so that the breaking state analysis model extracts characteristic parameters of the mechanical characteristic curve, and determines the static arc contact length of the circuit breaker to be analyzed and the static arc contact state of the circuit breaker to be analyzed according to the characteristic parameters; wherein the characteristic parameters include: opening time, opening speed, closing time, closing speed, opening overtravel and closing distance; the static arc contact state includes: normal state, potential abnormal state, abnormal state and severe state; The breaking state of the circuit breaker to be analyzed is determined according to the static arc contact length of the circuit breaker to be analyzed and the static arc contact state of the circuit breaker to be analyzed.
2. A circuit breaker disconnection state analysis method according to claim 1, characterized in that: The construction of the breaking state analysis model includes: Acquire a training sample data set; wherein the training sample data set includes a number of mechanical characteristic curve samples of a number of different types of circuit breakers under various working conditions; each mechanical characteristic curve sample includes: a sample static arc contact state, a sample static arc contact length, a sample opening time, a sample opening speed, a sample closing time, a sample closing speed, a sample opening overtravel, and a sample closing distance; A random forest model is constructed, and the random forest model is trained with the training sample data set, and when the random forest model converges, a breaking state analysis model is generated.
3. A circuit breaker breaking state analysis method according to claim 2, characterized in that: Training the random forest model with the training sample data set includes: Performing multiple sampling with replacement on the training sample data set to obtain a number of training sample sampling sets; For each training sample sampling set, a decision tree is constructed in the random forest model according to the training sample sampling set, and the decision tree is trained according to the training sample sampling set.
4. A circuit breaker breaking state analysis method according to claim 2, characterized in that: The step of obtaining a training sample data set includes: Get several different types of circuit breakers; For each type of circuit breaker, multiple simulations are performed in normal state, potential abnormal state, abnormal state and severe state to obtain several mechanical characteristic curve samples in normal state, potential abnormal state, abnormal state and severe state; A training sample data set is generated according to several mechanical characteristic curve samples of various types of circuit breakers.
5. A circuit breaker disconnection state analysis device, characterized in that: include: Data acquisition module, state analysis module and state determination module; The data acquisition module is used to acquire the mechanical characteristic curve of the circuit breaker to be analyzed; wherein the mechanical characteristic curve includes an opening stroke curve and a closing stroke curve; The state analysis module is used to input the mechanical characteristic curve into the breaking state analysis model, so that the breaking state analysis model extracts the characteristic parameters of the mechanical characteristic curve, and determines the static arc contact length of the circuit breaker to be analyzed and the static arc contact state of the circuit breaker to be analyzed according to the characteristic parameters; wherein the characteristic parameters include: opening time, opening speed, closing time, closing speed, opening overtravel and closing distance; the static arc contact state includes: normal state, potential abnormal state, abnormal state and serious state; The state determination module is used to determine the breaking state of the circuit breaker to be analyzed according to the static arc contact length of the circuit breaker to be analyzed and the static arc contact state of the circuit breaker to be analyzed.
6. A circuit breaker disconnection state analysis device as claimed in claim 5, characterized in that: It also includes a state analysis model building module; The state analysis model building module is used to obtain a training sample data set; wherein the training sample data set includes a number of mechanical characteristic curve samples of different types of circuit breakers under various working conditions; each mechanical characteristic curve sample includes: a sample static arc contact state, a sample static arc contact length, a sample opening time, a sample opening speed, a sample closing time, a sample closing speed, a sample opening overtravel and a sample closing distance; a random forest model is built, and the random forest model is trained with the training sample data set, and when the random forest model converges, a breaking state analysis model is generated.
7. A circuit breaker disconnection state analysis device as claimed in claim 6, characterized in that: Training the random forest model with the training sample data set includes: Performing multiple sampling with replacement on the training sample data set to obtain a number of training sample sampling sets; For each training sample sampling set, a decision tree is constructed in the random forest model according to the training sample sampling set, and the decision tree is trained according to the training sample sampling set.
8. A circuit breaker disconnection state analysis device as claimed in claim 6, characterized in that: The step of obtaining a training sample data set includes: Get several different types of circuit breakers; For each type of circuit breaker, multiple simulations are performed in normal state, potential abnormal state, abnormal state and severe state to obtain several mechanical characteristic curve samples in normal state, potential abnormal state, abnormal state and severe state; A training sample data set is generated according to several mechanical characteristic curve samples of various types of circuit breakers.
9. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a circuit breaker disconnection state analysis method as claimed in any one of claims 1 to 4 is implemented.
10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute a circuit breaker disconnection state analysis method as claimed in any one of claims 1 to 4.