Cabin type intelligent substation risk early warning method

Abstract

The invention provides a cabin-type intelligent substation risk early warning method, and relates to the technical field of substation fault diagnosis, and the method comprises the steps: obtaining the historical fault information of a substation; clustering the environment data by adopting a clustering algorithm, and constructing an environment category-fault type-fault probability mapping relation table; obtaining current environment data of the transformer substation, and determining fault categories and fault probabilities corresponding to the fault categories; determining a target device based on the fault category, and determining a monitoring frequency of the target device based on a fault probability corresponding to the fault category and an importance coefficient of the target device; acquiring operation parameters of the target equipment based on the monitoring frequency; comparing the operation parameter with a standard parameter, and determining a parameter variation of the target equipment; taking the parameter variation as the input of a pre-constructed fault diagnosis model, and outputting the fault probability of the target equipment; and when the fault probability is greater than a preset threshold value, generating and sending early warning information. And the system load is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of substation fault diagnosis, and in particular to a risk early warning method for a cabin-type intelligent substation. Background Art

[0002] A substation is a place in the power system that transforms voltage and current, receives electricity, and distributes it. As the core hub of the smart grid, smart substations have developed rapidly in recent years, featuring intelligent equipment, full station informatization, and data networking. As a key node in the power system, the safety and stability of smart substations are crucial to the reliable operation of the entire power grid. By integrating advanced sensing, communication, and information technologies, smart substations achieve real-time monitoring and control of power flow and equipment status. As the intelligence level of substations continues to improve, the degree of automation in each link is becoming increasingly higher, resulting in the management and processing of large-scale and ultra-large-scale massive status data. In existing technologies, as the environment in which the substation is located changes, the types of faults generated in the substation vary to a certain extent, but existing fault diagnosis methods generally do not adjust diagnostic strategies based on environmental changes. Summary of the Invention

[0003] In response to the above-mentioned problems, the present invention proposes a cabin-type intelligent substation risk warning method, which solves the technical problem in the existing technology that as the environment in which the substation is located changes, the types of faults generated in the substation vary to a certain extent, but the existing fault diagnosis method usually does not adjust the diagnosis strategy according to the environmental changes. The present invention can adjust the fault diagnosis strategy according to the changes in the environment in which the substation is located, thereby meeting the fault diagnosis needs of the substation while reducing the system load.

[0004] An embodiment of the present invention provides a risk warning method for a cabin-type smart substation, comprising:

[0005] Acquiring historical fault information of the substation, wherein the historical fault information includes the fault type and environmental data of the fault stage;

[0006] Clustering the environmental data using a clustering algorithm to obtain several environmental categories, and constructing a mapping relationship table of environmental category-fault type-fault probability;

[0007] Obtain the current environmental data of the substation and determine the environmental category. Based on the mapping relationship table of the environmental category, fault type, and fault probability, determine the fault category and the corresponding fault probability of each fault category.

[0008] Determine the target device based on the fault category, and determine the monitoring frequency of the target device based on the fault probability corresponding to the fault category and the importance coefficient of the target device;

[0009] Collect operating parameters of target equipment based on monitoring frequency;

[0010] Compare the operating parameters with the standard parameters to determine the parameter changes of the target equipment;

[0011] The parameter changes are used as input to the pre-built fault diagnosis model, and the failure probability of the target device is output;

[0012] When the failure probability is greater than the preset threshold, an early warning message is generated and sent.

[0013] In some embodiments, the clustering algorithm is used to cluster the environmental data to obtain a number of environmental categories, and a mapping relationship table of environmental category-fault type-fault probability is constructed, including:

[0014] Preprocess environmental data;

[0015] Extract meteorological characteristics of pre-processed environmental data;

[0016] Calculate the Euclidean distance between meteorological features and the preset cluster center;

[0017] Divide the environmental data into different environmental categories and obtain clustering results;

[0018] Construct a mapping relationship table of environment category-fault type-fault probability based on the clustering results, fault type and fault probability corresponding to the fault type.

[0019] In some embodiments, the pre-processing of the environmental data includes:

[0020] For missing values, mean interpolation method was used for processing;

[0021] For outliers, the box plot method was used to detect and correct them.

[0022] In some embodiments, including:

[0023] Calculate the failure probability of different failure types under each environmental category using the following formula:

[0024]

[0025] Where P is the failure probability, N f is the number of times the fault type occurs under the environment category, N t The total number of faults under the environment category.

[0026] In some embodiments, the target device is determined based on the fault category, and the monitoring frequency of the target device is determined based on the fault probability corresponding to the fault category and the importance coefficient of the target device, using the following formula:

[0027] F=k×P×I

[0028] Where F is the monitoring frequency of the target equipment, k is the adjustment coefficient, P is the failure probability, and I is the importance coefficient of the target equipment.

[0029] In some embodiments, including:

[0030] Obtain the criticality coefficient, complexity coefficient and cost coefficient of the target equipment;

[0031] Based on the criticality coefficient, complexity coefficient and cost coefficient, the importance coefficient is determined, and the importance coefficient adopts the following formula:

[0032] I=ω1×C1+ω2×C2+ω3×C3

[0033] Where I is the importance coefficient, C1 is the criticality coefficient, C2 is the complexity coefficient, C3 is the cost coefficient, and ω1, ω2, and ω3 are weight coefficients.

[0034] In some embodiments, the operating parameters include current, voltage, and temperature.

[0035] In some embodiments, comparing the operating parameters with the standard parameters to determine the parameter change of the target device includes:

[0036] Calculate the Euclidean distance between the target device's operating parameters and the upper and lower boundaries of its corresponding standard parameter range, and use the boundary value corresponding to the minimum Euclidean distance as the reference data;

[0037] Calculate the deviation between the operating parameters of the target device and its corresponding standard parameters, and use the deviation value as the parameter change of the target device.

[0038] In some embodiments, including:

[0039] The fault diagnosis model is:

[0040] P=σ(W·X+b)

[0041] Where P is the failure probability of the target device, σ is the Sigmoid function, W is the model weight, X is the parameter change, and b is the bias term.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] The system acquires historical fault information of the substation, including the fault type and environmental data at the fault stage; clusters the environmental data using a clustering algorithm to obtain several environmental categories, and constructs a mapping relationship table of environmental category, fault type, and fault probability; acquires current environmental data of the substation and determines the environmental category; and determines the fault category and the corresponding fault probability of each fault category based on the mapping relationship table of environmental category, fault type, and fault probability; determines the target device based on the fault category, and determines the monitoring frequency of the target device based on the fault probability corresponding to the fault category and the importance coefficient of the target device; collects operating parameters of the target device based on the monitoring frequency; compares the operating parameters with standard parameters to determine the parameter change of the target device; uses the parameter change as input to a pre-built fault diagnosis model to output the fault probability of the target device; and generates and sends an early warning message when the fault probability exceeds a preset threshold. The system can adjust the fault diagnosis strategy according to changes in the substation environment, meeting the fault diagnosis needs of the substation while reducing the system load. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The embodiments of the present invention are further described below with reference to the accompanying drawings:

[0045] Figure 1 A schematic diagram of the implementation flow of a cabin-type smart substation risk warning method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting the present invention. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0047] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0048] If similar descriptions of "first\second\third" appear in the application documents, the following explanation is added. In the following description, the terms "first\second\third" are only used to distinguish similar objects and do not represent a specific order of the objects. It can be understood that "first\second\third" can be interchanged with the specific order or sequence where permitted, so that the embodiments of the present invention described herein can be implemented in an order other than that illustrated or described herein.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention pertains. The terms used herein are for the purpose of describing embodiments of the present invention only and are not intended to limit the present invention.

[0050] The embodiment of the present invention provides a risk warning method for a cabin-type smart substation. Figure 1 A schematic diagram of the implementation process of a cabin-type smart substation risk warning method provided by an embodiment of the present invention is shown as follows: Figure 1 Shown, including:

[0051] Step S1: Acquire historical fault information of the substation, wherein the historical fault information includes the fault type and environmental data of the fault stage;

[0052] In this embodiment of the present invention, the backend system stores historical fault information about the operation of the pod-type smart substation. This historical fault information includes fault types and environmental data. Fault types include transformer faults, circuit breaker faults, busbar faults, capacitor faults, and cable faults. Environmental data includes temperature, humidity, and rainfall. Historical fault information can be obtained through the backend system.

[0053] Step S2: clustering the environmental data using a clustering algorithm to obtain several environmental categories, and constructing a mapping relationship table of environmental category-fault type-fault probability;

[0054] In some embodiments, step S2 includes:

[0055] Step S21: pre-processing the environmental data;

[0056] Step S22: extracting meteorological characteristics of the pre-processed environmental data;

[0057] Step S23: Calculating the Euclidean distance between the meteorological feature and the preset cluster center;

[0058] Step S24: Divide the environmental data into different environmental categories to obtain clustering results;

[0059] Step S25: constructing a mapping relationship table of environment category-fault type-fault probability based on the clustering results, the fault type and the fault probability corresponding to the fault type.

[0060] In an embodiment of the present invention, the meteorological characteristics of the environmental data are first extracted, and then a normalization method can be used to map each meteorological characteristic of the environmental data to the [0,1] interval. Then, the Euclidean distance between the meteorological characteristic and the preset cluster center is calculated, so as to divide the environmental data into different environmental categories and obtain clustering results. According to the clustering results and the fault types corresponding to the environmental data and the fault probabilities corresponding to the fault types, a mapping relationship table of environmental category-fault type-fault probability is constructed.

[0061] In some embodiments, step S21 includes:

[0062] Step S211: For missing values, use the mean interpolation method to process;

[0063] Step S212: For outliers, use the box plot method to detect and correct them.

[0064] In the embodiment of the present invention, missing values are processed by the mean interpolation method, and outliers are detected and corrected using the boxplot method, which can effectively ensure the integrity and rationality of environmental data for clustering processing.

[0065] The embodiment of the present invention calculates the failure probability corresponding to the failure type by the following method, including:

[0066] Calculate the failure probability of different failure types under each environmental category using the following formula:

[0067]

[0068] Where P is the failure probability, N f is the number of times the fault type occurs under the environment category, N t The total number of faults under the environment category.

[0069] Step S3: Obtain the current environmental data of the substation and determine the environmental category. Based on the mapping relationship table of environmental category-fault type-fault probability, determine the fault category and the fault probability corresponding to each fault category.

[0070] In this embodiment of the present invention, the environmental category can be determined based on the current environmental data of the substation. Then, a pre-established mapping table of environmental category, fault type, and fault probability can be used to determine the fault type and the corresponding fault probability for each fault type. In this mapping table, the fault types corresponding to different environmental categories may vary, or even be completely different.

[0071] Step S4: determining the target device based on the fault category, and determining the monitoring frequency of the target device based on the fault probability corresponding to the fault category and the importance coefficient of the target device;

[0072] In some embodiments, the step S4 uses the following formula:

[0073] F=k×P×I

[0074] Where F is the monitoring frequency of the target equipment, k is the adjustment coefficient, P is the failure probability, and I is the importance coefficient of the target equipment.

[0075] In this embodiment of the present invention, the target device's failure probability and importance coefficient are comprehensively considered to determine the target device's monitoring frequency. A higher failure probability indicates a higher monitoring frequency, while a lower failure probability indicates a lower monitoring frequency. A larger importance coefficient indicates a higher monitoring frequency, while a smaller importance coefficient indicates a lower monitoring frequency.

[0076] In some embodiments, including:

[0077] Step S41: Obtain the criticality coefficient, complexity coefficient and cost coefficient of the target device;

[0078] Step S42: Determine the importance coefficient based on the criticality coefficient, complexity coefficient and cost coefficient. The importance coefficient adopts the following formula:

[0079] I=ω1×C1+ω2×C2+ω3×C3

[0080] Where I is the importance coefficient, C1 is the criticality coefficient, C2 is the complexity coefficient, C3 is the cost coefficient, and ω1, ω2, and ω3 are weight coefficients.

[0081] In this embodiment of the present invention, the importance coefficient is determined by the target device's criticality coefficient, complexity coefficient, and cost coefficient. The criticality coefficient is determined based on the device's impact on the operation of the pod-type smart substation and ranges from 0 to 1. The complexity coefficient reflects the device's structural complexity and maintenance difficulty and ranges from 0 to 1. The cost coefficient takes into account the device's purchase and maintenance costs and ranges from 0 to 1. The criticality coefficient, complexity coefficient, and cost coefficient are assigned corresponding weights: ω1 + ω2 + ω3 = 1.

[0082] Step S5: collecting operating parameters of the target device based on the monitoring frequency;

[0083] In this embodiment of the present invention, the operating parameters include current, voltage, and temperature. Current can be acquired using a current transformer, voltage can be acquired using a voltage transformer, and temperature can be acquired using a temperature sensor. Acquiring the operating parameters of the target device based on the monitoring frequency can effectively reduce system load and energy consumption.

[0084] Step S6: Compare the operating parameters with the standard parameters to determine the parameter change of the target device;

[0085] In some embodiments, step S6 includes:

[0086] Step S61: Calculate the Euclidean distance between the operating parameters of the target device and the upper and lower boundaries of the corresponding standard parameter range, and use the boundary value corresponding to the minimum Euclidean distance as reference data;

[0087] Step S61: Calculate the deviation between the operating parameters of the target device and its corresponding standard parameters, and use the deviation value as the parameter change of the target device.

[0088] In an embodiment of the present invention, in the process of determining the parameter change, the changes in the operating parameters corresponding to each target device under each fault type in the fault stage are fully considered, and the gap between the operating parameters collected in the fault stage and the standard parameters is determined. When the substation is in the non-fault stage, each operating parameter changes within the standard parameter range.

[0089] Step S7: taking the parameter change as the input of the pre-built fault diagnosis model and outputting the failure probability of the target device;

[0090] In some embodiments, including:

[0091] The fault diagnosis model is:

[0092] P=σ(W·X+b)

[0093] Where P is the failure probability of the target device, σ is the Sigmoid function, W is the model weight, X is the parameter change, and b is the bias term.

[0094] In the embodiment of the present invention, the fault diagnosis model adopts a logistic regression model. The logistic regression model is a commonly used classification model used to predict the probability of an event occurring and can quickly and accurately output the fault probability of the target device.

[0095] Step S8: When the failure probability is greater than a preset threshold, generate and send an early warning message.

[0096] In an embodiment of the present invention, when the failure probability is greater than a preset threshold, an early warning message is generated and sent to prompt relevant personnel to deal with it in a timely manner. It can be understood that the early warning message can be transmitted to a mobile terminal configured by the relevant personnel to facilitate timely notification of the relevant personnel.

[0097] In summary, by acquiring historical fault information of a substation, wherein the historical fault information includes the fault type and environmental data of the fault stage; clustering the environmental data using a clustering algorithm to obtain several environmental categories, and constructing a mapping relationship table of environmental category, fault type, and fault probability; acquiring the current environmental data of the substation and determining the environmental category, and based on the mapping relationship table of environmental category, fault type, and fault probability, determining the fault category and the corresponding fault probability of each fault category; determining the target device based on the fault category, and determining the monitoring frequency of the target device based on the fault probability corresponding to the fault category and the importance coefficient of the target device; collecting the operating parameters of the target device based on the monitoring frequency; comparing the operating parameters with standard parameters to determine the parameter change of the target device; using the parameter change as input to a pre-built fault diagnosis model to output the fault probability of the target device; and generating and sending an early warning message when the fault probability exceeds a preset threshold. The system can adjust the fault diagnosis strategy according to changes in the substation environment, meeting the fault diagnosis needs of the substation while reducing the system load.

[0098] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present invention. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention. The serial numbers of the above-mentioned embodiments of the present invention are for description only and do not represent the advantages and disadvantages of the embodiments.

[0099] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, object, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, object, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of other identical elements in the process, method, object, or apparatus comprising the element.

[0100] The above description is merely an embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A risk warning method for a cabin-type smart substation, characterized in that: include: Acquiring historical fault information of the substation, wherein the historical fault information includes the fault type and environmental data of the fault stage; Clustering the environmental data using a clustering algorithm to obtain several environmental categories, and constructing a mapping relationship table of environmental category-fault type-fault probability; Obtain the current environmental data of the substation and determine the environmental category. Based on the mapping relationship table of the environmental category, fault type, and fault probability, determine the fault category and the corresponding fault probability of each fault category. Determine the target device based on the fault category, and determine the monitoring frequency of the target device based on the fault probability corresponding to the fault category and the importance coefficient of the target device; Collect operating parameters of target equipment based on monitoring frequency; Compare the operating parameters with the standard parameters to determine the parameter changes of the target equipment; The parameter changes are used as input to the pre-built fault diagnosis model, and the failure probability of the target device is output; When the failure probability is greater than the preset threshold, an early warning message is generated and sent.

2. A cabin-type smart substation risk warning method according to claim 1, characterized in that: The clustering algorithm is used to cluster the environmental data to obtain several environmental categories, and a mapping relationship table of environmental category-fault type-fault probability is constructed, including: Preprocess environmental data; Extract meteorological characteristics of pre-processed environmental data; Calculate the Euclidean distance between meteorological features and the preset cluster center; Divide the environmental data into different environmental categories and obtain clustering results; Construct a mapping relationship table of environment category-fault type-fault probability based on the clustering results, fault type and fault probability corresponding to the fault type.

3. A cabin-type smart substation risk warning method according to claim 2, characterized in that: The preprocessing of the environmental data includes: For missing values, mean interpolation method was used for processing; For outliers, the box plot method was used to detect and correct them.

4. A cabin-type smart substation risk warning method according to claim 2, characterized in that: include: Calculate the failure probability of different failure types under each environmental category using the following formula: Where P is the failure probability, N f is the number of times the fault type occurs under the environment category, N t The total number of faults under the environment category.

5. The risk warning method for a cabin-type smart substation according to claim 1 is characterized in that: The target device is determined based on the fault category, and the monitoring frequency of the target device is determined based on the fault probability corresponding to the fault category and the importance coefficient of the target device, using the following formula: F=k×P×I Where F is the monitoring frequency of the target equipment, k is the adjustment coefficient, P is the failure probability, and I is the importance coefficient of the target equipment.

6. A cabin-type smart substation risk warning method according to claim 1, characterized in that: include: Obtain the criticality coefficient, complexity coefficient and cost coefficient of the target equipment; Based on the criticality coefficient, complexity coefficient and cost coefficient, the importance coefficient is determined, and the importance coefficient adopts the following formula: I=ω1×C1+ω2×C2+ω3×C3 Where I is the importance coefficient, C1 is the criticality coefficient, C2 is the complexity coefficient, C3 is the cost coefficient, and ω1, ω2, and ω3 are weight coefficients.

7. A risk warning method for a cabin-type smart substation according to claim 1, characterized in that: The operating parameters include current, voltage and temperature.

8. The risk warning method for a cabin-type smart substation according to claim 1 is characterized in that: The step of comparing the operating parameters with the standard parameters to determine the parameter change of the target device includes: Calculate the Euclidean distance between the target device's operating parameters and the upper and lower boundaries of its corresponding standard parameter range, and use the boundary value corresponding to the minimum Euclidean distance as the reference data; Calculate the deviation between the operating parameters of the target device and its corresponding standard parameters, and use the deviation value as the parameter change of the target device.

9. The risk warning method for a cabin-type smart substation according to claim 1 is characterized in that: include: The fault diagnosis model is: P=σ(W·X+b) Where P is the failure probability of the target device, σ is the Sigmoid function, W is the model weight, X is the parameter change, and b is the bias term.

Images