Intelligent substation monitoring method

Abstract

The invention provides an intelligent substation monitoring method, and relates to the technical field of substation fault diagnosis, and the method comprises the steps: obtaining an equipment information set of a substation; based on the equipment information set, acquiring equipment information corresponding to each piece of equipment, and determining an attention degree corresponding to each piece of equipment based on the equipment information; determining the fault diagnosis frequency of the corresponding equipment based on the attention degree; acquiring operation data of corresponding equipment according to the fault diagnosis frequency; based on the operation data, judging whether the equipment has a fault or not; generating alarm information under the condition that the equipment has a fault; the method can dynamically adjust the fault diagnosis frequency according to the attention degree of the equipment of the transformer substation, improves the fault diagnosis frequency for the equipment with high attention degree, timely discovers the equipment fault, reduces the fault diagnosis frequency for the equipment with high attention degree, and reduces the calculation amount.

Description

Technical Field

[0001] This application relates to the technical field of substation fault diagnosis, and particularly to an intelligent substation monitoring method. Background Art

[0002] A substation refers to a place in the power system that transforms voltage and current, receives electric energy, and distributes electric energy. As the core hub of the smart grid, intelligent substations have developed rapidly in recent years, featuring intelligent equipment, station-wide informatization, and data networking. As a key node in the power system, the safety and stability of intelligent substations are crucial for the reliable operation of the entire power grid. Intelligent substations achieve real-time monitoring and control of the flow of electric energy and the status of equipment by integrating advanced sensing technologies, communication technologies, and information technologies. With the continuous improvement of the intelligence level of substations, the degree of automation in each link is getting higher and higher, and the management and processing of large-scale and ultra-large-scale massive status data have emerged. In the prior art, real-time fault diagnosis of the operation data of the equipment in the intelligent substation has a large amount of calculation and will occupy a lot of computing resources. Summary of the Invention

[0003] In view of the above problems, this application provides an intelligent substation monitoring method, which solves the technical problem in the prior art that real-time fault diagnosis of the operation data of the equipment in the intelligent substation has a large amount of calculation and will occupy a lot of computing resources, and can dynamically adjust the fault diagnosis frequency according to the degree of attention of the equipment in the substation, increase the fault diagnosis frequency for equipment with a high degree of attention to timely detect equipment faults, and reduce the fault diagnosis frequency for equipment with a low degree of attention to reduce the amount of calculation.

[0004] An embodiment of this application provides an intelligent substation monitoring method, and the method includes:

[0005] Obtain the equipment information set of the substation;

[0006] Based on the equipment information set, obtain the equipment information corresponding to each equipment, and determine the attention degree corresponding to each equipment based on the equipment information;

[0007] Based on the attention degree, determine the fault diagnosis frequency of the corresponding equipment;

[0008] According to the fault diagnosis frequency, obtain the operation data of the corresponding equipment;

[0009] Based on the operation data, determine whether the equipment has a fault;

[0010] In the case where the equipment has a fault, generate an alarm message.

[0011] In some embodiments, the equipment information set is M = {M1, M2,..., Mi ,..., M n}, where M i represents the device information of the i-th device, and M i =(t i , v i , f i ), t i is the aging degree of the i-th device, v i is the economic value of the i-th device, and f i is the number of historical failures of the i-th device.

[0012] In some embodiments, the method includes:

[0013] Obtain the theoretical operating duration and historical operating duration of the device, and calculate the aging degree using the following formula:

[0014] In the formula, t is the aging degree, S is the historical operating duration, and L is the theoretical operating duration.

[0015] Divide the historical operating duration by the theoretical operating duration to calculate the aging degree t of the device.

[0016] In some embodiments, the method includes:

[0017] Obtain the maintenance information of the device, and perform quantization processing on the maintenance information to obtain the maintenance quality quantization value m;

[0018] Obtain the environmental information of the device, and perform quantization processing on the environmental information to obtain the environmental quality quantization value e;

[0019] Correct the aging degree through the maintenance quality quantization value and the environmental quality quantization value:

[0020] t′ = ×(1 - β×m - γ×e)

[0021] In the formula, t′ is the corrected aging degree, t is the aging degree before correction, and β and γ are the weights corresponding to the maintenance information and environmental information respectively.

[0022] In some embodiments, based on the device information set, obtaining the device information corresponding to each device, and determining the attention level corresponding to each device based on the device information includes:

[0023] Obtain the aging degree t i , economic value v i and the number of historical failures f i of the i-th device in the substation;

[0024] Based on the aging degree T i , economic value V iand the number of historical failures N i , the degree of concern of the device is calculated using the following formula:

[0025] C i = α1×E(t i ) + α2×G(v i ) + α3×H(f i )

[0026] In the formula, C i is the degree of concern of the i-th device, E(·) is a unified conversion function for the aging degree of the device, G(·) is a unified conversion function for the economic value of the device, H(·) is a unified conversion function for the number of historical failures of the device, and α1, α2, and α3 are the weights corresponding to the aging degree, economic value, and number of historical failures of the device.

[0027] In some embodiments, determining the fault diagnosis frequency of the corresponding device based on the degree of concern includes:

[0028] In the formula, F i is the fault diagnosis frequency of the i-th device, F is the basic monitoring frequency, k is an adjustment coefficient, and C i is the degree of concern of the i-th device.

[0029] In some embodiments, the operating data includes current, voltage, and temperature.

[0030] In some embodiments, determining whether the device has a fault based on the operating data includes:

[0031] Normalize the current I i , voltage V i , and temperature T i of the i-th device to obtain the normalized current I′ i , voltage V′ i , and temperature T′ i ;

[0032] Extract the feature vector X i of the current I′ i , voltage V′ i , and temperature T′ i ;

[0033] Input the feature vector X i into the fault diagnosis model to output the fault probability, where the fault diagnosis model is:

[0034] P i = σ(W·X i + b)

[0035] In the formula, Pi is the failure probability of the i-th device, σ is the Sigmoid function, W is the model weight, and b is the bias term;

[0036] When P i is greater than the preset threshold, it is determined that the device has failed.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] By obtaining the device information set of the substation; based on the device information set, obtaining the device information corresponding to each device, and determining the attention level corresponding to each device based on the device information; based on the attention level, determining the fault diagnosis frequency of the corresponding device; according to the fault diagnosis frequency, obtaining the operation data of the corresponding device; based on the operation data, determining whether the device has a fault; in the case of a device failure, generating an alarm message; it is possible to dynamically adjust the fault diagnosis frequency according to the attention level of the substation devices, increase the fault diagnosis frequency for devices with a high attention level to detect device failures in a timely manner, and reduce the fault diagnosis frequency for devices with a low attention level to reduce the computational amount. Description of the Drawings

[0039] The following further describes the embodiments of the present invention with reference to the drawings:

[0040] Figure 1 is a schematic flowchart of the implementation of an intelligent substation monitoring method provided by an embodiment of this application. Detailed Embodiments

[0041] In order to make the objectives, technical solutions, and advantages of this application clearer, the following will further describe this application in detail with reference to the drawings. The described embodiments should not be regarded as limitations of this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

[0042] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0043] If similar descriptions such as "first / second / third" appear in the application documents, the following explanation is added. In the following description, the terms "first / second / third" merely distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first / second / third" can be interchanged with a specific order or sequence when allowed, so that the embodiments of this application described here can be implemented in an order other than that illustrated or described here.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terms used herein are for the purpose of describing embodiments of this application only and are not intended to limit this application.

[0045] Embodiments of this application provide an intelligent substation monitoring method. Figure 1 As shown in the schematic implementation flowchart of an intelligent substation monitoring method provided by embodiments of this application, Figure 1 as shown, the method includes:

[0046] Step S1: Obtain the set of device information of the substation;

[0047] In some embodiments, the set of device information is M = {M1, M2,..., M i ,..., M n}, where M i represents the device information of the i-th device, and M i = (t i , v i , f i ), t i is the aging degree of the i-th device, v i is the economic value of the i-th device, and f i is the historical failure times of the i-th device.

[0048] In embodiments of this application, the devices of the substation include primary devices and secondary devices. Primary devices are those directly involved in power transmission and distribution, including intelligent transformers, intelligent high-voltage switchgear, electronic current transformers, busbars, disconnectors, load switches, etc.; secondary devices are used to control, protect, measure, and monitor primary devices, including intelligent terminals and merging units, relay protection devices, measurement and control devices, etc. Device information includes aging degree, economic value, and historical failure times. The aging degree is used to reflect the operating condition of the device, the economic value is used to reflect the purchase price of the device, and the historical failure times are used to reflect the failure condition of the device put into operation.

[0049] In some embodiments, the method includes:

[0050] Step S11: Obtain the theoretical operating duration and historical operating duration of the device, and calculate the aging degree using the following formula:

[0051] In the formula, t is the aging degree, S is the historical operating duration, and L is the theoretical operating duration.

[0052] Step S12: Divide the historical operating duration by the theoretical operating duration to calculate the aging degree t of the device.

[0053] In the embodiments of the present application, the aging degree can be reflected by the ratio of the historical operation duration to the theoretical operation duration. The larger the ratio, the longer the operation time of the device, and the smaller the ratio, the shorter the operation duration of the device.

[0054] Step S2: Based on the device information set, obtain the device information corresponding to each device, and determine the attention level corresponding to each device based on the device information;

[0055] In some embodiments, step S2 includes:

[0056] Step S21: Obtain the aging degree t of the i-th device in the substation i , economic value v i and historical failure times f i ;

[0057] Step S22: Based on the aging degree T i , economic value V i and historical failure times N i , use the following formula to calculate the attention level of the device:

[0058] C i = α1×E(t i )+α2×G(v i )+α3×H(f i )

[0059] In the formula, C i is the attention level of the i-th device, E(·) is a function for uniformly converting the aging degree of the device, G(·) is a function for uniformly converting the economic value of the device, H(·) is a function for uniformly converting the historical failure times of the device, and α1, α2, α3 are the weights corresponding to the aging degree, economic value, and historical failure times of the device.

[0060] In the embodiments of the present application, through the corresponding conversion functions, the aging degree, economic value, and historical failure times are converted into corresponding scores, then the scores are multiplied by the corresponding weight values to obtain the final scores of each item, and the final scores of each item are added together to obtain the attention level, where α1 + α2 + α3 = 1. It can be understood that the larger the aging degree, the larger the economic value, and the more the historical failure times, the higher the attention level. On the contrary, the smaller the aging degree, the smaller the economic value, and the fewer the historical failure times, the lower the attention level.

[0061] Step S3: Based on the attention level, determine the fault diagnosis frequency of the corresponding device;

[0062] In some embodiments, step S3 includes:

[0063]

[0064] In the formula, F i is the fault diagnosis frequency of the i-th device, F is the basic monitoring frequency, k is the adjustment coefficient, and C i is the degree of attention to the i-th device.

[0065] In the embodiment of the present application, when determining the degree of attention to the device, the fault diagnosis frequency can be determined through the preset basic monitoring frequency. The higher the degree of attention, the higher the fault diagnosis frequency. Conversely, the lower the degree of attention, the lower the fault diagnosis frequency. The influence degree of the degree of attention on the monitoring frequency is controlled by the adjustment coefficient, and the specific value is determined according to the importance of the device and the actual requirements.

[0066] Step S4: Obtain the operation data of the corresponding device according to the fault diagnosis frequency;

[0067] In some embodiments, the operation data includes current, voltage, and temperature.

[0068] In the embodiment of the present application, the current can be collected by setting a corresponding current transformer, the voltage can be collected by setting a corresponding voltage transformer, and the temperature can be collected by setting a corresponding temperature sensor. The collected current, voltage, and temperature are uploaded to the background system for storage, and when it is necessary to obtain the operation data of the corresponding device, the corresponding operation data can be directly called from the background system.

[0069] Step S5: Determine whether the device has a fault based on the operation data;

[0070] In some embodiments, step S5 includes:

[0071] Step S51: Normalize the current I i , voltage V i , and temperature T i of the i-th device to obtain the normalized current I′ i , voltage V′ i , and temperature T′ i ;

[0072] Step S52: Extract the feature vector X i , voltage V′ i , and temperature T′ i ; i ;

[0073] Step S53: Input the feature vector X i into the fault diagnosis model and output the fault probability, where the fault diagnosis model is:

[0074] P i =σ(W·X i+b)

[0075] Wherein, P i is the failure probability of the i-th device, σ is the Sigmoid function, W is the model weight, and b is the bias term;

[0076] Step S54: When P i is greater than the preset threshold, it is determined that the device has a failure.

[0077] In the embodiments of the present application, the current, voltage, and temperature data are obtained and normalized. The current, voltage, and temperature are normalized to the interval [0, 1] to obtain the normalized current, voltage, and temperature data. Then, feature vectors are extracted. The feature vectors can be the mean and standard deviation. The mean and standard deviation are input into the fault diagnosis model. The fault diagnosis model outputs the fault probability. Then, the fault probability is compared with the preset threshold. When the fault probability is greater than the preset threshold, it is determined that the device has a failure.

[0078] Step S6: Generate an alarm message when the device has a failure.

[0079] In the embodiments of the present application, when the device has a failure, an alarm message is generated for alarming to prompt relevant personnel to handle it in time. It can be understood that the alarm message can be transmitted to the mobile terminal configured by relevant personnel for timely notification of relevant personnel.

[0080] In summary, by obtaining the device information set of the substation; based on the device information set, obtaining the device information corresponding to each device, and determining the attention level corresponding to each device based on the device information; based on the attention level, determining the fault diagnosis frequency of the corresponding device; according to the fault diagnosis frequency, obtaining the operation data of the corresponding device; based on the operation data, determining whether the device has a failure; generating an alarm message when the device has a failure; it is possible to dynamically adjust the fault diagnosis frequency according to the attention level of the devices in the substation, increase the fault diagnosis frequency for devices with a high attention level to detect device failures in time, and reduce the fault diagnosis frequency for devices with a low attention level to reduce the calculation amount.

[0081] In some embodiments, the method includes:

[0082] Step S100: Obtain the maintenance information of the device, and perform quantization processing on the maintenance information to obtain the maintenance quality quantization value m;

[0083] Step S200: Obtain the environmental information of the device, and perform quantization processing on the environmental information to obtain the environmental quality quantization value e;

[0084] Step S300: Correct the aging degree through the maintenance quality quantization value and the environmental quality quantization value:

[0085] t′ = t × (1 - β × m - γ × e)

[0086] In the formula, t′ is the corrected aging degree, t is the aging degree before correction, and β and γ are the weights corresponding to the maintenance information and the environmental information respectively.

[0087] In the embodiments of the present application, the actual service life of the device not only depends on the designed service life, but is also affected by maintenance and the environment. Therefore, the aging degree can be corrected by the maintenance quality quantization value m and the environmental quality quantization value e. The corrected aging degree can better reflect the state of the device, which is beneficial to further improving the accuracy of the attention degree.

[0088] It should be understood that the "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 application. Therefore, the "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 application, the order numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The serial numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0089] It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, object or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, object or device. Without more limitations, the element defined by the statement "including a..." does not exclude the existence of other identical elements in the process, method, object or device including the element.

[0090] The above is only the implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A smart substation monitoring method, characterized in that: The method comprises: Get the equipment information set of the substation; Based on the device information set, acquiring device information corresponding to each device, and determining a degree of attention corresponding to each device based on the device information; Based on the degree of concern, determining a fault diagnosis frequency of a corresponding device; According to the fault diagnosis frequency, obtaining operation data of the corresponding equipment; Based on the operating data, determining whether the device has a fault; In the event of a device failure, an alarm message is generated.

2. A smart substation monitoring method according to claim 1, characterized in that: The device information set is M={M1, M2, ..., M n }, where M i Indicates the device information of the i-th device, M i =(t i ,v i ,f o ), t i is the aging degree of the i-th device, v i is the economic value of the ith equipment, f i is the historical failure count of the ith device.

3. A smart substation monitoring method according to claim 2, characterized in that: The method comprises: Obtain the theoretical operating time and historical operating time of the device, and use the following formula to calculate the aging degree: Where t is the aging degree, S is the historical operating time, and L is the theoretical operating time. Divide the historical operating time by the theoretical operating time to calculate the aging degree t of the equipment.

4. A smart substation monitoring method according to claim 3, characterized in that: The method comprises: Obtain equipment maintenance information, and quantify the maintenance information to obtain a maintenance quality quantified value m; Obtain the environmental information of the equipment, and quantify the environmental information to obtain the environmental quality quantification value e; The degree of aging is corrected by the maintenance quality quantification value and the environmental quality quantification value: t′=t×(1-β×m-γ×e) Where t′ is the corrected aging degree, t is the aging degree before correction, β and γ are the weights corresponding to maintenance information and environmental information, respectively.

5. A smart substation monitoring method according to claim 2, characterized in that: The acquiring device information corresponding to each device based on the device information set, and determining the attention level corresponding to each device based on the device information, includes: Get the aging degree t of the i-th device in the substation i 、Economic value i and the number of historical failures f i ; Based on the aging degree T i 、Economic Value V i and the number of historical failures N i , the following formula is used to calculate the attention level of the device: C i =α1×E(t i )+α2×G(v i )+α3×H(f i ) In the formula, C i is the attention level of the ith device, E(·) is the unified conversion function for the aging degree of the equipment, G(·) is the unified conversion function for the economic value of the equipment, H(·) is the unified conversion function for the number of historical failures of the equipment, α1, α2, α3 are the weights corresponding to the aging degree, economic value and number of historical failures of the equipment.

6. A smart substation monitoring method according to claim 1, characterized in that: The determining, based on the degree of concern, a fault diagnosis frequency of a corresponding device includes: In the formula, F i is the fault diagnosis frequency of the i-th device, F is the basic monitoring frequency, k is the adjustment coefficient, C i is the attention level of the i-th device.

7. A smart substation monitoring method according to claim 1, characterized in that: The operating data includes current, voltage and temperature.

8. A smart substation monitoring method according to claim 7, characterized in that: The determining whether the device has a fault based on the operation data includes: The current I for the i-th device i , voltage V i and temperature T i Normalize it and get the current I′ i , voltage V′ i and temperature T′ i ; Extraction current I′ i , voltage V′ i and temperature T′ i The eigenvector X i ; The feature vector X i Input the fault diagnosis model and output the fault probability, where the fault diagnosis model is: P i =σ(W·X i +b) Where P i is the failure probability of the i-th device, σ is the Sigmoid function, W is the model weight, and b is the bias term; When P i When it is greater than the preset threshold, the device is judged to be faulty.

Images