Cable data classification processing method and system for operation and maintenance management of power distribution system

Abstract

The invention discloses a cable data classification processing method and system for operation and maintenance management of a power distribution system, and relates to the field of operation and maintenance management of a power distribution network. A sampling value of basic data of a cable is obtained, a sampling value data time sequence # imgabs0 # is constructed, a prediction model is constructed according to the obtained sequence # imgabs1 #, a prediction value # imgabs2 # of the basic data of the rth type of cable at the moment t is calculated, a data residual value # imgabs5 # is calculated according to a sampling value # imgabs3 # and the prediction value # imgabs4 #, and a data residual value # imgabs2 # is calculated according to the sampling value # imgabs3 # and the prediction value # imgabs3 # and the prediction value # imgabs4 #. The method comprises the following steps of: calculating a local outlier factor of each element # imgabs9 # in a data residual sequence # imgabs8 # by using an LOF algorithm, judging an abnormal condition of an element # imgabs10 # by using the obtained local outlier factor, determining whether a sampling value # imgabs12 # is abnormal data or not according to an abnormal condition judgment result of # imgabs11 #, analyzing the data residual sequence, and judging whether the sampling value # imgabs12 # is abnormal data or not. Whether the sampling value of the cable basic data is in an abnormal state at a certain moment in the operation period of the power grid can be accurately judged, and the operation state of the power distribution network can be further evaluated and judged.

Description

Technical Field

[0001] The present invention relates to the field of power distribution network operation and maintenance management, and in particular to a cable data classification processing method and system for power distribution system operation and maintenance management. Background Art

[0002] The distribution network is a key component of the power grid system. The adoption of effective operation and maintenance management methods during the operation of the power grid can greatly improve the safety and reliability of operation and provide users with high-quality services. With the continuous expansion of power service business, the complexity of power enterprise operation control has also increased accordingly, which requires strengthening the inspection and maintenance of the power operation system.

[0003] Collecting a large amount of basic cable data during the operation of the power grid and analyzing the collected data to find fault points is one of the basic tasks of operation and maintenance management. At present, the analysis and processing method for basic cable data generally uses the threshold method to determine its operating status. By analyzing historical data, a reasonable threshold range is set, and early warning processing is performed when the operating data exceeds the range. Since some basic cable data, such as current values ​​and voltage values, are related to multiple influencing factors in the power grid and are always changing, it is impossible to accurately determine whether it is in an abnormal state at a certain moment in the operation cycle with a fixed threshold. Further, it is not conducive to accurately evaluate and determine the operating status of the distribution network. To this end, we propose a cable data classification and processing method and system for distribution system operation and maintenance management. Summary of the invention

[0004] The main purpose of the present invention is to provide a cable data classification and processing method and system for power distribution system operation and maintenance management, which can effectively solve the problems in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] A cable data classification and processing method for power distribution system operation and maintenance management, comprising:

[0007] Get the sampling value of the cable basic data and construct the sampling value data time series {x t r}, where x t r represents the sampling value of the basic data of the rth type of cable at time t, t=1, 2, ..., N, N is the total amount of data, wherein the basic data of the cable includes basic data of the cable channel, basic data of the cable body, and basic data of the cable accessory equipment;

[0008] According to the sequence obtained Construct a prediction model to calculate the predicted value of the basic data of the rth type of cable at time t Among them, the expression of the prediction model is:

[0009]

[0010] In the formula, and is a non-zero undetermined coefficient; independent error terms, and n and m are both positive numbers less than or equal to 2;

[0011] According to the sampling value and predicted values Calculate the residual value of the data in, And construct the data residual sequence

[0012] Use LOF algorithm to calculate data residual sequence Elements The local outlier factor of the element is obtained by using the local outlier factor The abnormal situation is judged and The abnormal situation determination result determines the sampling value Whether it is abnormal data;

[0013] element The abnormal situation determination process includes the following steps:

[0014] Calculate the elements separately and the data residual sequence The remaining elements The distance between Among them, q∈N, and q≠t, the distance value calculation formula is:

[0015] The distance value to be obtained Sort by small to large, let The kth element closest to p∈N, and p≠t, get the element With the element The kth distance value in, k is a positive odd number greater than 1, and k∝N;

[0016] According to the kth distance value Identify the elements The kth distance neighbor of

[0017] Get elements The k-th reachable distance of For elements The k-th reachable distance of To obtain The maximum value operation in For elements With the kth distance neighbor The set of distance values ​​between all elements in ;

[0018] Get elements The local reachable density is defined as:

[0019]

[0020] Calculate the element based on the local reachable density obtained The local outlier factor is calculated as:

[0021]

[0022] In the formula, For elements The local outlier factor of For elements The local reachable density of

[0023] Use the obtained local outlier factor to Determine the abnormal situation.

[0024] when Representation Elements It may be abnormal data;

[0025] when Close to 1, indicating an element It may belong to the same cluster as the neighboring points and is normal data;

[0026] when Representation Elements are dense data points.

[0027] when hour, Local outlier factor values ​​and elements The abnormality of

[0028] Sample value The principle for determining whether it is abnormal data is:

[0029] When the data residual series Elements in When it is normal data, determine the sampling value is normal data;

[0030] When the data residual series Elements in When it is abnormal data, determine the sampling value is abnormal data.

[0031] A cable data classification and processing system for power distribution system operation and maintenance management, comprising a data acquisition module, a prediction model building module, a data processing module, and an abnormal data determination module;

[0032] The data acquisition module is used to acquire the sampling values ​​of the cable basic data and construct a sampling value data time series;

[0033] The prediction model building module is used to obtain the sequence Construct a prediction model and calculate the prediction value of the basic data of the rth type of cable at time t;

[0034] The data processing module is used to and predicted values Calculate the residual value of the data in, And construct the data residual sequence

[0035] The abnormal data determination module is used to calculate the data residual sequence using the LOF algorithm Elements The local outlier factor of the element is obtained by using the local outlier factor The abnormal situation is judged and The abnormal situation determination result determines the sampling value Whether it is abnormal data;

[0036] The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0037] The present invention has the following beneficial effects:

[0038] Compared with the existing technology, by obtaining the sampling values ​​of the basic cable data, the sampling value data time series is constructed. Among them, according to the obtained sequence Construct a prediction model to calculate the predicted value of the basic data of the rth type of cable at time t According to the sampling value and predicted values Calculate the residual value of the data in, And construct the data residual sequence Use LOF algorithm to calculate data residual sequence Elements The local outlier factor of the element is obtained by using the local outlier factor The abnormal situation is judged and The abnormal situation determination result determines the sampling value Whether it is abnormal data, by analyzing the data residual sequence, it is possible to accurately determine whether the sampling value of the cable basic data is in an abnormal state at a certain moment in the power grid operation cycle, which is conducive to further evaluation and determination of the distribution network operation status. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a flow chart of a cable data classification and processing method for power distribution system operation and maintenance management according to the present invention;

[0040] Figure 2 The present invention is a structural block diagram of a cable data classification and processing system for power distribution system operation and maintenance management. DETAILED DESCRIPTION

[0041] The present invention will be further described below in conjunction with specific implementation methods, wherein the accompanying drawings are only used for exemplary descriptions and represent only schematic diagrams rather than actual drawings, and should not be understood as limiting the present invention. In order to better illustrate the specific implementation methods of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0042] Example 1

[0043] The implementation process of the technical solution of the present invention includes the following steps:

[0044] Step 1: Obtain the sampling values ​​of the basic cable data and construct the sampling value data time series in, It is represented by the sampling value of the basic data of the rth type cable at time t, t = 1, 2, ..., N, N is the total amount of data;

[0045] Among them, the data time series It should be noted that the basic data of cables include basic data of cable channels, basic data of cable bodies, and basic data of cable accessory equipment; wherein, the basic data involved in the technical solution of the present invention is discrete variable data, such as,

[0046] For cable channel basic data, the following categories are included:

[0047] 1) Electrical properties of the cable: such as maximum load current, short-circuit current peak, cable phase center distance, cable length, and cable DC resistivity and resistance temperature coefficient;

[0048] 2) Cable channel structure information: including the usage of internal cable resources;

[0049] These basic data are crucial for the design, construction, operation and maintenance, and safety management of cable channels, and help improve the reliability and safety of the power grid;

[0050] For the basic data of cable body, the following categories are included:

[0051] 1) Cable current carrying capacity: the current carrying capacity of the cable under different conditions, that is, the current capacity that the cable can safely transmit;

[0052] 2) Cable resistance: DC resistance and AC resistance per unit length of cable, including resistivity and temperature coefficient of resistance;

[0053] 3) Electrical performance of the cable: including the rated voltage, phase sequence, capacitance, inductance and other electrical parameters of the cable;

[0054] 4) Mechanical properties of cables: such as tensile strength, compressive strength, etc.;

[0055] 5) Thermal performance of cables: including thermal stability and thermal life of cables;

[0056] These basic data help ensure the correct selection, safe operation and effective maintenance of cables, which is crucial to the reliability and economy of the distribution system;

[0057] For basic data of cable accessory equipment, the following categories are included:

[0058] 1) Cable terminal: including the rated voltage of the terminal;

[0059] 2) Cable connector: including rated voltage of the connector;

[0060] 3) Cable brackets and fixings: including the bearing capacity of the brackets, etc.;

[0061] 4) Cable operating parameters: including cable current carrying capacity, operating temperature, voltage drop, etc.;

[0062] 5) Cable installation and use records: including ambient temperature, ambient humidity, etc.;

[0063] These basic data help to effectively manage and maintain cable ancillary equipment and ensure the safe, reliable and economical operation of the cable system;

[0064] Step 2: Based on the acquired sequence Construct a prediction model to calculate the predicted value of the basic data of the rth type of cable at time t Among them, the expression of the prediction model is:

[0065]

[0066] In the formula, and is a non-zero undetermined coefficient; independent error terms, and n and m are both positive numbers less than or equal to 2;

[0067] Step 3: Based on the sample value and predicted values Calculate the residual value of the data in, And construct the data residual sequence in,

[0068] Step 4: Use the LOF algorithm to calculate the data residual sequence Elements The local outlier factor of the element is obtained by using the local outlier factor The abnormal situation is judged and Abnormal situation judgment result determines the sampling value Whether it is abnormal data;

[0069] element The abnormal situation determination process includes the following steps:

[0070] Step 41: Calculate the elements separately and the data residual sequence The remaining elements The distance between Among them, q∈N, and q≠t, the distance value calculation formula is:

[0071] Step 42: Get the distance value Sort by small to large, let The kth element closest to p∈N, and p≠t, get the element With the element The kth distance value in, k is a positive odd number greater than 1, and k∝N;

[0072] Step 43: According to the kth distance value Identify the elements The kth distance neighbor of

[0073] Step 44: Get the element The k-th reachable distance of

[0074] in, For elements The k-th reachable distance of To obtain The maximum value operation in For elements With the kth distance neighbor The set of distance values ​​between all elements in ;

[0075] Step 45: Get the element The local reachable density of

[0076] Among them, the local reachable density is defined as:

[0077]

[0078] Step 46: Calculate the element based on the local reachable density obtained The local outlier factor is calculated as:

[0079]

[0080] In the formula, For elements The local outlier factor of For elements The local reachable density of

[0081] Step 47: Use the obtained local outlier factor to Determine the abnormal situation.

[0082] when Representation Elements It may be abnormal data;

[0083] when Close to 1, indicating an element It may belong to the same cluster as the neighboring points and is normal data;

[0084] when Representation Elements are dense data points.

[0085] when hour, Local outlier factor values ​​and elements The abnormality of

[0086] Among them, the sampling value The principle for determining whether it is abnormal data is:

[0087] When the data residual series Elements in When it is normal data, determine the sampling value is normal data;

[0088] When the data residual series Elements in When it is abnormal data, determine the sampling value is abnormal data.

[0089] Example 2

[0090] The technical solution of the present invention can also be used to predict discrete cable basic data variables, and the specific implementation process includes the following steps:

[0091] Step 1: Obtain the sampling values ​​of the basic cable data and construct the sampling value data time series in, It is represented by the sampling value of the basic data of the rth type cable at time t, t = 1, 2, ..., N, N is the total amount of data;

[0092] Among them, the data time series It should be noted that the basic data of cables include basic data of cable channels, basic data of cable bodies, and basic data of cable accessory equipment; wherein, the basic data involved in the technical solution of the present invention is discrete variable data, such as,

[0093] For cable channel basic data, the following categories are included:

[0094] 1) Electrical properties of the cable: such as maximum load current, short-circuit current peak, cable phase center distance, cable length, and cable DC resistivity and resistance temperature coefficient;

[0095] 2) Cable channel structure information: including the usage of internal cable resources;

[0096] For the basic data of cable body, the following categories are included:

[0097] 1) Cable current carrying capacity: the current carrying capacity of the cable under different conditions, that is, the current capacity that the cable can safely transmit;

[0098] 2) Cable resistance: DC resistance and AC resistance per unit length of cable, including resistivity and temperature coefficient of resistance;

[0099] 3) Electrical performance of the cable: including the rated voltage, phase sequence, capacitance, inductance and other electrical parameters of the cable;

[0100] 4) Mechanical properties of cables: such as tensile strength, compressive strength, etc.;

[0101] 5) Thermal performance of cables: including thermal stability and thermal life of cables;

[0102] For basic data of cable accessory equipment, the following categories are included:

[0103] 1) Cable terminal: including the rated voltage of the terminal;

[0104] 2) Cable connector: including rated voltage of the connector;

[0105] 3) Cable brackets and fixings: including the bearing capacity of the brackets, etc.;

[0106] 4) Cable operating parameters: including cable current carrying capacity, operating temperature, voltage drop, etc.;

[0107] 5) Cable installation and use records: including ambient temperature, ambient humidity, etc.;

[0108] Step 2: Based on the acquired sequence Construct a prediction model to calculate the predicted value of the basic data of the rth type of cable at time t+1 Among them, the expression of the prediction model is:

[0109]

[0110] The above formula can be used to obtain the predicted value of the basic cable data at the future time t+1, so that the operating status of the distribution network can be evaluated and determined based on the predicted value.

[0111] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A cable data classification and processing method for power distribution system operation and maintenance management, It is characterized in that include: Get the sampling values ​​of the basic cable data and construct the sampling value data time series in, It is represented by the sampling value of the basic data of the rth type cable at time t, t = 1, 2, ..., N, N is the total amount of data; According to the sequence obtained Construct a prediction model to calculate the predicted value of the basic data of the rth type of cable at time t Among them, the expression of the prediction model is: In the formula, and is a non-zero undetermined coefficient; independent error terms, and n and m are both positive numbers less than or equal to 2; According to the sampling value and predicted values Calculate the residual value of the data in, And construct the data residual sequence Use LOF algorithm to calculate data residual sequence Elements The local outlier factor of the element is obtained by using the local outlier factor The abnormal situation is judged and The abnormal situation determination result determines the sampling value Whether it is abnormal data.

2. According to claim 1, a cable data classification and processing method for power distribution system operation and maintenance management, It is characterized in that element The abnormal situation determination process includes the following steps: Calculate the elements separately and the data residual sequence The remaining elements The distance between Among them, q∈N, and q≠t, the distance value calculation formula is: The distance value to be obtained Sort by small to large, let The kth element closest to p∈N, and p≠t, get the element With the element The kth distance value in, According to the kth distance value Identify the elements The kth distance neighbor of Get elements The k-th reachable distance of For elements The k-th reachable distance of To obtain The maximum value operation in For elements With the kth distance neighbor The set of distance values ​​between all elements in ; Get elements The local reachable density is defined as: Calculate the element based on the local reachable density obtained The local outlier factor is calculated as: In the formula, For elements The local outlier factor of For elements The local reachable density of Use the obtained local outlier factor to Determine the abnormal situation.

3. According to claim 2, a cable data classification and processing method for power distribution system operation and maintenance management, Features ； when Representation elements It may be abnormal data; when Close to 1, indicating an element It may belong to the same cluster as the neighboring points and is normal data; when Representation elements are dense data points.

4. According to claim 3, a cable data classification and processing method for power distribution system operation and maintenance management, It is characterized in that when hour, Local outlier factor values ​​and elements The degree of abnormality is positively correlated.

5. According to claim 2, a cable data classification and processing method for power distribution system operation and maintenance management, It is characterized in that k is a positive odd number greater than 1, and k∝N.

6. A cable data classification and processing method for power distribution system operation and maintenance management according to claim 1, It is characterized in that The cable basic data is discrete variable data, including cable channel basic data, cable body basic data, and cable accessory equipment basic data.

7. A cable data classification and processing method for power distribution system operation and maintenance management according to claim 1, It is characterized in that Sample value The principle for determining whether the data is abnormal is as follows: When the data residual series Elements in When it is normal data, determine the sampling value is normal data; When the data residual series Elements in When it is abnormal data, determine the sampling value is abnormal data.

8. A cable data classification and processing system for power distribution system operation and maintenance management, It is characterized in that It includes data acquisition module, prediction model building module, data processing module and abnormal data determination module; The data acquisition module is used to obtain the sampling values ​​of the cable basic data and construct the sampling value data time series in, It is represented by the sampling value of the basic data of the rth type cable at time t, t = 1, 2, ..., N, N is the total amount of data; The prediction model building module is used to obtain the sequence Construct a prediction model to calculate the predicted value of the basic data of the rth type of cable at time t Among them, the expression of the prediction model is: In the formula, and is a non-zero undetermined coefficient; independent error terms, and n and m are both positive numbers less than or equal to 2; The data processing module is used to and predicted values Calculate the residual value of the data in, And construct the data residual sequence The abnormal data determination module is used to calculate the data residual sequence using the LOF algorithm Elements The local outlier factor of the element is obtained by using the local outlier factor The abnormal situation is judged and The abnormal situation determination result determines the sampling value Whether it is abnormal data.

9. A cable data classification and processing system for power distribution system operation and maintenance management according to claim 8, It is characterized in that The system comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the steps of the method according to any one of claims 1 to 6 are implemented when the processor executes the program.

Images