A method for analyzing and troubleshooting defects in power communication equipment

Abstract

The present invention discloses a method for analyzing and troubleshooting defects in power communication equipment. The method comprises: collecting historical power communication equipment defect data from the power communication equipment transmission network to generate a primary database of power communication equipment defects; quantifying the primary database of power communication equipment defects according to data discretization rules pre-determined based on the characteristics of power communication equipment defects to generate a database of power communication equipment defect-influencing factors; and importing a pre-built improved Apriori algorithm model for analysis to obtain frequent item sets with varying support and confidence levels and two types of strong rules. Advantages: Based on the physical model of power communication equipment and based on the characteristics of the equipment defect database, the method improves the traditional Apriori algorithm and performs correlation analysis on power communication equipment defects based on the improved Apriori algorithm, effectively identifying and detecting the causes of power communication equipment failures and locating the fault points.

Description

Technical Field

[0001] The present invention relates to a method for analyzing and troubleshooting defects in electric power communication equipment, and belongs to the technical field of electric power communication. Background Art

[0002] With the development of the Energy Internet, the number of power communication equipment continues to increase. As an important infrastructure to ensure the safe operation of the power system, it provides transmission channels of various types and rates for secondary equipment such as grid stability control and telecontrol. Its operating status has gradually increased the impact on the grid's safety and stability control devices. Communication equipment defect analysis has become a key factor affecting the safe and stable operation of the grid. Therefore, intelligent and efficient equipment fault analysis is the guarantee for the stable operation of large-scale power communication equipment connected to the grid.

[0003] As the scale of power communications continues to expand, the original communication equipment maintenance work method is unable to support the pressure brought by the large-scale commissioning of communication equipment. The large number and complexity of equipment have brought a considerable workload to maintenance personnel, and also brought certain risks to the operation of the power grid. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the defects of the existing technology and provide a method for analyzing the correlation between defects in power communication equipment and a method for troubleshooting defects, which can solve the technical problem that the existing technology is insufficient in identifying the causes of defects in power communication equipment and detecting the location of fault points.

[0005] To solve the above technical problems, the present invention provides a method for analyzing the correlation of defects in power communication equipment, comprising:

[0006] Collect historical power communication equipment defect data in the power communication equipment transmission network, classify and analyze the historical power communication equipment defect data, and generate a power communication equipment defect original database;

[0007] According to the data discretization rules pre-determined based on the defect characteristics of the power communication equipment, the original database of power communication equipment defects is quantified to generate a power communication equipment defect-influencing factor database;

[0008] The power communication equipment defect-influencing factor database was imported into the pre-built improved Apriori algorithm model for analysis, and frequent item sets with different support and confidence levels and two types of strong rules were obtained. The two types of strong rules are the associations between influencing factors and defects, and between defects and fault locations of defective equipment.

[0009] Further,

[0010] The collecting of historical power communication equipment defect data in the power communication equipment transmission network, classifying and analyzing the historical power communication equipment defect data, and generating a power communication equipment defect original database includes:

[0011] The historical power communication equipment defect data of the power communication equipment transmission network is collected, and the various equipment defects and their influencing factors in the historical power communication equipment defect data are classified and analyzed to obtain the mapping relationship between the power communication equipment defect influencing factors and defect types and fault modules, and generate the original power communication equipment defect database.

[0012] Furthermore, the method of performing quantization processing on the original database of power communication equipment defects according to the data discretization rules pre-determined based on the power communication equipment defect characteristics to generate a power communication equipment defect-influencing factor database includes:

[0013] Based on the defect characteristics of power communication equipment, the validity of the collected defects of power communication equipment is analyzed to obtain each data set E, where E = {signal loss, pigtail break, excessive bit errors, optical power overload, and ambient temperature change}. Each data set E is then coded and integrated, with the defect type classified by letters and the influencing factors classified by numbers, forming a data set E' consisting of letters and numbers. Each data set E' is introduced into the improved Apriori algorithm. By calculating the support of the equipment defect candidate set and the confidence between the influencing factors and the equipment defects, the frequent defect itemsets with high support are found, and the influencing factors with high confidence are strongly associated with the defects to generate a power communication equipment defect-influencing factor database.

[0014] Furthermore, the power communication equipment defect-influencing factor database is imported into the pre-built improved Apriori algorithm model for analysis to obtain frequent item sets with different support and confidence levels and two types of strong rules, including:

[0015] The power communication equipment defect-influencing factor database is hierarchically processed according to the circuit layer, the channel layer, and the transmission medium layer. A mapping relationship between the power communication equipment defect influencing factors is determined through the hierarchically processed power communication equipment defect-influencing factor database. According to the mapping relationship, the power communication equipment defect-influencing factor database is mapped into a hierarchically arranged Boolean matrix containing only "0" and "1" elements, where each row in the Boolean matrix is a defect database and each column is a defect type.

[0016] The Boolean matrix is imported into the pre-built improved Apriori algorithm model for analysis, and frequent itemsets with different support and confidence levels and two types of strong rules are obtained.

[0017] Furthermore, the Boolean matrix is imported into the pre-built improved Apriori algorithm model for analysis to obtain frequent item sets with different support and confidence levels and two types of strong rules, including:

[0018] Pruning is performed by counting the number of "1" elements in each column of the Boolean matrix and comparing it with a preset threshold. After the pruning operation, a self-join operation is performed by performing a logical "AND" operation on the defect type item column of the Boolean matrix to generate frequent item sets.

[0019] Repeat the pruning and self-connection operations and terminate under certain circumstances to obtain frequent item sets with different support and confidence levels and two types of strong rules.

[0020] A method for troubleshooting defects in power communication equipment, comprising:

[0021] Obtain frequent item sets and two types of strong rules with different support and confidence levels determined by the power communication equipment defect correlation analysis method;

[0022] According to the frequent item sets with different support and confidence and the two types of strong rules, equipment defects with high support are checked first during preventive condition maintenance and fault repair. When power communication equipment fails, influencing factors and fault locations with high confidence are checked first.

[0023] A computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions, which, when executed by a computing device, enable the computing device to execute any one of the methods for analyzing the correlation between defects in power communication equipment or the method for troubleshooting defects in power communication equipment.

[0024] A computing device comprising:

[0025] One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any one of the methods for analyzing the defect correlation of power communication equipment or the method for troubleshooting defects in power communication equipment.

[0026] The beneficial effects achieved by the present invention are:

[0027] Based on the physical model of power communication equipment, combined with the equipment itself, human factors, and the external environment, the traditional Apriori algorithm is improved according to the characteristics of the equipment defect database. Based on the improved Apriori algorithm, correlation analysis of power communication equipment defects is performed, and specific strong correlations are extracted as the basis for fault tracing. This is an effective method for identifying and detecting the causes of power communication equipment faults and locating the fault points. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A schematic diagram of the process of the present invention;

[0029] Figure 2 This is a defect analysis diagram for power communication equipment;

[0030] Figure 3 Generate frequent itemset flow chart to improve Apriori algorithm;

[0031] Figure 4 This is a diagram of defect data rules for power communication equipment. DETAILED DESCRIPTION

[0032] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and are not intended to limit the scope of protection of the present invention.

[0033] like Figure 1 As shown, a method for analyzing the correlation of defects in power communication equipment solves the technical problem that the existing technology is insufficient in identifying the causes of defects in power communication equipment and detecting the location of fault points.

[0034] The present invention adopts the following technical solutions to achieve the above-mentioned purpose:

[0035] Step 1: Construct a physical model of power communication equipment and analyze its defect characteristics and influencing factors. The power communication equipment transmission network is layered, including the circuit layer, channel layer, and transmission medium layer. This provides a basis for the subsequent hierarchical import of the defect database into the improved Apriori algorithm and reduces algorithm complexity. The circuit layer is service-oriented and directly provides users with SDH communication services. The channel layer is further divided into the high-order channel layer and the low-order channel layer. The segment layer within the transmission medium layer is further divided into the multiplexing segment and the regeneration segment. This provides a basis for the subsequent hierarchical import of the defect database after coding integration into the improved Apriori algorithm.

[0036] Collect defect data of local equipment, classify and analyze various equipment defects and their influencing factors based on their characteristics, obtain the power communication equipment defect influencing factor system and the mapping relationship between the two, and generate the original defect database.

[0037] Step 2: Develop data discretization rules based on equipment defect characteristics, quantify the raw defect data, and generate a database of power communication equipment defects and influencing factors. To overcome the inconsistencies inherent in integrating data into the algorithm, quantize and encode the raw data. Based on the data model and physical model, combined with association rules, a power communication equipment defect analysis model is established.

[0038] Step 3: Improve the algorithm based on database characteristics. Using the improved Apriori algorithm, analyze and process power communication equipment defects and their influencing factors to generate frequent itemsets. The quantized and encoded defect database is then imported into the improved Apriori algorithm for analysis. This yields frequent itemsets with varying support and confidence levels, as well as two types of strong rules: the associations between influencing factors and defects, and between defects and the fault locations of defective equipment.

[0039] Step 4: Trace the cause of the defect and locate the fault by using the strong correlation between the equipment defect, influencing factors, and fault modules. By calculating the support and confidence of the absence database, prioritize matching influencing factors and fault modules with high confidence to determine and identify the cause of the defect and the location of the fault.

[0040] Further, such as Figure 2 As shown, in step 1, taking Synchronous Digital Hierarchy (SDH) transmission equipment as an example, its layered model and basic multiplexing mapping structure are analyzed. For example, information received at the far end of the multiplexing section and mismatch and error information detected at the high-order channel receiving end are collected. Using its layered model and multiplexing mapping structure, possible faults along the transmission route and their close relationship with certain modules are analyzed, thereby establishing a physical model of the SDH transmission equipment. Local power communication equipment defect data is collected, with each piece of data being considered a sample. N data samples are selected, and the defect characteristics and influencing factors are analyzed. These include multiple defects such as signal loss, frame loss, and excessive bit errors, as well as multiple influencing factors such as pigtail breakage, optical power overload, and ambient temperature changes. A multi-dimensional influencing factor system is generated, serving as the original database for power communication equipment defects.

[0041] Furthermore, in step 2, the collected power communication equipment defects are analyzed for validity based on the power communication equipment defect characteristics to obtain each data set E, E = {signal loss, pigtail break, excessive bit error, optical power overload, ambient temperature change}, and then each data set E is coded and integrated, the defect type is classified by letters, and the influencing factors are classified by numbers to form data composed of letters and numbers. Each data set E' is imported into the improved Apriori algorithm, and the support of the equipment defect candidate item set and the confidence between the influencing factors and the equipment defects are calculated to find the defect frequent item set with higher support, and the influencing factors with high confidence are strongly associated with the defects to generate a power communication equipment defect-influencing factor database.

[0042] Furthermore, in step 3, the defect data is first hierarchically processed, and then the equipment defect database is preprocessed and mapped into a Boolean matrix containing only 0 and 1, with one equipment defect record as a row and each defect category as a column. A candidate frequent item set is generated by the union of each column, and then a pruning operation is performed according to the minimum threshold. A logical "and" operation is performed on the defect item column to connect the operation, and this process is repeated in sequence to continuously update the candidate frequent item set, and finally a frequent item set is obtained according to the minimum threshold.

[0043] Furthermore, in step 3, according to the association rule, the mapping relationship between the power communication equipment defects and the influencing factors is expressed as influencing factor A Defect B and faulty module C Influencing factor A, then the defect database is mapped into a Boolean matrix and then imported into the improved Apriori algorithm for analysis and processing. The frequent item sets of equipment defects are generated according to the support, and then strong associations are generated according to the confidence, including the strong associations between influencing factors and defects, and defects and fault locations of defective equipment.

[0044] Furthermore, in step 4, based on the obtained frequent item sets and strong associations, equipment defects with high support are prioritized for checking during preventive status maintenance and fault maintenance. When a fault occurs in the power communication equipment, influencing factors and fault locations with high confidence are prioritized for investigation, thereby tracing the cause of the fault and the location of the fault point, thereby minimizing load loss and economic losses.

[0045] Embodiment: The present invention is described with SDH transmission equipment as a specific embodiment:

[0046] Collect defect data of local equipment, and classify and analyze various defects of the equipment and their influencing factors based on the characteristics. According to the SDH transmission equipment model, analyze its performance and operating parameters, as well as the defects that the equipment is prone to at different channel layers, and find that the multi-dimensional influencing factors of power communication equipment can usually be divided into two aspects: external factors and internal factors. External factors include changes in ambient temperature and humidity, optical fiber line quality, improper human operation, shockproof and dustproof conditions, extreme natural disasters, etc. Among them, improper human operation is mostly the wrong direction of optical fiber connection and incorrect setting of clock source parameters. Internal factors refer to the equipment-origin factors that cause alarm defects, including a series of factors such as the length of time the equipment has been in operation, optical power overload, network layer message errors, equipment manufacturer type, equipment load level, etc. Power communication equipment has a variety of defects, which can be divided into signal loss, frame loss, excessive bit errors, track identifier mismatch, pointer loss, clock failure, signal degradation, link failure, etc., such as Figure 1 shown.

[0047] The collected communication equipment defects were sorted and summarized, resulting in a set of 800 valid defects. The defect types were classified into eight main categories, including signal loss, frame loss, excessive bit errors, track marker mismatch, pointer loss, clock failure, signal degradation, and link failure. Influencing factors included nine main categories: fiber pigtail break, optical power overload, network layer message errors, ambient temperature changes, equipment operating time, equipment manufacturing parameters, ambient humidity changes, extreme natural disasters, and equipment load level. The sample data was numbered: nine influencing factors, such as fiber pigtail break and optical power overload, were numbered 1-9, while eight defects, such as signal loss and frame loss, were numbered AH. The collected defect data was analyzed using the improved Apriori algorithm for power communication equipment defect correlation analysis. The equipment defects and influencing factors in each record are mapped into a Boolean matrix through coding. Due to the large amount of sample data, the minimum support threshold and minimum confidence threshold of the improved Apriori algorithm are set to 10% and 50%, respectively. After cyclic self-connection and pruning of frequent itemsets, frequent itemsets can be obtained, and strong rules can be mined based on the confidence index.

[0048] The algorithm is now improved to enable faster analysis of power communication equipment defect data. First, the defect data is layered and divided into the channel layer and the transmission medium layer. The channel layer is further divided into low-order and high-order, and the segment layer in the transmission medium layer is further divided into multiplexing segment and regeneration segment. Then, the equipment defect database is preprocessed and mapped into a matrix containing only "0" and "1" elements, that is, a Boolean matrix. The matrix row represents a defect data, and the column represents the defect classification and influencing factors; if B i×j =1 means defect j appears in the i-th data. If B i×j = 0 indicates that defect j does not appear in the i-th data. Therefore, the matrix B is composed of "0" and "1" elements to generate the communication equipment defect Boolean matrix. For example, there are five equipment defect records, corresponding to five types of equipment defects: signal loss, frame loss, track identifier mismatch, pointer loss, and signal degradation. They are numbered A, B, C, D, and E, respectively. Each record is 1 if the corresponding defect exists, and 0 otherwise. This forms a 5×5 Boolean matrix as shown below:

[0049]

[0050] like Figure 3As shown in the figure, the Apriori algorithm is improved. Before the frequent itemsets are connected, the definition that if the number of single defective items j in the k-dimensional frequent itemset is less than the dimension k, then it cannot appear in the frequent k+1 itemset is modified. Specifically, the union of the defective items in each column of the Boolean matrix B of the power communication equipment generates a candidate frequent C-1 item set; the number of "1" elements in each column of the Boolean matrix B is counted, and a pruning operation is performed, that is, if the number of "1" elements in column j appears S j ≤n×a%, delete the column of the Boolean matrix, that is, delete the defective item, and generate a frequent L-1 item set; then perform a connection operation on the frequent L-1 item set, that is, perform a logical "AND" operation on the defective item column of the Boolean matrix B, and generate a candidate frequent C-2 item set. For example, for the above matrix, the minimum threshold is set to 20%, that is, S j When ≤1, delete the E column of the matrix, that is, the signal degradation defect, and then perform a logical "AND" operation on the new matrix to obtain the following matrix:

[0051]

[0052] Then compare the "1" of each sub-element of the candidate frequent C-2 item set with the set minimum threshold. If it does not meet the threshold, delete it and update the frequent L-2 item set. Prune and connect operations are performed in sequence until the Lk item set is updated.

[0053] A series of frequent item sets were obtained by improving the Apriori algorithm. A total of 23 strong rules were mined based on the frequent item sets. From them, 17 effective strong rules that meet the minimum threshold conditions were screened out for analyzing the defect mechanism and proposing the correlation analysis method. The results are shown in Table 1.

[0054] Table 1 Communication equipment defect data strong rules

[0055]

[0056] According to the calculation results of support and confidence, the elements are divided according to the strong rule results, and the classification and summary are carried out to build a power communication equipment defect data rule base, such as Figure 4 shown.

[0057] Correspondingly, the present invention also provides a computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions, which, when executed by a computing device, enable the computing device to execute any one of the methods for analyzing the defect correlation of power communication equipment or the method for troubleshooting defects in power communication equipment.

[0058] A computing device comprising:

[0059] One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any one of the methods for analyzing the defect correlation of power communication equipment or the method for troubleshooting defects in power communication equipment.

[0060] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0061] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0062] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0064] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for analyzing the correlation of defects in power communication equipment, characterized in that: include: Collect historical power communication equipment defect data from the power communication equipment transmission network, classify and analyze the historical power communication equipment defect data, and generate a power communication equipment defect original database, specifically including: Collect historical power communication equipment defect data from the power communication equipment transmission network, classify and analyze various equipment defects and their influencing factors in the historical power communication equipment defect data, obtain the mapping relationship between power communication equipment defect influencing factors and defect types and fault modules, and generate a power communication equipment defect original database; According to the data discretization rules pre-determined based on the defect characteristics of power communication equipment, the original database of power communication equipment defects is quantified to generate a power communication equipment defect-influencing factor database, which specifically includes: Based on the characteristics of power communication equipment defects, the effectiveness of the collected power communication equipment defects was analyzed to obtain each data set E, where E = {signal loss, pigtail break, excessive bit errors, optical power overload, and ambient temperature change}. Each data set E was then coded and integrated, with the defect type classified by letter and the influencing factors classified by number, forming a data set E' consisting of letters and numbers. Each data set E' was then introduced into the improved Apriori algorithm. By calculating the support of the equipment defect candidate item set and the confidence between the influencing factors and the equipment defects, frequent defect itemsets with a support of 10% or more were identified. Influencing factors with a confidence of 50% or more were strongly associated with the defects, thus generating a power communication equipment defect-influencing factor database. The power communication equipment defect-influencing factor database was imported into the pre-built improved Apriori algorithm model for analysis, and frequent item sets with different support and confidence levels and two types of strong rules were obtained, including: Performing layered processing on the power communication equipment defect-influencing factor database based on the circuit layer, the channel layer, and the transmission medium layer, determining a mapping relationship between the power communication equipment defect influencing factors based on the layered power communication equipment defect-influencing factor database, and mapping the power communication equipment defect-influencing factor database into a hierarchically arranged Boolean matrix containing only "0" and "1" elements based on the mapping relationship, wherein each row in the Boolean matrix is a defect database, and each column is a defect type; Pruning is performed by counting the number of "1" elements in each column of a Boolean matrix and comparing them with a preset support threshold of 10%. After pruning, a self-join operation is performed by performing a logical "AND" operation on the defect type items in the Boolean matrix to generate frequent item sets. Repeating the pruning and self-join operations yields frequent item sets with a support of ≥10% and a confidence of ≥50%, as well as two types of strong rules. These two types of strong rules represent the associations between influencing factors and defects, and between defects and the fault locations of defective equipment.

2. A method for troubleshooting defects in power communication equipment, characterized in that: include: Obtaining frequent item sets of different support and confidence levels and two types of strong rules determined by the power communication equipment defect correlation analysis method according to claim 1; According to the frequent item sets with different support and confidence and the two types of strong rules, equipment defects with support ≥ 10% are prioritized for checking during preventive status maintenance and fault repair. When power communication equipment fails, influencing factors and fault locations with confidence ≥ 50% are prioritized for checking.

3. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform the method according to claim 1 or the method according to claim 2 .

4. A computing device, characterized in that include, One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing the method according to claim 1 or the method according to claim 2.

Images