Site power supply abnormal state analysis method and system based on data driving

Abstract

The invention belongs to the field of power supply, relates to a data analysis technology, and aims to solve the problem of low accuracy of a station power supply abnormal state analysis result in the prior art, in particular to a data-driven station power supply abnormal state analysis method and system. The anomaly analysis platform is in communication connection with a fault statistics module, a state analysis module, a state evaluation module, a diagnosis optimization module and a database; the fault statistics module is used for carrying out statistical analysis on faults of a station power supply; a statistical period is generated, and a comprehensive data set and a fault data set of an analysis object are obtained at the end moment of the statistical period; statistical analysis can be performed on faults of station power supplies, a fault data set is generated in a fault type-state sequence-processing sequence mode, the fault data set reflects a fault frequency architecture of a single station power supply, and then comprehensive fault frequency architectures of all station power supplies are reflected through a comprehensive data set. And data support is provided for the state analysis process.

Description

Technical Field

[0001] The present invention belongs to the field of power supply and relates to data analysis technology, in particular to a method and system for analyzing abnormal power supply status of a site based on data drive. Background Art

[0002] Site power abnormality status analysis mainly includes the identification and analysis of common power failure types such as power outages, voltage fluctuations, and frequency anomalies. These failures may be caused by a variety of reasons, including power supply line failures, aging of power supply equipment, unstable grid load, etc. The invention patent with announcement number CN115061061B discloses an abnormal state prediction method and device for a wireless site switch power supply. The abnormal state prediction method can analyze, predict and report the abnormal state of the switch power supply, help operation and maintenance personnel to timely discover, verify and solve possible abnormal states, and analyze and classify the abnormal state points and related causes, assisting front-line operation and maintenance personnel to quickly troubleshoot and solve problems, making up for the shortcomings of the alarm module of the switch power supply itself, and improving the protection and operation and maintenance capabilities of wireless sites; however, the prior art generally adopts a unified state judgment basis for fault diagnosis, and the operation stages of power supply components in different site power supplies are not the same, and the fault states when they fail are also different. Therefore, the accuracy of the state diagnosis results of the prior art needs to be improved; at the same time, the prior art cannot evaluate the overlap of the individual and overall equipment operation stages based on the fault state statistical data, resulting in the equipment maintenance timing of a single site power supply being difficult to grasp and the equipment failure rate being difficult to control.

[0003] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0004] The purpose of the present invention is to provide a data-driven site power supply abnormal state analysis method and system, which is used to solve the problem of low accuracy of site power supply abnormal state analysis results in the prior art; The technical problem to be solved by the present invention is: how to provide a data-driven site power abnormal state analysis method and system that can ensure the accuracy of the site power abnormal state analysis results.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A data-driven site power supply abnormal status analysis system includes an abnormal analysis platform, wherein the abnormal analysis platform is communicatively connected with a fault statistics module, a status analysis module, a status evaluation module, a diagnosis optimization module, and a database; The fault statistics module is used to perform statistical analysis on the faults of the site power supply: generate a statistical cycle, mark the site power supply connected to the abnormal analysis platform as an analysis object, and obtain a comprehensive data group and a fault data group of the analysis object at the end of the statistical cycle; The state analysis module is used to analyze the equipment state of the site power supply: all fault data groups of the analysis objects are compared with the comprehensive data group one by one and the coincidence coefficient CH of the analysis object is obtained; The state evaluation module is used to evaluate the equipment operation stage of the site power supply: obtain the coincidence threshold CHmin through the database, compare the coincidence coefficient CH of the analysis object within the statistical period with the coincidence threshold CHmin, and determine whether the equipment operation stage of the analysis object meets the overall characteristics through the comparison result; The diagnostic optimization module is used to perform equipment maintenance optimization analysis on the site power supply.

[0006] Furthermore, the fault data group includes several fault types, each fault type corresponds to a state sequence, the state sequence includes several fault states, the fault state is marked according to the fault type when a fault occurs in the analysis object, and the fault states are arranged in order of the number of markings from large to small to obtain the state sequence; each fault state corresponds to a processing sequence, the processing sequence includes several processing measures, the processing efficiency of the processing measures after the fault state marking of the analysis object is completed, the processing efficiency of the fault processing using the same processing measure for the same fault state is summed and averaged to obtain the efficiency performance value, and the processing measures are arranged in order of the efficiency performance value from large to small to obtain the processing sequence; the comprehensive data group is obtained at the end of the statistical period, the statistical method of the comprehensive data group is the same as that of the fault data group, but the statistical object of the comprehensive data group is all analysis objects.

[0007] Furthermore, the specific process of comparing the fault data group of the analysis object with the comprehensive data group includes: taking the state sequence of the comprehensive data group under the same fault type as the state reference sequence, and taking the state sequence in the fault data group as the state comparison sequence; if the fault state corresponding to the same sequence number in the state reference sequence and the state comparison sequence is the same, then the corresponding sequence number is marked as the state coincidence sequence number; otherwise, the corresponding sequence number is marked as the state deviation sequence number, and the ratio of the number of state coincidence sequence numbers to the number of elements in the state reference sequence is marked as the state coincidence value of the fault type; taking the processing sequence of the comprehensive data group under the same fault state as the processing reference sequence, and taking the processing sequence of the fault data group as the processing comparison sequence; if the processing measures corresponding to the same sequence number in the processing reference sequence and the processing comparison sequence are the same, then the corresponding sequence number is marked as the processing coincidence sequence number; otherwise, the corresponding sequence number is marked as the processing deviation sequence number; and the ratio of the number of processing coincidence sequence numbers to the number of elements in the processing reference sequence is marked as the processing coincidence value of the fault state.

[0008] Furthermore, the process of obtaining the overlap coefficient CH of the analysis object includes: calculating the average value of the state overlap values ​​of all fault types in the fault data group and marking it as the state overlap data ZC of the analysis object, calculating the average value of the processing overlap values ​​of all fault states in the fault data group and marking it as the processing overlap data CC of the analysis object; performing numerical calculations on the state overlap data ZC and the processing overlap data CC to obtain the overlap coefficient CH of the analysis object within the statistical period.

[0009] Furthermore, the specific process of comparing the coincidence coefficient CH of the analysis object within the statistical period with the coincidence threshold CHmin includes: if the coincidence coefficient CH is less than or equal to the coincidence threshold CHmin, it is determined that the equipment operation stage of the analysis object within the statistical period does not conform to the overall characteristics, and the fault data group is used as the fault diagnosis basis for the analysis object in the next statistical period. At the same time, an equipment maintenance signal is generated and the equipment maintenance signal is sent to the mobile phone terminal of the manager through the abnormal analysis platform. After receiving the equipment maintenance signal, the manager performs maintenance analysis on the components in the analysis object and screens out the components that need to be replaced, and marks the components that need to be replaced as processing objects. After the processing object is replaced, the comprehensive data group is used as the fault diagnosis basis for the analysis object; if the coincidence coefficient CH is greater than the coincidence threshold CHmin, it is determined that the equipment operation stage of the analysis object within the statistical period conforms to the overall characteristics, and the comprehensive data group is used as the fault diagnosis basis for the analysis object in the next statistical period.

[0010] Furthermore, the specific process of the diagnostic optimization module performing equipment maintenance optimization analysis on the site power supply includes: marking the processing object marking process within the most recent L1 statistical cycles as a maintenance process, obtaining the overlap coefficient CH of the analysis object corresponding to the maintenance process, forming an overlap range by the value zero and the overlap threshold CHmin, dividing the overlap range into several overlap intervals, marking the maintenance process whose overlap coefficient CH is within the overlap interval as a matching process of the overlap interval, marking the number of times the same processing object is marked in all matching processes within the overlap interval as a priority value of the processing object relative to the overlap interval, marking the L2 processing objects with the largest priority values ​​as priority screening objects of the overlap interval, forming a priority maintenance set of the overlap interval by the priority screening objects of the overlap interval, and sending the priority maintenance sets of all overlap intervals to the database for storage.

[0011] The data-driven site power supply abnormal status analysis method includes the following steps: Step 1: Perform statistical analysis on the site power failure: Generate a statistical cycle, mark the site power connected to the abnormal analysis platform as the analysis object, and obtain the comprehensive data group and the failure data group of the analysis object at the end of the statistical cycle; Step 2: Analyze the equipment status of the site power supply: compare the fault data groups of all analyzed objects with the comprehensive data group one by one and obtain the coincidence coefficient CH of the analyzed object within the statistical period; Step 3: Evaluate the equipment operation stage of the site power supply: Use the coincidence coefficient CH to determine whether the equipment operation stage of the analysis object within the statistical period meets the overall characteristics; Step 4: Perform equipment maintenance optimization analysis on the site power supply: mark the processing object marking process within the latest L1 statistical cycles as a maintenance process, obtain the overlap coefficient CH of the analysis object corresponding to the maintenance process, and form an overlap range consisting of a value of zero and the overlap threshold CHmin. Divide the overlap range into several overlap intervals, and mark the priority maintenance set of the overlap interval.

[0012] The present invention has the following beneficial effects: The fault statistics module can be used to perform statistical analysis on site power supply faults, and generate fault data groups in the form of fault type-state sequence-processing sequence. The fault data group reflects the fault frequency architecture of a single site power supply, and then the comprehensive data group reflects the comprehensive fault frequency architecture of all site power supplies, providing data support for the state analysis process; The status analysis module can be used to analyze the equipment status of the site power supply. The coincidence coefficient can be obtained by comparing the fault data group with the comprehensive data group. The coincidence coefficient represents the degree of overlap of the fault frequency structure of a single site power supply with that of the entire site. The coincidence coefficient can then be used to evaluate the necessity of equipment maintenance for the site power supply. The status assessment module can be used to assess the equipment operation stage of the site power supply, determine whether the equipment operation stage of the analyzed object meets the overall characteristics, and mark the fault diagnosis basis of the analyzed object in the next statistical period based on the determination results, so as to ensure the accuracy of the fault diagnosis results while carrying out equipment maintenance in a timely manner; 4. The diagnostic optimization module can be used to optimize the site power supply for equipment maintenance. The overlap interval and priority maintenance set can be generated based on the overlap coefficient during component maintenance and the processing object marking results. In this way, priority screening objects can be extracted based on the overlap coefficient during subsequent equipment maintenance, thereby improving equipment maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0014] Figure 1 is a system block diagram of Embodiment 1 of the present invention; Figure 2 This is a flow chart of the method of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0015] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] Embodiment 1: Figure 1 As shown, the data-driven site power supply abnormal status analysis system includes an abnormal analysis platform, which is communicatively connected to a fault statistics module, a status analysis module, a status evaluation module, a diagnosis optimization module and a database.

[0017] The fault statistics module is used to perform statistical analysis on the faults of the site power supply: generate a statistical cycle, mark the site power supply connected to the abnormal analysis platform as the analysis object, and obtain the fault data group of the analysis object at the end of the statistical cycle. The fault data group includes several fault types, each fault type corresponds to a state sequence, and the state sequence includes several fault states. When a fault occurs in the analysis object, the fault state is marked according to the fault type, and the fault states are arranged in order from the most to the least number of markings to obtain a state sequence; each fault state corresponds to a processing sequence, and the processing sequence includes several processing measures; the fault types generally include power failure, voltage fluctuation, overcurrent fault, overvoltage fault, and power quality abnormality; exemplarily, when the fault type is a power failure, the corresponding fault state generally includes circuit breaker tripping, AC power failure, power phase loss, power phase mismatch, and neutral line interruption, etc. Similarly, when the fault state is circuit breaker tripping, the corresponding processing measures generally include power supply maintenance processing, circuit load maintenance processing, leakage maintenance processing, short circuit maintenance processing, etc.

[0018] Obtain the processing efficiency of the post-processing measures after the fault state marking of the analysis object is completed, sum and average the processing efficiency of the fault processing using the same processing measure for the same fault state to obtain the efficiency performance value, and arrange the processing measures in descending order of the efficiency performance value to obtain a processing sequence; obtain a comprehensive data group at the end of the statistical period, the statistical method of the comprehensive data group is the same as that of the fault data group, but the statistical object of the comprehensive data group is all analysis objects; generate a fault data group in the form of fault type-state sequence-processing sequence, the fault data group reflects the fault frequency structure of the power supply of a single site, and then the comprehensive fault frequency structure of the power supplies of all sites is reflected through the comprehensive data group, providing data support for the state analysis process.

[0019] The status analysis module is used to analyze the equipment status of the site power supply: all fault data groups of the analysis objects are compared with the comprehensive data group one by one: the status sequence of the comprehensive data group under the same fault type is used as the status reference sequence, and the status sequence in the fault data group is used as the status comparison sequence. If the fault status corresponding to the same sequence number in the status reference sequence and the status comparison sequence is the same, the corresponding sequence number is marked as the status coincidence sequence number; otherwise, the corresponding sequence number is marked as the status deviation sequence number, and the ratio of the number of state coincidence sequence numbers to the number of elements in the status reference sequence is marked as the status coincidence value of the fault type; the processing sequence of the comprehensive data group under the same fault state is used as the processing reference sequence, and the processing sequence of the fault data group is used as the processing comparison sequence. If the processing measures corresponding to the same sequence number in the processing reference sequence and the processing comparison sequence are the same, the corresponding sequence number is marked as the processing measure. otherwise, mark the corresponding number as the processing deviation number; mark the ratio of the number of processing coincidence numbers to the number of elements in the processing reference sequence as the processing coincidence value of the fault state; calculate the average value of the state coincidence values ​​of all fault types in the fault data group and mark it as the state coincidence data ZC of the analysis object, calculate the average value of the processing coincidence values ​​of all fault states in the fault data group and mark it as the processing coincidence data CC of the analysis object; obtain the coincidence coefficient CH of the analysis object within the statistical period through the formula CH=k1×ZC+k2×CC, where k1 and k2 are both proportional coefficients, and k1>k2>1; compare the fault data group with the comprehensive data group to obtain the coincidence coefficient, which represents the degree of overlap of the fault frequency structure of a single site power supply relative to the overall site, and then evaluate the necessity of equipment maintenance of the site power supply through the coincidence coefficient.

[0020] The status assessment module is used to assess the equipment operation stage of the site power supply: obtain the coincidence threshold CHmin through the database, and compare the coincidence coefficient CH of the analysis object in the statistical period with the coincidence threshold CHmin: if the coincidence coefficient CH is less than or equal to the coincidence threshold CHmin, it is determined that the equipment operation stage of the analysis object in the statistical period does not meet the overall characteristics, and the fault data group is used as the fault diagnosis basis of the analysis object in the next statistical period. At the same time, an equipment maintenance signal is generated and sent to the mobile terminal of the manager through the abnormal analysis platform. After receiving the equipment maintenance signal, the manager performs maintenance analysis on the components in the analysis object and screens out the components that need to be replaced, and marks the components that need to be replaced as the processing object. After the processing object is replaced, the comprehensive data group is used as the fault diagnosis basis of the analysis object; if the coincidence coefficient CH is greater than the coincidence threshold CHmin, it is determined that the equipment operation stage of the analysis object in the statistical period meets the overall characteristics, and the comprehensive data group is used as the fault diagnosis basis of the analysis object in the next statistical period; whether the equipment operation stage of the analysis object meets the overall characteristics is determined, and the fault diagnosis basis of the analysis object in the next statistical period is marked according to the determination result, so that the equipment maintenance is carried out in time while ensuring the accuracy of the fault diagnosis result.

[0021] The diagnosis optimization module is used to perform equipment maintenance optimization analysis on the site power supply: mark the processing object marking process within the latest L1 statistical cycles as a maintenance process, obtain the overlap coefficient CH of the analysis object corresponding to the maintenance process, and form an overlap range with a value of zero and an overlap threshold value CHmin. The overlap range is divided into several overlap intervals, and the maintenance process with the overlap coefficient CH within the overlap interval is marked as a matching process of the overlap interval. The number of times the same processing object is marked in all matching processes within the overlap interval is marked as the priority value of the processing object relative to the overlap interval, and the L2 processing objects with the largest priority values ​​are marked as priority screening objects of the overlap interval. L1 and L2 are both numerical constants, and the specific values ​​of L1 and L2 are set by the management personnel themselves; the priority screening objects of the overlap interval constitute a priority maintenance set of the overlap interval, and the priority maintenance sets of all overlap intervals are sent to the database for storage; the overlap interval and the priority maintenance set are generated according to the overlap coefficient and the processing object marking result during component maintenance, so that the priority screening objects can be extracted according to the overlap coefficient during subsequent equipment maintenance, thereby improving the equipment maintenance efficiency.

[0022] Embodiment 2: Figure 2 As shown, the data-driven site power supply abnormal status analysis method includes the following steps: Step 1: Perform statistical analysis on the site power failure: Generate a statistical cycle, mark the site power connected to the abnormal analysis platform as the analysis object, and obtain the comprehensive data group and the failure data group of the analysis object at the end of the statistical cycle; Step 2: Analyze the equipment status of the site power supply: compare the fault data groups of all analyzed objects with the comprehensive data group one by one and obtain the coincidence coefficient CH of the analyzed object within the statistical period; Step 3: Evaluate the equipment operation stage of the site power supply: Use the coincidence coefficient CH to determine whether the equipment operation stage of the analysis object within the statistical period meets the overall characteristics; Step 4: Perform equipment maintenance optimization analysis on the site power supply: mark the processing object marking process within the latest L1 statistical cycles as a maintenance process, obtain the overlap coefficient CH of the analysis object corresponding to the maintenance process, and form an overlap range consisting of a value of zero and the overlap threshold CHmin. Divide the overlap range into several overlap intervals, and mark the priority maintenance set of the overlap interval.

[0023] The data-driven site power supply abnormal status analysis method and system generate a statistical cycle when working, mark the site power supply connected to the abnormal analysis platform as the analysis object, obtain the comprehensive data group and the fault data group of the analysis object at the end of the statistical cycle; compare the fault data groups of all analysis objects with the comprehensive data group one by one and obtain the overlap coefficient CH of the analysis object within the statistical cycle; determine whether the equipment operation stage of the analysis object within the statistical cycle meets the overall characteristics through the overlap coefficient CH; mark the processing object marking process within the latest L1 statistical cycles as a maintenance process, obtain the overlap coefficient CH of the maintenance process corresponding to the analysis object, and form an overlap range with a value of zero and an overlap threshold CHmin, divide the overlap range into several overlap intervals, and mark the priority maintenance set of the overlap interval.

[0024] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0025] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the real value. The coefficients in the formula are set by technicians in this field according to the actual situation; for example: formula CH=k1×ZC+k2×CC; technicians in this field collect multiple groups of sample data and set corresponding coincidence coefficients for each group of sample data; substitute the set coincidence coefficients and the collected sample data into the formula, any two formulas constitute a set of two-variable linear equations, screen the calculated coefficients and take the average, and obtain the values ​​of k1 and k2 as 3.74, 2.97 and 2.65 respectively; The size of the coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the initial setting of the corresponding overlap coefficient for each set of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value, such as the overlap coefficient is proportional to the value of the state overlap data.

[0026] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0027] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A data-driven site power supply abnormality status analysis system, characterized in that: It includes an abnormality analysis platform, which is communicatively connected with a fault statistics module, a state analysis module, a state evaluation module, a diagnosis optimization module and a database; The fault statistics module is used to perform statistical analysis on the faults of the site power supply: generate a statistical cycle, mark the site power supply connected to the abnormal analysis platform as an analysis object, and obtain a comprehensive data group and a fault data group of the analysis object at the end of the statistical cycle; The state analysis module is used to analyze the equipment state of the site power supply: all fault data groups of the analysis objects are compared with the comprehensive data group one by one and the coincidence coefficient CH of the analysis object is obtained; The state evaluation module is used to evaluate the equipment operation stage of the site power supply: obtain the coincidence threshold CHmin through the database, compare the coincidence coefficient CH of the analysis object within the statistical period with the coincidence threshold CHmin, and determine whether the equipment operation stage of the analysis object meets the overall characteristics through the comparison result; The diagnostic optimization module is used to perform equipment maintenance optimization analysis on the site power supply.

2. The data-driven site power supply abnormal status analysis system according to claim 1, characterized in that: The fault data group includes several fault types, each fault type corresponds to a state sequence, and the state sequence includes several fault states. When a fault occurs in the analysis object, the fault state is marked according to the fault type, and the fault states are arranged in order of the number of markings from large to small to obtain the state sequence; each fault state corresponds to a processing sequence, and the processing sequence includes several processing measures. The processing efficiency of the processing measures after the fault state marking of the analysis object is obtained, the processing efficiency of the fault processing using the same processing measure for the same fault state is summed and averaged to obtain the efficiency performance value, and the processing measures are arranged in order of the efficiency performance value from large to small to obtain the processing sequence; at the end of the statistical period, a comprehensive data group is obtained, and the statistical method of the comprehensive data group is the same as that of the fault data group, but the statistical object of the comprehensive data group is all analysis objects.

3. The data-driven site power supply abnormal status analysis system according to claim 2, characterized in that: The specific process of comparing the fault data group of the analysis object with the comprehensive data group includes: taking the state sequence of the comprehensive data group under the same fault type as the state reference sequence, taking the state sequence in the fault data group as the state comparison sequence, if the fault state corresponding to the same sequence number in the state reference sequence is the same as that in the state comparison sequence, then the corresponding sequence number is marked as the state coincidence sequence number; otherwise, the corresponding sequence number is marked as the state deviation sequence number, and the ratio of the number of state coincidence sequence numbers to the number of elements in the state reference sequence is marked as the state coincidence value of the fault type; taking the processing sequence of the comprehensive data group under the same fault state as the processing reference sequence, taking the processing sequence of the fault data group as the processing comparison sequence, if the processing measures corresponding to the same sequence number in the processing reference sequence and the processing comparison sequence are the same, then the corresponding sequence number is marked as the processing coincidence sequence number; otherwise, the corresponding sequence number is marked as the processing deviation sequence number; and the ratio of the number of processing coincidence sequence numbers to the number of elements in the processing reference sequence is marked as the processing coincidence value of the fault state.

4. The data-driven site power supply abnormal status analysis system according to claim 3, characterized in that: The process of obtaining the overlap coefficient CH of the analysis object includes: calculating the average value of the state overlap values ​​of all fault types in the fault data group and marking it as the state overlap data ZC of the analysis object, calculating the average value of the processing overlap values ​​of all fault states in the fault data group and marking it as the processing overlap data CC of the analysis object; performing numerical calculations on the state overlap data ZC and the processing overlap data CC to obtain the overlap coefficient CH of the analysis object within the statistical period.

5. The data-driven site power supply abnormal status analysis system according to claim 4, characterized in that: The specific process of comparing the coincidence coefficient CH of the analysis object within the statistical period with the coincidence threshold CHmin includes: if the coincidence coefficient CH is less than or equal to the coincidence threshold CHmin, it is determined that the equipment operation stage of the analysis object within the statistical period does not meet the overall characteristics, and the fault data group is used as the fault diagnosis basis for the analysis object in the next statistical period. At the same time, an equipment maintenance signal is generated and sent to the mobile phone terminal of the manager through the abnormal analysis platform. After receiving the equipment maintenance signal, the manager performs maintenance analysis on the components in the analysis object and screens out the components that need to be replaced, and marks the components that need to be replaced as the processing object. After the replacement of the processing object is completed, the comprehensive data group is used as the fault diagnosis basis for the analysis object; if the coincidence coefficient CH is greater than the coincidence threshold CHmin, it is determined that the equipment operation stage of the analysis object within the statistical period meets the overall characteristics, and the comprehensive data group is used as the fault diagnosis basis for the analysis object in the next statistical period.

6. The data-driven site power supply abnormal status analysis system according to claim 5, characterized in that: The specific process of the diagnostic optimization module performing equipment maintenance optimization analysis on the site power supply includes: marking the processing object marking process within the latest L1 statistical cycles as a maintenance process, obtaining the overlap coefficient CH of the analysis object corresponding to the maintenance process, forming an overlap range by the value zero and the overlap threshold CHmin, dividing the overlap range into several overlap intervals, marking the maintenance process with the overlap coefficient CH within the overlap interval as a matching process of the overlap interval, marking the number of times the same processing object is marked in all matching processes in the overlap interval as the priority value of the processing object relative to the overlap interval, marking the L2 processing objects with the largest priority values ​​as priority screening objects of the overlap interval, forming a priority maintenance set of the overlap interval by the priority screening objects of the overlap interval, and sending all priority maintenance sets of the overlap interval to the database for storage.

7. A data-driven site power supply abnormality status analysis method, characterized in that: The following steps are involved: Step 1: Perform statistical analysis on the site power failure: Generate a statistical cycle, mark the site power connected to the abnormal analysis platform as the analysis object, and obtain the comprehensive data group and the failure data group of the analysis object at the end of the statistical cycle; Step 2: Analyze the equipment status of the site power supply: compare the fault data groups of all analyzed objects with the comprehensive data group one by one and obtain the coincidence coefficient CH of the analyzed object within the statistical period; Step 3: Evaluate the equipment operation stage of the site power supply: Use the coincidence coefficient CH to determine whether the equipment operation stage of the analysis object within the statistical period meets the overall characteristics; Step 4: Perform equipment maintenance optimization analysis on the site power supply: mark the processing object marking process within the latest L1 statistical cycles as a maintenance process, obtain the overlap coefficient CH of the analysis object corresponding to the maintenance process, and form an overlap range consisting of a value of zero and the overlap threshold CHmin. Divide the overlap range into several overlap intervals, and mark the priority maintenance set of the overlap interval.

Images