A control cabinet intelligent control system and method based on data analysis

Abstract

The present invention discloses an intelligent control system and method for a control cabinet based on data analysis, and relates to the technical field of scheme formulation. The present invention compares and analyzes equipment data and function data of a control cabinet to generate different function blocks; classifies the abnormalities of the control cabinet; extracts the induced characteristics and abnormal elements of each abnormality to construct an abnormality database; matches the function blocks in a maintenance scheme with the induced characteristics in the abnormality database; matches the maintenance factors of each function block in the maintenance data of different types of abnormalities with the abnormal elements to finally generate a maintenance database; calculates the abnormality limit of the control cabinet using common characteristics; determines the type of abnormality and selects a maintenance scheme; and when it is determined that the abnormality occurring in real time does not exist in the abnormality database as a new abnormality, combines the maintenance function blocks and the maintenance factors to generate a maintenance scheme for the new abnormality.

Description

Technical Field

[0001] The present invention relates to the technical field of solution formulation, and in particular to an intelligent control system and method for a control cabinet based on data analysis. Background Art

[0002] The control cabinet is the core component of the industrial automation system, which is used to centrally control and manage the operation of various electrical equipment. It includes power distribution equipment, control equipment, protection devices, monitoring devices, etc., and is the key to ensuring the safe and efficient operation of industrial equipment. With the improvement of industrial automation, the complexity of the control cabinet is also increasing. Once a fault or abnormality occurs, it may have a serious impact on production and safety. Early control cabinet maintenance mainly relied on regular inspections and passive repairs; with the expansion of production scale and the increase in equipment reliability requirements, traditional maintenance methods have been difficult to meet the needs of modern industry. For this reason, intelligent maintenance technology came into being. Through real-time monitoring and data analysis, it can predict faults in advance, optimize maintenance plans, and reduce downtime and maintenance costs; however, due to the development of modernization, the technical principles contained in the control cabinet are more complicated. When the control cabinet is abnormal, professional technicians are required to perform maintenance, which undoubtedly greatly increases the maintenance cost of the control cabinet; therefore, it is crucial to enable ordinary staff to maintain the control cabinet abnormalities. Summary of the invention

[0003] The object of the present invention is to provide an intelligent control system and method for a control cabinet based on data analysis to solve the problems raised in the prior art.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A control cabinet intelligent control method based on data analysis, the method comprising the following steps:

[0006] S100, collecting equipment data and function data of the control cabinet in historical work, comparing and analyzing the equipment data and function data of the control cabinet, dividing the control cabinet into blocks according to different functions of the control cabinet, and generating different function blocks;

[0007] Furthermore, the specific steps of dividing the control cabinet into blocks according to the different functions of the control cabinet are as follows:

[0008] S101, collect the equipment data of the control cabinet in the historical work as {S1, S2, S3, ..., S n}, S1, S2, S3, ..., S n Indicates the collected equipment data of the control cabinet at the 1st, 2nd, 3rd, ..., nth position in the historical work, where n is a positive integer; the collected function data of the control cabinet in the historical work is {G1, G2, G3, ..., Gm}, G1, G2, G3, ..., G m Indicates collecting the 1st, 2nd, 3rd, ..., mth function data of the control cabinet in historical work, where m is a positive integer;

[0009] S102, extract the device data that changes when each functional data changes in the history, and construct the accompanying device data set {Sb1, Sb2, Sb3, ..., Sb k}, Sb1, Sb2, Sb3,..., Sb k Indicates that when the function data changes, the 1st, 2nd, 3rd, ..., kth device data changes, where k is a positive integer; extract the changed device data when m types of function data change, and obtain m accompanying device data sets; compare and analyze the m accompanying data sets, and count the number of times each device data appears in the m accompanying device data sets as P, and assume that the number of times each device data appears is {P1, P2, P3, ..., P n}, P1, P2, P3, ..., P n Indicates the number of occurrences of the 1st, 2nd, 3rd, ..., nth device data in the accompanying data set;

[0010] S103. When P=m, the corresponding device data is judged to be shared device data, and the area where the shared device data is located is the shared functional area; when P=1, the device data is judged to be the control data of the functional data corresponding to the accompanying device data set, and the area where the control data is located is used as the functional block of the corresponding functional data; when m>P>1, the device data is judged to be multi-control data, and the area where the multi-control data is located is used as the collaborative functional block corresponding to multiple functions; after judging the device data at each location in the control cabinet, the control cabinet is divided into different functional blocks.

[0011] By dividing the control cabinet into blocks using the functional data and equipment data of the control cabinet during its operation in history, the control cabinet can clearly indicate the functional roles of different blocks. When analyzing and testing the different functions of the control cabinet, the corresponding functional blocks can be accurately tested, greatly improving the work efficiency of the system.

[0012] S200, collecting equipment data when abnormalities occurred in the control cabinet in history, and classifying the abnormalities of the control cabinet using the equipment data when the abnormalities occurred; analyzing each abnormality after classification, extracting the induced characteristics and abnormal elements of each abnormality, and constructing an abnormality database using the induced characteristics and abnormal elements of each abnormality;

[0013] Furthermore, the specific steps of constructing an anomaly database using the inducing features and abnormal elements of each anomaly are as follows:

[0014] S201, collect all the equipment data before and after each abnormality of the control cabinet in history, calculate the difference of all the equipment data before and after each abnormality in history as Sc, judge the calculated difference of each equipment data, when Sc>0, the corresponding equipment data is the abnormal element Sy of each abnormality; after judgment, the abnormal elements of each abnormality in history are {Sy1, Sy2, Sy3, ..., Sy j},Sy1,Sy2,Sy3,...,Sy j represents the 1st, 2nd, 3rd, ..., jth abnormal element of each abnormality judged, where j is a positive integer;

[0015] S202, collect the function data before and after each abnormality of the control cabinet in history, calculate the difference of all function data before and after each abnormality in history as Gc, compare the calculated difference of each function data, and select the maximum value Gc among all function data max As the individual feature Td of each anomaly in history, after calculation and judgment, the individual feature of each anomaly in history is {Td1, Td2, Td3, ..., Td p}, Td1, Td2, Td3,..., Td p It means that the individual features of the 1st, 2nd, 3rd, ..., pth abnormalities in the history are calculated, and p is a positive integer; the individual features of each abnormality are compared, and the ones with the same individual features are classified into the same abnormality type. After judgment, all abnormalities of the control cabinet are classified into {Ab1, Ab2, Ab3, ..., Ab g},Ab1,Ab2,Ab3,...,Ab g Indicates the 1st, 2nd, 3rd, ..., gth abnormality of the control cabinet after classification, where g is a positive integer;

[0016] S203, collect the mutation time of all abnormal elements when each abnormality occurs in the history {Bt1, Bt2, Bt3, ..., Bt j}, Bt1, Bt2, Bt3,..., Bt j Indicates the mutation time of the 1st, 2nd, 3rd, ..., jth abnormal element when each abnormality occurs in history. The mutation time of j abnormal elements is compared, and the abnormal element that mutates earliest is selected as the induced feature Ty of the corresponding type of abnormality; the induced feature of each abnormality is determined to be {Ty1, Ty2, Ty3, ..., Ty g},Ty1,Ty2,Ty3,...,Ty g Indicates the induced characteristics of the 1st, 2nd, 3rd, ..., gth abnormal categories judged;

[0017] S204: using the classified abnormal types of the control cabinet, and combining the inducing characteristics and abnormal elements of each abnormality, construct an abnormality database.

[0018] Analyze the abnormal data in history, classify the abnormalities, find the inducing characteristics and abnormal elements of each abnormality, and analyze the abnormalities when they occur; judge the cause of the abnormality based on the inducing characteristics, and determine the degree of the abnormality using the abnormal elements, making the analysis of the abnormality more accurate;

[0019] S300, collecting the maintenance data of professionals performing maintenance when each abnormality occurs in the control cabinet in history, determining the functional blocks processed in each abnormal maintenance plan, and matching the functional blocks in the maintenance plan with the induced features in the abnormality database; analyzing the collected maintenance data, extracting the maintenance factor for each functional block in the maintenance data, matching the maintenance factor of each functional block in the maintenance data of different types of abnormalities with the abnormal elements, and finally generating a maintenance database;

[0020] Furthermore, the specific steps for generating and maintaining the database are:

[0021] S301, collect the maintenance data of professionals performing maintenance when each abnormality occurs in the control cabinet in history, extract the equipment data that changes when the control cabinet is maintained using the maintenance data, and correspond in the functional blocks of the control cabinet in S100 according to the changed equipment data, and find the functional blocks of each collected maintenance data as {Q1, Q2, Q3, ..., Q h},

[0022] Q1, Q2, Q3, ..., Q h represents the 1st, 2nd, 3rd, ..., hth functional blocks in the maintenance data, where h is a positive integer; collects the induced features of the abnormality corresponding to each maintenance data, compares the functional blocks of r abnormal maintenance data with the same induced features, calculates the number of occurrences of each functional block in the r abnormal maintenance data with the same induced features, matches the functional block with the largest number of occurrences with the induced features of the corresponding type to form a block matching pair (Q, Ty);

[0023] S302, collect the maintenance data of the professional personnel performing maintenance when each abnormality of the control cabinet occurs in the history, and the maintenance factor of each functional block is {Wz1, Wz2, Wz3, ..., Wz f}, Wz1, Wz2, Wz3,..., Wz f represents the 1st, 2nd, 3rd, ..., fth maintenance factor in each functional block in the maintenance data, where f is a positive integer; the change amount of the abnormal element when each abnormality occurs is {Syb1, Syb2, Syb3, ..., Syb j},Syb1,Syb2,Syb3,...,Syb j Indicates the change amount of the 1st, 2nd, 3rd, ..., jth abnormal element when each abnormality occurs in the history, matches the change amount of each abnormal element with the maintenance factor in the maintenance data, and when Syb = Wz, it is judged that the maintenance factor and the abnormal element match successfully, and when Syb ≠ Wz, it is judged that the maintenance factor and the abnormal element match failed; all abnormal elements and maintenance factors are matched to obtain element matching pairs (Szh, Wz);

[0024] S303: construct a maintenance database using the matched block matching pairs, element matching pairs and maintenance data of each anomaly.

[0025] Analyze the maintenance data of different anomalies in history and build a maintenance database. Find the functional blocks and maintenance factors of the maintenance data to further analyze the maintenance skills of professionals for anomalies. After matching with the abnormal elements and induced characteristics in the abnormal database, a deeper maintenance analysis is achieved. After the maintenance data is refined, it is convenient for staff to learn and make the maintenance of anomalies more convenient.

[0026] S400, analyzing all types of abnormal data in the abnormal database, extracting common features of all types of abnormalities, and calculating abnormal limit values ​​of the control cabinet using the common features;

[0027] Furthermore, the specific steps of calculating the abnormal limit value of the control cabinet using the common characteristics are as follows:

[0028] S401, analyzing the abnormal elements calculated in S201, extracting the abnormal elements existing in each abnormality as the common feature Tg of all types of abnormalities; collecting the common feature values ​​of the control cabinet when the abnormality occurs in the history as {Tg1, Tg2, Tg3, ..., Tg q}, Tg1, Tg2, Tg3,..., Tg q Indicates the common characteristic value when the 1st, 2nd, 3rd, ..., qth abnormality of the control cabinet occurs in the history, where q is a positive integer;

[0029] S402. Calculate the abnormal limit of the control cabinet using the common characteristic values ​​of abnormalities in the collected history. The formula is: In the formula, In represents the abnormal limit of the control cabinet, Tg max Indicates the maximum value of the common characteristics when anomalies occur in the collected history, Tg min Indicates the minimum value of the common characteristics when anomalies occur in history, |Tg-Tg x Represents the difference between adjacent common features in the collected history.

[0030] S500, collect common features of the control cabinet in real time, use the abnormal limit to determine whether the control cabinet is abnormal, extract the abnormal elements and determine the abnormal type according to the abnormal database, and select a maintenance plan;

[0031] Furthermore, the specific steps for selecting a maintenance plan are:

[0032] S501, collect the common characteristics of the control cabinet in real time as Tgs, and use the abnormal limit value of the control cabinet to judge the real-time common characteristics. When Tgs≥In, it is judged that the control cabinet in real-time operation has an abnormality; when Tgs<In, it is judged that the control cabinet in real-time operation has no abnormality; the abnormal situation of the control cabinet is automatically monitored to avoid failure to discover the abnormality in time after it occurs, causing greater losses and dangers;

[0033] S502. When it is determined that an abnormality occurs in a control cabinet during real-time operation, extract individual features of the real-time abnormality and make a judgment among all types of abnormalities in the abnormality database. After the individual features of the real-time abnormality are found in the abnormality database, select the corresponding maintenance data in the maintenance database as a maintenance plan for the real-time abnormality, and process and maintain the real-time abnormality of the control cabinet.

[0034] S600. When it is determined that the real-time exception does not exist in the exception database and is a new exception, the maintenance function block is determined using the inducing characteristics in the real-time exception, and the maintenance factor of each abnormal function block is determined using the abnormal elements of the real-time exception. The maintenance function block and the maintenance factor are combined to generate a maintenance plan for the new exception.

[0035] Furthermore, the specific steps of combining the maintenance function block and the maintenance factor to generate a maintenance plan for the new abnormality are as follows:

[0036] S601. When the same single feature is not found in the abnormality database using the single feature of the real-time abnormality, the real-time abnormality is judged to be a new abnormality; the induced feature and abnormal element of the new abnormality are extracted; the block matching pair is searched in the maintenance database using the induced feature of the new abnormality, and when the same induced feature is found in all the block matching pairs, the functional block in the corresponding block matching pair is selected as the maintenance block of the new abnormality;

[0037] S602, using the abnormal element of the new abnormality to search for element matching pairs in the maintenance database, when the same abnormal element is found in the element matching pairs, selecting the maintenance factor in the corresponding element matching pair as the maintenance amount of each abnormal element in the new abnormality;

[0038] S603: formulate a maintenance plan based on the maintenance block of the new anomaly and the maintenance amount of each abnormal element found in the maintenance database, and perform maintenance processing on the new anomaly.

[0039] When a new abnormality that has not occurred in the history of the control cabinet occurs, the new abnormality can be analyzed in detail. After using the induced characteristics and abnormal elements to determine the cause and extent of the new abnormality, a maintenance plan can be formulated based on the new abnormality using the functional blocks and maintenance factors in the maintenance database, thereby realizing automated processing of control cabinet abnormalities and reducing the cost of control cabinet abnormal maintenance. The system can automatically adjust the details of the maintenance plan based on different abnormal characteristics.

[0040] A control cabinet intelligent control system based on data analysis, the control cabinet intelligent control system includes a data collection module, a function block module, an abnormality analysis module, a maintenance analysis module, a matching module, an abnormality judgment module and a plan formulation module;

[0041] The data collection module is used to collect equipment data, function data and maintenance data when abnormalities occur in the control cabinet in the past;

[0042] The functional block module is used to process the control cabinet according to different functional data to obtain different functional blocks;

[0043] The abnormality analysis module is used to analyze the device data when abnormalities occurred in the control cabinet history, classify the abnormalities and obtain the abnormal elements and induced characteristics of each abnormality, and build an abnormality database;

[0044] The maintenance analysis module is used to analyze the maintenance data of the control cabinet when abnormalities occurred in the history, find out the functional blocks and maintenance factors when performing maintenance for each abnormality, and build a maintenance database;

[0045] The matching module is used to match the abnormal elements in the abnormal database with the maintenance factors in the maintenance database, and to match the induced features in the abnormal database with the functional blocks in the maintenance database;

[0046] The abnormality judgment module is used to find the common characteristics of all abnormalities, calculate the abnormality limit of the control cabinet using the common characteristics when the abnormalities occurred in the history, and judge the abnormality of the real-time control cabinet;

[0047] The plan formulation module is used to determine the type of abnormality occurring in real time, select maintenance data as a maintenance plan, and formulate a corresponding maintenance plan when it is a new abnormality.

[0048] The abnormality judgment module includes an abnormality limit calculation unit and an abnormality judgment unit;

[0049] The abnormal limit value calculation unit is used to calculate the abnormal limit value of the control cabinet by using the common characteristics when the abnormality occurs in the history;

[0050] The abnormality judgment unit is used to collect common characteristics of the control cabinet in real time, and use the abnormality limit value to judge whether an abnormality occurs in the control cabinet.

[0051] The plan formulation module includes an abnormality type determination unit and a plan formulation unit;

[0052] The abnormality type determination unit is used to extract a separate feature of the real-time abnormality and search it in the abnormality database to determine the type of the real-time abnormality. When the abnormality type is not found in the abnormality database, the real-time abnormality is determined to be a new abnormality;

[0053] The plan formulation unit is used to select corresponding maintenance data in the maintenance database as a maintenance plan when determining the type of abnormality; when judging it as a new abnormality, formulate a maintenance plan for the new abnormality using the matching pair in the maintenance database.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] 1. The present invention conducts detailed analysis on the abnormalities occurring in the control cabinet, classifies the abnormalities and searches for the inducing characteristics and abnormal elements of each abnormality, so as to determine the cause and extent of the abnormality, enable the staff to handle the abnormality more accurately, and increase the efficiency of abnormal maintenance.

[0056] 2. The present invention collects and analyzes the maintenance data of professionals in history, and decomposes and searches for functional blocks and maintenance factors after detailed analysis. When an abnormality occurs in the control cabinet in real time, the system automatically formulates a maintenance plan according to the type of abnormality. The staff only needs to handle the abnormality according to the maintenance plan, and no professional personnel are required to perform maintenance, which greatly reduces the maintenance cost of the control cabinet. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A module distribution diagram of an intelligent control system of a control cabinet based on data analysis according to the present invention;

[0058] Figure 2 The present invention is a structural schematic diagram of an intelligent control method for a control cabinet based on data analysis. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not 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.

[0060] Example: Figure 1-Figure 2 As shown, the present invention provides a technical solution.

[0061] A control cabinet intelligent control method based on data analysis, the method comprising the following steps:

[0062] S100, collecting equipment data and function data of the control cabinet in historical work, comparing and analyzing the equipment data and function data of the control cabinet, dividing the control cabinet into blocks according to different functions of the control cabinet, and generating different function blocks;

[0063] The specific steps for dividing the control cabinet into blocks according to its different functions are as follows:

[0064] S101, collect the equipment data of the control cabinet in the historical work as {S1, S2, S3, ..., S n}, S1, S2, S3, ..., S n Indicates the collected equipment data of the control cabinet at the 1st, 2nd, 3rd, ..., nth position in the historical work, where n is a positive integer; the collected function data of the control cabinet in the historical work is {G1, G2, G3, ..., G m}, G1, G2, G3, ..., G m Indicates collecting the 1st, 2nd, 3rd, ..., mth function data of the control cabinet in historical work, where m is a positive integer;

[0065] S102, extract the device data that changes when each functional data changes in the history, and construct the accompanying device data set {Sb1, Sb2, Sb3, ..., Sb k}, Sb1, Sb2, Sb3,..., Sb k Indicates that when the function data changes, the 1st, 2nd, 3rd, ..., kth device data changes, where k is a positive integer; extract the changed device data when m types of function data change, and obtain m accompanying device data sets; compare and analyze the m accompanying data sets, and count the number of times each device data appears in the m accompanying device data sets as P, and assume that the number of times each device data appears is {P1, P2, P3, ..., P n}, P1, P2, P3, ..., P n Indicates the number of occurrences of the 1st, 2nd, 3rd, ..., nth device data in the accompanying data set;

[0066] S103. When P=m, the corresponding device data is judged to be shared device data, and the area where the shared device data is located is the shared functional area; when P=1, the device data is judged to be the control data of the functional data corresponding to the accompanying device data set, and the area where the control data is located is used as the functional block of the corresponding functional data; when m>P>1, the device data is judged to be multi-control data, and the area where the multi-control data is located is used as the collaborative functional block corresponding to multiple functions; after judging the device data at each location in the control cabinet, the control cabinet is divided into different functional blocks.

[0067] By dividing the control cabinet into blocks using the functional data and equipment data of the control cabinet during its operation in history, the control cabinet can clearly indicate the functional roles of different blocks. When analyzing and testing the different functions of the control cabinet, the corresponding functional blocks can be accurately tested, greatly improving the work efficiency of the system.

[0068] The control cabinet at a certain location is divided into blocks. The functional data include power distribution, protection monitoring and environmental control. The equipment data of the control cabinet include power transmission, monitoring data, sensor data and power supply data. By analyzing the equipment data of the control cabinet, it is calculated that the number of occurrences of the equipment data is 1, 1, 1 and 3 respectively. The control blocks of different functions of the control cabinet are determined to be power distribution-power transmission area, protection monitoring-monitoring data, sensor data-environmental control, and the power supply area is found to be a common block.

[0069] S200, collecting equipment data when abnormalities occurred in the control cabinet in history, and classifying the abnormalities of the control cabinet using the equipment data when the abnormalities occurred; analyzing each abnormality after classification, extracting the induced characteristics and abnormal elements of each abnormality, and constructing an abnormality database using the induced characteristics and abnormal elements of each abnormality;

[0070] The specific steps of constructing anomaly database using the inducing features and abnormal elements of each anomaly are as follows:

[0071] S201, collect all the equipment data before and after each abnormality of the control cabinet in history, calculate the difference of all the equipment data before and after each abnormality in history as Sc, judge the calculated difference of each equipment data, when Sc>0, the corresponding equipment data is the abnormal element Sy of each abnormality; after judgment, the abnormal elements of each abnormality in history are {Sy1, Sy2, Sy3, ..., Sy j},Sy1,Sy2,Sy3,...,Sy j represents the 1st, 2nd, 3rd, ..., jth abnormal element of each abnormality judged, where j is a positive integer;

[0072] S202, collect the function data before and after each abnormality of the control cabinet in history, calculate the difference of all function data before and after each abnormality in history as Gc, compare the calculated difference of each function data, and select the maximum value Gc among all function data max As the individual feature Td of each anomaly in history, after calculation and judgment, the individual feature of each anomaly in history is {Td1, Td2, Td3, ..., Td p}, Td1, Td2, Td3,..., Td p It means that the individual features of the 1st, 2nd, 3rd, ..., pth abnormalities in the history are calculated, and p is a positive integer; the individual features of each abnormality are compared, and the ones with the same individual features are classified into the same abnormality type. After judgment, all abnormalities of the control cabinet are classified into {Ab1, Ab2, Ab3, ..., Ab g},Ab1,Ab2,Ab3,...,Ab g Indicates the 1st, 2nd, 3rd, ..., gth abnormality of the control cabinet after classification, where g is a positive integer;

[0073] S203, collect the mutation time of all abnormal elements when each abnormality occurs in the history {Bt1, Bt2, Bt3, ..., Bt j}, Bt1, Bt2, Bt3,..., Bt j Indicates the mutation time of the 1st, 2nd, 3rd, ..., jth abnormal element when each abnormality occurs in history. The mutation time of j abnormal elements is compared, and the abnormal element that mutates earliest is selected as the induced feature Ty of the corresponding type of abnormality; the induced feature of each abnormality is determined to be {Ty1, Ty2, Ty3, ..., Ty g},Ty1,Ty2,Ty3,...,Ty g Indicates the induced characteristics of the 1st, 2nd, 3rd, ..., gth abnormal categories judged;

[0074] S204: using the classified abnormal types of the control cabinet, and combining the inducing characteristics and abnormal elements of each abnormality, construct an abnormality database.

[0075] Analyze the abnormal data in history, classify the abnormalities, find the inducing characteristics and abnormal elements of each abnormality, and analyze the abnormalities when they occur; judge the cause of the abnormality based on the inducing characteristics, and determine the degree of the abnormality using the abnormal elements, making the analysis of the abnormality more accurate;

[0076] S300, collecting the maintenance data of professionals performing maintenance when each abnormality occurs in the control cabinet in history, determining the functional blocks processed in each abnormal maintenance plan, and matching the functional blocks in the maintenance plan with the induced features in the abnormality database; analyzing the collected maintenance data, extracting the maintenance factor for each functional block in the maintenance data, matching the maintenance factor of each functional block in the maintenance data of different types of abnormalities with the abnormal elements, and finally generating a maintenance database;

[0077] The specific steps to generate a maintenance database are:

[0078] S301, collect the maintenance data of professionals performing maintenance when each abnormality occurs in the control cabinet in history, extract the equipment data that changes when the control cabinet is maintained using the maintenance data, and correspond in the functional blocks of the control cabinet in S100 according to the changed equipment data, and find the functional blocks of each collected maintenance data as {Q1, Q2, Q3, ..., Q h},

[0079] Q1, Q2, Q3, ..., Q h represents the 1st, 2nd, 3rd, ..., hth functional blocks in the maintenance data, where h is a positive integer; collects the induced features of the abnormality corresponding to each maintenance data, compares the functional blocks of r abnormal maintenance data with the same induced features, calculates the number of occurrences of each functional block in the r abnormal maintenance data with the same induced features, matches the functional block with the largest number of occurrences with the induced features of the corresponding type to form a block matching pair (Q, Ty);

[0080] S302, collect the maintenance data of the professional personnel performing maintenance when each abnormality of the control cabinet occurs in the history, and the maintenance factor of each functional block is {Wz1, Wz2, Wz3, ..., Wz f}, Wz1, Wz2, Wz3,..., Wz f represents the 1st, 2nd, 3rd, ..., fth maintenance factor in each functional block in the maintenance data, where f is a positive integer; the change amount of the abnormal element when each abnormality occurs is {Syb1, Syb2, Syb3, ..., Syb j},Syb1,Syb2,Syb3,...,Syb j Indicates the change amount of the 1st, 2nd, 3rd, ..., jth abnormal element when each abnormality occurs in the history, matches the change amount of each abnormal element with the maintenance factor in the maintenance data, and when Syb = Wz, it is judged that the maintenance factor and the abnormal element match successfully, and when Syb ≠ Wz, it is judged that the maintenance factor and the abnormal element match failed; all abnormal elements and maintenance factors are matched to obtain element matching pairs (Szh, Wz);

[0081] S303: construct a maintenance database using the matched block matching pairs, element matching pairs and maintenance data of each anomaly.

[0082] Analyze the maintenance data of different anomalies in history and build a maintenance database. Find the functional blocks and maintenance factors of the maintenance data to further analyze the maintenance skills of professionals for anomalies. After matching with the abnormal elements and induced characteristics in the abnormal database, a deeper maintenance analysis is achieved. After the maintenance data is refined, it is convenient for staff to learn and make the maintenance of anomalies more convenient.

[0083] For example, the types of anomalies in the anomaly database are environmental anomalies and electrical anomalies; the inducing characteristics of the corresponding environmental anomalies are external influences, and the abnormal elements are humidity and temperature; the inducing characteristics of electrical anomalies are workloads, and the abnormal elements are short circuits and weak currents; find the functional blocks and maintenance factors in the historical maintenance data and match them, specifically external influence-environmental control blocks, workload-protection monitoring blocks; temperature-cooling, humidity-ventilation, short circuit-circuit analysis, weak current-pressurization;

[0084] S400, analyzing all types of abnormal data in the abnormal database, extracting common features of all types of abnormalities, and calculating abnormal limit values ​​of the control cabinet using the common features;

[0085] The specific steps for calculating the abnormal limit of the control cabinet using common characteristics are:

[0086] S401, analyzing the abnormal elements calculated in S201, extracting the abnormal elements existing in each abnormality as the common feature Tg of all types of abnormalities; collecting the common feature values ​​of the control cabinet when the abnormality occurs in the history as {Tg1, Tg2, Tg3, ..., Tg q}, Tg1, Tg2, Tg3,..., Tg q Indicates the common characteristic value when the 1st, 2nd, 3rd, ..., qth abnormality of the control cabinet occurs in the history, where q is a positive integer;

[0087] S402. Calculate the abnormal limit of the control cabinet using the common characteristic values ​​of abnormalities in the collected history. The formula is: In the formula, In represents the abnormal limit of the control cabinet, Tg max Indicates the maximum value of the common characteristics when anomalies occur in the collected history, Tg min Indicates the minimum value of the common characteristics when anomalies occur in history, |Tg-Tg x Represents the difference between adjacent common features in the collected history.

[0088] S500, collect common features of the control cabinet in real time, use the abnormal limit to determine whether the control cabinet is abnormal, extract the abnormal elements and determine the abnormal type according to the abnormal database, and select a maintenance plan;

[0089] The specific steps for selecting a maintenance plan are:

[0090] S501, collect the common characteristics of the control cabinet in real time as Tgs, and use the abnormal limit value of the control cabinet to judge the real-time common characteristics. When Tgs≥In, it is judged that the control cabinet in real-time operation has an abnormality; when Tgs<In, it is judged that the control cabinet in real-time operation has no abnormality; the abnormal situation of the control cabinet is automatically monitored to avoid failure to discover the abnormality in time after it occurs, causing greater losses and dangers;

[0091] S502. When it is determined that an abnormality occurs in a control cabinet during real-time operation, extract individual features of the real-time abnormality and make a judgment among all types of abnormalities in the abnormality database. After the individual features of the real-time abnormality are found in the abnormality database, select the corresponding maintenance data in the maintenance database as a maintenance plan for the real-time abnormality, and process and maintain the real-time abnormality of the control cabinet.

[0092] S600. When it is determined that the real-time exception does not exist in the exception database and is a new exception, the maintenance function block is determined using the inducing characteristics in the real-time exception, and the maintenance factor of each abnormal function block is determined using the abnormal elements of the real-time exception. The maintenance function block and the maintenance factor are combined to generate a maintenance plan for the new exception.

[0093] The specific steps to combine the maintenance function block and the maintenance factor to generate a maintenance plan for new anomalies are:

[0094] S601. When the same single feature is not found in the abnormality database using the single feature of the real-time abnormality, the real-time abnormality is judged to be a new abnormality; the induced feature and abnormal element of the new abnormality are extracted; the block matching pair is searched in the maintenance database using the induced feature of the new abnormality, and when the same induced feature is found in all the block matching pairs, the functional block in the corresponding block matching pair is selected as the maintenance block of the new abnormality;

[0095] S602, using the abnormal element of the new abnormality to search for element matching pairs in the maintenance database, when the same abnormal element is found in the element matching pairs, selecting the maintenance factor in the corresponding element matching pair as the maintenance amount of each abnormal element in the new abnormality;

[0096] S603: formulate a maintenance plan based on the maintenance block of the new anomaly and the maintenance amount of each abnormal element found in the maintenance database, and perform maintenance processing on the new anomaly.

[0097] When a new abnormality that has not occurred in the history of the control cabinet occurs, the new abnormality can be analyzed in detail. After using the induced characteristics and abnormal elements to determine the cause and extent of the new abnormality, a maintenance plan can be formulated based on the new abnormality using the functional blocks and maintenance factors in the maintenance database, thereby realizing automated processing of control cabinet abnormalities and reducing the cost of control cabinet abnormal maintenance. The system can automatically adjust the details of the maintenance plan based on different abnormal characteristics.

[0098] For example, when the real-time anomaly is a fire, the induced feature is extracted as external influence, and the abnormal element is temperature; the maintenance block is determined to be environmental control, and the maintenance factor is cooling; and a maintenance plan is formulated for the new anomaly.

[0099] A control cabinet intelligent control system based on data analysis, the control cabinet intelligent control system includes a data collection module, a function block module, an abnormality analysis module, a maintenance analysis module, a matching module, an abnormality judgment module and a plan formulation module;

[0100] The data collection module is used to collect equipment data, function data and maintenance data when abnormalities occur in the control cabinet in the past;

[0101] The functional block module is used to process the control cabinet according to different functional data to obtain different functional blocks;

[0102] The abnormality analysis module is used to analyze the device data when abnormalities occurred in the control cabinet history, classify the abnormalities and obtain the abnormal elements and induced characteristics of each abnormality, and build an abnormality database;

[0103] The maintenance analysis module is used to analyze the maintenance data of the control cabinet when abnormalities occurred in the history, find out the functional blocks and maintenance factors when performing maintenance for each abnormality, and build a maintenance database;

[0104] The matching module is used to match the abnormal elements in the abnormal database with the maintenance factors in the maintenance database, and to match the induced features in the abnormal database with the functional blocks in the maintenance database;

[0105] The abnormality judgment module is used to find the common characteristics of all abnormalities, calculate the abnormality limit of the control cabinet using the common characteristics when the abnormalities occurred in the history, and judge the abnormality of the real-time control cabinet;

[0106] The plan formulation module is used to determine the type of abnormality occurring in real time, select maintenance data as a maintenance plan, and formulate a corresponding maintenance plan when it is a new abnormality.

[0107] The abnormality judgment module includes an abnormality limit calculation unit and an abnormality judgment unit;

[0108] The abnormal limit value calculation unit is used to calculate the abnormal limit value of the control cabinet by using the common characteristics when the abnormality occurs in the history;

[0109] The abnormality judgment unit is used to collect common characteristics of the control cabinet in real time, and use the abnormality limit value to judge whether an abnormality occurs in the control cabinet.

[0110] The plan formulation module includes an abnormality type determination unit and a plan formulation unit;

[0111] The abnormality type determination unit is used to extract a separate feature of the real-time abnormality and search it in the abnormality database to determine the type of the real-time abnormality. When the abnormality type is not found in the abnormality database, the real-time abnormality is determined to be a new abnormality;

[0112] The plan formulation unit is used to select corresponding maintenance data in the maintenance database as a maintenance plan when determining the type of abnormality; when judging it as a new abnormality, formulate a maintenance plan for the new abnormality using the matching pair in the maintenance database.

[0113] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A control cabinet intelligent control method based on data analysis, characterized in that: The method comprises the following steps: S100, collecting equipment data and function data of the control cabinet in historical work, comparing and analyzing the equipment data and function data of the control cabinet, dividing the control cabinet into blocks according to different functions of the control cabinet, and generating different function blocks; S200, collecting equipment data when abnormalities occurred in the control cabinet in history, and classifying the abnormalities of the control cabinet using the equipment data when the abnormalities occurred; analyzing each abnormality after classification, extracting the induced characteristics and abnormal elements of each abnormality, and constructing an abnormality database using the induced characteristics and abnormal elements of each abnormality; S300, collecting the maintenance data of professionals performing maintenance when each abnormality occurs in the control cabinet in history, determining the functional blocks processed in each abnormal maintenance plan, and matching the functional blocks in the maintenance plan with the induced features in the abnormality database; analyzing the collected maintenance data, extracting the maintenance factor for each functional block in the maintenance data, matching the maintenance factor of each functional block in the maintenance data of different types of abnormalities with the abnormal elements, and finally generating a maintenance database; S400, analyzing all types of abnormal data in the abnormal database, extracting common features of all types of abnormalities, and calculating abnormal limit values ​​of the control cabinet using the common features; S500, collect common features of the control cabinet in real time, use the abnormal limit to determine whether the control cabinet is abnormal, extract the abnormal elements and determine the abnormal type according to the abnormal database, and select a maintenance plan; S600. When it is determined that the real-time exception does not exist in the exception types in the exception database, the real-time exception is treated as a new exception, the inducing characteristics in the new exception are used to determine the maintenance function block, the abnormal elements of the new exception are used to determine the maintenance factor of each abnormal function block, and the maintenance function block and the maintenance factor are combined to generate a maintenance plan for the new exception.

2. The intelligent control method of a control cabinet based on data analysis according to claim 1 is characterized in that: The specific steps of dividing the control cabinet into blocks according to the different functions of the control cabinet in S100 are: S101, collect the equipment data of the control cabinet in the historical work as {S1, S2, S3, ..., S n }, S1, S2, S3, ..., S n Indicates the collected equipment data of the control cabinet at the 1st, 2nd, 3rd, ..., nth position in the historical work, where n is a positive integer; Collect the function data of the control cabinet in the historical work as {G1, G2, G3, ..., G m }, G1, G2, G3, ..., G m Indicates collecting the 1st, 2nd, 3rd, ..., mth function data of the control cabinet in historical work, where m is a positive integer; S102, extract the device data that changes when each functional data changes in the history, and construct the accompanying device data set {Sb1, Sb2, Sb3, ..., Sb k }, Sb1, Sb2, Sb3,..., Sb k Indicates that when the function data changes, the 1st, 2nd, 3rd, ..., kth device data changes, where k is a positive integer; extract the changed device data when m types of function data change, and obtain m accompanying device data sets; compare and analyze the m accompanying data sets, and count the number of times each device data appears in the m accompanying device data sets as P, and assume that the number of times each device data appears is {P1, P2, P3, ..., P n }, P1, P2, P3, ..., P n Indicates the number of occurrences of the 1st, 2nd, 3rd, ..., nth device data in the accompanying data set; S103. When P=m, the corresponding device data is judged to be shared device data, and the area where the shared device data is located is the shared functional area; when P=1, the device data is judged to be the control data of the functional data corresponding to the accompanying device data set, and the area where the control data is located is used as the functional block of the corresponding functional data; when m>P>1, the device data is judged to be multi-control data, and the area where the multi-control data is located is used as the collaborative functional block corresponding to multiple functions; after judging the device data at each location in the control cabinet, the control cabinet is divided into different functional blocks.

3. The intelligent control method of a control cabinet based on data analysis according to claim 1 is characterized in that: The specific steps of constructing an abnormality database using the inducing features and abnormal elements of each abnormality in S200 are: S201, collecting all the equipment data before and after each abnormality of the control cabinet in history, calculating the difference of all the equipment data before and after each abnormality in history as Sc, judging the calculated difference of each type of equipment data, and when Sc>0, setting the corresponding equipment data as the abnormal element Sy of each abnormality; After judgment, the abnormal elements of each abnormality in the history are {Sy1, Sy2, Sy3, ..., Sy j },Sy1,Sy2,Sy3,...,Sy j represents the 1st, 2nd, 3rd, ..., jth abnormal element of each abnormality judged, where j is a positive integer; S202, collect the function data before and after each abnormality of the control cabinet in history, calculate the difference of all function data before and after each abnormality in history as Gc, compare the calculated difference of each function data, and select the maximum value Gc among all function data max As the individual feature Td of each anomaly in history, after calculation and judgment, the individual feature of each anomaly in history is {Td1, Td2, Td3, ..., Td p }, Td1, Td2, Td3,..., Td p It means that the individual features of the 1st, 2nd, 3rd, ..., pth abnormalities in the history are calculated, and p is a positive integer; the individual features of each abnormality are compared, and the ones with the same individual features are classified into the same abnormality type. After judgment, all abnormalities of the control cabinet are classified into {Ab1, Ab2, Ab3, ..., Ab g }, Ab1, Ab2, Ab3, ..., Ab g Indicates the 1st, 2nd, 3rd, ..., gth abnormality of the control cabinet after classification, where g is a positive integer; S203, collect the mutation time of all abnormal elements when each abnormality occurs in the history {Bt1, Bt2, Bt3, ..., Bt j }, Bt1, Bt2, Bt3,..., Bt j Indicates the mutation time of the 1st, 2nd, 3rd, ..., jth abnormal element when each abnormality occurs in history. The mutation time of j abnormal elements is compared, and the abnormal element that mutates earliest is selected as the induced feature Ty of the corresponding type of abnormality; the induced feature of each abnormality is determined to be {Ty1, Ty2, Ty3, ..., Ty g },Ty1,Ty2,Ty3,...,Ty g Indicates the induced characteristics of the 1st, 2nd, 3rd, ..., gth abnormal categories judged; S204: using the classified abnormal types of the control cabinet, and combining the inducing characteristics and abnormal elements of each abnormality, construct an abnormality database.

4. The intelligent control method of a control cabinet based on data analysis according to claim 3 is characterized in that: The specific steps of generating the maintenance database in S300 are: S301, collect the maintenance data of professionals performing maintenance when each abnormality occurs in the control cabinet in history, extract the equipment data that changes when the control cabinet is maintained using the maintenance data, and correspond in the functional blocks of the control cabinet in S100 according to the changed equipment data, and find the functional blocks of each collected maintenance data as {Q1, Q2, Q3, ..., Q h }, Q1, Q2, Q3, ..., Q h represents the 1st, 2nd, 3rd, ..., hth functional blocks in the maintenance data, where h is a positive integer; collects the induced features of the abnormality corresponding to each maintenance data, compares the functional blocks of r abnormal maintenance data with the same induced features, calculates the number of occurrences of each functional block in the r abnormal maintenance data with the same induced features, matches the functional block with the largest number of occurrences with the induced features of the corresponding type to form a block matching pair (Q, Ty); S302, collect the maintenance data of the professional personnel performing maintenance when each abnormality of the control cabinet occurs in the history, and the maintenance factor of each functional block is {Wz1, Wz2, Wz3, ..., Wz f }, Wz1, Wz2, Wz3,..., Wz f represents the 1st, 2nd, 3rd, ..., fth maintenance factor in each functional block in the maintenance data, where f is a positive integer; the change amount of the abnormal element when each abnormality occurs is {Syb1, Syb2, Syb3, ..., Syb j },Syb1,Syb2,Syb3,...,Syb j Indicates the change amount of the 1st, 2nd, 3rd, ..., jth abnormal element when each abnormality occurs in the history, and matches the change amount of each abnormal element with the maintenance factor in the maintenance data. When Syb = Wz, it is judged that the maintenance factor and the abnormal element match successfully. When Syb ≠ Wz, it is judged that the maintenance factor and the abnormal element match unsuccessfully. Match all abnormal elements and maintenance factors to obtain element matching pairs (Szh, Wz); S303: construct a maintenance database using the matched block matching pairs, element matching pairs and maintenance data of each anomaly.

5. The intelligent control method of a control cabinet based on data analysis according to claim 3 is characterized in that: The specific steps of calculating the abnormal limit value of the control cabinet using the common characteristics in S400 are: S401, analyzing the abnormal elements calculated in S201, extracting the abnormal elements existing in each abnormality as the common feature Tg of all types of abnormalities; collecting the common feature values ​​of the control cabinet when the abnormality occurs in the history as {Tg1, Tg2, Tg3, ..., Tg q }, Tg1, Tg2, Tg3,..., Tg q Indicates the common characteristic value when the 1st, 2nd, 3rd, ..., qth abnormality of the control cabinet occurs in the history, where q is a positive integer; S402. Calculate the abnormal limit of the control cabinet using the common characteristic values ​​of abnormalities in the collected history. The formula is: In the formula, In represents the abnormal limit of the control cabinet, Tg max Indicates the maximum value of the common characteristics when anomalies occur in the collected history, Tg min Indicates the minimum value of the common characteristics when anomalies occur in history, |Tg-Tg x Represents the difference between adjacent common features in the collected history.

6. The intelligent control method of a control cabinet based on data analysis according to claim 5 is characterized in that: The specific steps of selecting a maintenance plan in S500 are: S501, collect the common characteristics of the control cabinet in real time as Tgs, use the abnormal limit value of the control cabinet to judge the real-time common characteristics, and when Tgs≥In, judge that the control cabinet in real-time operation is abnormal; When Tgs<In, it is judged that no abnormality occurs in the control cabinet during real-time operation; S502. When it is determined that an abnormality occurs in a control cabinet during real-time operation, extract individual features of the real-time abnormality and make a judgment among all types of abnormalities in the abnormality database. After the individual features of the real-time abnormality are found in the abnormality database, select the corresponding maintenance data in the maintenance database as a maintenance plan for the real-time abnormality, and process and maintain the real-time abnormality of the control cabinet.

7. The intelligent control method of a control cabinet based on data analysis according to claim 5 is characterized in that: The specific steps of combining the maintenance function block and the maintenance factor in S600 to generate a maintenance plan for the new abnormality are: S601. When the same single feature is not found in the abnormality database using the single feature of the real-time abnormality, the real-time abnormality is judged to be a new abnormality; the induced feature and abnormal element of the new abnormality are extracted; the block matching pair is searched in the maintenance database using the induced feature of the new abnormality, and when the same induced feature is found in all the block matching pairs, the functional block in the corresponding block matching pair is selected as the maintenance block of the new abnormality; S602, using the abnormal element of the new abnormality to search for element matching pairs in the maintenance database, when the same abnormal element is found in the element matching pairs, selecting the maintenance factor in the corresponding element matching pair as the maintenance amount of each abnormal element in the new abnormality; S603: formulate a maintenance plan based on the maintenance block of the new anomaly and the maintenance amount of each abnormal element found in the maintenance database, and perform maintenance processing on the new anomaly.

8. An intelligent control system for a control cabinet based on data analysis, characterized in that: The intelligent control system of the control cabinet includes a data collection module, a function block module, an abnormality analysis module, a maintenance analysis module, a matching module, an abnormality judgment module and a plan formulation module; The data collection module is used to collect equipment data, function data and maintenance data when abnormalities occur in the control cabinet in the past; The functional block module is used to process the control cabinet according to different functional data to obtain different functional blocks; The abnormality analysis module is used to analyze the device data when abnormalities occurred in the control cabinet history, classify the abnormalities and obtain the abnormal elements and induced characteristics of each abnormality, and build an abnormality database; The maintenance analysis module is used to analyze the maintenance data of the control cabinet when abnormalities occurred in the history, find out the functional blocks and maintenance factors when performing maintenance for each abnormality, and build a maintenance database; The matching module is used to match the abnormal elements in the abnormal database with the maintenance factors in the maintenance database, and to match the induced features in the abnormal database with the functional blocks in the maintenance database; The abnormality judgment module is used to find the common characteristics of all abnormalities, calculate the abnormality limit of the control cabinet using the common characteristics when the abnormalities occurred in the history, and judge the abnormality of the real-time control cabinet; The plan formulation module is used to determine the type of abnormality occurring in real time, select maintenance data as a maintenance plan, and formulate a corresponding maintenance plan when it is a new abnormality.

9. The intelligent control system of a control cabinet based on data analysis according to claim 8, characterized in that: The abnormality judgment module includes an abnormality limit calculation unit and an abnormality judgment unit; The abnormal limit value calculation unit is used to calculate the abnormal limit value of the control cabinet by using the common characteristics when the abnormality occurs in the history; The abnormality judgment unit is used to collect common characteristics of the control cabinet in real time, and use the abnormality limit value to judge whether an abnormality occurs in the control cabinet.

10. The intelligent control system of a control cabinet based on data analysis according to claim 8, characterized in that: The plan formulation module includes an abnormality type determination unit and a plan formulation unit; The abnormality type determination unit is used to extract a separate feature of the real-time abnormality and search it in the abnormality database to determine the type of the real-time abnormality. When the abnormality type is not found in the abnormality database, the real-time abnormality is determined to be a new abnormality; The plan formulation unit is used to select corresponding maintenance data in the maintenance database as a maintenance plan when determining the type of abnormality; when judging it as a new abnormality, formulate a maintenance plan for the new abnormality using the matching pair in the maintenance database.

Images