Comprehensive quality management abnormal fluctuation monitoring identification method and system

Abstract

The invention discloses a comprehensive quality management abnormal fluctuation monitoring identification system and method, and the system comprises a first monitoring system which is used for monitoring the operation condition of a to-be-detected target object, and transmitting a first abnormal operation condition to a server platform after the first abnormal operation condition is monitored; the server platform is used for acquiring a first influence factor type corresponding to the first abnormal operation condition; obtaining corresponding influence factor feature data; determining an actual influence factor type of the first abnormal operation condition according to the influence factor feature data; performing addition processing on an early warning value corresponding to the management term data to obtain a corresponding first early warning value; and when the first early warning value exceeds an early warning threshold value, an early warning prompt signal is sent out. By means of the scheme, the timeliness of management term content modification and the processing efficiency of modification and improvement work can be improved, the high matching degree between a management system and the actual situation is improved, and the enterprise / project operation quality is guaranteed.

Description

Technical Field

[0001] The present invention relates to data anomaly monitoring and analysis technology, and in particular to a system and method for monitoring, identifying and analyzing abnormal fluctuations in total quality management. Background Art

[0002] In order to ensure the stability and reliability of power supply, relevant enterprises will formulate relevant management systems and promote their implementation and execution. Generally speaking, the terms of the management system are formulated to better improve the quality of the overall project / enterprise. Therefore, the closer the content of the terms is to the actual operation, the better. However, the actual operation / implementation situation will vary according to the actual application scenario, and the actual problems generated in the process will generally be delayed in feedback to the management. Therefore, the time point for the improvement / modification of the management system terms will have a significant lag, resulting in the management of the management system terms in actual management. The management quality is low, and when the management terms are improved / modified, there is a lack of statistical analysis of relevant data as support, so it is difficult to improve / modify accurately when improving / modifying, and for the system review and approval personnel, a lot of repetitive communication with relevant personnel is required to ensure the accuracy of the improved / modified terms and the actual situation, which greatly increases the workload of the review and approval work and leads to very low work processing efficiency. Summary of the invention

[0003] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a comprehensive quality management abnormal fluctuation monitoring and identification method and system to analyze and count the monitored abnormal fluctuation data, and use it as an early warning basis for clause modification, so as to improve the efficiency and timeliness of clause modification / improvement.

[0004] In a first aspect, an embodiment of the present application provides a comprehensive quality management abnormal fluctuation monitoring and identification system, the system comprising:

[0005] A first monitoring system is used to monitor the operation status of the target object to be measured to obtain first monitoring data, and after determining that a first abnormal operation status exists according to the first monitoring data, the first abnormal operation status is sent to the server platform;

[0006] The server platform includes at least one processor for loading a program to execute the following steps:

[0007] S1. After receiving a first abnormal operation condition, obtaining a plurality of first influencing factor types corresponding to the first abnormal operation condition;

[0008] S2. Acquire corresponding influencing factor characteristic data according to a plurality of first influencing factor types;

[0009] S3. Determine the actual influencing factor type of the first abnormal operation condition according to the influencing factor characteristic data;

[0010] S4. When it is determined that there is management clause data matching the actual influencing factor type, the warning value corresponding to the management clause data is increased to obtain a first warning value corresponding to the management clause data;

[0011] S5. When the first warning value corresponding to the management clause data exceeds the first warning threshold, a first warning prompt signal is issued.

[0012] In some embodiments, the acquiring of a plurality of first influencing factor types corresponding to the first abnormal operation condition specifically includes:

[0013] Using a clustering algorithm, querying from the first database the historical abnormal operation situation with the highest matching degree with the first abnormal operation situation, wherein the historical abnormal operation situation with the smallest Euclidean distance with the first abnormal operation situation is the historical abnormal operation situation with the highest matching degree;

[0014] From the mapping relationship between the historical abnormal operation conditions and the historical influencing factor types, the historical influencing factor types corresponding to the queried historical abnormal operation conditions are obtained.

[0015] In some embodiments, the step S4 of increasing the warning value corresponding to the management clause data specifically includes:

[0016] S401, obtaining the severity of the impact of the first abnormal operation condition;

[0017] S402: Determine a first weighted value corresponding to the severity of the impact, wherein the severity of the impact and the first weighted value are in direct proportion to each other;

[0018] S403: Use the reference value and the first weighted value to increase the warning value corresponding to the management clause data.

[0019] In some embodiments, step S403 specifically includes:

[0020] S4031. When a first satisfaction evaluation value corresponding to the management clause data is obtained from the evaluation system, a second weighted value corresponding to the first satisfaction evaluation value is determined, wherein the first satisfaction evaluation value and the second weighted value are in inverse proportion to each other;

[0021] S4032: Use the reference value, the first weighted value, and the second weighted value to increase the warning value corresponding to the management clause data.

[0022] In some embodiments, determining the second weighted value corresponding to the first satisfaction evaluation value specifically includes:

[0023] S40311. According to a preset sampling quantity, a number of second satisfaction evaluation values ​​corresponding to the management clause data are randomly selected from the evaluation system;

[0024] S40312, after performing standard deviation calculation processing on a plurality of second satisfaction evaluation values, a first standard deviation value is obtained;

[0025] S40313. Determine whether the first standard deviation value is less than or equal to the first stability threshold. If so, determine the first satisfaction rating value based on the average of several second satisfaction rating values. Otherwise, return to execute step S40311 until the first standard deviation value is less than or equal to the first stability threshold.

[0026] In some embodiments, the system further comprises:

[0027] The second monitoring system is used to monitor the maintenance status of the fault target to obtain second monitoring data, and after determining that a first maintenance abnormality exists according to the second monitoring data, the first maintenance abnormality is sent to the server platform; wherein the first maintenance abnormality at least includes maintenance time abnormality data;

[0028] The server platform is also used to load a program to perform the following steps:

[0029] S6. Determine corresponding management clause data according to the abnormal maintenance time type corresponding to the abnormal maintenance time data;

[0030] S7, determining a second warning value of the corresponding management clause data according to the maintenance time difference value included in the maintenance time abnormality data;

[0031] S8. When the second warning value corresponding to the management clause data exceeds the second warning threshold, a second warning prompt signal is issued.

[0032] In some embodiments, step S7 specifically includes:

[0033] S701, determining a third weighted value corresponding to the maintenance time difference, wherein the maintenance time difference and the third weighted value are in direct proportion;

[0034] S702: Use the reference value and the third weighted value to increase the warning value corresponding to the corresponding management clause data, so as to obtain a second warning value.

[0035] In some embodiments, the maintenance time difference includes a first maintenance time difference, the first maintenance time difference refers to a maintenance time difference corresponding to the maintenance sub-step, the first maintenance time difference is determined according to the actual maintenance time corresponding to the maintenance sub-step, wherein the actual maintenance time corresponding to the maintenance sub-step is obtained by obtaining and determining the following steps:

[0036] In response to a click signal of the start timing button, the current moment is used as the first maintenance actual start time node;

[0037] In response to a click signal of a maintenance information upload button, after obtaining the uploaded maintenance status information, determining whether the maintenance status information meets a first maintenance requirement, wherein the first maintenance requirement corresponds to a maintenance sub-step one by one;

[0038] When it is determined that the maintenance status information meets the first maintenance requirement, the current time is used as the actual end time node of the first maintenance;

[0039] The time difference between the first maintenance actual start time node and the first maintenance actual end time node is used as the actual maintenance duration of the maintenance sub-step;

[0040] The start timing button and the maintenance information upload button are arranged on a second-level display interface for displaying a plurality of maintenance sub-steps.

[0041] In some embodiments, the second-level display interface is also provided with a play button for triggering the playing of the maintenance demonstration video corresponding to the maintenance sub-step.

[0042] In a second aspect, an embodiment of the present application provides a method for monitoring and identifying abnormal fluctuations in comprehensive quality management, the method comprising the following steps:

[0043] S1. After receiving a first abnormal operation condition, obtaining a plurality of first influencing factor types corresponding to the first abnormal operation condition;

[0044] S2. Acquire corresponding influencing factor characteristic data according to a plurality of first influencing factor types;

[0045] S3. Determine the actual influencing factor type of the first abnormal operation condition according to the influencing factor characteristic data;

[0046] S4. When it is determined that there is management clause data matching the actual influencing factor type, the warning value corresponding to the management clause data is increased to obtain a first warning value corresponding to the management clause data;

[0047] S5. When the first warning value corresponding to the management clause data exceeds the first warning threshold, a first warning prompt signal is issued.

[0048] The present application can achieve at least one of the following technical effects: after the present application scheme performs abnormal monitoring and identification on the target object to be measured (such as power supply equipment, power supply layout lines, power-consuming equipment, etc.), when it is determined that there is data abnormality, it is sent to the server platform, and the server platform will obtain the type of influencing factor matching the abnormal data from the first database based on the abnormal data; then, after obtaining the corresponding influencing factor characteristic data based on these influencing factor types, the actual influencing factor type is judged and identified based on the influencing factor characteristic data, and then, when it is determined that there is management clause data matching it based on the actual influencing factor type, the warning value corresponding to the management clause data is increased to obtain the first warning value corresponding to the management clause data, and when the first warning value corresponding to the management clause data exceeds the first warning threshold, a warning prompt signal is issued. It can be seen that in this way, the statistical analysis results of abnormal situations can be used as an early warning basis for the modification and improvement of management clauses. Not only can the corresponding management clause data be improved / modified in a timely manner to make it more in line with actual operation, ensuring the quality of power operation management, thereby improving the reliability and stability of power operation, but also the modification / improvement process of management clauses (including early revisions and improvements and later approval and review) is conducive to rapid data tracing of the basis for modifying the clauses, greatly reducing the workload of staff, improving work processing efficiency, and improving the accuracy of clause modifications and improvements. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments.

[0050] Figure 1 A schematic diagram of the architecture of a comprehensive quality management abnormal fluctuation monitoring and identification system is provided for an embodiment of the present application;

[0051] Figure 2 A schematic diagram of the steps of a method for monitoring and identifying abnormal fluctuations in comprehensive quality management is provided for an embodiment of the present application;

[0052] Figure 3 An interface diagram of a second-level display interface is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described through the implementation method with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0054] The purpose of formulating the management system clauses of an enterprise / project is to ensure the reliability and stability of its operation. Therefore, the content of the management clauses should be as close to the actual operation as possible. However, in the process of formulating the current management clause data, due to the lack of appropriate data as support, the time point of modifying / improving the management clause data is seriously delayed, resulting in the mismatch between the specific management regulations and the actual situation. This not only fails to guarantee the quality of the enterprise / project operation, but also leads to too much ineffective management process work, reducing the work efficiency of the entire enterprise / project implementation. At the same time, for the system review and approval personnel, a lot of repetitive communication with relevant personnel is required during the review and approval process to ensure the accuracy of the improved / modified clauses and their relevance to the actual situation, which greatly increases the workload of the review and approval work and leads to very low work processing efficiency.

[0055] In view of the above problems, after studying and analyzing the overall situation of the current enterprise / project and the relevant management clause data, it is found that the factors affecting operational reliability and stability mainly come from the factors that cause abnormal operating conditions, that is, the factors that cause abnormal operating conditions. Among them, these factors can include environmental factors (such as temperature, humidity, electromagnetic interference, lightning strikes, earthquakes and other environmental conditions of the operating environment), connected loads, equipment failure factors (which include the failure of the circuit / electronic components of the equipment itself, aging / loss factors of the equipment, etc.), human factors (such as manual cable cutting, equipment parameter setting errors, operation errors, etc.), technical factors (such as unreasonable layout of power system architecture / cables, lines, etc., equipment performance does not meet the actual operating conditions, etc.). Therefore, in order to avoid the occurrence of these factors, the current system content in the management system is basically formulated around these types of factors. For example: 1. The management clause content formulated for the influencing factor of the environment may include equipment specifications, protective measures, monitoring measures, emergency warning plans, etc. selected for different specific environments (such as too high / too low temperature, excessive humidity, lightning strikes, and high electromagnetic interference). 1. To avoid the problem of abnormal power operation caused by extreme / abnormal weather; 2. The management clauses formulated for the influencing factor of access load mainly include the content of load management strategy, such as power management regulations on the demand side, peak power management regulations, etc., so as to avoid the interference of power metering data due to sudden changes in load (such as large power equipment being started and operated), resulting in subsequent measurement errors; 3. The management clauses formulated for equipment failure factors may include: equipment specification and performance selection regulations, equipment detection (such as fault detection, equipment aging / loss detection) management regulations; 4. The management clauses formulated for human factors may include: operation regulations such as the use / setting of various types of operations / designs; 5. The management clauses formulated for technical factors may include: design management regulations such as system architecture / cable layout design, etc. It can be seen that there is an inevitable mapping relationship between the factors that affect abnormal operation and the management clauses. When the operation is often abnormal due to a certain factor, it means that the content of the management clause corresponding to the factor is basically not suitable for the current usage scenario. At this time, it is necessary to focus on analyzing, improving and modifying these management clause data in a timely manner. Based on this, the embodiment of the present application optimizes the existing monitoring and control system architecture so that it can communicate with multiple management terminals for data transmission, so as to achieve statistical analysis and processing based on the number of occurrences of factors that cause abnormal situations, and use this as a basis for early warning prompts for the modification / improvement of the content of the management clauses, and feed back this data basis to the corresponding management terminal.

[0056] Reference Figure 1A total quality management abnormal fluctuation monitoring and identification system includes a first monitoring system and a server platform, wherein the first monitoring system and the server platform are connected in communication, and the server platform is also provided with a first data interface connected in communication with a management terminal. The first monitoring system and the server platform are described in detail as follows.

[0057] The first monitoring system is mainly used to monitor the operation status of the target object to be measured to obtain first monitoring data. After determining the existence of a first abnormal operation status according to the first monitoring data, the first abnormal operation status is sent to the server platform.

[0058] Specifically, for the above-mentioned first monitoring data, it can be obtained by monitoring the attribute data of the target object to be measured, such as voltage, circuit, impedance, frequency, power, equipment status, etc. As for the step of determining the existence of the first abnormal operation condition according to the first monitoring data, it can be specifically as follows: the value and / or value change trend of the monitored first monitoring data is compared and identified with the historical normal value and / or the historical normal value change trend. When the difference between the value and / or value change trend of the monitored first monitoring data and the historical normal value and / or the historical normal value change trend exceeds the specified difference threshold, it is judged that the current target object to be measured has an abnormal operation condition. Of course, in addition to determining whether there is an abnormal operation condition by identifying and comparing the value / value change trend, other technical means can also be used to achieve it, which can be set according to actual needs, and no special limitation is made here.

[0059] In addition, for the first abnormal operation condition sent to the server platform, the information that may be included includes the type of monitoring data, the equipment specifications of the monitored object, the environmental conditions of the equipment (including indoor and outdoor environmental conditions), the comparison and identification results between the monitoring data and historical data, the project / enterprise information of the monitored object, the geographical environment information of the monitored object, etc.

[0060] The server platform comprises at least one processor for loading a program to execute the steps of a method for monitoring and identifying abnormal fluctuations in comprehensive quality management.

[0061] Reference Figure 2 , an embodiment of the present application provides a method for monitoring and identifying abnormal fluctuations in comprehensive quality management, which includes the following specific implementation steps.

[0062] S1. After receiving a first abnormal operation situation, obtain a plurality of first influencing factor types corresponding to the first abnormal operation situation.

[0063] Specifically, for several first influencing factor types, they can be influencing factor types obtained after factor analysis of historical abnormal operation conditions, wherein the number of first influencing factor types can be m in total. And for obtaining several first influencing factor types corresponding to the first abnormal operation condition, the specific implementation method may include the following.

[0064] Method ①, based on the mapping relationship between historical abnormal operation conditions and historical influencing factor types: It is achieved by constructing a mapping relationship between historical abnormal operation conditions and historical influencing factor types, that is, by performing data identification, comparison and judgment on the historical abnormal operation conditions, the judgment results are combined with other attribute data to analyze and process to obtain the corresponding historical influencing factor types, and then a mapping relationship between the historical abnormal operation conditions and the corresponding historical influencing factor types is constructed; then in actual use, the first abnormal operation condition determined by monitoring can be matched and compared with the historical abnormal operation conditions to obtain the first historical abnormal operation condition that is closest to the first abnormal operation condition. At this time, based on the mapping relationship between the historical abnormal operation conditions and the historical influencing factor types, several first historical influencing factor types corresponding to the first historical abnormal operation conditions can be obtained. The several first historical influencing factor types obtained at this time are the required first influencing factor types with a high degree of matching.

[0065] Method ② is implemented based on a deep learning model: the data identification, comparison and judgment of historical abnormal operation conditions and the combination of other attribute data are used as training input data, and the corresponding historical influencing factor types obtained by analyzing and processing them are used as training output data, and then the preset deep learning model is trained using the above training input data and training output data to obtain a trained deep learning model; then in actual use, the data identification, comparison and judgment of the first abnormal operation condition and the combination of other attribute data are obtained as the first data input matrix, and then they are input into the trained deep learning model for data processing to obtain the corresponding data output results, that is, several first influencing factor types.

[0066] For the above methods ① and ②, they can be selected and set accordingly according to the actual situation, and no special restrictions are made here.

[0067] Alternatively, after impact analysis of all historical abnormal situations, a total of N types of influencing factors are obtained. Then, to obtain several first types of influencing factors corresponding to the first abnormal operation situation, it can be directly obtained by: directly obtaining N types of influencing factors, which is equivalent to obtaining all types of influencing factors. Compared with the above two methods, this method does not need to execute the matching query processing flow, nor does it need to use the deep learning model for data processing, which greatly reduces the processing flow work.

[0068] S2. Acquire corresponding influencing factor characteristic data according to a plurality of first influencing factor types.

[0069] Specifically, since the obtained first influencing factor types may be different from the actual situation, after obtaining the first influencing factor types, the corresponding influencing factor characteristic data can be obtained based on these types to determine whether these first influencing factor types are actual influencing factors. For example, the first influencing factor types obtained include equipment failure factors and environmental factors, then the evaluation data corresponding to the two aspects of equipment failure and environment, that is, the influencing factor characteristic data, such as judging whether the circuit of the equipment is short-circuited / open-circuited, whether the loss rate of the equipment is lower than the specified requirements, whether the environment in which the equipment is located has extreme weather conditions, etc., can be used to determine whether the first influencing factor type currently obtained is the actual influencing factor of the current abnormal operation based on these data.

[0070] S3. Determine the actual influencing factor type of the first abnormal operation condition according to the influencing factor characteristic data.

[0071] Specifically, the step S3 may specifically include the following steps.

[0072] S301. Screen and determine an actual influencing factor type from a plurality of first influencing factor types according to influencing factor characteristic data.

[0073] S302. When the number of actual influencing factor types screened and determined from several first influencing factor types is 0 and the number of first influencing factor types is less than N, then the second influencing factor type is obtained, and then the actual influencing factor type of the first abnormal operating condition is determined according to the influencing factor characteristic data corresponding to the second influencing factor type; wherein N is the total number of all influencing factor types corresponding to all abnormal operating conditions; the second influencing factor type refers to the influencing factor type other than the first influencing factor type among the N influencing factor types, for example, a total of the 1st to 8th influencing factor types are included. At this time, the first influencing factor types obtained are the 3rd, 5th, 7th, and 8th influencing factor types, respectively, and the 1st, 2nd, 4th, and 6th influencing factor types belong to the second influencing factor type.

[0074] Specifically, after analyzing, identifying and judging all historical abnormal operation conditions, a total of N influencing factor types will be obtained. If the influencing factor characteristic data corresponding to the currently obtained first influencing factor type is analyzed, identified and judged, it is determined that the actual situation does not have the specified situation that produces these influencing factor types, for example, the equipment does not have a circuit failure, the loss rate / aging degree of the equipment meets the specified requirements, and there is no extreme weather, etc., then at this time, in order to improve the accuracy and comprehensiveness of the identification and judgment, the remaining influencing factor types can be obtained for judgment, so as to determine the actual influencing factor type. Of course, if the number of actual influencing factor types screened and judged from several first influencing factor types is not 0, the actual influencing factor types screened and judged are used as the actual influencing factor types required in the end.

[0075] S303: When the number of actual influencing factor types screened and determined from a plurality of first influencing factor types or second influencing factor types is not 0, the actual influencing factor types screened and determined are used as the actual influencing factor types required finally.

[0076] S304, when the number of actual influencing factor types screened and judged from a plurality of first influencing factor types and second influencing factor types is 0, it indicates that a new influencing factor type exists, which causes an abnormal operation, and the current first abnormal operation is stored in the corresponding first designated area, and a fourth early warning prompt signal is sent to prompt relevant staff to conduct further specific influencing factor analysis on the abnormal operation. It can be seen that through this data processing step, the emergence of new influencing factors can be discovered quickly and timely, thereby improving the update rate of the influencing factor type and avoiding the situation where new influencing factors are missed in detection and analysis.

[0077] S4. When it is determined that there is management clause data matching the actual influencing factor type, the warning value corresponding to the management clause data is increased to obtain the first warning value corresponding to the management clause data. The first warning value is mainly used to provide a warning prompt for timely modification and improvement of the management clause data.

[0078] Specifically, for an influencing factor type, if it is judged to be identified once, it means that the number of occurrences of the influencing factor type is increased by 1, and it also means that the management clause data content matching the influencing factor type is less suitable for the current usage scenario, and for the actual influencing factor type, it is the influencing factor type that is finally identified. Therefore, based on these identified influencing factor types, the warning value of the corresponding management clause data is increased, that is, for the warning value, it is used to indicate the degree of mismatch between the corresponding management clause data content and the current actual scenario. Among them, the influencing factor type is identified once, and the warning value is increased by 1, or it can also be increased according to other preset values. This can be selected and set according to the actual situation, and the increase process is not particularly limited here.

[0079] Furthermore, in view of the fact that the actual use scenarios are changeable, the update speed of the influencing factor types for abnormal operation conditions will also be relatively fast, that is, there will be a situation where there is no management clause data matching the actual influencing factor type. For example, there are a total of 8 original influencing factor types, and in the existing management clause content, there are management clause data corresponding to these 8 original influencing factor types, and based on factors such as changes in scenarios and monitoring technology, new influencing factor types may appear on this basis in the future, such as the 9th, 10th, and 11th influencing factor types. Therefore, when the actual influencing factor type identified is a new influencing factor type, there will be a situation where there is no management clause data matching the actual influencing factor type. At this time, this abnormal operation condition and its corresponding actual influencing factor type can be stored in a designated area, and when the number of times a new actual influencing factor type is identified exceeds the preset warning threshold, the corresponding warning prompt signal is output to prompt the relevant staff to formulate the corresponding management clause data matching this influencing factor type as soon as possible. It can be seen that the method steps of the embodiment of the present application can also include the following steps.

[0080] S9. When it is determined that there is no matching management clause data based on the actual influencing factor type, the actual influencing factor type and its corresponding first abnormal operating condition are stored in the second designated area, and the number of occurrences of the actual influencing factor type is increased (generally, the number of occurrences is increased by 1).

[0081] S10. When the number of occurrences of the actual influencing factor type exceeds the first preset number threshold, a third early warning signal is issued to promptly remind relevant staff to formulate corresponding management clauses for this actual influencing factor type as soon as possible.

[0082] It can be seen that the above-mentioned data processing method can greatly improve the timeliness of the formulation of new management systems, thereby improving the reliability and stability of actual operation and improving the quality of management; moreover, when formulating the specific content of management clauses, all corresponding abnormal operation information can be directly screened out from the designated area according to the actual influencing factor type, which provides great convenience for the formulation of new management systems, reduces the workload of staff in collecting sample data, and thus improves work efficiency.

[0083] S5. When the first warning value corresponding to the management clause data exceeds the first warning threshold, a first warning prompt signal is issued to prompt relevant staff to promptly and quickly analyze, modify and improve the management clause data.

[0084] Based on the content of the solution in the above-mentioned embodiment, this solution can timely warn and remind relevant staff to make corresponding improvements / modifications to the corresponding management clause data to make it more in line with actual operation, thereby ensuring the quality of power operation management, thereby improving the reliability and stability of power operation, and the modification / improvement process of management clauses is conducive to rapid data tracing of the basis for modifying the clauses and avoiding excessive repetitive communication and statistical work, which greatly reduces the workload of staff, improves work processing efficiency, and improves the accuracy of clause modifications and improvements.

[0085] In some embodiments, in the process of using the mapping relationship between historical abnormal operation conditions and historical influencing factor types to obtain the first influencing factor type required for matching, the clustering method in the big data analysis technology can be used to realize the data search of the historical abnormal operation conditions with the highest matching degree with the first abnormal operation condition, so as to ensure the accuracy of the matching data search. Therefore, for the acquisition of several first influencing factor types corresponding to the first abnormal operation condition described in step S1, it specifically includes:

[0086] S101. Query a first database for a historical abnormal operation condition that has the highest matching degree with a first abnormal operation condition by using a clustering algorithm, wherein the historical abnormal operation condition that has the smallest Euclidean distance with the first abnormal operation condition is the historical abnormal operation condition that has the highest matching degree.

[0087] S102. From the mapping relationship between the historical abnormal operation conditions and the historical influencing factor types, obtain the historical influencing factor type corresponding to the queried historical abnormal operation conditions, which is the first influencing factor type obtained by the queried.

[0088] In some embodiments, for different abnormal operation conditions, different specific abnormal details such as the location of the abnormal point, the degree of data fluctuation, and the degree of negative impact caused later (for example, one abnormal operation condition only causes a single device to fail to operate normally, but another abnormal operation condition causes the paralysis of the local power architecture), etc., can be configured with different severity of impact, wherein the severity of the impact can be represented by a numerical value, wherein the greater the severity of the impact, the greater the numerical value of the benchmark, and the numerical value of the increase in the warning value should also be greater, which means that when the severity of the abnormal operational situation is greater, the type of influencing factor that causes it to appear is more important, therefore, the numerical value of the increase in the warning value should be greater, so that the management clause data corresponding to the influencing factor type should be improved and modified more timely. For example, if a certain influencing factor type is identified 10 times, and the abnormal operation conditions corresponding to 5 of them will cause more serious impacts, then the management clause data corresponding to this influencing factor type should be analyzed, improved and modified as soon as possible.

[0089] Therefore, the step S4 of increasing the warning value corresponding to the management clause data specifically includes the following steps.

[0090] S401. Obtain the severity of the impact of a first abnormal operating condition.

[0091] S402: Determine a first weighted value corresponding to the severity of the impact, wherein the severity of the impact is directly proportional to the first weighted value. The first weighted value should be greater than or equal to 1, and further preferably, the value range of the first weighted value may be between [a, b], where a is 1 and b is greater than or equal to 2, or the specific value of b may be determined according to the number of levels of the severity of the impact.

[0092] S403, using the reference value and the first weighted value to increase the warning value corresponding to the management clause data. The reference value refers to a unit reference value, such as 1, which means that if the factor of the severity of the impact is not considered, when the type of impact factor corresponding to the abnormal operation is identified once, the current warning value corresponding to the management clause data is increased by 1 to obtain a new warning value.

[0093] Specifically, the step S403 may include: using the product of the reference value and the first weighted value as the added value, and then summing the added value with the current warning value of the management clause data to obtain a new warning value. It can be seen that the calculation formula of the new warning value is: i+1 =M*k1 i+1 +I i , where Ii k1 is the warning value obtained after the i-th execution and processing, which is equivalent to the current warning value of the management clause data; i+1 It is represented as the i+1th first weighted value; M is represented as the reference value; I i+1 The warning value obtained after the i+1th execution of the added processing. That is, when a certain actual influencing factor type is identified for the i+1th time, the benchmark value M and the i+1th first weighted value k1 are first calculated. i+1 After the product is performed, the product result is used as the increase value required in the i+1th increase process, and then it is combined with the warning value I obtained after the i-th increase process is completed. i Add them together to get the warning value I obtained after the current i+1th execution of the increase process i+1 , and when the warning value corresponding to the management clause data exceeds the threshold, an early warning signal is issued.

[0094] It can be seen that the severity of the impact of abnormal operation is introduced as a consideration factor to increase the warning value of the clause. The greater the severity of the abnormal operation, the greater the increase in value, so that the warning value is easier to send a warning prompt signal after exceeding the warning threshold, thereby further improving the timeliness of modification and improvement of the corresponding management clause data.

[0095] In some embodiments, in addition to considering the severity of the impact of abnormal operation, the satisfaction evaluation corresponding to the existing management clause can also be considered. Generally, for this satisfaction evaluation, it is possible to collect the satisfaction scores of each user on the content of these management clauses through existing questionnaires. Generally, the more satisfied, the higher the score. Therefore, if the satisfaction score corresponding to the management clause is lower, it means that from the perspective of employee execution, the rationality of the use and execution of the clause is lower. At this time, the priority of reviewing, modifying and improving the management clause should be greater. Of course, the determination and acquisition method of the satisfaction evaluation score corresponding to the management clause can also be achieved by other existing technical methods, which are not particularly limited here.

[0096] Therefore, the step S403 may further specifically include the following steps.

[0097] S4031. When a first satisfaction evaluation value corresponding to the management clause data is obtained from the evaluation system, a second weighted value corresponding to the first satisfaction evaluation value is determined, wherein the first satisfaction evaluation value and the second weighted value are in inverse proportion.

[0098] Specifically, in this embodiment, the server platform is further provided with a second data interface for communication with the evaluation system to perform data transmission and processing between the evaluation system. The second weighted value may be greater than or equal to 1, or the value range of the second weighted value may be [c, d], where c is 1, and d may be determined based on the first satisfaction evaluation value (i.e., satisfaction evaluation score).

[0099] S4032: Use the reference value M, the first weighted value k1, and the second weighted value k2 to increase the warning value corresponding to the management clause data.

[0100] Specifically, first, according to the reference value M and the i+1th first weighted value k1 i+1 After the product is performed, the product result is used as the increase value required in the i+1th increase process, and then it is combined with the warning value I obtained after the i-th increase process is completed. i Add them together to get the warning value I obtained after the current i+1th execution of the increase process i+1 Then, calculate k2 and the warning value I i+1 The sum of the two (i.e. k2+I i+1 ) or the product result (i.e. k2*I i+1 ), and then use this summation result or product result to judge the warning threshold value, and when it exceeds the first warning threshold value, a first warning prompt signal is issued.

[0101] It can be seen that by introducing the second weighted value corresponding to the satisfaction evaluation score, where the satisfaction evaluation score and the second weighted value are inversely proportional, the lower the satisfaction evaluation score, the higher the second weighted value, and the warning value approaches the warning threshold faster. This is equivalent to shortening the waiting time for modification / improvement of management terms and improving the priority and timeliness of improvement and modification of management terms data.

[0102] In some embodiments, in order to improve the accuracy of determining the second weighted value, the process of determining the second weighted value corresponding to the first satisfaction evaluation value may specifically include the following steps.

[0103] S40311. According to a preset sampling quantity, a number of second satisfaction evaluation values ​​corresponding to the management clause data are randomly selected from the evaluation system.

[0104] S40312. After performing standard deviation calculation on a plurality of second satisfaction evaluation values, a first standard deviation value is obtained.

[0105] S40313. Determine whether the first standard deviation value is less than or equal to the first stability threshold. If so, determine the first satisfaction rating value based on the average of several second satisfaction rating values. Otherwise, return to execute step S40311 until the first standard deviation value is less than or equal to the first stability threshold.

[0106] S40314. Determine a corresponding second weighted value according to the first satisfaction evaluation value obtained in step S40311.

[0107] It can be seen that for any management clause data, by randomly selecting several corresponding satisfaction scores, and then after their standard deviation value is less than the first stable threshold, the average value of several satisfaction scores is used as the final required satisfaction score as the basis for determining the second weighted value. This can avoid extreme values ​​of the evaluation, so that the obtained satisfaction score can be more in line with the actual use evaluation situation, greatly improving the accuracy of identifying and determining the second weighted value.

[0108] In some embodiments, the system of this embodiment further includes:

[0109] The second monitoring system is used to monitor the maintenance status of the fault target to obtain the second monitoring data. After determining the existence of the first maintenance abnormality according to the second monitoring data, the first maintenance abnormality is sent to the server platform; wherein the first maintenance abnormality at least includes maintenance time abnormality data. That is, in the embodiment of the present application, for maintenance abnormality, it is mainly based on the maintenance time for identification and judgment. When the time difference between the actual maintenance time and the preset maintenance time (i.e., the maintenance time difference) is greater than or equal to the first time threshold, it is judged that the maintenance abnormality exists.

[0110] Correspondingly, the method of this embodiment may further include the following steps.

[0111] S6. Determine corresponding management clause data according to the abnormal maintenance time type corresponding to the abnormal maintenance time data.

[0112] Specifically, for the time abnormality type, if the second monitoring data is the actual maintenance time required to perform all maintenance steps, then the time abnormality type belongs to the first maintenance abnormality type, and the first management clause matching it mainly involves maintenance training management clauses (such as training examination regulations, training frequency regulations, etc.), because, if there is an abnormality in the actual maintenance time required to perform all maintenance steps, then it means that the current training examination regulations, training frequency, etc. can no longer well guarantee the work efficiency of the maintenance work; if the second monitoring data is the actual maintenance time required to perform any maintenance sub-step, then the time abnormality type belongs to the second maintenance abnormality type, and the second management clause matching it mainly involves maintenance operation regulations, because, if there is an abnormality in the actual maintenance time required to perform any maintenance sub-step, then it means that the maintenance operation step content designed in the maintenance operation regulations (this operation step content can be displayed in the form of text description or video animation) has design defects or display defects in the operation process steps (that is, the text content and / or video animation displayed by the maintenance operation step cannot be easily understood by maintenance personnel, or it itself has expression defects), then it needs to be improved and modified.

[0113] S7. Determine a second warning value of the corresponding management clause data according to the maintenance time difference included in the maintenance time abnormality data.

[0114] Specifically, the step S7 may include the following steps.

[0115] S701. Determine a third weighted value corresponding to the maintenance time difference, wherein the maintenance time difference and the third weighted value are in direct proportion, i.e., the larger the maintenance time difference, the larger the corresponding third weighted value. In other words, if the maintenance time difference is larger, it means that the current management regulations are less suitable for the actual maintenance situation. Therefore, introducing the weighted value determined based on the maintenance time difference to adjust the warning value can improve the timeliness of the modification of the management clause data and avoid using inappropriate management regulations to perform corresponding maintenance training, operations, etc.

[0116] S702: Use the reference value and the third weighted value to increase the warning value corresponding to the corresponding management clause data, thereby obtaining a second warning value. The reference value refers to a unit reference value, such as 1.

[0117] Specifically, the product of the reference value and the third weighted value is first used as the added value, and then the added value and the current warning value of the management clause data are summed to obtain a new warning value. It can be seen that the warning value corresponding to the management clause data is updated and determined in this way, which is more accurate and more in line with the actual situation, and improves the timeliness of the modification and improvement of the corresponding training / maintenance management regulations.

[0118] In some embodiments, when the maintenance time difference includes a maintenance time difference corresponding to a maintenance sub-step (i.e., a first maintenance time difference), the first maintenance time difference is determined based on an actual maintenance time corresponding to the maintenance sub-step. Specifically, the first maintenance time difference is determined by the time difference between an actual maintenance time corresponding to a maintenance sub-step and a preset maintenance time.

[0119] At this time, on this basis, the increase processing of the warning value corresponding to the management clause data can also introduce the consideration factor of the importance of the maintenance sub-step, because if the importance of the maintenance sub-step is low, then the priority and timeliness of the modification and improvement of the corresponding maintenance operation regulations do not need to be too high. On the contrary, it is necessary to improve the timeliness of the modification and improvement of the maintenance sub-steps with high importance. Therefore, for step S701, it can specifically include: S7011, determine the fourth weighted value corresponding to the first maintenance time difference, wherein the first maintenance time difference and the fourth weighted value are in positive proportion. Correspondingly, for the step S702, it can specifically include the following steps.

[0120] S7021, determining a first importance of a maintenance sub-step corresponding to the first maintenance time difference;

[0121] S7022: Determine a fifth weighted value corresponding to the first importance, wherein the greater the first importance, the greater the fifth weighted value, that is, there is a positive proportional relationship between the first importance and the fifth weighted value;

[0122] S7023: Use the reference value, the fourth weighted value, and the fifth weighted value to increase the warning value corresponding to the corresponding management clause data, thereby obtaining a second warning value. Wherein, the fourth weighted value and the fifth weighted value are both greater than or equal to 1.

[0123] Specifically, the product of the base value, the fourth weighted value and the fifth weighted value is calculated and used as the added value, and then the added value and the current warning value of the management clause data are summed to obtain a new warning value.

[0124] S8. When the second warning value corresponding to the management clause data exceeds the second warning threshold, a second warning prompt signal is issued to remind relevant staff to review, modify and improve the content of relevant management clauses such as training and maintenance.

[0125] In some embodiments, the first maintenance time difference is obtained by calculating the time difference between the actual maintenance time for executing a maintenance sub-step and the preset maintenance time, wherein the actual maintenance time for executing the maintenance sub-step can generally be determined by the time difference between the maintenance start time node and the end time node. For this actual maintenance time, it can generally be obtained by the maintenance personnel entering maintenance information, so that the maintenance time and the maintenance start / end time nodes can be directly obtained. However, it basically all involves manual operation records, so the accuracy of the actual maintenance time is relatively low. For this reason, in the assistant management software commonly used by staff, a data collection and analysis function for collecting the actual maintenance time corresponding to the maintenance sub-step is designed.

[0126] For the above-mentioned functional data collection and analysis function, the first-level display interface is provided with options for maintenance operation steps corresponding to various target objects such as different situations, different equipment, and different cables. When the option of the maintenance operation step corresponding to the required target object is selected and clicked, the next-level display interface is entered; Figure 3 As shown, the second-level display interface displays a number of corresponding maintenance sub-steps, such as maintenance sub-steps 1, 2, 3, etc. For each maintenance sub-step, a start timing button and a maintenance information upload button are configured on the second-level display interface. For this function, for the actual maintenance time of a maintenance sub-step, the specific acquisition and determination steps may include the following steps.

[0127] A1. In response to a click signal of the start timing button, the timing function is triggered to start, and the current moment is used as the first actual start time node of maintenance. That is, when the maintenance personnel start maintenance, they can click this button to collect and record the maintenance start time point.

[0128] A2. In response to a click signal of the maintenance information upload button, after obtaining the uploaded maintenance status information, determine whether the maintenance status information meets the first maintenance requirement, wherein the first maintenance requirement corresponds to the maintenance sub-step one by one, that is, the contents of the maintenance requirements corresponding to different maintenance sub-steps are different.

[0129] Specifically, after a maintenance sub-step is executed, its maintenance status should be consistent with the status required by the regulations, so that it can be indicated that the maintenance sub-step is executed successfully. If it is determined that the maintenance sub-step is executed successfully, it means that the execution of this sub-step can be ended. For example, if after executing a maintenance sub-step, the current circuit connection status should be the same as the status required by the regulations, then it means that this maintenance sub-step can be ended. Therefore, after executing a maintenance sub-step, when it is determined that the maintenance status information is consistent with the first maintenance requirement, this moment can be used as the actual end time node of the maintenance. Among them, the acquisition and collection of maintenance status information can be achieved by existing technical means, which is not particularly limited here.

[0130] The start timing button and the maintenance information upload button are arranged on a second-level display interface for displaying a plurality of maintenance sub-steps, and one maintenance sub-step corresponds to a start timing button and one maintenance information upload button.

[0131] A3. When it is determined that the maintenance status information meets the first maintenance requirement, the current time is used as the actual end time node of the first maintenance.

[0132] A4. The time difference between the first maintenance actual start time node and the first maintenance actual end time node is used as the actual maintenance time of the maintenance sub-step.

[0133] Furthermore, in order to improve the accuracy of obtaining the actual start time node of the first maintenance and avoid erroneous triggering of the operation, which results in the start time node of the next maintenance sub-step not being completed before the previous maintenance sub-step is completed, therefore, the above step A1 may specifically include:

[0134] In response to the click signal of the start timing button corresponding to the i+1th maintenance sub-step, it is detected and determined whether there is a first maintenance actual end time node corresponding to the i-th maintenance sub-step. If so, the timing function is triggered to start, and the current moment is used as the first maintenance actual start time node of the i+1th maintenance sub-step. Otherwise, an early warning prompt signal is output to prompt the maintenance personnel of the operation error and to confirm whether the end time node of the i-th maintenance sub-step has been collected.

[0135] In some embodiments, a play button is also provided on the second-level display interface for triggering the maintenance demonstration video corresponding to the maintenance sub-step to play, wherein one maintenance sub-step corresponds to one play button. In this way, by playing the maintenance demonstration video, maintenance personnel can be assisted to quickly and correctly perform the corresponding maintenance operations, further ensuring the accuracy of maintenance work and improving processing efficiency.

[0136] In addition, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the above method embodiment.

[0137] For the processors mentioned in the above storage medium embodiment and the system embodiment, the number can be at least 1, and at least any step in the above method embodiment can be executed. When the number is at least two, at least two processors can be connected to each other by communication, not limited to wired or wireless communication connection, and the at least one processor can be connected to various intelligent terminal devices by communication. In addition, the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0138] Finally, it should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0139] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A comprehensive quality management abnormal fluctuation monitoring and identification system, characterized in that: The system includes: A first monitoring system is used to monitor the operation status of the target object to be measured to obtain first monitoring data, and after determining that a first abnormal operation status exists according to the first monitoring data, the first abnormal operation status is sent to the server platform; The server platform includes at least one processor for loading a program to execute the following steps: S1. After receiving a first abnormal operation condition, obtaining a plurality of first influencing factor types corresponding to the first abnormal operation condition; S2. Acquire corresponding influencing factor characteristic data according to a plurality of first influencing factor types; S3. Determine the actual influencing factor type of the first abnormal operation condition according to the influencing factor characteristic data; S4. When it is determined that there is management clause data matching the actual influencing factor type, the warning value corresponding to the management clause data is increased to obtain a first warning value corresponding to the management clause data; S5. When the first warning value corresponding to the management clause data exceeds the first warning threshold, a first warning prompt signal is issued.

2. The system according to claim 1, characterized in that The obtaining of a plurality of first influencing factor types corresponding to the first abnormal operation condition specifically includes: Using a clustering algorithm, querying from the first database the historical abnormal operation situation with the highest matching degree with the first abnormal operation situation, wherein the historical abnormal operation situation with the smallest Euclidean distance with the first abnormal operation situation is the historical abnormal operation situation with the highest matching degree; From the mapping relationship between the historical abnormal operation conditions and the historical influencing factor types, the historical influencing factor types corresponding to the queried historical abnormal operation conditions are obtained.

3. The system according to claim 1, characterized in that The step S4 of increasing the warning value corresponding to the management clause data specifically includes: S401, obtaining the severity of the impact of the first abnormal operation condition; S402: Determine a first weighted value corresponding to the severity of the impact, wherein the severity of the impact and the first weighted value are in direct proportion to each other; S403: Use the reference value and the first weighted value to increase the warning value corresponding to the management clause data.

4. The system according to claim 3, characterized in that The step S403 specifically includes: S4031. When a first satisfaction evaluation value corresponding to the management clause data is obtained from the evaluation system, a second weighted value corresponding to the first satisfaction evaluation value is determined, wherein the first satisfaction evaluation value and the second weighted value are in inverse proportion to each other; S4032: Use the reference value, the first weighted value, and the second weighted value to increase the warning value corresponding to the management clause data.

5. The system according to claim 4, characterized in that The step of determining a second weighted value corresponding to the first satisfaction evaluation value specifically includes: S40311. According to a preset sampling quantity, a number of second satisfaction evaluation values ​​corresponding to the management clause data are randomly selected from the evaluation system; S40312, after performing standard deviation calculation processing on a plurality of second satisfaction evaluation values, a first standard deviation value is obtained; S40313. Determine whether the first standard deviation value is less than or equal to the first stability threshold. If so, determine the first satisfaction rating value based on the average of several second satisfaction rating values. Otherwise, return to execute step S40311 until the first standard deviation value is less than or equal to the first stability threshold.

6. The system according to claim 1, wherein: The system also includes: The second monitoring system is used to monitor the maintenance status of the fault target to obtain second monitoring data, and after determining that a first maintenance abnormality exists according to the second monitoring data, the first maintenance abnormality is sent to the server platform; wherein the first maintenance abnormality at least includes maintenance time abnormality data; The server platform is also used to load a program to perform the following steps: S6. Determine corresponding management clause data according to the abnormal maintenance time type corresponding to the abnormal maintenance time data; S7, determining a second warning value of the corresponding management clause data according to the maintenance time difference value included in the maintenance time abnormality data; S8. When the second warning value corresponding to the management clause data exceeds the second warning threshold, a second warning prompt signal is issued.

7. The system according to claim 6, characterized in that The step S7 specifically includes: S701, determining a third weighted value corresponding to the maintenance time difference, wherein the maintenance time difference and the third weighted value are in direct proportion; S702: Use the reference value and the third weighted value to increase the warning value corresponding to the corresponding management clause data, so as to obtain a second warning value.

8. The system according to claim 6, characterized in that The maintenance time difference includes a first maintenance time difference, which refers to a maintenance time difference corresponding to the maintenance sub-step, and the first maintenance time difference is determined according to the actual maintenance time corresponding to the maintenance sub-step, wherein the actual maintenance time corresponding to the maintenance sub-step is obtained by obtaining and determining the following steps: In response to a click signal of the start timing button, the current moment is used as the first maintenance actual start time node; In response to a click signal of a maintenance information upload button, after obtaining the uploaded maintenance status information, determining whether the maintenance status information meets a first maintenance requirement, wherein the first maintenance requirement corresponds to a maintenance sub-step one by one; When it is determined that the maintenance status information meets the first maintenance requirement, the current time is used as the actual end time node of the first maintenance; The time difference between the first maintenance actual start time node and the first maintenance actual end time node is used as the actual maintenance duration of the maintenance sub-step; The start timing button and the maintenance information upload button are arranged on a second-level display interface for displaying a plurality of maintenance sub-steps.

9. The system according to claim 8, characterized in that The second-level display interface is also provided with a play button for triggering the playing of the maintenance demonstration video corresponding to the maintenance sub-step.

10. A method for monitoring and identifying abnormal fluctuations in total quality management, characterized in that: The method comprises the following steps: S1. After receiving a first abnormal operation condition, obtaining a plurality of first influencing factor types corresponding to the first abnormal operation condition; S2. Acquire corresponding influencing factor characteristic data according to a plurality of first influencing factor types; S3. Determine the actual influencing factor type of the first abnormal operation condition according to the influencing factor characteristic data; S4. When it is determined that there is management clause data matching the actual influencing factor type, the warning value corresponding to the management clause data is increased to obtain a first warning value corresponding to the management clause data; S5. When the first warning value corresponding to the management clause data exceeds the first warning threshold, a first warning prompt signal is issued.

Images