Equipment operation state intelligent supervision system and method based on big data analysis
Through real-time monitoring of device sensors and historical data analysis, combined with sensor association relationships to calculate the coordinated risk determination value, locking the source of fault risk, solving the problem of false alarms in monitoring results caused by sensor service life, and achieving effective supervision of the operating status of the equipment.
Patent Information
- Application Number
- CN202410982603.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-12
AI Technical Summary
The existing intelligent monitoring system for operating status of equipment based on big data analysis failed to effectively consider the service life of the sensor, resulting in false alarms of monitoring results and failure to coordinate with the monitoring results of other sensors of the equipment, resulting in abnormal monitoring results and poor supervision of equipment operation status. question.
By numbering and real-time monitoring results of the sensors of the equipment to be tested, combining historical data and sensor association relationships, synergistic risk determination values are calculated, fault risk sources are locked, and status risk warning information is generated to feedback to the administrator to realize the operation status of the equipment effective supervision.
Accurately judge the operating status of the equipment, reduce false alarms of sensor monitoring results, and improve the effectiveness of equipment operating status supervision.
Smart Images

Figure CN118938822A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of equipment supervision, and specifically to an intelligent supervision system and method for equipment operating status based on big data analysis. Background Art
[0002] With the deep integration of industrialization and informatization, the supervision of equipment operation status is of great significance to ensure production safety and improve production efficiency. Traditional supervision methods rely on manual inspections and regular maintenance, which have problems such as low efficiency, high cost, and slow response. The rise of big data technology provides a new way to solve these problems. By collecting, processing and analyzing equipment operation status data in real time, intelligent supervision of equipment status can be achieved.
[0003] The existing intelligent supervision system for equipment operation status based on big data analysis only realizes intelligent judgment and supervision of equipment operation status through sensor monitoring results, without taking into account the service life of the sensor. That is, when the corresponding sensor reaches the upper limit of its service life, even if the equipment operation status is normal, the monitoring results of the corresponding sensor will still have monitoring abnormalities, and thus the existing technology has the risk of false alarm of monitoring results; it fails to effectively coordinate the monitoring results of other sensors of the equipment to realize effective supervision of the equipment operation status, and thus the existing technology has major defects. Summary of the invention
[0004] The purpose of the present invention is to provide an intelligent monitoring system and method for equipment operation status based on big data analysis to solve the problems raised in the above background technology.
[0005] In order to solve the above technical problems, the present invention provides the following technical solution: a method for intelligent monitoring of equipment operation status based on big data analysis, the method comprising the following steps:
[0006] S1. Number each sensor during the operation of the equipment to be tested, and obtain the monitoring results of each numbered sensor in real time; compare the monitoring results of each numbered sensor with the preset monitoring interval corresponding to the corresponding numbered sensor in the database, and summarize the sensors with abnormal monitoring results in real time to obtain a set of sensors with abnormal status;
[0007] S2. Combining the monitoring data of each fault sensor in the historical data and the relationship between the monitoring components corresponding to each numbered sensor in the device under test, generate a sensor-associated interference set corresponding to each numbered sensor;
[0008] S3, combining the sensor-associated interference set corresponding to each element in the state-abnormal sensor set and its historical monitoring results, calculating the collaborative risk judgment value of each element in the state-abnormal sensor set based on the corresponding sensor-associated interference set, and locking the fault risk source;
[0009] S4. Obtain the abnormal monitoring results corresponding to each fault risk source obtained at the current time, combine the fault risk sources corresponding to different times in the historical data and their corresponding abnormal monitoring results, generate the status risk warning information corresponding to the current time, save the obtained status risk warning information corresponding to the current time to the equipment operation log, and feedback to the administrator of the equipment to be tested.
[0010] Furthermore, when numbering each sensor during the operation of the device under test, the number of the i-th sensor during the operation of the device under test is recorded as Bi; the monitoring result corresponding to Bi at the time point t is recorded as Ci;
[0011] Different numbered sensors in the database correspond to different preset monitoring intervals, and the preset monitoring intervals represent the fluctuation range of the collected data of the monitoring component of the equipment to which the corresponding sensor belongs under normal operating conditions;
[0012] When comparing the monitoring results of each numbered sensor with the preset monitoring interval corresponding to the corresponding numbered sensor in the database, if the monitoring result of the corresponding numbered sensor does not belong to the preset monitoring interval corresponding to the corresponding numbered sensor in the database, the monitoring result of the corresponding numbered sensor is judged to be abnormal; if the monitoring result of the corresponding numbered sensor belongs to the preset monitoring interval corresponding to the corresponding numbered sensor in the database, the monitoring result of the corresponding numbered sensor is judged to be normal.
[0013] Further, when S2 generates the sensor-associated interference set corresponding to each numbered sensor, the monitoring data of each faulty sensor in the historical data is obtained to obtain a faulty sensor number set corresponding to each occurrence of a sensor fault behavior, wherein the faulty sensor number set is a set consisting of each sensor number corresponding to an abnormal monitoring result each time the monitoring result is abnormal;
[0014] Extract the union of all fault sensor number sets containing Bi in the historical data to obtain the reference factor analysis set; any element except Bi in the reference factor analysis set is recorded as the comparison element of Bi, and analyze the relationship between the comparison element of Bi and Bi.
[0015] The number of fault sensor number sets containing Bi in the historical data is recorded as Ni, the number of fault sensor number sets containing comparison elements of Bi in the historical data is recorded as NDi, and the number of fault sensor number sets containing both comparison elements of Bi and Bi in the historical data is recorded as NHi;
[0016] When NHi / Ni is greater than or equal to the first preset value, it is determined that the comparison factor of Bi belongs to the first associated interference factor set of Bi; when NHi / NDi is greater than or equal to the second preset value, it is determined that the comparison factor of Bi belongs to the second associated interference factor set of Bi; the set consisting of the first associated interference factor set that does not belong to Bi, the second associated interference factor set that does not belong to Bi in the reference factor analysis set and the corresponding monitoring components of the corresponding sensors in the device under test and the elements of Bi is recorded as the third associated interference factor set of Bi;
[0017] The sensor associated interference set corresponding to the sensor to which Bi belongs is a set consisting of Bi's first associated interference element set, Bi's second associated interference element set, and Bi's third associated interference element set as elements.
[0018] When the present invention generates sensor associated interference sets corresponding to sensors of each number, a first associated interference element set, a second associated interference element set and a third associated interference element set are respectively constructed. This is because in view of the fact that in the subsequent collaborative analysis process of sensor monitoring results, different sensor monitoring results have different reference weights, which provides data support for the subsequent step of calculating the collaborative risk judgment value of each element in the abnormal state sensor set based on the corresponding sensor associated interference set.
[0019] Furthermore, the method of calculating the collaborative risk determination value of each element in the abnormal state sensor set based on the corresponding sensor associated interference set in S3 includes the following steps:
[0020] S31, obtaining the sensor-associated interference set corresponding to each element in the state abnormal sensor set and its historical monitoring results;
[0021] S32, obtain the collaborative risk factor corresponding to the sensor-associated interference set corresponding to the sensor to which Bi belongs, denoted as Yi,
[0022] Yi=a1·ZH{M1i,CP{M1i}}+a2·ZH{M2i,,CP{M2i}}+a3·ZH{M3i,,CP{M3i}},
[0023] in,
[0024]
[0025] ZH{,} represents a determination function. When the value of the first variable in the determination function is 0, the value of the corresponding determination function is 0; otherwise, the value of the corresponding determination function is the value of the second variable.
[0026] a1, a2 and a3 are confidence weight values, and the values of a1, a2 and a3 are constants preset in the database;
[0027] M1i represents the number of elements in the first associated interference factor set of Bi;
[0028] M2i represents the number of elements in the second associated interference factor set of Bi;
[0029] M3i represents the number of elements in the third associated interference factor set of Bi;
[0030] PZ (1,g) The monitoring result of the g-th element in the first associated interference factor set of Bi at the corresponding time point is based on the monitoring deviation confidence value of the corresponding preset monitoring interval;
[0031] PZ (2,b) The monitoring result of the bth element in the second associated interference factor set of Bi at the corresponding time point is based on the monitoring deviation confidence value of the corresponding preset monitoring interval;
[0032] PZ (3,d) The monitoring result of the dth element in the third associated interference factor set of Bi at the corresponding time point is based on the monitoring deviation confidence value of the corresponding preset monitoring interval;
[0033] The monitoring deviation confidence value of the monitoring result based on the corresponding preset monitoring interval is equal to the quotient of the absolute value of the difference between the corresponding monitoring result and the midpoint of the corresponding preset monitoring interval divided by half the length of the corresponding preset monitoring interval;
[0034] S33, obtain the collaborative risk determination value corresponding to the sensor-associated interference set corresponding to the sensor to which Bi belongs, denoted as XPi,
[0035] XPi=Yi·[(HBi-HBGi)+r1·(QPi-QPGi)],
[0036] Among them, r1 represents the risk determination factor, and r1 is a constant preset in the database;
[0037] HBi represents the monitoring environment fluctuation deviation ratio of the sensor to which Bi belongs; the monitoring environment fluctuation deviation ratio is equal to the quotient of the fluctuation deviation of the corresponding sensor in the most recent preset time period divided by the average value of the fluctuation deviations corresponding to the corresponding sensor at each time point in the historical data;
[0038] HBGi represents the average value of the monitoring environment fluctuation deviation ratio of the sensor to which each element belongs in the sensor-associated interference set corresponding to the sensor to which Bi belongs;
[0039] QPi represents the life cycle replacement deviation ratio of the sensor to which Bi belongs; the life cycle replacement deviation ratio is equal to the quotient of the interval between the current time and the most recent damage replacement time of the corresponding sensor divided by the average of any two adjacent replacement times of the corresponding sensor in the historical data;
[0040] QPGi represents the average value of the life cycle replacement deviation ratio of the sensor to which each element belongs in the sensor-associated interference set corresponding to the sensor to which Bi belongs;
[0041] When locking the fault risk source, the average value of the collaborative risk judgment value corresponding to each element in the sensor associated interference set corresponding to the sensor to which Bi belongs is calculated, and recorded as XPGi; when XPi is greater than or equal to XPGi, it is determined that the locked fault risk source is the monitoring component of the sensor corresponding to Bi in the device under test; otherwise, it is determined that the locked fault risk source is the sensor corresponding to Bi.
[0042] When locking the risk source, the present invention realizes accurate locking of the fault risk source through the corresponding collaborative risk judgment value, that is, distinguishing whether the cause of the abnormal sensor monitoring result is the equipment operation state or the sensor itself fault.
[0043] Further, the state risk warning information includes one or more elements, and each element corresponds to a state feature array, each state feature array includes a sensor number, an abnormal detection result set corresponding to the corresponding sensor number, a set of fault risk sources corresponding to each element in the abnormal detection result set corresponding to the corresponding sensor number, and a time interval corresponding to the abnormal detection result set corresponding to the corresponding sensor number;
[0044] The time interval from the time when the corresponding administrator last read the device operation log to the current time is recorded as the time reference interval;
[0045] The sensor number included in the status risk warning information corresponding to the current time is the sensor number corresponding to the abnormal monitoring result within the time reference interval;
[0046] The abnormal detection result set corresponding to the corresponding sensor number included in the state risk warning information corresponding to the current time is a set of abnormal monitoring results obtained by the sensor with the corresponding number within the time reference interval;
[0047] The time interval corresponding to the abnormal detection result set corresponding to the corresponding sensor number contained in the status risk warning information corresponding to the current time is the time interval between the minimum time point and the maximum time point among the monitoring time points corresponding to the abnormal monitoring results obtained by the sensor with the corresponding number within the time reference interval.
[0048] An intelligent monitoring system for equipment operation status based on big data analysis, the system comprising:
[0049] An abnormal sensor acquisition module, which numbers each sensor during the operation of the device to be tested and obtains the monitoring results of each numbered sensor in real time; compares the monitoring results of each numbered sensor with the preset monitoring interval corresponding to the corresponding numbered sensor in the database, and summarizes the sensors with abnormal monitoring results in real time to obtain a set of abnormal state sensors;
[0050] A sensor-related interference analysis module, which combines the monitoring data of each fault sensor in the historical data and the relationship between the monitoring components corresponding to each numbered sensor in the device under test to generate a sensor-related interference set corresponding to each numbered sensor;
[0051] A collaborative risk assessment module, which combines the sensor-related interference set corresponding to each element in the state-abnormal sensor set and its historical monitoring results, calculates the collaborative risk judgment value of each element in the state-abnormal sensor set based on the corresponding sensor-related interference set, and locks the fault risk source;
[0052] A status risk warning control module obtains the abnormal monitoring results corresponding to each fault risk source obtained at the current time, combines the fault risk sources corresponding to different times in the historical data and their corresponding abnormal monitoring results, generates the status risk warning information corresponding to the current time, saves the status risk warning information corresponding to the current time into the equipment operation log, and feeds it back to the administrator of the equipment under test.
[0053] Furthermore, the sensor-related interference analysis module includes a monitoring component relationship acquisition unit and a sensor-related interference set generation unit.
[0054] The monitoring component relationship acquisition unit is used to acquire the monitoring data of each fault sensor in the historical data and the relationship between each numbered sensor and the corresponding monitoring component in the device under test;
[0055] The sensor-associated interference set generating unit generates a sensor-associated interference set corresponding to each numbered sensor according to the acquisition result of the monitoring component relationship acquiring unit.
[0056] Furthermore, the state risk warning control module includes a state risk warning information generation unit and a warning information control unit.
[0057] The state risk warning information generation unit obtains the abnormal monitoring results corresponding to each fault risk source obtained at the current time, combines the fault risk sources corresponding to different times in the historical data and their corresponding abnormal monitoring results, and generates the state risk warning information corresponding to the current time;
[0058] The early warning information management and control unit saves the status risk early warning information corresponding to the current time into the equipment operation log, and feeds it back to the administrator of the equipment to be tested.
[0059] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: when intelligently supervising the operating status of the equipment, the present invention takes into account the false alarm situation caused by the upper limit of the service life of the sensor, and analyzes the correlation between different sensors in the equipment to be tested, and conducts collaborative analysis based on the monitoring results of the associated sensors, so as to accurately judge the operating status of the equipment to be tested and realize effective supervision of the operating status of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0061] Figure 1 It is a structural schematic diagram of the intelligent monitoring system for equipment operation status based on big data analysis of the present invention;
[0062] Figure 2 It is a flow chart of the intelligent monitoring method of equipment operation status based on big data analysis of the present invention. DETAILED DESCRIPTION
[0063] 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.
[0064] See also Figure 1 The present invention provides a technical solution: an intelligent monitoring system for equipment operation status based on big data analysis, the system comprising:
[0065] An abnormal sensor acquisition module, which numbers each sensor during the operation of the device to be tested and obtains the monitoring results of each numbered sensor in real time; compares the monitoring results of each numbered sensor with the preset monitoring interval corresponding to the corresponding numbered sensor in the database, and summarizes the sensors with abnormal monitoring results in real time to obtain a set of abnormal state sensors;
[0066] A sensor-related interference analysis module, which combines the monitoring data of each fault sensor in the historical data and the relationship between the monitoring components corresponding to each numbered sensor in the device under test to generate a sensor-related interference set corresponding to each numbered sensor;
[0067] A collaborative risk assessment module, which combines the sensor-related interference set corresponding to each element in the state-abnormal sensor set and its historical monitoring results, calculates the collaborative risk judgment value of each element in the state-abnormal sensor set based on the corresponding sensor-related interference set, and locks the fault risk source;
[0068] A status risk warning control module obtains the abnormal monitoring results corresponding to each fault risk source obtained at the current time, combines the fault risk sources corresponding to different times in the historical data and their corresponding abnormal monitoring results, generates the status risk warning information corresponding to the current time, saves the status risk warning information corresponding to the current time into the equipment operation log, and feeds it back to the administrator of the equipment under test.
[0069] The sensor-related interference analysis module includes a monitoring component relationship acquisition unit and a sensor-related interference set generation unit.
[0070] The monitoring component relationship acquisition unit is used to acquire the monitoring data of each fault sensor in the historical data and the relationship between each numbered sensor and the corresponding monitoring component in the device under test;
[0071] The sensor-associated interference set generating unit generates a sensor-associated interference set corresponding to each numbered sensor according to the acquisition result of the monitoring component relationship acquiring unit.
[0072] The state risk warning control module includes a state risk warning information generation unit and a warning information control unit.
[0073] The state risk warning information generation unit obtains the abnormal monitoring results corresponding to each fault risk source obtained at the current time, combines the fault risk sources corresponding to different times in the historical data and their corresponding abnormal monitoring results, and generates the state risk warning information corresponding to the current time;
[0074] The early warning information management and control unit saves the status risk early warning information corresponding to the current time into the equipment operation log, and feeds it back to the administrator of the equipment to be tested.
[0075] like Figure 2 As shown, a method for intelligently supervising the operation status of equipment based on big data analysis comprises the following steps:
[0076] S1. Number each sensor during the operation of the equipment to be tested, and obtain the monitoring results of each numbered sensor in real time; compare the monitoring results of each numbered sensor with the preset monitoring interval corresponding to the corresponding numbered sensor in the database, and summarize the sensors with abnormal monitoring results in real time to obtain a set of sensors with abnormal status;
[0077] When numbering each sensor during the operation of the device under test, the number of the i-th sensor during the operation of the device under test is recorded as Bi; the monitoring result corresponding to Bi at the time point t is recorded as Ci;
[0078] Different numbered sensors in the database correspond to different preset monitoring intervals, and the preset monitoring intervals represent the fluctuation range of the collected data of the monitoring component of the equipment to which the corresponding sensor belongs under normal operating conditions;
[0079] When comparing the monitoring results of each numbered sensor with the preset monitoring interval corresponding to the corresponding numbered sensor in the database, if the monitoring result of the corresponding numbered sensor does not belong to the preset monitoring interval corresponding to the corresponding numbered sensor in the database, the monitoring result of the corresponding numbered sensor is judged to be abnormal; if the monitoring result of the corresponding numbered sensor belongs to the preset monitoring interval corresponding to the corresponding numbered sensor in the database, the monitoring result of the corresponding numbered sensor is judged to be normal.
[0080] S2. Combining the monitoring data of each fault sensor in the historical data and the relationship between the monitoring components corresponding to each numbered sensor in the device under test, generate a sensor-associated interference set corresponding to each numbered sensor;
[0081] When the S2 generates the sensor-associated interference set corresponding to each numbered sensor, the monitoring data of each faulty sensor in the historical data is obtained to obtain the faulty sensor number set corresponding to each occurrence of sensor fault behavior, wherein the faulty sensor number set is a set consisting of each sensor number corresponding to the abnormal monitoring result each time the monitoring result is abnormal;
[0082] Extract the union of all fault sensor number sets containing Bi in the historical data to obtain the reference factor analysis set; any element except Bi in the reference factor analysis set is recorded as the comparison element of Bi, and analyze the relationship between the comparison element of Bi and Bi.
[0083] The number of fault sensor number sets containing Bi in the historical data is recorded as Ni, the number of fault sensor number sets containing comparison elements of Bi in the historical data is recorded as NDi, and the number of fault sensor number sets containing both comparison elements of Bi and Bi in the historical data is recorded as NHi;
[0084] When NHi / Ni is greater than or equal to the first preset value, it is determined that the comparison factor of Bi belongs to the first associated interference factor set of Bi; when NHi / NDi is greater than or equal to the second preset value, it is determined that the comparison factor of Bi belongs to the second associated interference factor set of Bi; the set consisting of the first associated interference factor set that does not belong to Bi, the second associated interference factor set that does not belong to Bi in the reference factor analysis set and the corresponding monitoring components of the corresponding sensors in the device under test and the elements of Bi is recorded as the third associated interference factor set of Bi;
[0085] The sensor associated interference set corresponding to the sensor to which Bi belongs is a set consisting of Bi's first associated interference element set, Bi's second associated interference element set, and Bi's third associated interference element set as elements.
[0086] S3, combining the sensor-associated interference set corresponding to each element in the state-abnormal sensor set and its historical monitoring results, calculating the collaborative risk judgment value of each element in the state-abnormal sensor set based on the corresponding sensor-associated interference set, and locking the fault risk source;
[0087] The method for calculating the collaborative risk determination value of each element in the abnormal state sensor set based on the corresponding sensor associated interference set in S3 includes the following steps:
[0088] S31, obtaining the sensor-associated interference set corresponding to each element in the state abnormal sensor set and its historical monitoring results;
[0089] S32, obtain the collaborative risk factor corresponding to the sensor-associated interference set corresponding to the sensor to which Bi belongs, denoted as Yi,
[0090] Yi=a1·ZH{M1i,CP{M1i}}+a2·ZH{M2i,,CP{M2i}}+a3·ZH{M3i,,CP{M3i}},
[0091] in,
[0092]
[0093] ZH{,} represents a determination function. When the value of the first variable in the determination function is 0, the value of the corresponding determination function is 0; otherwise, the value of the corresponding determination function is the value of the second variable.
[0094] a1, a2 and a3 are confidence weight values, and the values of a1, a2 and a3 are constants preset in the database;
[0095] M1i represents the number of elements in the first associated interference factor set of Bi;
[0096] M2i represents the number of elements in the second associated interference factor set of Bi;
[0097] M3i represents the number of elements in the third associated interference factor set of Bi;
[0098] PZ (1,g) The monitoring result of the g-th element in the first associated interference factor set of Bi at the corresponding time point is based on the monitoring deviation confidence value of the corresponding preset monitoring interval;
[0099] PZ (2,b) The monitoring result of the bth element in the second associated interference factor set of Bi at the corresponding time point is based on the monitoring deviation confidence value of the corresponding preset monitoring interval;
[0100] PZ (3,d) The monitoring result of the dth element in the third associated interference factor set of Bi at the corresponding time point is based on the monitoring deviation confidence value of the corresponding preset monitoring interval;
[0101] The monitoring deviation confidence value of the monitoring result based on the corresponding preset monitoring interval is equal to the quotient of the absolute value of the difference between the corresponding monitoring result and the midpoint of the corresponding preset monitoring interval divided by half the length of the corresponding preset monitoring interval;
[0102] S33, obtain the collaborative risk determination value corresponding to the sensor-associated interference set corresponding to the sensor to which Bi belongs, denoted as XPi,
[0103] XPi=Yi·[(HBi-HBGi)+r1·(QPi-QPGi)],
[0104] Among them, r1 represents the risk determination factor, and r1 is a constant preset in the database;
[0105] HBi represents the monitoring environment fluctuation deviation ratio of the sensor to which Bi belongs; the monitoring environment fluctuation deviation ratio is equal to the quotient of the fluctuation deviation of the corresponding sensor in the most recent preset time period divided by the average value of the fluctuation deviations corresponding to the corresponding sensor at each time point in the historical data;
[0106] HBGi represents the average value of the monitoring environment fluctuation deviation ratio of the sensor to which each element belongs in the sensor-associated interference set corresponding to the sensor to which Bi belongs;
[0107] QPi represents the life cycle replacement deviation ratio of the sensor to which Bi belongs; the life cycle replacement deviation ratio is equal to the quotient of the interval between the current time and the most recent damage replacement time of the corresponding sensor divided by the average of any two adjacent replacement times of the corresponding sensor in the historical data;
[0108] QPGi represents the average value of the life cycle replacement deviation ratio of the sensor to which each element belongs in the sensor-associated interference set corresponding to the sensor to which Bi belongs;
[0109] When locking the fault risk source, the average value of the collaborative risk judgment value corresponding to each element in the sensor associated interference set corresponding to the sensor to which Bi belongs is calculated, and recorded as XPGi; when XPi is greater than or equal to XPGi, it is determined that the locked fault risk source is the monitoring component of the sensor corresponding to Bi in the device under test; otherwise, it is determined that the locked fault risk source is the sensor corresponding to Bi.
[0110] S4. Obtain the abnormal monitoring results corresponding to each fault risk source obtained at the current time, combine the fault risk sources corresponding to different times in the historical data and their corresponding abnormal monitoring results, generate the status risk warning information corresponding to the current time, save the obtained status risk warning information corresponding to the current time to the equipment operation log, and feedback to the administrator of the equipment to be tested.
[0111] The state risk warning information includes one or more elements, and each element corresponds to a state feature array, each state feature array includes a sensor number, an abnormal detection result set corresponding to the corresponding sensor number, a set of fault risk sources corresponding to each element in the abnormal detection result set corresponding to the corresponding sensor number, and a time interval corresponding to the abnormal detection result set corresponding to the corresponding sensor number;
[0112] The time interval from the time when the corresponding administrator last read the device operation log to the current time is recorded as the time reference interval;
[0113] The sensor number included in the status risk warning information corresponding to the current time is the sensor number corresponding to the abnormal monitoring result within the time reference interval;
[0114] The abnormal detection result set corresponding to the corresponding sensor number included in the state risk warning information corresponding to the current time is a set of abnormal monitoring results obtained by the sensor with the corresponding number within the time reference interval;
[0115] The time interval corresponding to the abnormal detection result set corresponding to the corresponding sensor number contained in the status risk warning information corresponding to the current time is the time interval between the minimum time point and the maximum time point among the monitoring time points corresponding to the abnormal monitoring results obtained by the sensor with the corresponding number within the time reference interval.
[0116] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0117] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. An intelligent monitoring method for equipment operation status based on big data analysis, characterized in that: The method comprises the following steps: S1. Number each sensor during the operation of the equipment to be tested, and obtain the monitoring results of each numbered sensor in real time; compare the monitoring results of each numbered sensor with the preset monitoring interval corresponding to the corresponding numbered sensor in the database, and summarize the sensors with abnormal monitoring results in real time to obtain a set of abnormal state sensors; S2. Combining the monitoring data of each fault sensor in the historical data and the relationship between the monitoring components corresponding to each numbered sensor in the device under test, generate a sensor-associated interference set corresponding to each numbered sensor; S3, combining the sensor-associated interference set corresponding to each element in the state-abnormal sensor set and its historical monitoring results, calculating the collaborative risk judgment value of each element in the state-abnormal sensor set based on the corresponding sensor-associated interference set, and locking the fault risk source; S4. Obtain the abnormal monitoring results corresponding to each fault risk source obtained at the current time, combine the fault risk sources corresponding to different times in the historical data and their corresponding abnormal monitoring results, generate the status risk warning information corresponding to the current time, save the obtained status risk warning information corresponding to the current time to the equipment operation log, and feedback to the administrator of the equipment to be tested.
2. The method for intelligent monitoring of equipment operation status based on big data analysis according to claim 1 is characterized in that: When numbering each sensor during the operation of the device under test, the number of the i-th sensor during the operation of the device under test is recorded as Bi; the monitoring result corresponding to Bi at the time point t is recorded as Ci; Different numbered sensors in the database correspond to different preset monitoring intervals, and the preset monitoring intervals represent the fluctuation range of the collected data of the monitoring component of the equipment to which the corresponding sensor belongs under normal operating conditions; When comparing the monitoring results of each numbered sensor with the preset monitoring interval corresponding to the corresponding numbered sensor in the database, if the monitoring result of the corresponding numbered sensor does not belong to the preset monitoring interval corresponding to the corresponding numbered sensor in the database, the monitoring result of the corresponding numbered sensor is judged to be abnormal; if the monitoring result of the corresponding numbered sensor belongs to the preset monitoring interval corresponding to the corresponding numbered sensor in the database, the monitoring result of the corresponding numbered sensor is judged to be normal.
3. The method for intelligent monitoring of equipment operation status based on big data analysis according to claim 2 is characterized in that: When the S2 generates the sensor-associated interference set corresponding to each numbered sensor, the monitoring data of each faulty sensor in the historical data is obtained to obtain the faulty sensor number set corresponding to each occurrence of sensor fault behavior, wherein the faulty sensor number set is a set consisting of each sensor number corresponding to the abnormal monitoring result each time the monitoring result is abnormal; Extract the union of all fault sensor number sets containing Bi in the historical data to obtain the reference factor analysis set; any element except Bi in the reference factor analysis set is recorded as the comparison element of Bi, and analyze the relationship between the comparison element of Bi and Bi. The number of fault sensor number sets containing Bi in the historical data is recorded as Ni, the number of fault sensor number sets containing comparison elements of Bi in the historical data is recorded as NDi, and the number of fault sensor number sets containing both comparison elements of Bi and Bi in the historical data is recorded as NHi; When NHi / Ni is greater than or equal to a first preset value, it is determined that the comparison factor of Bi belongs to the first associated interference factor set of Bi; when NHi / NDi is greater than or equal to a second preset value, it is determined that the comparison factor of Bi belongs to the second associated interference factor set of Bi; The first associated interference element set not belonging to Bi, the second associated interference element set not belonging to Bi and the set consisting of the monitoring components corresponding to the corresponding sensors in the device under test and the elements of Bi in the reference element analysis set are recorded as the third associated interference element set of Bi; The sensor associated interference set corresponding to the sensor to which Bi belongs is a set consisting of Bi's first associated interference element set, Bi's second associated interference element set, and Bi's third associated interference element set as elements.
4. The method for intelligent monitoring of equipment operation status based on big data analysis according to claim 3 is characterized in that: The method for calculating the collaborative risk determination value of each element in the abnormal state sensor set based on the corresponding sensor associated interference set in S3 includes the following steps: S31, obtaining the sensor-associated interference set corresponding to each element in the state abnormal sensor set and its historical monitoring results; S32, obtain the collaborative risk factor corresponding to the sensor-associated interference set corresponding to the sensor to which Bi belongs, denoted as Yi, Yi=a1·ZH{M1i,CP{M1i}}+a2·ZH{M2i,,CP{M2i}}+a3·ZH{M3i,,CP{M3i}}, in, ZH{,} represents a determination function. When the value of the first variable in the determination function is 0, the value of the corresponding determination function is 0; otherwise, the value of the corresponding determination function is the value of the second variable. a1, a2 and a3 are confidence weight values, and the values of a1, a2 and a3 are constants preset in the database; M1i represents the number of elements in the first associated interference factor set of Bi; M2i represents the number of elements in the second associated interference factor set of Bi; M3i represents the number of elements in the third associated interference factor set of Bi; PZ (1,g) represents the monitoring deviation confidence value of the g-th element in the first associated interference factor set of Bi at the corresponding time point based on the corresponding preset monitoring interval; PZ (2,b) The monitoring result of the bth element in the second associated interference factor set of Bi at the corresponding time point is based on the monitoring deviation confidence value of the corresponding preset monitoring interval; PZ (3,d) The monitoring result of the dth element in the third associated interference factor set of Bi at the corresponding time point is based on the monitoring deviation confidence value of the corresponding preset monitoring interval; The monitoring deviation confidence value of the monitoring result based on the corresponding preset monitoring interval is equal to the quotient of the absolute value of the difference between the corresponding monitoring result and the midpoint of the corresponding preset monitoring interval divided by half the length of the corresponding preset monitoring interval; S33, obtain the collaborative risk determination value corresponding to the sensor-associated interference set corresponding to the sensor to which Bi belongs, denoted as XPi, XPi=Yi·[(HBi-HBGi)+r1·(QPi-QPGi)], Among them, r1 represents the risk determination factor, and r1 is a constant preset in the database; HBi represents the monitoring environment fluctuation deviation ratio of the sensor to which Bi belongs; the monitoring environment fluctuation deviation ratio is equal to the quotient of the fluctuation deviation of the corresponding sensor in the most recent preset time period divided by the average value of the fluctuation deviations corresponding to the corresponding sensor at each time point in the historical data; HBGi represents the average value of the monitoring environment fluctuation deviation ratio of the sensor to which each element belongs in the sensor-associated interference set corresponding to the sensor to which Bi belongs; QPi represents the life cycle replacement deviation ratio of the sensor to which Bi belongs; the life cycle replacement deviation ratio is equal to the quotient of the interval between the current time and the most recent damage replacement time of the corresponding sensor divided by the average of any two adjacent replacement times of the corresponding sensor in the historical data; QPGi represents the average value of the life cycle replacement deviation ratio of the sensor to which each element belongs in the sensor-associated interference set corresponding to the sensor to which Bi belongs; When locking the fault risk source, the average value of the collaborative risk judgment value corresponding to each element in the sensor associated interference set corresponding to the sensor to which Bi belongs is calculated, and recorded as XPGi; when XPi is greater than or equal to XPGi, it is determined that the locked fault risk source is the monitoring component of the sensor corresponding to Bi in the device under test; otherwise, it is determined that the locked fault risk source is the sensor corresponding to Bi.
5. The method for intelligent monitoring of equipment operation status based on big data analysis according to claim 1 is characterized in that: The state risk warning information includes one or more elements, and each element corresponds to a state feature array, each state feature array includes a sensor number, an abnormal detection result set corresponding to the corresponding sensor number, a set of fault risk sources corresponding to each element in the abnormal detection result set corresponding to the corresponding sensor number, and a time interval corresponding to the abnormal detection result set corresponding to the corresponding sensor number; The time interval from the time when the corresponding administrator last read the device operation log to the current time is recorded as the time reference interval; The sensor number included in the status risk warning information corresponding to the current time is the sensor number corresponding to the abnormal monitoring result within the time reference interval; The abnormal detection result set corresponding to the corresponding sensor number included in the state risk warning information corresponding to the current time is a set of abnormal monitoring results obtained by the sensor with the corresponding number within the time reference interval; The time interval corresponding to the abnormal detection result set corresponding to the corresponding sensor number contained in the status risk warning information corresponding to the current time is the time interval between the minimum time point and the maximum time point among the monitoring time points corresponding to the abnormal monitoring results obtained by the sensor with the corresponding number within the time reference interval.
6. Intelligent monitoring system for equipment operation status based on big data analysis, characterized by: The system comprises: An abnormal sensor acquisition module, which numbers each sensor during the operation of the device to be tested and obtains the monitoring results of each numbered sensor in real time; compares the monitoring results of each numbered sensor with the preset monitoring interval corresponding to the corresponding numbered sensor in the database, and summarizes the sensors with abnormal monitoring results in real time to obtain a set of abnormal state sensors; A sensor-related interference analysis module, which combines the monitoring data of each fault sensor in the historical data and the relationship between the monitoring components corresponding to each numbered sensor in the device under test to generate a sensor-related interference set corresponding to each numbered sensor; A collaborative risk assessment module, which combines the sensor-related interference set corresponding to each element in the state-abnormal sensor set and its historical monitoring results, calculates the collaborative risk judgment value of each element in the state-abnormal sensor set based on the corresponding sensor-related interference set, and locks the fault risk source; A status risk warning control module obtains the abnormal monitoring results corresponding to each fault risk source obtained at the current time, combines the fault risk sources corresponding to different times in the historical data and their corresponding abnormal monitoring results, generates the status risk warning information corresponding to the current time, saves the status risk warning information corresponding to the current time into the equipment operation log, and feeds it back to the administrator of the equipment under test.
7. The intelligent monitoring system for equipment operation status based on big data analysis according to claim 6 is characterized by: The sensor-related interference analysis module includes a monitoring component relationship acquisition unit and a sensor-related interference set generation unit. The monitoring component relationship acquisition unit is used to acquire the monitoring data of each fault sensor in the historical data and the relationship between each numbered sensor and the corresponding monitoring component in the device under test; The sensor-associated interference set generating unit generates a sensor-associated interference set corresponding to each numbered sensor according to the acquisition result of the monitoring component relationship acquiring unit.
8. The intelligent monitoring system for equipment operation status based on big data analysis according to claim 6 is characterized by: The state risk warning control module includes a state risk warning information generation unit and a warning information control unit. The state risk warning information generation unit obtains the abnormal monitoring results corresponding to each fault risk source obtained at the current time, combines the fault risk sources corresponding to different times in the historical data and their corresponding abnormal monitoring results, and generates the state risk warning information corresponding to the current time; The early warning information management and control unit saves the status risk early warning information corresponding to the current time into the equipment operation log, and feeds it back to the administrator of the equipment to be tested.
Citation Information
Patent Citations
Digital intelligent monitoring system and method for optical fiber device processing equipment
CN116126836A
Goods circulation management system and method applied to wholesale market
CN116384849A
Intelligent building two-bus monitoring system and method based on artificial intelligence
CN116668482A
Rotary transformer sensor performance detection system and method based on data analysis
CN116907565A
Multi-control scheme digital intelligent granary data supervision system and method
CN117666447A
Cited By
Detection robot inspection scheduling management system and method based on Internet of Things
CN119168329A
Simulation voice line intervention state monitoring system and method based on big data
CN119520679A
Cloud edge data collaboration system and method for sewage treatment
CN119892886A
Intelligent detection method and system for transformer
CN120044444A
Method for early warning and dynamic tracking monitoring of power transformation main equipment
CN120109995A
