CN117235649B - Industrial equipment state intelligent monitoring system and method based on big data - Google Patents
Industrial equipment state intelligent monitoring system and method based on big data Download PDFInfo
- Publication number
- CN117235649B CN117235649B CN202311489262.4A CN202311489262A CN117235649B CN 117235649 B CN117235649 B CN 117235649B CN 202311489262 A CN202311489262 A CN 202311489262A CN 117235649 B CN117235649 B CN 117235649B
- Authority
- CN
- China
- Prior art keywords
- target
- parameter
- equipment
- abnormal
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 233
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000002159 abnormal effect Effects 0.000 claims abstract description 162
- 238000004458 analytical method Methods 0.000 claims abstract description 23
- 230000004044 response Effects 0.000 claims abstract description 18
- 238000010276 construction Methods 0.000 claims abstract description 11
- 238000013479 data entry Methods 0.000 claims abstract description 5
- 230000008859 change Effects 0.000 claims description 23
- 230000005856 abnormality Effects 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000012163 sequencing technique Methods 0.000 claims description 10
- 238000012423 maintenance Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 230000009471 action Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the field of industrial equipment state monitoring, in particular to an industrial equipment state intelligent monitoring system and method based on big data, comprising an equipment record data input module, an abnormal priority analysis module, an associated equipment set generation module, an associated early warning event package construction module and an associated early warning response module; the equipment record data entry module is used for acquiring state data and abnormal events recorded by target monitoring industrial equipment in the entry monitoring system; the abnormal priority analysis module is used for determining abnormal priorities of different types of parameters corresponding to each target monitoring industrial equipment; the associated equipment set generating module is used for judging the relevance of the state parameters recorded by the state numbers and generating an associated equipment set; the associated early warning event package construction module is used for analyzing an associated early warning event package through the history abnormal event; the associated early warning response module is used for analyzing and generating the priority of the associated early warning event package and carrying out associated early warning response when the target monitoring industrial equipment is in early warning.
Description
Technical Field
The invention relates to the technical field of industrial equipment state monitoring, in particular to an industrial equipment state intelligent monitoring system and method based on big data.
Background
The purpose of the industrial equipment state monitoring is to grasp the health condition of the equipment in real time, discover potential fault signs in time and take corresponding maintenance and maintenance measures. Through effective state monitoring, enterprises can reduce equipment fault risks, reduce unplanned downtime, improve production efficiency, save maintenance cost and ensure the safety and reliability of a working environment;
however, the state monitoring of the existing industrial equipment basically uses the same monitoring method for one equipment or one type of equipment, and does not consider whether the monitoring equipment has an influence relation on the same monitoring parameters, so that the abnormality of other types of industrial equipment in a short period is generated, and when a plurality of equipment possibly having related influence are generated, the existing state monitoring cannot divide the reasonable early warning level difference of the equipment so as to make a data clear and effective direction prompt for a manager.
Disclosure of Invention
The invention aims to provide an industrial equipment state intelligent monitoring system and method based on big data, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: an intelligent monitoring method for the state of industrial equipment based on big data comprises the following analysis steps:
step S100: acquiring state data and abnormal events recorded by target monitoring industrial equipment in a monitoring system, wherein the state data refers to state parameters recorded by the target monitoring industrial equipment by using a corresponding monitoring method; the abnormal event is an event that the monitoring system generates an early warning signal when the early warning condition set by the system is met and the interval period is smaller than the average abnormal period for each target monitoring industrial device; determining abnormal priorities of different types of parameters corresponding to each target monitoring industrial equipment;
step S200: the primary abnormal event record is an event recorded by early warning of target monitoring industrial equipment; judging the relevance of state parameters of the state number recording based on the abnormal priority and generating a relevant equipment set;
step S300: when the record state parameter does not have the associated equipment set, continuing to monitor; when the state parameters have the associated equipment set, extracting a target query parameter pair, and analyzing an associated early warning event package through the history abnormal event;
step S400: and obtaining the number of the target query parameter pairs, analyzing and generating the priority of the associated early warning event package, and carrying out associated early warning response when the target monitoring industrial equipment is in early warning.
Further, determining abnormal priorities of the target monitoring industrial devices corresponding to different types of parameters, wherein the abnormal priorities comprise the following steps:
step S110: acquiring all state parameters recorded by the ith target monitoring industrial equipment in historical abnormal events, classifying the state parameters according to corresponding types, and extracting an event log Q recorded by the jth state parameters in each abnormal event j The event log refers to data of maintenance records of abnormal target monitoring industrial equipment after an abnormal event occurs; the event log comprises maintenance object data and abnormal frequencies of state parameters;
step S120: using the formula: w (W) ij =k 1 *(n ij /N)+k 2 *(r ij /T ij )；
Calculating a monitoring index W of a j-th type state parameter of the i-th target monitoring industrial equipment ij ；
Wherein k is 1 、k 2 Representing the corresponding reference coefficient, n ij The method comprises the steps that overhauling object data of a j-th type state parameter of an i-th target monitoring industrial device in an abnormal event is represented, namely the number of other target monitoring industrial devices to be detected is related to the j-th type state parameter; n represents the total number of target monitoring industrial equipment, and i is less than or equal to N; n is n ij N represents the influence proportion of the ith target monitoring industrial equipment when the jth state parameter is abnormal;
r ij indicating the number of times of recording the j-th type state parameter abnormality of the i-th target monitoring industrial equipment in the monitoring period, T ij The j-th type state parameter of the i-th target monitoring industrial equipment is represented by the interval duration of the first abnormality and the last abnormality of the monitoring period; r is (r) ij /T ij A status parameter anomaly frequency representing a jth type of status parameter of the ith target monitoring industrial equipment;
W ij the larger the monitoring index under the corresponding target monitoring industrial equipment is, the larger the range of the monitoring index needs to be overhauled in case of abnormality is, and the possibility of influencing other industrial equipment is higher;
step S130: sequencing M-type state parameters of the ith target monitoring industrial equipment from large to small according to the value of the monitoring index to generate different types of parameters corresponding to the target monitoring industrial equipmentAbnormal priority P of number i ，j≤M。
Further, the association device set includes the following analysis steps:
step S210: extracting a first state parameter in the abnormal priority recorded by any target monitoring industrial equipment as a target parameter, traversing the abnormal priorities recorded by all target monitoring industrial equipment, and determining the number F of the state parameters of the same type as the target parameter and the position serial number D of the corresponding abnormal priority;
step S220: when f=0, the output state parameter does not have an associated device set;
when f=1, marking the same type of state parameter as the target parameter as the state parameter to be analyzed, and calculating a first position difference d between the state parameter to be analyzed and the target parameter 1 ，d 1 =D 1 -D 0 The method comprises the steps of carrying out a first treatment on the surface of the And set a first position difference threshold d 0 The first position difference threshold value is calculated by the number of all state parameters in the abnormal priority corresponding to the target parameter and the number of all state parameters in the abnormal priority corresponding to the state parameter to be analyzed, and specifically comprises the following steps: d, d 0 =「U 0 /(F+1)」，U 0 Representing the number average value of all state parameters contained in the abnormal priorities to which different state parameters belong, 'U' 0 /(F+1)' represents the sum of U 0 The value of/(F+1) is rounded;
when F >1, marking the state parameters of the same type as the target parameters as the state parameters to be analyzed, and sequentially calculating first position differences of the target parameters and the state parameters to be analyzed to obtain a first position difference set;
step S230: when d is present 1 >d 0 When the state parameters to be analyzed are marked as filtering parameters, deleting the filtering parameters; when d is present 1 ≤d 0 When the target parameter is compared with the monitoring index W corresponding to the state parameter to be analyzed, the difference value W of the monitoring index is calculated 0 ，w 0 =｜W 1 -W 2 ｜，W 1 Representing the corresponding monitoring index of the target parameter, W 2 Representing a monitoring index corresponding to the state parameter to be analyzed; setting a monitoring index threshold value w when 0 >w time outputThe state parameter to be analyzed has no relevance with the target parameter, when w 0 When w is less than or equal to w, outputting the correlation between the state parameter to be analyzed and the target parameter, and outputting target industrial monitoring equipment to which the state parameter to be analyzed with the correlation belongs to generate a correlation equipment set;
the smaller difference value indicates that the mutual influence and the association degree are larger; it is more convincing to determine the state parameters that may have an associated influence by two comparisons.
Step S240: and traversing all state parameters recorded by all target monitoring industrial equipment, generating each state parameter as an associated equipment set corresponding to the target parameter, and storing.
Further, step S300 includes:
step S310: extracting target monitoring industrial equipment corresponding to the target parameters as first equipment and target monitoring industrial equipment in a target parameter corresponding association equipment set as second equipment, and taking the same state parameters recorded by the first equipment and the second equipment as target query parameter pairs H, H= (H) 1 ,h 2 )，h 1 Representing the corresponding state parameter of the first equipment, h 2 Representing state parameters corresponding to the second equipment, wherein the target query parameter pairs are ordered according to the occurrence sequence of the abnormal event; i.e. h 1 Recording earlier than h 2 ；
Step S320: traversing two adjacent abnormal events in the history abnormal events, and marking the event with the adjacent abnormal event meeting the target query parameter pair as an adjacent event group; extracting data records of the same state parameters in adjacent event groups, wherein the data records refer to a numerical value change set recorded in the second industrial equipment by the same state parameters in a period from the time when the first industrial equipment is determined to be abnormal to the time when the second industrial equipment is determined to be abnormal;
step S330: if the historical abnormal event records that the two adjacent abnormal events are unique, marking the data record as an effective feature set of the target query parameter pair; if the historical abnormal event record is not unique in two adjacent abnormal events, equally dividing the numerical value change set, and extracting the numerical value change of the corresponding segmented record with the highest similarity to generate an effective feature set of the target query parameter pair;
step S340: traversing to generate all target query parameter pairs, using a first industrial device in the target query parameter pairs as identifiable devices, using state parameters corresponding to the first industrial device as identifiable device parameters, using an effective feature set of the target query parameter pairs as a matching set, and using a second industrial device after successful matching as early warning device to generate an associated early warning event package; and the successful matching means that the similarity between the parameter change data of the second industrial equipment after the early warning of the first industrial equipment and the data recorded by the effective feature set is larger than a similarity threshold under the real-time monitoring.
Further, step S400 includes the following analysis steps:
when the number of the target query parameter pairs is greater than or equal to two and the similarity between the parameter value change recorded by the second industrial equipment in the target query parameter pairs and the effective feature set is greater than a similarity threshold;
sequencing the second industrial equipment from large to small according to the magnitude of the similarity value to generate the priority of the corresponding associated early warning event package;
and when the target monitoring industrial equipment is in early warning, acquiring early warning parameters of the target monitoring industrial equipment and extracting associated early warning response which satisfies the sequentially reduced degree of the associated early warning event package of the step S340 in the order of corresponding priority.
The intelligent monitoring system for the state of the industrial equipment comprises an equipment record data input module, an abnormal priority analysis module, an associated equipment set generation module, an associated early warning event package construction module and an associated early warning response module;
the equipment record data entry module is used for acquiring state data and abnormal events recorded by target monitoring industrial equipment in the entry monitoring system;
the abnormal priority analysis module is used for determining abnormal priorities of different types of parameters corresponding to each target monitoring industrial equipment;
the associated equipment set generating module is used for judging the relevance of the state parameters recorded by the state numbers and generating an associated equipment set;
the associated early warning event package construction module is used for analyzing an associated early warning event package through the history abnormal event;
the associated early warning response module is used for analyzing and generating the priority of the associated early warning event package and carrying out associated early warning response when the target monitoring industrial equipment is in early warning.
Further, the abnormal priority analysis module comprises a monitoring index calculation unit and a ranking generation unit;
the monitoring index calculation unit is used for acquiring all state parameters recorded by the target monitoring industrial equipment in the historical abnormal events, classifying the state parameters according to the corresponding types, extracting event logs recorded by the state parameters in each abnormal event, and calculating the monitoring index;
the sequencing generation unit is used for sequencing the M-type state parameters of the target monitoring industrial equipment from large to small according to the values of the monitoring indexes, and generating abnormal priorities of the target monitoring industrial equipment corresponding to different types of parameters.
Further, the associated device set generating module comprises a target parameter determining unit, a state parameter determining unit, a first position difference calculating unit, a monitoring index difference calculating unit and an associated device set output unit;
the target parameter determining unit is used for extracting a first state parameter in the abnormal priority recorded by any target monitoring industrial equipment as a target parameter;
the state parameter determining unit is used for traversing the abnormal priorities recorded by all the target monitoring industrial equipment and determining the number of the state parameters of the same type as the target parameters and the position serial numbers of the corresponding abnormal priorities;
the first position difference calculation unit is used for calculating a first position difference between the state parameters to be analyzed and the target parameters when the number of the state parameters is larger than 1;
the monitoring index difference value calculation unit is used for comparing the monitoring index corresponding to the target parameter and the state parameter to be analyzed to calculate a monitoring index difference value when the first position difference is smaller than or equal to a first position difference threshold value;
the association equipment set output unit is used for outputting the association between the state parameter to be analyzed and the target parameter when the monitoring index difference value is smaller than or equal to the monitoring index threshold value, and outputting the target industrial monitoring equipment to which the state parameter to be analyzed marked with the association belongs to generate an association equipment set.
Further, the associated early warning event package construction module comprises a target query parameter pair extraction unit, an effective feature set determination unit and an associated early warning event package output unit;
the target query parameter pair extraction unit is used for extracting target monitoring industrial equipment corresponding to the target parameters as first equipment and target monitoring industrial equipment in the target parameter corresponding association equipment set as second equipment, and taking the same state parameters recorded by the first equipment and the second equipment as a target query parameter pair;
the effective feature set determining unit is used for marking that the event with the adjacent abnormal event meeting the target query parameter pair is an adjacent event group; extracting data records related to the same state parameters from adjacent event groups, and marking the data records as an effective feature set of a target query parameter pair if the historical abnormal event records are unique in two adjacent abnormal events; if the historical abnormal event record is not unique in two adjacent abnormal events, equally dividing the numerical value change set, and extracting the numerical value change of the corresponding segmented record with the highest similarity to generate an effective feature set of the target query parameter pair;
the associated early warning event package output unit is used for generating all target query parameter pairs in a traversing way, wherein a first industrial device in the target query parameter pairs is used as identifiable equipment, state parameters corresponding to the first industrial device are used as identifiable equipment parameters, an effective feature set of the target query parameter pairs is used as a matching set, and a second industrial device after successful matching is used as early warning equipment to generate an associated early warning event package.
Compared with the prior art, the invention has the following beneficial effects: according to the invention, through carrying out data extraction of state parameters and record analysis of abnormal events on the monitoring records of each type of industrial equipment, determining the priority of recording all state parameters under each type of industrial equipment, finding out the associated equipment set under the condition of determining each target parameter based on priority traversal, judging equipment possibly having associated influence, realizing real-time monitoring of different industrial equipment states influenced by the same parameter, maximally improving the prejudgment degree and the pre-protection capability of other associated influence anomalies under the condition of knowing one anomaly, enhancing the monitoring relevance of the industrial equipment, forming an analysis path from point to line instead of independent individual monitoring, reducing the possibility of causing chain reaction when anomalies occur in a short period, making a sufficient early warning space for the existing risks, and simultaneously carrying out reasonable grade distinguishing difference on a plurality of associated industrial equipment, so that the early warning degree reminding of data definition and datamation can be effectively carried out on management staff.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of an intelligent monitoring system and method for the status of industrial equipment based on big data.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides the following technical solutions: an intelligent monitoring method for the state of industrial equipment based on big data comprises the following analysis steps:
step S100: acquiring state data and abnormal events recorded by target monitoring industrial equipment in a monitoring system, wherein the state data refers to state parameters recorded by the target monitoring industrial equipment by using a corresponding monitoring method; the abnormal event is an event that the monitoring system generates an early warning signal when the early warning condition set by the system is met and the interval period is smaller than the average abnormal period for each target monitoring industrial device; determining abnormal priorities of different types of parameters corresponding to each target monitoring industrial equipment;
the interval period can be compared with the adjacent subsequent abnormal event or the previous abnormal event, and the abnormal event can be used as the analysis of the application as long as any condition is met;
step S200: the primary abnormal event record is an event recorded by early warning of target monitoring industrial equipment; judging the relevance of state parameters of the state number recording based on the abnormal priority and generating a relevant equipment set;
step S300: when the record state parameter does not have the associated equipment set, continuing to monitor; when the state parameters have the associated equipment set, extracting a target query parameter pair, and analyzing an associated early warning event package through the history abnormal event;
step S400: and obtaining the number of the target query parameter pairs, analyzing and generating the priority of the associated early warning event package, and carrying out associated early warning response when the target monitoring industrial equipment is in early warning.
Determining abnormal priorities of different types of parameters corresponding to each target monitoring industrial equipment, wherein the abnormal priorities comprise the following steps:
step S110: acquiring all state parameters recorded by the ith target monitoring industrial equipment in historical abnormal events, classifying the state parameters according to corresponding types, and extracting an event log Q recorded by the jth state parameters in each abnormal event j The event log refers to data of maintenance records of abnormal target monitoring industrial equipment after an abnormal event occurs; the event log comprises maintenance object data and abnormal frequencies of state parameters;
step S120: using the formula: w (W) ij =k 1 *(n ij /N)+k 2 *(r ij /T ij )；
Calculating a monitoring index W of a j-th type state parameter of the i-th target monitoring industrial equipment ij ；
Wherein k is 1 、k 2 Representing the corresponding reference coefficient, n ij Maintenance object data representing a j-th class status parameter of an i-th target monitoring industrial plant in an abnormal eventNamely, the j-th type state parameter relates to the number of other target monitoring industrial equipment to be detected; n represents the total number of target monitoring industrial equipment, and i is less than or equal to N; n is n ij N represents the influence proportion of the ith target monitoring industrial equipment when the jth state parameter is abnormal;
r ij indicating the number of times of recording the j-th type state parameter abnormality of the i-th target monitoring industrial equipment in the monitoring period, T ij The j-th type state parameter of the i-th target monitoring industrial equipment is represented by the interval duration of the first abnormality and the last abnormality of the monitoring period; r is (r) ij /T ij A status parameter anomaly frequency representing a jth type of status parameter of the ith target monitoring industrial equipment;
W ij the larger the monitoring index under the corresponding target monitoring industrial equipment is, the larger the range of the monitoring index needs to be overhauled in case of abnormality is, and the possibility of influencing other industrial equipment is higher; the reference coefficient may be set by the system; and normalizing the data when calculating the monitoring index;
step S130: sorting M-type state parameters of the ith target monitoring industrial equipment from large to small according to the values of the monitoring indexes to generate abnormal priority P of the target monitoring industrial equipment corresponding to different types of parameters i ，j≤M。
As shown in the examples: the object for monitoring the state of the industrial equipment has a variety, such as a tray electric push rod, a fan, a gear box and an industrial mechanical arm; different monitoring objects can have the same type of monitoring parameters, for example, when the tray electric push rod and the fan are monitored, the temperature sensor is needed to monitor the temperature, and then whether the influence of temperature abnormality on the fan monitoring is related in the process of monitoring the temperature of the tray electric push rod is needed to be further analyzed.
The association device set includes the following analysis steps:
step S210: extracting a first state parameter in the abnormal priority recorded by any target monitoring industrial equipment as a target parameter, traversing the abnormal priorities recorded by all target monitoring industrial equipment, and determining the number F of the state parameters of the same type as the target parameter and the position serial number D of the corresponding abnormal priority;
step S220: when f=0, the output state parameter does not have an associated device set;
when f=1, marking the same type of state parameter as the target parameter as the state parameter to be analyzed, and calculating a first position difference d between the state parameter to be analyzed and the target parameter 1 ，d 1 =D 1 -D 0 The method comprises the steps of carrying out a first treatment on the surface of the And set a first position difference threshold d 0 The first position difference threshold value is calculated by the number of all state parameters in the abnormal priority corresponding to the target parameter and the number of all state parameters in the abnormal priority corresponding to the state parameter to be analyzed, and specifically comprises the following steps: d, d 0 =「U 0 /(F+1)」，U 0 Representing the number average value of all state parameters contained in the abnormal priorities to which different state parameters belong, 'U' 0 /(F+1)' represents the sum of U 0 The value of/(F+1) is rounded;
if f=1 indicates that there is one target parameter and one state parameter to be analyzed, u0= (U 1 +U 2 )/2；
When F >1, marking the state parameters of the same type as the target parameters as the state parameters to be analyzed, and sequentially calculating first position differences of the target parameters and the state parameters to be analyzed to obtain a first position difference set;
step S230: when d is present 1 >d 0 When the state parameters to be analyzed are marked as filtering parameters, deleting the filtering parameters; when d is present 1 ≤d 0 When the target parameter is compared with the monitoring index W corresponding to the state parameter to be analyzed, the difference value W of the monitoring index is calculated 0 ，w 0 =｜W 1 -W 2 ｜，W 1 Representing the corresponding monitoring index of the target parameter, W 2 Representing a monitoring index corresponding to the state parameter to be analyzed; setting a monitoring index threshold value w when 0 >when w, outputting that the state parameter to be analyzed has no correlation with the target parameter, and when w 0 When w is less than or equal to w, outputting the correlation between the state parameter to be analyzed and the target parameter, and outputting target industrial monitoring equipment to which the state parameter to be analyzed with the correlation belongs to generate a correlation equipment set;
the smaller difference value indicates that the mutual influence and the association degree are larger; it is more convincing to determine the state parameters that may have an associated influence by two comparisons.
Step S240: and traversing all state parameters recorded by all target monitoring industrial equipment, generating each state parameter as an associated equipment set corresponding to the target parameter, and storing.
Step S300 includes:
step S310: extracting target monitoring industrial equipment corresponding to the target parameters as first equipment and target monitoring industrial equipment in a target parameter corresponding association equipment set as second equipment, and taking the same state parameters recorded by the first equipment and the second equipment as target query parameter pairs H, H= (H) 1 ,h 2 )，h 1 Representing the corresponding state parameter of the first equipment, h 2 Representing state parameters corresponding to the second equipment, wherein the target query parameter pairs are ordered according to the occurrence sequence of the abnormal event; i.e. h 1 Recording earlier than h 2 ；
Step S320: traversing two adjacent abnormal events in the history abnormal events, and marking the event with the adjacent abnormal event meeting the target query parameter pair as an adjacent event group; extracting data records of the same state parameters in adjacent event groups, wherein the data records refer to a numerical value change set recorded in the second industrial equipment by the same state parameters in a period from the time when the first industrial equipment is determined to be abnormal to the time when the second industrial equipment is determined to be abnormal;
the satisfaction means that the former abnormal event of two adjacent abnormal events exists in the history record is industrial equipment corresponding to the target query parameter pair h1, the latter abnormal event is industrial equipment corresponding to the h2, and the abnormal state parameters are the same;
step S330: if the historical abnormal event records that the two adjacent abnormal events are unique, marking the data record as an effective feature set of the target query parameter pair; if the historical abnormal event record is not unique in two adjacent abnormal events, equally dividing the numerical value change set, and extracting the numerical value change of the corresponding segmented record with the highest similarity to generate an effective feature set of the target query parameter pair;
step S340: traversing to generate all target query parameter pairs, using a first industrial device in the target query parameter pairs as identifiable devices, using state parameters corresponding to the first industrial device as identifiable device parameters, using an effective feature set of the target query parameter pairs as a matching set, and using a second industrial device after successful matching as early warning device to generate an associated early warning event package; and the successful matching means that the similarity between the parameter change data of the second industrial equipment after the early warning of the first industrial equipment and the data recorded by the effective feature set is larger than a similarity threshold under the real-time monitoring.
As shown in the examples: if the first industrial equipment 'fan' is abnormal, the fan is used as identifiable equipment of the first industrial equipment, and the abnormal state parameter is determined to be temperature; the temperature is an identifiable device parameter; extracting an associated equipment set recorded corresponding to the temperature, and if a gear box and a tray electric push rod exist, respectively corresponding effective characteristic sets of two industrial equipment are set 1 and set 2;
the similarity between the temperature change value after abnormality of the fan and the temperature change value in the set 1 is larger than a threshold value;
the gearbox can be output as a second industrial device as an early warning device for early warning that the abnormality of the temperature parameter corresponding to the gearbox may exist in the next abnormal event.
Step S400 includes the following analysis steps:
when the number of the target query parameter pairs is greater than or equal to two and the similarity between the parameter value change recorded by the second industrial equipment in the target query parameter pairs and the effective feature set is greater than a similarity threshold;
sequencing the second industrial equipment from large to small according to the magnitude of the similarity value to generate the priority of the corresponding associated early warning event package;
and when the target monitoring industrial equipment is in early warning, acquiring early warning parameters of the target monitoring industrial equipment and extracting associated early warning response which satisfies the sequentially reduced degree of the associated early warning event package of the step S340 in the order of corresponding priority.
The intelligent monitoring system for the state of the industrial equipment comprises an equipment record data input module, an abnormal priority analysis module, an associated equipment set generation module, an associated early warning event package construction module and an associated early warning response module;
the equipment record data entry module is used for acquiring state data and abnormal events recorded by target monitoring industrial equipment in the entry monitoring system;
the abnormal priority analysis module is used for determining abnormal priorities of different types of parameters corresponding to each target monitoring industrial equipment;
the associated equipment set generating module is used for judging the relevance of the state parameters recorded by the state numbers and generating an associated equipment set;
the associated early warning event package construction module is used for analyzing an associated early warning event package through the history abnormal event;
the associated early warning response module is used for analyzing and generating the priority of the associated early warning event package and carrying out associated early warning response when the target monitoring industrial equipment is in early warning.
The abnormality priority analysis module comprises a monitoring index calculation unit and a ranking generation unit;
the monitoring index calculation unit is used for acquiring all state parameters recorded by the target monitoring industrial equipment in the historical abnormal events, classifying the state parameters according to the corresponding types, extracting event logs recorded by the state parameters in each abnormal event, and calculating the monitoring index;
the sequencing generation unit is used for sequencing the M-type state parameters of the target monitoring industrial equipment from large to small according to the values of the monitoring indexes, and generating abnormal priorities of the target monitoring industrial equipment corresponding to different types of parameters.
The associated equipment set generating module comprises a target parameter determining unit, a state parameter determining unit, a first position difference calculating unit, a monitoring index difference calculating unit and an associated equipment set output unit;
the target parameter determining unit is used for extracting a first state parameter in the abnormal priority recorded by any target monitoring industrial equipment as a target parameter;
the state parameter determining unit is used for traversing the abnormal priorities recorded by all the target monitoring industrial equipment and determining the number of the state parameters of the same type as the target parameters and the position serial numbers of the corresponding abnormal priorities;
the first position difference calculation unit is used for calculating a first position difference between the state parameters to be analyzed and the target parameters when the number of the state parameters is larger than 1;
the monitoring index difference value calculation unit is used for comparing the monitoring index corresponding to the target parameter and the state parameter to be analyzed to calculate a monitoring index difference value when the first position difference is smaller than or equal to a first position difference threshold value;
the association equipment set output unit is used for outputting the association between the state parameter to be analyzed and the target parameter when the monitoring index difference value is smaller than or equal to the monitoring index threshold value, and outputting the target industrial monitoring equipment to which the state parameter to be analyzed marked with the association belongs to generate an association equipment set.
The associated early warning event package construction module comprises a target query parameter pair extraction unit, an effective feature set determination unit and an associated early warning event package output unit;
the target query parameter pair extraction unit is used for extracting target monitoring industrial equipment corresponding to the target parameters as first equipment and target monitoring industrial equipment in the target parameter corresponding association equipment set as second equipment, and taking the same state parameters recorded by the first equipment and the second equipment as a target query parameter pair;
the effective feature set determining unit is used for marking that the event with the adjacent abnormal event meeting the target query parameter pair is an adjacent event group; extracting data records related to the same state parameters from adjacent event groups, and marking the data records as an effective feature set of a target query parameter pair if the historical abnormal event records are unique in two adjacent abnormal events; if the historical abnormal event record is not unique in two adjacent abnormal events, equally dividing the numerical value change set, and extracting the numerical value change of the corresponding segmented record with the highest similarity to generate an effective feature set of the target query parameter pair;
the associated early warning event package output unit is used for generating all target query parameter pairs in a traversing way, wherein a first industrial device in the target query parameter pairs is used as identifiable equipment, state parameters corresponding to the first industrial device are used as identifiable equipment parameters, an effective feature set of the target query parameter pairs is used as a matching set, and a second industrial device after successful matching is used as early warning equipment to generate an associated early warning event package.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. The intelligent industrial equipment state monitoring method based on the big data is characterized by comprising the following analysis steps:
step S100: acquiring state data and abnormal events recorded by target monitoring industrial equipment in a monitoring system, wherein the state data refers to state parameters recorded by the target monitoring industrial equipment by using a corresponding monitoring method; the abnormal event is an event that the monitoring system generates an early warning signal when the early warning condition set by the system is met and the interval period is smaller than the average abnormal period for each target monitoring industrial device; determining abnormal priorities of different types of parameters corresponding to each target monitoring industrial equipment;
the determining of the abnormal priority of the different types of parameters corresponding to each target monitoring industrial equipment comprises the following steps:
step S110: acquiring all state parameters recorded by the ith target monitoring industrial equipment in historical abnormal events, classifying the state parameters according to corresponding types, and extracting an event log Q recorded by the jth state parameters in each abnormal event j The event log refers to data of maintenance records of abnormal target monitoring industrial equipment after an abnormal event occurs; the event log comprises overhaul object data and abnormal frequencies of state parameters;
step S120: using the formula: w (W) ij =k 1 *(n ij /N)+k 2 *(r ij /T ij )；
Calculating a monitoring index W of a j-th type state parameter of the i-th target monitoring industrial equipment ij ；
Wherein k is 1 、k 2 Representing the corresponding reference coefficient, n ij The method comprises the steps that overhauling object data of a j-th type state parameter of an i-th target monitoring industrial device in an abnormal event is represented, namely the number of other target monitoring industrial devices to be detected is related to the j-th type state parameter; n represents the total number of target monitoring industrial equipment, and i is less than or equal to N; n is n ij N represents the influence proportion of the ith target monitoring industrial equipment when the jth state parameter is abnormal;
r ij indicating the number of times of recording the j-th type state parameter abnormality of the i-th target monitoring industrial equipment in the monitoring period, T ij The j-th type state parameter of the i-th target monitoring industrial equipment is represented by the interval duration of the first abnormality and the last abnormality of the monitoring period; r is (r) ij /T ij A status parameter anomaly frequency representing a jth type of status parameter of the ith target monitoring industrial equipment;
step S130: sorting M-type state parameters of the ith target monitoring industrial equipment from large to small according to the values of the monitoring indexes to generate abnormal priority P of the target monitoring industrial equipment corresponding to different types of parameters i ，j≤M；
Step S200: the primary abnormal event record is an event recorded by early warning of target monitoring industrial equipment; judging the relevance of state parameters of the state number recording based on the abnormal priority and generating a relevant equipment set;
step S300: when the record state parameter does not have the associated equipment set, continuing to monitor; when the state parameters have the associated equipment set, extracting a target query parameter pair, and analyzing an associated early warning event package through the history abnormal event;
step S400: and obtaining the number of the target query parameter pairs, analyzing and generating the priority of the associated early warning event package, and carrying out associated early warning response when the target monitoring industrial equipment is in early warning.
2. The intelligent industrial equipment state monitoring method based on big data according to claim 1, wherein the method comprises the following steps: the association device set comprises the following analysis steps:
step S210: extracting a first state parameter in the abnormal priority recorded by any target monitoring industrial equipment as a target parameter, traversing the abnormal priorities recorded by all target monitoring industrial equipment, and determining the number F of the state parameters of the same type as the target parameter and the position serial number D of the corresponding abnormal priority;
step S220: when f=0, the output state parameter does not have an associated device set;
when f=1, marking the same type of state parameter as the target parameter as the state parameter to be analyzed, and calculating a first position difference d between the state parameter to be analyzed and the target parameter 1 ，d 1 =D 1 -D 0 The method comprises the steps of carrying out a first treatment on the surface of the And set a first position difference threshold d 0 The first position difference threshold value is calculated from the number of all state parameters in the abnormal priority corresponding to the target parameter and the number of all state parameters in the abnormal priority corresponding to the state parameter to be analyzed, and specifically comprises the following steps: d, d 0 =「U 0 /(F+1)」，U 0 Representing the number average value of all state parameters contained in the abnormal priorities to which different state parameters belong, 'U' 0 /(F+1)' represents the sum of U 0 The value of/(F+1) is rounded;
when F >1, marking the state parameters of the same type as the target parameters as the state parameters to be analyzed, and sequentially calculating first position differences of the target parameters and the state parameters to be analyzed to obtain a first position difference set;
step S230: when d is present 1 >d 0 When the state parameters to be analyzed are marked as filtering parameters, deleting the filtering parameters; when d is present 1 ≤d 0 When the target parameter is compared with the monitoring index W corresponding to the state parameter to be analyzed, the difference value W of the monitoring index is calculated 0 ，w 0 =｜W 1 -W 2 ｜，W 1 Representing the corresponding monitoring index of the target parameter, W 2 Representing a monitoring index corresponding to the state parameter to be analyzed; setting a monitoring index threshold value w when 0 >when w, outputting that the state parameter to be analyzed has no correlation with the target parameter, and when w 0 When w is less than or equal to w, outputting the correlation between the state parameter to be analyzed and the target parameter, and outputting target industrial monitoring equipment to which the state parameter to be analyzed with the correlation belongs to generate a correlation equipment set;
step S240: and traversing all state parameters recorded by all target monitoring industrial equipment, generating each state parameter as an associated equipment set corresponding to the target parameter, and storing.
3. The intelligent industrial equipment state monitoring method based on big data according to claim 2, wherein the method comprises the following steps: the step S300 includes:
step S310: extracting target monitoring industrial equipment corresponding to the target parameters as first equipment and target monitoring industrial equipment in a target parameter corresponding association equipment set as second equipment, and taking the same state parameters recorded by the first equipment and the second equipment as target query parameter pairs H, H= (H) 1 ,h 2 )，h 1 Representing the corresponding state parameter of the first equipment, h 2 Representing state parameters corresponding to the second equipment, wherein the target query parameter pairs are ordered according to the occurrence sequence of the abnormal event; i.e. h 1 Recording earlier than h 2 ；
Step S320: traversing two adjacent abnormal events in the history abnormal events, and marking the event with the adjacent abnormal event meeting the target query parameter pair as an adjacent event group; extracting data records of the same state parameters in adjacent event groups, wherein the data records refer to a numerical value change set recorded in the second industrial equipment by the same state parameters in a period from the time when the first industrial equipment is determined to be abnormal to the time when the second industrial equipment is determined to be abnormal;
step S330: if the historical abnormal event records that the two adjacent abnormal events are unique, marking the data record as an effective feature set of the target query parameter pair; if the historical abnormal event record is not unique in two adjacent abnormal events, equally dividing the numerical value change set, and extracting the numerical value change of the corresponding segmented record with the highest similarity to generate an effective feature set of the target query parameter pair;
step S340: traversing to generate all target query parameter pairs, using a first industrial device in the target query parameter pairs as identifiable devices, using state parameters corresponding to the first industrial device as identifiable device parameters, using an effective feature set of the target query parameter pairs as a matching set, and using a second industrial device after successful matching as early warning device to generate an associated early warning event package; the successful matching means that the similarity between the parameter change data of the second industrial equipment after the early warning of the first industrial equipment and the data recorded by the effective feature set is larger than a similarity threshold under the real-time monitoring.
4. The intelligent industrial equipment state monitoring method based on big data according to claim 3, wherein the method comprises the following steps: the step S400 includes the following analysis steps:
when the number of the target query parameter pairs is greater than or equal to two and the similarity between the parameter value change recorded by the second industrial equipment in the target query parameter pairs and the effective feature set is greater than a similarity threshold;
sequencing the second industrial equipment from large to small according to the magnitude of the similarity value to generate the priority of the corresponding associated early warning event package;
and when the target monitoring industrial equipment is in early warning, acquiring early warning parameters of the target monitoring industrial equipment and extracting associated early warning response which satisfies the sequentially reduced degree of the associated early warning event package of the step S340 in the order of corresponding priority.
5. An intelligent monitoring system for the state of industrial equipment based on the intelligent monitoring method for the state of industrial equipment of big data as set forth in any one of claims 1 to 4, which is characterized by comprising an equipment record data entry module, an abnormal priority analysis module, an associated equipment set generation module, an associated early warning event package construction module and an associated early warning response module;
the equipment record data entry module is used for acquiring state data and abnormal events recorded by target monitoring industrial equipment in the entry monitoring system;
the abnormal priority analysis module is used for determining abnormal priorities of different types of parameters corresponding to each target monitoring industrial equipment;
the abnormality priority analysis module comprises a monitoring index calculation unit and a ranking generation unit;
the monitoring index calculation unit is used for acquiring all state parameters recorded by the target monitoring industrial equipment in the historical abnormal events, classifying the state parameters according to corresponding types, extracting event logs recorded by the state parameters in each abnormal event, and calculating the monitoring index;
the sequencing generation unit is used for sequencing the M-type state parameters of the target monitoring industrial equipment from large to small according to the values of the monitoring indexes to generate abnormal priorities of the target monitoring industrial equipment corresponding to different types of parameters;
the associated equipment set generating module is used for judging the relevance of the state parameters recorded by the state numbers and generating an associated equipment set;
the associated early warning event package construction module is used for analyzing an associated early warning event package through the history abnormal event;
the associated early warning response module is used for analyzing and generating the priority of the associated early warning event package and carrying out associated early warning response when the target monitoring industrial equipment is in early warning.
6. The intelligent monitoring system for industrial equipment status according to claim 5, wherein: the associated equipment set generating module comprises a target parameter determining unit, a state parameter determining unit, a first position difference calculating unit, a monitoring index difference calculating unit and an associated equipment set output unit;
the target parameter determining unit is used for extracting a first state parameter in the abnormal priority recorded by any target monitoring industrial equipment as a target parameter;
the state parameter determining unit is used for traversing the abnormal priorities recorded by all target monitoring industrial equipment and determining the number of the state parameters of the same type as the target parameters and the position serial numbers of the corresponding abnormal priorities;
the first position difference calculation unit is used for calculating a first position difference between the state parameter to be analyzed and the target parameter when the number of the state parameters is greater than 1;
the monitoring index difference value calculation unit is used for comparing the monitoring index corresponding to the target parameter and the state parameter to be analyzed to calculate a monitoring index difference value when the first position difference is smaller than or equal to a first position difference threshold value;
the association equipment set output unit is used for outputting the association between the state parameter to be analyzed and the target parameter when the monitoring index difference value is smaller than or equal to the monitoring index threshold value, and outputting the target industrial monitoring equipment to which the state parameter to be analyzed marked with the association belongs to generate an association equipment set.
7. The intelligent monitoring system for industrial equipment status according to claim 6, wherein: the associated early warning event package construction module comprises a target query parameter pair extraction unit, an effective feature set determination unit and an associated early warning event package output unit;
the target query parameter pair extraction unit is used for extracting target monitoring industrial equipment corresponding to the target parameters as first equipment and target monitoring industrial equipment in the target parameter corresponding association equipment set as second equipment, and taking the same state parameters recorded by the first equipment and the second equipment as a target query parameter pair;
the effective feature set determining unit is used for marking that the event with the adjacent abnormal event meeting the target query parameter pair is an adjacent event group; extracting data records related to the same state parameters from adjacent event groups, and marking the data records as an effective feature set of a target query parameter pair if the historical abnormal event records are unique in two adjacent abnormal events; if the historical abnormal event record is not unique in two adjacent abnormal events, equally dividing the numerical value change set, and extracting the numerical value change of the corresponding segmented record with the highest similarity to generate an effective feature set of the target query parameter pair;
the associated early warning event package output unit is used for generating all target query parameter pairs in a traversing way, wherein a first industrial device in the target query parameter pairs is used as identifiable equipment, state parameters corresponding to the first industrial device are used as identifiable equipment parameters, an effective feature set of the target query parameter pairs is used as a matching set, and a second industrial device after successful matching is used as early warning equipment to generate an associated early warning event package.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311489262.4A CN117235649B (en) | 2023-11-09 | 2023-11-09 | Industrial equipment state intelligent monitoring system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311489262.4A CN117235649B (en) | 2023-11-09 | 2023-11-09 | Industrial equipment state intelligent monitoring system and method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117235649A CN117235649A (en) | 2023-12-15 |
| CN117235649B true CN117235649B (en) | 2024-02-13 |
Family
ID=89093133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311489262.4A Active CN117235649B (en) | 2023-11-09 | 2023-11-09 | Industrial equipment state intelligent monitoring system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117235649B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117875905B (en) * | 2024-01-08 | 2024-05-28 | 广东科技学院 | Digital management system and method for catering supply chain based on big data |
| CN117540281B (en) * | 2024-01-09 | 2024-03-22 | 深圳市宇辉光学科技有限公司 | Data optimization analysis system and method applied to optical film |
| CN117612693B (en) * | 2024-01-24 | 2024-04-05 | 四川互慧软件有限公司 | Patient real-time monitoring and early warning method, device, computer and storage medium |
| CN117786099B (en) * | 2024-02-27 | 2024-04-26 | 中建安装集团有限公司 | Engineering technical data informatization management system and method |
| CN117902474B (en) * | 2024-03-20 | 2024-05-17 | 江苏省特种设备安全监督检验研究院 | Crane safety monitoring system and method based on multi-mode data analysis |
| CN117935519A (en) * | 2024-03-22 | 2024-04-26 | 深圳市中燃科技有限公司 | Gas detection alarm system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015176565A1 (en) * | 2014-05-22 | 2015-11-26 | 袁志贤 | Method for predicting faults in electrical equipment based on multi-dimension time series |
| CN113452542A (en) * | 2020-03-27 | 2021-09-28 | 华为技术有限公司 | Fault detection method and equipment |
| CN113822570A (en) * | 2021-09-20 | 2021-12-21 | 河南惠誉网络科技有限公司 | Enterprise production data storage method and system based on big data analysis |
| DE102022201761A1 (en) * | 2021-03-03 | 2022-09-08 | Aktiebolaget Skf | Method, system and storage medium for automatically diagnosing devices |
| CN116204842A (en) * | 2023-03-10 | 2023-06-02 | 广东省建设工程质量安全检测总站有限公司 | Abnormality monitoring method and system for electrical equipment |
| CN116308082A (en) * | 2023-02-24 | 2023-06-23 | 国网四川省电力公司物资公司 | Accurate storage and allocation management method and system for electric power emergency materials |
| CN116505738A (en) * | 2023-06-26 | 2023-07-28 | 易充新能源（深圳）有限公司 | Control method and system for energy-saving consumption-reducing power supply |
| CN116668482A (en) * | 2023-06-02 | 2023-08-29 | 南京国铁电气有限责任公司 | Intelligent building two-bus monitoring system and method based on artificial intelligence |
| CN116805068A (en) * | 2023-05-24 | 2023-09-26 | 江苏卓特电气科技有限公司 | Fault monitoring and early warning system and method based on big data |
-
2023
- 2023-11-09 CN CN202311489262.4A patent/CN117235649B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015176565A1 (en) * | 2014-05-22 | 2015-11-26 | 袁志贤 | Method for predicting faults in electrical equipment based on multi-dimension time series |
| CN113452542A (en) * | 2020-03-27 | 2021-09-28 | 华为技术有限公司 | Fault detection method and equipment |
| DE102022201761A1 (en) * | 2021-03-03 | 2022-09-08 | Aktiebolaget Skf | Method, system and storage medium for automatically diagnosing devices |
| CN113822570A (en) * | 2021-09-20 | 2021-12-21 | 河南惠誉网络科技有限公司 | Enterprise production data storage method and system based on big data analysis |
| CN116308082A (en) * | 2023-02-24 | 2023-06-23 | 国网四川省电力公司物资公司 | Accurate storage and allocation management method and system for electric power emergency materials |
| CN116204842A (en) * | 2023-03-10 | 2023-06-02 | 广东省建设工程质量安全检测总站有限公司 | Abnormality monitoring method and system for electrical equipment |
| CN116805068A (en) * | 2023-05-24 | 2023-09-26 | 江苏卓特电气科技有限公司 | Fault monitoring and early warning system and method based on big data |
| CN116668482A (en) * | 2023-06-02 | 2023-08-29 | 南京国铁电气有限责任公司 | Intelligent building two-bus monitoring system and method based on artificial intelligence |
| CN116505738A (en) * | 2023-06-26 | 2023-07-28 | 易充新能源（深圳）有限公司 | Control method and system for energy-saving consumption-reducing power supply |
Non-Patent Citations (1)
| Title |
|---|
| 基于相似性建模的发电机组设备故障预警系统;常剑 等;机电工程;第29卷(第5期);第576-579页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117235649A (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117235649B (en) | Industrial equipment state intelligent monitoring system and method based on big data | |
| CN108197845B (en) | Transaction index abnormity monitoring method based on deep learning model LSTM | |
| CN112083244B (en) | Integrated intelligent diagnosis system for faults of avionic equipment | |
| CN111027615B (en) | Middleware fault early warning method and system based on machine learning | |
| WO2006046251A2 (en) | Detection system for rare situation in processes | |
| CN117575332A (en) | Road construction safety monitoring method and system | |
| CN111931849A (en) | Hydroelectric generating set operation data trend early warning method | |
| CN112462734A (en) | Industrial production equipment fault prediction analysis method and model | |
| US20130173480A1 (en) | Maintenance cycle for an aircraft | |
| CN115883163A (en) | Network safety alarm monitoring method | |
| CN117439822B (en) | Network security data management system and method based on Internet of things | |
| CN113612625A (en) | Network fault positioning method and device | |
| CN117436846A (en) | Equipment predictive maintenance method and system based on neural network | |
| CN116705272A (en) | Comprehensive evaluation method for equipment health state based on multidimensional diagnosis | |
| CN111667391A (en) | Environment-friendly big data monitoring system | |
| CN114492636B (en) | Transformer winding state signal acquisition system | |
| CN114662981B (en) | Pollution source enterprise supervision method based on big data application | |
| CN115688016A (en) | Integrated method for intelligent operation and maintenance of large database | |
| CN111597510B (en) | Power transmission and transformation operation detection data quality assessment method and system | |
| CN115296933A (en) | Industrial production data risk level assessment method and system | |
| Smeraldo et al. | A data-driven approach to fault diagnostics for industrial process plants based on feature extraction and inferential statistics | |
| CN117902474B (en) | Crane safety monitoring system and method based on multi-mode data analysis | |
| CN116551467B (en) | Cutter abrasion state identification method based on internet of things monitoring data | |
| CN117172139B (en) | Performance test method and system for copper-clad aluminum alloy cable for communication | |
| CN116523466B (en) | Production data tracing system and method based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |