CN116381490B - Push rod motor performance detection system and method based on data analysis - Google Patents
Push rod motor performance detection system and method based on data analysis Download PDFInfo
- Publication number
- CN116381490B CN116381490B CN202310652684.2A CN202310652684A CN116381490B CN 116381490 B CN116381490 B CN 116381490B CN 202310652684 A CN202310652684 A CN 202310652684A CN 116381490 B CN116381490 B CN 116381490B
- Authority
- CN
- China
- Prior art keywords
- push rod
- node
- fault maintenance
- characteristic
- operation node
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000007405 data analysis Methods 0.000 title claims abstract description 12
- 238000012423 maintenance Methods 0.000 claims abstract description 130
- 230000002159 abnormal effect Effects 0.000 claims abstract description 114
- 238000012544 monitoring process Methods 0.000 claims abstract description 94
- 238000005070 sampling Methods 0.000 claims abstract description 85
- 238000012512 characterization method Methods 0.000 claims abstract description 26
- 238000007726 management method Methods 0.000 claims abstract description 23
- 238000004364 calculation method Methods 0.000 claims abstract description 20
- 238000009960 carding Methods 0.000 claims abstract description 10
- 238000012216 screening Methods 0.000 claims description 30
- 230000008569 process Effects 0.000 claims description 11
- 238000013523 data management Methods 0.000 claims description 9
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 230000010365 information processing Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/34—Testing dynamo-electric machines
- G01R31/343—Testing dynamo-electric machines in operation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Control Of Electric Motors In General (AREA)
Abstract
The invention relates to the technical field of motor performance detection and management, in particular to a push rod motor performance detection system and method based on data analysis, comprising the steps of collecting state data on each operation node corresponding to each push rod motor, and respectively carding state characteristic values of each operation node; setting a first sampling monitoring period before fault occurrence and a second sampling monitoring period after fault maintenance is completed for each historical fault maintenance record; capturing initial abnormal operation nodes which cause the fault characterization of the push rod motor in each historical fault maintenance record based on the state data; respectively carrying out characteristic index calculation on each characteristic abnormal operation node; every time the operation nodes which are captured by the push rod motor and exceed the number threshold value and any characteristic abnormal operation nodes belong to the same operation node, a detector is prompted to detect the performance of the push rod motor.
Description
Technical Field
The invention relates to the technical field of motor performance detection and management, in particular to a push rod motor performance detection system and method based on data analysis.
Background
The push rod motor is also called an electric push rod, is an electric driving device for converting the rotary motion of the motor into the linear reciprocating motion of the push rod, and mainly comprises a novel linear actuating mechanism consisting of a motor, a speed reducing mechanism, a push rod head, a housing tube, a travel switch, a control device and the like, and can be regarded as an extension of the rotary motor in terms of structure; the push rod motor can be applied to various aspects of work and life of people, and products of the electric push rod can play an important role in a plurality of places such as a wash basin, a television, a tatami and the like in the aspect of being close to life, so that intelligent home is shown everywhere;
for the detection of the reliability of the performance of the electric push rod, some detection means and methods exist at present, of course, the detection needs longer time, and if the application occasion is severe, continuous monitoring and recording for about 3 months are needed; if the time is not allowed, several different models can be selected, and under the same load condition, the running current, noise and temperature rise of the model can be detected, so that relatively simple judgment can be made. Of course, the reliability of long-term operation requires testing in practice.
Disclosure of Invention
The invention aims to provide a push rod motor performance detection system and method based on data analysis, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a push rod motor performance detection method based on data analysis comprises the following steps:
step S100: setting a push rod in the push rod motor as an operation node of the push rod motor due to one-time telescopic movement which is completed by the rotation of the screw rod; respectively installing sensors on all push rod motors in a target monitoring area, collecting state data on all operation nodes corresponding to all push rod motors, and respectively combing state characteristic values of all operation nodes;
step S200: collecting historical fault maintenance records of all push rod motors in a target monitoring area, setting a first sampling monitoring period before fault occurrence and a second sampling monitoring period after fault maintenance is completed on each historical fault maintenance record, and setting each operation node contained in the first sampling monitoring period and the second sampling monitoring period in each historical fault maintenance record as a reference node;
step S300: capturing initial abnormal operation nodes which cause the fault characterization of the push rod motor in each historical fault maintenance record on the basis of the state data of each historical fault maintenance record on all operation nodes contained in a first sampling monitoring period and a second sampling monitoring period, and locking the abnormal operation periods which cause the fault of the push rod motor in the historical fault maintenance records on the basis of the initial abnormal operation nodes;
step S400: classifying historical fault maintenance records of all push rod motors in a target monitoring area based on similarity among fault characterizations of the corresponding push rod motors; capturing a plurality of historical fault maintenance records with the similarity of fault characterization larger than a similarity threshold value in corresponding abnormal operation periods, respectively carrying out characteristic index calculation on each characteristic abnormal operation node, and completing screening of the characteristic abnormal operation nodes based on the characteristic indexes;
step S500: and feeding back the information of the abnormal operation nodes with the characteristics after screening to a port of a detection personnel, wherein each time the operation nodes which are captured by the push rod motor and exceed the number threshold value belong to the same operation node with any abnormal operation node with the characteristics, the detection personnel is prompted to detect the performance of the push rod motor.
Further, step S100 includes:
step S101: respectively collecting state data for each operation node, wherein the state data comprises a motor driving force X1 born by a corresponding screw rod when the push rod is driven to complete one-time telescopic movement, a maximum dynamic load value X2 born by the push rod in the process of completing one-time telescopic movement, a maximum displacement Y1 reached by the push rod in the process of completing one-time telescopic movement, and a time Y2 spent by restoring from the maximum displacement in the process of completing one-time telescopic movement;
step S102: setting a first state characteristic value P1=x1/X2 of each operation node, and setting a second state characteristic value P2=y1/Y2 of each operation node;
the first state characteristic value of each operation node is p1=x1/x2, which is used for locking operation external condition data of each operation node, and the second state characteristic value of each operation node is p2=y1/Y2, which is used for locking performance data presented by each operation node under corresponding operation external condition data, so that necessary data laying is completed for calculating the similarity of the operation nodes in the follow-up operation, a certain calculation error is eliminated for calculating the similarity of the operation nodes, and the initial abnormal operation node and the characteristic abnormal operation node which are finally captured are more accurate.
Further, step S200 includes:
step S201: the corresponding time of diagnosing the corresponding push rod motor as a fault in each historical fault maintenance record is taken as a fault reference time T, the number threshold K of the running nodes is set, and the period duration threshold T is set min The method comprises the steps of carrying out a first treatment on the surface of the Randomly setting a plurality of sampling monitoring periods forward at a fault reference time t;
step S202: acquiring the number N of running nodes contained in a sampling monitoring period which is arbitrarily set and the period duration T covered by the running nodes; will satisfy N ∈ K, T ∈ T min And sampling start time T b Setting a sampling monitoring period closest to the fault reference time T as a first sampling monitoring period T1; after each historical fault maintenance record is executed, capturing N operation nodes closest to a fault reference time T, and setting the period duration covering the N operation nodes as a second sampling monitoring period T2;
step S203: respectively acquiring a first state characteristic value and a second state characteristic value of each operation node contained in a first sampling monitoring period T1 and a second sampling monitoring period T2 of each historical fault maintenance record; and setting each operation node contained in a first sampling monitoring period T1 of each historical fault maintenance record as a first reference node of each historical fault maintenance record, and setting each operation node contained in a second sampling monitoring period T2 of each historical fault maintenance record as a second reference node of each historical fault maintenance record.
Further, step S300 includes:
step S301: before a corresponding fault reference time T, acquiring each historical fault maintenance record, except for other operation nodes covered in a corresponding first sampling monitoring period T1, setting the other operation nodes as target operation nodes of each historical fault maintenance record, respectively extracting a first state characteristic value and a second state characteristic value of each target operation node, and respectively extracting a first state characteristic value and a second state characteristic value of each first reference node and a second reference node of each historical fault maintenance record;
step S302; setting a first similarity threshold W 1 Respectively carrying out similarity calculation on each target operation node of each historical fault maintenance record and the first reference node and the second reference node of each historical fault maintenance record based on the state characteristic values; obtaining the similarity S of the first state characteristic value P1 of each target operation node and the first reference node P1 Similarity S of second state characteristic value P2 P2 Obtaining the similarity H of the first state characteristic value P1 of each target operation node and the second reference node P1 Similarity H of second state characteristic value P2 P2 ；
Step S303: when a certain target operation node meets S P1 +S P2 >W 1 >H P1 +H P2 Judging a certain target operation node as an abnormal operation node which causes the fault representation of the corresponding push rod motor in each historical fault maintenance record; will correspond to the run time T g The abnormal operation node farthest from the fault reference time t is judged to be the initial abnormal operation node; judging the running time T g Sampling start time T to corresponding first sampling monitoring period in historical fault maintenance record b The covered time period is the abnormal operation period of the push rod motor in the corresponding historical fault maintenance record.
Further, step S400 includes:
step S401: classifying historical fault maintenance records with similarity larger than a similarity threshold value among fault characterizations presented by corresponding push rod motors in a target monitoring area, and respectively obtaining a plurality of historical fault maintenance record sets; extracting state data of each operation node covered by an abnormal operation period corresponding to each historical fault maintenance record in each historical fault maintenance record set respectively; respectively acquiring a first state characteristic value P1 and a second state characteristic value P2 of each operation node; respectively collecting the operation nodes with the same first state characteristic value P1 or the corresponding first state characteristic value P1 with the deviation smaller than the deviation threshold value to obtain a plurality of operation node sets; marking corresponding historical fault maintenance records for each operation node in each operation node set respectively;
step S402: setting the operation nodes with the accumulated occurrence times larger than the frequency threshold value in each operation node set as characteristic operation nodes respectively to obtain corresponding characteristic operation node sets; wherein, if the similarity S of the first state characteristic value P1 between the two operation nodes P1 ' similarity S with the second State characteristic value P2 P2 ' satisfy S P1 '+S P2 '≧W 2 Judging that the two operation nodes are the same operation node; calculating a feature index r=u for each feature operation node in each feature operation node set (y1/y2) The method comprises the steps of carrying out a first treatment on the surface of the Wherein U represents the accumulated occurrence times corresponding to each characteristic operation node; y1 represents the total number of the historical fault maintenance records of each characteristic operation node obtained by extraction; y2 represents the total number of the historical fault maintenance records corresponding to each operation node set; and removing the characteristic abnormal operation nodes with the characteristic index R smaller than the index threshold value from the corresponding characteristic operation node set.
If y1/y2 corresponding to a certain characteristic operation node is larger, the phenomenon that the certain characteristic operation node is extracted from all historical fault maintenance records presenting similar fault characterization is more common; if the feature index value R corresponding to a certain feature operation node is larger, the probability that the feature operation node is an abnormal operation node which causes the fault representation of the push rod motor in the corresponding historical fault maintenance record is larger.
In order to better implement the method, a push rod motor performance detection system is also provided, and the system comprises: the system comprises a push rod motor state data management module, a historical fault maintenance record information carding module, an abnormal information processing module, an abnormal information screening management module and a performance detection prompt management module;
the push rod motor state data management module is used for respectively installing sensors on the push rod motors in the target monitoring area, collecting state data on the corresponding operation nodes of the push rod motors, and respectively combing state characteristic values of the operation nodes;
the historical fault maintenance record information carding module is used for setting a first sampling monitoring period before fault occurrence and a second sampling monitoring period after fault maintenance is completed on each historical fault maintenance record, and each operation node contained in the first sampling monitoring period and the second sampling monitoring period in each historical fault maintenance record is set as a reference node;
the abnormal information processing module is used for capturing initial abnormal operation nodes which cause the occurrence of the fault characterization of the push rod motor in each historical fault maintenance record, and locking the abnormal operation period which causes the fault of the push rod motor in the historical fault maintenance record based on the initial abnormal operation nodes;
the abnormal information screening management module is used for respectively capturing a plurality of historical fault maintenance records with fault characterization similarity larger than a similarity threshold, characteristic abnormal operation nodes in corresponding abnormal operation periods, respectively carrying out characteristic index calculation on the characteristic abnormal operation nodes, and completing screening of the characteristic abnormal operation nodes based on the characteristic indexes;
the performance detection prompt management module is used for feeding back the information of each characteristic abnormal operation node after screening to the port of the detection personnel, and prompting the detection personnel to perform performance detection on the push rod motor every time the operation nodes which are captured by the push rod motor and exceed the number threshold value and any characteristic abnormal operation nodes belong to the same operation node.
Further, the push rod motor state data management module comprises a state data acquisition unit and a state characteristic value calculation unit;
the state data acquisition unit is used for acquiring state data of each push rod motor corresponding to each operation node;
and the state characteristic value calculation unit is used for carding the state characteristic values of all the operation nodes respectively.
Further, the abnormal information screening management module comprises a characteristic abnormal operation node capturing management unit and a characteristic abnormal operation node screening unit;
the characteristic abnormal operation node capturing management unit is used for capturing the characteristic abnormal operation nodes in the corresponding abnormal operation periods according to a plurality of historical fault maintenance records with the fault characterization similarity larger than a similarity threshold value;
the characteristic abnormal operation node screening unit is used for respectively carrying out characteristic index calculation on each characteristic abnormal operation node and completing screening of the characteristic abnormal operation nodes based on the characteristic indexes.
Compared with the prior art, the invention has the following beneficial effects: according to the invention, through analyzing the state data of each historical fault maintenance record of the push rod motor before and after maintenance, the abnormal operation nodes which cause the fault characterization of the push rod motor in each historical fault maintenance record are captured, the abnormal operation period is defined, the abnormal operation nodes which cause the fault characterization of the push rod motor in each historical fault maintenance record to present a certain characteristic rule are captured in the abnormal operation period of the historical fault maintenance record with the same fault characterization, the start judgment of a performance detection mechanism of the push rod motor by a detection personnel is assisted, the performance service life of the push rod motor can be improved to a certain extent, and a more scientific and effective performance detection start mechanism is provided for the push rod motor.
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 flow chart of a method for detecting performance of a push rod motor based on data analysis;
fig. 2 is a schematic structural diagram of a push rod motor performance detection system based on data analysis according to the present invention.
Description of the embodiments
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. 1-2, the present invention provides the following technical solutions: a push rod motor performance detection method based on data analysis comprises the following steps:
step S100: setting a push rod in the push rod motor as an operation node of the push rod motor due to one-time telescopic movement which is completed by the rotation of the screw rod; respectively installing sensors on all push rod motors in a target monitoring area, collecting state data on all operation nodes corresponding to all push rod motors, and respectively combing state characteristic values of all operation nodes;
wherein, step S100 includes:
step S101: respectively collecting state data for each operation node, wherein the state data comprises a motor driving force X1 born by a corresponding screw rod when the push rod is driven to complete one-time telescopic movement, a maximum dynamic load value X2 born by the push rod in the process of completing one-time telescopic movement, a maximum displacement Y1 reached by the push rod in the process of completing one-time telescopic movement, and a time Y2 spent by restoring from the maximum displacement in the process of completing one-time telescopic movement;
step S102: setting a first state characteristic value P1=x1/X2 of each operation node, and setting a second state characteristic value P2=y1/Y2 of each operation node;
step S200: collecting historical fault maintenance records of all push rod motors in a target monitoring area, setting a first sampling monitoring period before fault occurrence and a second sampling monitoring period after fault maintenance is completed on each historical fault maintenance record, and setting each operation node contained in the first sampling monitoring period and the second sampling monitoring period in each historical fault maintenance record as a reference node;
wherein, step S200 includes:
step S201: the time corresponding to the diagnosis of the corresponding push rod motor as the fault in each historical fault maintenance record is taken as the fault reference time t, and the operation is setNumber threshold K of row nodes, period duration threshold T min The method comprises the steps of carrying out a first treatment on the surface of the Randomly setting a plurality of sampling monitoring periods forward at a fault reference time t;
step S202: acquiring the number N of running nodes contained in a sampling monitoring period which is arbitrarily set and the period duration T covered by the running nodes; will satisfy N ∈ K, T ∈ T min And sampling start time T b Setting a sampling monitoring period closest to the fault reference time T as a first sampling monitoring period T1; after each historical fault maintenance record is executed, capturing N operation nodes closest to a fault reference time T, and setting the period duration covering the N operation nodes as a second sampling monitoring period T2;
for example, the number of running nodes is threshold k=28, and the period duration is threshold T min =30 days; randomly setting a plurality of sampling monitoring periods forward at the fault reference time t, and respectively tracing the fault reference time t forward for 15 days, 20 days, 25 days and 28 days;
acquiring the number N of running nodes contained in a sampling monitoring period which is arbitrarily set and the period duration T covered by the running nodes; wherein, in a first sampling monitoring period: the fault reference time t is traced back for 15 days: the number of the contained running nodes is N=18;
in the second sampling monitoring period: the fault reference time t is traced back for 20 days: the number of the contained running nodes n=24; in a third sampling monitoring period: the fault reference time t is traced back for 25 days: the number of the contained operation nodes N=30;
in a fourth sampling monitoring period: the fault reference time t is traced back for 28 days: the number of the contained running nodes n=36;
in summary, sampling monitoring periods satisfying the conditions that n+.28, t+.30 days respectively include: a third sampling monitoring period and a fourth sampling monitoring period; wherein, the sampling start time T of the third sampling monitoring period b The third sampling monitoring period is set as a first sampling monitoring period T1 in a factor way, wherein the third sampling monitoring period is closest to the fault reference time T;
step S203: respectively acquiring a first state characteristic value and a second state characteristic value of each operation node contained in a first sampling monitoring period T1 and a second sampling monitoring period T2 of each historical fault maintenance record; setting each operation node contained in a first sampling monitoring period T1 of each historical fault maintenance record as a first reference node of each historical fault maintenance record, and setting each operation node contained in a second sampling monitoring period T2 of each historical fault maintenance record as a second reference node of each historical fault maintenance record;
step S300: capturing initial abnormal operation nodes which cause the fault characterization of the push rod motor in each historical fault maintenance record on the basis of the state data of each historical fault maintenance record on all operation nodes contained in a first sampling monitoring period and a second sampling monitoring period, and locking the abnormal operation periods which cause the fault of the push rod motor in the historical fault maintenance records on the basis of the initial abnormal operation nodes;
wherein, step S300 includes:
step S301: before a corresponding fault reference time T, acquiring each historical fault maintenance record, except for other operation nodes covered in a corresponding first sampling monitoring period T1, setting the other operation nodes as target operation nodes of each historical fault maintenance record, respectively extracting a first state characteristic value and a second state characteristic value of each target operation node, and respectively extracting a first state characteristic value and a second state characteristic value of each first reference node and a second reference node of each historical fault maintenance record;
step S302; setting a first similarity threshold W 1 Respectively carrying out similarity calculation on each target operation node of each historical fault maintenance record and the first reference node and the second reference node of each historical fault maintenance record based on the state characteristic values; obtaining the similarity S of the first state characteristic value P1 of each target operation node and the first reference node P1 Similarity S of second state characteristic value P2 P2 Obtaining the similarity H of the first state characteristic value P1 of each target operation node and the second reference node P1 Similarity H of second state characteristic value P2 P2 ；
Step S303: when a certain target operation node meets S P1 +S P2 >W 1 >H P1 +H P2 Judging a certain target operation node as an abnormal operation node which causes the fault representation of the corresponding push rod motor in each historical fault maintenance record; will correspond to the run time T g The abnormal operation node farthest from the fault reference time t is judged to be the initial abnormal operation node; judging the running time T g Sampling start time T to corresponding first sampling monitoring period in historical fault maintenance record b The covered time period is an abnormal operation period of the push rod motor in the corresponding historical fault maintenance record;
step S400: classifying historical fault maintenance records of all push rod motors in a target monitoring area based on similarity among fault characterizations of the corresponding push rod motors; capturing a plurality of historical fault maintenance records with the similarity of fault characterization larger than a similarity threshold value in corresponding abnormal operation periods, respectively carrying out characteristic index calculation on each characteristic abnormal operation node, and completing screening of the characteristic abnormal operation nodes based on the characteristic indexes;
wherein, step S400 includes:
step S401: classifying historical fault maintenance records with similarity larger than a similarity threshold value among fault characterizations presented by corresponding push rod motors in a target monitoring area, and respectively obtaining a plurality of historical fault maintenance record sets; extracting state data of each operation node covered by an abnormal operation period corresponding to each historical fault maintenance record in each historical fault maintenance record set respectively; respectively acquiring a first state characteristic value P1 and a second state characteristic value P2 of each operation node; respectively collecting the operation nodes with the same first state characteristic value P1 or the corresponding first state characteristic value P1 with the deviation smaller than the deviation threshold value to obtain a plurality of operation node sets; marking corresponding historical fault maintenance records for each operation node in each operation node set respectively;
step S402: will be accumulated in each running node set respectivelyCounting the operation nodes with the occurrence times larger than the frequency threshold, setting the operation nodes as characteristic operation nodes, and respectively obtaining corresponding characteristic operation node sets; wherein, if the similarity S of the first state characteristic value P1 between the two operation nodes P1 ' similarity S with the second State characteristic value P2 P2 ' satisfy S P1 '+S P2 '≧W 2 Judging that the two operation nodes are the same operation node; calculating a feature index r=u for each feature operation node in each feature operation node set (y1/y2) The method comprises the steps of carrying out a first treatment on the surface of the Wherein U represents the accumulated occurrence times corresponding to each characteristic operation node; y1 represents the total number of the historical fault maintenance records of each characteristic operation node obtained by extraction; y2 represents the total number of the historical fault maintenance records corresponding to each operation node set; removing the characteristic abnormal operation nodes with the characteristic index R smaller than the index threshold value from the corresponding characteristic operation node set;
step S500: and feeding back the information of the abnormal operation nodes with the characteristics after screening to a port of a detection personnel, wherein each time the operation nodes which are captured by the push rod motor and exceed the number threshold value belong to the same operation node with any abnormal operation node with the characteristics, the detection personnel is prompted to detect the performance of the push rod motor.
In order to better implement the method, a push rod motor performance detection system is also provided, and the system comprises: the system comprises a push rod motor state data management module, a historical fault maintenance record information carding module, an abnormal information processing module, an abnormal information screening management module and a performance detection prompt management module;
the push rod motor state data management module is used for respectively installing sensors on the push rod motors in the target monitoring area, collecting state data on the corresponding operation nodes of the push rod motors, and respectively combing state characteristic values of the operation nodes;
the push rod motor state data management module comprises a state data acquisition unit and a state characteristic value calculation unit;
the state data acquisition unit is used for acquiring state data of each push rod motor corresponding to each operation node;
the state characteristic value calculation unit is used for carding the state characteristic values of all the operation nodes respectively;
the historical fault maintenance record information carding module is used for setting a first sampling monitoring period before fault occurrence and a second sampling monitoring period after fault maintenance is completed on each historical fault maintenance record, and each operation node contained in the first sampling monitoring period and the second sampling monitoring period in each historical fault maintenance record is set as a reference node;
the abnormal information processing module is used for capturing initial abnormal operation nodes which cause the occurrence of the fault characterization of the push rod motor in each historical fault maintenance record, and locking the abnormal operation period which causes the fault of the push rod motor in the historical fault maintenance record based on the initial abnormal operation nodes;
the abnormal information screening management module is used for respectively capturing a plurality of historical fault maintenance records with fault characterization similarity larger than a similarity threshold, characteristic abnormal operation nodes in corresponding abnormal operation periods, respectively carrying out characteristic index calculation on the characteristic abnormal operation nodes, and completing screening of the characteristic abnormal operation nodes based on the characteristic indexes;
the abnormal information screening management module comprises a characteristic abnormal operation node capturing management unit and a characteristic abnormal operation node screening unit;
the characteristic abnormal operation node capturing management unit is used for capturing the characteristic abnormal operation nodes in the corresponding abnormal operation periods according to a plurality of historical fault maintenance records with the fault characterization similarity larger than a similarity threshold value;
the characteristic abnormal operation node screening unit is used for respectively carrying out characteristic index calculation on each characteristic abnormal operation node and completing screening of the characteristic abnormal operation nodes based on the characteristic indexes;
the performance detection prompt management module is used for feeding back the information of each characteristic abnormal operation node after screening to the port of the detection personnel, and prompting the detection personnel to perform performance detection on the push rod motor every time the operation nodes which are captured by the push rod motor and exceed the number threshold value and any characteristic abnormal operation nodes belong to the same operation node.
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 method for detecting the performance of the push rod motor based on data analysis is characterized by comprising the following steps of:
step S100: setting a push rod in a push rod motor as an operation node of the push rod motor due to one-time telescopic movement completed by the rotation of a screw rod; respectively installing sensors on all push rod motors in a target monitoring area, collecting state data on all operation nodes corresponding to all push rod motors, and respectively combing state characteristic values of all operation nodes;
the step S100 includes:
step S101: respectively collecting state data for each operation node, wherein the state data comprises a motor driving force X1 born by a corresponding screw rod when the push rod is driven to complete one-time telescopic movement, a maximum dynamic load value X2 born by the push rod in the process of completing one-time telescopic movement, a maximum displacement Y1 reached by the push rod in the process of completing one-time telescopic movement, and a time Y2 spent by restoring from the maximum displacement in the process of completing one-time telescopic movement;
step S102: setting a first state characteristic value P1=x1/X2 of each operation node, and setting a second state characteristic value P2=y1/Y2 of each operation node;
step S200: collecting historical fault maintenance records of all push rod motors in a target monitoring area, setting a first sampling monitoring period before fault occurrence and a second sampling monitoring period after fault maintenance is completed on each historical fault maintenance record, and setting each operation node contained in the first sampling monitoring period and the second sampling monitoring period in each historical fault maintenance record as a reference node;
step S300: capturing initial abnormal operation nodes which cause the fault characterization of the push rod motor in each historical fault maintenance record on the basis of the state data of each historical fault maintenance record on all operation nodes contained in a first sampling monitoring period and a second sampling monitoring period, and locking the abnormal operation periods which cause the fault of the push rod motor in the historical fault maintenance records on the basis of the initial abnormal operation nodes;
step S400: classifying historical fault maintenance records of all push rod motors in a target monitoring area based on similarity among fault characterizations of the corresponding push rod motors; capturing a plurality of historical fault maintenance records with the similarity of fault characterization larger than a similarity threshold value in corresponding abnormal operation periods, respectively carrying out characteristic index calculation on each characteristic abnormal operation node, and completing screening of the characteristic abnormal operation nodes based on the characteristic indexes;
step S500: and feeding back the information of the abnormal operation nodes with the characteristics after screening to a port of a detection personnel, wherein each time the operation nodes which are captured by the push rod motor and exceed the number threshold value belong to the same operation node with any abnormal operation node with the characteristics, the detection personnel is prompted to detect the performance of the push rod motor.
2. The method for detecting performance of a push rod motor according to claim 1, wherein the step S200 includes:
step S201: the corresponding time of diagnosing the corresponding push rod motor as a fault in each historical fault maintenance record is taken as a fault reference time T, the number threshold K of the running nodes is set, and the period duration threshold T is set min The method comprises the steps of carrying out a first treatment on the surface of the Randomly setting a plurality of sampling monitoring periods forward at the fault reference time t;
step S202: acquiring the number N of running nodes contained in a sampling monitoring period which is arbitrarily set and the period duration T covered by the running nodes; will satisfy N ∈ K, T ∈ T min And sampling start time T b Setting a sampling monitoring period closest to the fault reference time T as a first sampling monitoring period T1; after the execution of each historical fault maintenance record is finished, capturing N operation nodes closest to the fault reference time T, and setting the period duration covering the N operation nodes as a second sampling monitoring period T2;
step S203: respectively acquiring a first state characteristic value and a second state characteristic value of each operation node contained in a first sampling monitoring period T1 and a second sampling monitoring period T2 of each historical fault maintenance record; setting each operation node included in the first sampling monitoring period T1 of each historical fault maintenance record as a first reference node of each historical fault maintenance record, and setting each operation node included in the second sampling monitoring period T2 of each historical fault maintenance record as a second reference node of each historical fault maintenance record.
3. The method for detecting performance of a push rod motor according to claim 2, wherein the step S300 includes:
step S301: before a corresponding fault reference time T, acquiring each historical fault maintenance record, except for other operation nodes covered in the corresponding first sampling monitoring period T1, setting the other operation nodes as target operation nodes of each historical fault maintenance record, respectively extracting a first state characteristic value and a second state characteristic value of each target operation node, and respectively extracting a first state characteristic value and a second state characteristic value of each first reference node and a second reference node of each historical fault maintenance record;
step S302; setting a first similarity threshold W 1 Respectively carrying out similarity calculation on each target operation node of each historical fault maintenance record and the first reference node and the second reference node of each historical fault maintenance record based on state characteristic values; obtaining the similarity S of the first state characteristic value P1 of each target operation node and the first reference node P1 Similarity S of second state characteristic value P2 P2 Obtaining the similarity H of the first state characteristic value P1 of each target operation node and the second reference node P1 Similarity H of second state characteristic value P2 P2 ；
Step S303: when a certain target operation node meets S P1 +S P2 >W 1 >H P1 +H P2 Judging that the certain target operation node is an abnormal operation node which causes the fault representation of the corresponding push rod motor in each historical fault maintenance record; will correspond to the run time T g The abnormal operation node farthest from the fault reference time t is judged to be the initial abnormal operation node; judging the running time T g Sampling start time T to corresponding first sampling monitoring period in historical fault maintenance record b And the covered time period is the abnormal operation period of the push rod motor in the corresponding historical fault maintenance record.
4. A method for detecting performance of a push rod motor based on data analysis according to claim 3, wherein the step S400 includes:
step S401: classifying historical fault maintenance records with similarity larger than a similarity threshold value among fault characterizations presented by corresponding push rod motors in a target monitoring area, and respectively obtaining a plurality of historical fault maintenance record sets; extracting state data of each operation node covered by an abnormal operation period corresponding to each historical fault maintenance record in each historical fault maintenance record set respectively; respectively acquiring a first state characteristic value P1 and a second state characteristic value P2 of each operation node; respectively collecting the operation nodes with the same first state characteristic value P1 or the corresponding first state characteristic value P1 with the deviation smaller than the deviation threshold value to obtain a plurality of operation node sets; marking corresponding historical fault maintenance records for each operation node in each operation node set respectively;
step S402: setting the operation nodes with the accumulated occurrence times larger than the frequency threshold value in each operation node set as characteristic operation nodes respectively to obtain corresponding characteristic operation node sets; wherein, if the similarity S of the first state characteristic value P1 between the two operation nodes P1 ' similarity S with the second State characteristic value P2 P2 ' satisfy S P1 '+S P2 '≧W 2 Judging that the two operation nodes are the same operation node; calculating a feature index r=u for each feature operation node in each feature operation node set (y1/y2) The method comprises the steps of carrying out a first treatment on the surface of the Wherein U represents the accumulated occurrence times corresponding to each characteristic operation node; y1 represents the total number of the historical fault maintenance records of each characteristic operation node obtained by extraction; y2 represents the total number of the historical fault maintenance records corresponding to each operation node set; and removing the characteristic abnormal operation nodes with the characteristic index R smaller than the index threshold value from the corresponding characteristic operation node set.
5. A push rod motor performance detection system applied to a push rod motor performance detection method based on data analysis as claimed in any one of claims 1-4, characterized in that the system comprises: the system comprises a push rod motor state data management module, a historical fault maintenance record information carding module, an abnormal information processing module, an abnormal information screening management module and a performance detection prompt management module;
the push rod motor state data management module is used for respectively installing sensors on the push rod motors in the target monitoring area, collecting state data on the corresponding operation nodes of the push rod motors, and respectively combing state characteristic values of the operation nodes;
the historical fault maintenance record information carding module is used for setting a first sampling monitoring period before fault occurrence and a second sampling monitoring period after fault maintenance is completed on each historical fault maintenance record, and each operation node contained in the first sampling monitoring period and the second sampling monitoring period in each historical fault maintenance record is set as a reference node;
the abnormal information processing module is used for capturing initial abnormal operation nodes which cause the occurrence of the fault characterization of the push rod motor in each historical fault maintenance record, and locking the abnormal operation period which causes the fault of the push rod motor in the historical fault maintenance record based on the initial abnormal operation nodes;
the abnormal information screening management module is used for respectively capturing a plurality of historical fault maintenance records with fault characterization similarity larger than a similarity threshold, characteristic abnormal operation nodes in corresponding abnormal operation periods, respectively carrying out characteristic index calculation on the characteristic abnormal operation nodes, and completing screening of the characteristic abnormal operation nodes based on the characteristic indexes;
the performance detection prompt management module is used for feeding back the information of each characteristic abnormal operation node after screening to the port of the detection personnel, and each time the operation nodes which are captured by the push rod motor and exceed the number threshold value and any characteristic abnormal operation nodes belong to the same operation node, the detection personnel are prompted to perform performance detection on the push rod motor.
6. The push rod motor performance detection system according to claim 5, wherein the push rod motor status data management module comprises a status data acquisition unit and a status feature value calculation unit;
the state data acquisition unit is used for acquiring state data of each push rod motor corresponding to each operation node;
and the state characteristic value calculation unit is used for carding the state characteristic values of all the operation nodes respectively.
7. The pushrod motor performance detection system of claim 5, wherein the anomaly information screening management module comprises a characteristic anomaly operation node capture management unit, a characteristic anomaly operation node screening unit;
the characteristic abnormal operation node capturing management unit is used for capturing a plurality of historical fault maintenance records with the fault characterization similarity larger than a similarity threshold value in the corresponding abnormal operation period;
the characteristic abnormal operation node screening unit is used for respectively carrying out characteristic index calculation on each characteristic abnormal operation node and completing screening of the characteristic abnormal operation nodes based on the characteristic indexes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310652684.2A CN116381490B (en) | 2023-06-05 | 2023-06-05 | Push rod motor performance detection system and method based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310652684.2A CN116381490B (en) | 2023-06-05 | 2023-06-05 | Push rod motor performance detection system and method based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116381490A CN116381490A (en) | 2023-07-04 |
| CN116381490B true CN116381490B (en) | 2023-08-11 |
Family
ID=86971552
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310652684.2A Active CN116381490B (en) | 2023-06-05 | 2023-06-05 | Push rod motor performance detection system and method based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116381490B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116865623B (en) * | 2023-09-05 | 2023-11-03 | 深圳市磐锋精密技术有限公司 | New energy motor operation control system based on data analysis |
| CN117217740B (en) * | 2023-11-09 | 2024-02-06 | 江苏德琛常工新能源科技创新有限公司 | Hydrogen energy equipment fault data transmission system and method based on artificial intelligence |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103217286A (en) * | 2013-03-23 | 2013-07-24 | 中国水利电力物资有限公司 | Wind power unit transmission system failure identification method and system based on failure data |
| CN103245912A (en) * | 2013-03-23 | 2013-08-14 | 中国水利电力物资有限公司 | Analytical and diagnostic method for running states of wind turbines |
| CN103294891A (en) * | 2013-03-23 | 2013-09-11 | 中国水利电力物资有限公司 | Wind generator unit state evaluation method and system based on historical failure data |
| CN107229017A (en) * | 2017-01-06 | 2017-10-03 | 科诺伟业风能设备（北京）有限公司 | A kind of wind generating set pitch control battery abnormal failure Forecasting Methodology |
| CN110297178A (en) * | 2018-05-11 | 2019-10-01 | 宫文峰 | Diesel generating set fault diagnosis and detection device and method based on deep learning |
| CN110941725A (en) * | 2019-11-29 | 2020-03-31 | 国网湖南省电力有限公司 | Knowledge graph-based hydroelectric generating set fault diagnosis method and system |
| CN112763908A (en) * | 2020-12-25 | 2021-05-07 | 中国机械设备工程股份有限公司 | Motor health index evaluation system based on multi-fault feature combination |
| CN113759876A (en) * | 2021-09-14 | 2021-12-07 | 西安交通大学 | Wind turbine generator fault diagnosis method and system based on case reasoning |
| CN114114006A (en) * | 2021-10-18 | 2022-03-01 | 华能会理风力发电有限公司 | Wind driven generator diagnosis device and diagnosis method thereof |
| CN114167282A (en) * | 2021-12-03 | 2022-03-11 | 深圳市双合电气股份有限公司 | Motor fault diagnosis and degradation trend prediction method and system |
| CN114722529A (en) * | 2022-03-31 | 2022-07-08 | 南通倍佳机械科技有限公司 | Push rod equipment service life prediction method and system based on artificial intelligence |
| CN114720872A (en) * | 2022-03-24 | 2022-07-08 | 深圳市双合电气股份有限公司 | Fault diagnosis method and system for motor load transmission mechanism |
| CN115048591A (en) * | 2022-06-17 | 2022-09-13 | 四川高融软科信息技术有限公司 | Power distribution network holographic data visualization intelligent display analysis system based on artificial intelligence |
| CN115618976A (en) * | 2022-10-19 | 2023-01-17 | 珠海三体芯变频科技有限公司 | Heat pump fault detection system and method based on Internet of things |
| CN115728057A (en) * | 2022-11-03 | 2023-03-03 | 华能国际电力股份有限公司安徽风电分公司 | Vibration monitoring and fault diagnosis method for gearbox of wind generating set |
| CN116142913A (en) * | 2023-02-03 | 2023-05-23 | 深圳奥龙检测科技有限公司 | Equipment health state analysis method and system based on big data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2594512B (en) * | 2020-04-30 | 2022-08-24 | Spatialbuzz Ltd | Network fault diagnosis |
-
2023
- 2023-06-05 CN CN202310652684.2A patent/CN116381490B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103217286A (en) * | 2013-03-23 | 2013-07-24 | 中国水利电力物资有限公司 | Wind power unit transmission system failure identification method and system based on failure data |
| CN103245912A (en) * | 2013-03-23 | 2013-08-14 | 中国水利电力物资有限公司 | Analytical and diagnostic method for running states of wind turbines |
| CN103294891A (en) * | 2013-03-23 | 2013-09-11 | 中国水利电力物资有限公司 | Wind generator unit state evaluation method and system based on historical failure data |
| CN107229017A (en) * | 2017-01-06 | 2017-10-03 | 科诺伟业风能设备（北京）有限公司 | A kind of wind generating set pitch control battery abnormal failure Forecasting Methodology |
| CN110297178A (en) * | 2018-05-11 | 2019-10-01 | 宫文峰 | Diesel generating set fault diagnosis and detection device and method based on deep learning |
| CN110941725A (en) * | 2019-11-29 | 2020-03-31 | 国网湖南省电力有限公司 | Knowledge graph-based hydroelectric generating set fault diagnosis method and system |
| CN112763908A (en) * | 2020-12-25 | 2021-05-07 | 中国机械设备工程股份有限公司 | Motor health index evaluation system based on multi-fault feature combination |
| CN113759876A (en) * | 2021-09-14 | 2021-12-07 | 西安交通大学 | Wind turbine generator fault diagnosis method and system based on case reasoning |
| CN114114006A (en) * | 2021-10-18 | 2022-03-01 | 华能会理风力发电有限公司 | Wind driven generator diagnosis device and diagnosis method thereof |
| CN114167282A (en) * | 2021-12-03 | 2022-03-11 | 深圳市双合电气股份有限公司 | Motor fault diagnosis and degradation trend prediction method and system |
| CN114720872A (en) * | 2022-03-24 | 2022-07-08 | 深圳市双合电气股份有限公司 | Fault diagnosis method and system for motor load transmission mechanism |
| CN114722529A (en) * | 2022-03-31 | 2022-07-08 | 南通倍佳机械科技有限公司 | Push rod equipment service life prediction method and system based on artificial intelligence |
| CN115048591A (en) * | 2022-06-17 | 2022-09-13 | 四川高融软科信息技术有限公司 | Power distribution network holographic data visualization intelligent display analysis system based on artificial intelligence |
| CN115618976A (en) * | 2022-10-19 | 2023-01-17 | 珠海三体芯变频科技有限公司 | Heat pump fault detection system and method based on Internet of things |
| CN115728057A (en) * | 2022-11-03 | 2023-03-03 | 华能国际电力股份有限公司安徽风电分公司 | Vibration monitoring and fault diagnosis method for gearbox of wind generating set |
| CN116142913A (en) * | 2023-02-03 | 2023-05-23 | 深圳奥龙检测科技有限公司 | Equipment health state analysis method and system based on big data |
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05期);第576-579页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116381490A (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116381490B (en) | Push rod motor performance detection system and method based on data analysis | |
| CN110794227B (en) | Fault detection method, system, device and storage medium | |
| US20020183971A1 (en) | Diagnostic systems and methods for predictive condition monitoring | |
| KR101848193B1 (en) | Prediction method of disk capacity, equipment, facilities and non-volatile computer storage media | |
| CN111947928A (en) | Multi-source information fusion bearing fault prediction system and method | |
| KR102067344B1 (en) | Apparatus and Method for Detecting Abnormal Vibration Data | |
| CN110738255A (en) | device state monitoring method based on clustering algorithm | |
| CN117131110B (en) | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis | |
| CN116308305B (en) | Bridge health monitoring data management system | |
| CN112285557A (en) | Fault diagnosis system and method for train traction motor | |
| KR102545672B1 (en) | Method and apparatus for machine fault diagnosis | |
| CN109257952B (en) | Method, system and storage medium for data transmission with reduced data volume | |
| CN115220396A (en) | Intelligent monitoring method and system for numerical control machine tool | |
| KR102471427B1 (en) | Predictive diagnosis system for mechanical and electrical failures through motor noise and thermal distribution analysis | |
| CN117439822B (en) | Network security data management system and method based on Internet of things | |
| CN112508209A (en) | Robot-based elevator fault diagnosis method and device and storage medium | |
| CN116977708B (en) | Bearing intelligent diagnosis method and system based on self-adaptive aggregation visual view | |
| CN117435883A (en) | Method and system for predicting equipment faults based on digital twinning | |
| CN112524077A (en) | Method, device and system for detecting fan fault | |
| CN112528227A (en) | Sensor abnormal data identification method based on mathematical statistics | |
| CN1669198A (en) | Method and apparatus for monitoring a technical installation, especially for carrying out diagnosis | |
| CN116226719A (en) | Bearing fault diagnosis method based on multidimensional steady-state vibration characteristics and related components | |
| CN110727669A (en) | Device and method for cleaning sensor data of power system | |
| EP3604195B1 (en) | Method, system and computer program product for predicting failure of a noise-emitting apparatus | |
| US11454243B2 (en) | Artificial intelligence training method for a target model based on the label matrix |
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 |