CN114648227B - Method, device, equipment and storage medium for detecting abnormal time sequence of aviation hydraulic pump station - Google Patents
Method, device, equipment and storage medium for detecting abnormal time sequence of aviation hydraulic pump station Download PDFInfo
- Publication number
- CN114648227B CN114648227B CN202210294001.6A CN202210294001A CN114648227B CN 114648227 B CN114648227 B CN 114648227B CN 202210294001 A CN202210294001 A CN 202210294001A CN 114648227 B CN114648227 B CN 114648227B
- Authority
- CN
- China
- Prior art keywords
- data
- detection
- abnormal
- hydraulic pump
- pump station
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 128
- 238000000034 method Methods 0.000 title claims abstract description 71
- 238000003860 storage Methods 0.000 title claims description 13
- 238000001514 detection method Methods 0.000 claims abstract description 178
- 238000013138 pruning Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims description 32
- 230000015654 memory Effects 0.000 claims description 20
- 230000005856 abnormality Effects 0.000 claims description 11
- 238000004519 manufacturing process Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000011497 Univariate linear regression Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 abstract description 3
- 230000011218 segmentation Effects 0.000 abstract description 2
- 239000003921 oil Substances 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 239000007788 liquid Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 238000013450 outlier detection Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000013515 script Methods 0.000 description 2
- SLXKOJJOQWFEFD-UHFFFAOYSA-N 6-aminohexanoic acid Chemical compound NCCCCCC(O)=O SLXKOJJOQWFEFD-UHFFFAOYSA-N 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 239000010720 hydraulic oil Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Manufacturing & Machinery (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The utility model discloses an aviation hydraulic pump station time sequence anomaly detection method, through carrying out preliminary treatment to aviation hydraulic pump station's time sequence data, remove meaningless data and the obvious anomaly data that does not accord with industry standard, through carrying out classification segmentation to the time sequence data after the preliminary treatment according to the working condition, carry out anomaly detection in same class data, simultaneously carry out pruning processing to the testing process, can shorten the detection time and promote detection efficiency, after above-mentioned twice detection screen out anomaly data, the data quantity that awaits measuring reduces greatly, carry out local outlier factor detection again, both remain the precision of local outlier factor detection method, the time complexity of this detection method has also been reduced, further promoted the detection speed, quick output anomaly detection result, help the technician to grasp the abnormal conditions in the equipment operation in-process accurately, improve aviation hydraulic pump station equipment use efficiency, guarantee aircraft assembly operation safety goes on smoothly.
Description
Technical Field
The application relates to the field of industrial equipment data anomaly detection, in particular to a method, a device, equipment and a storage medium for detecting timing anomaly of an aviation hydraulic pump station.
Background
The hydraulic pump station is required to be used for installing, debugging, detecting and the like of an aircraft hydraulic system in the aircraft final assembly, and the aviation hydraulic pump station system has the characteristics of high pressure, large flow and the like, so that the aviation hydraulic pump station system has higher requirements on the surrounding environment in the use process, a large amount of heat is easily generated in the use process, heat is required to be dissipated in time, and meanwhile, the pollution degree of oil is required to be smaller, so that the filter screen is prevented from being blocked, pressure fluctuation is prevented from being abnormal and the like. Once the operation process of the hydraulic pump station is abnormal, the conditions of suspending tasks, planning delay and the like are caused by light weight, the products are damaged, and even operation safety accidents occur. Aiming at the abnormal problems of overhigh temperature, serious oil pollution, abnormal pressure fluctuation, lower liquid level than a working value and the like in the use process of the hydraulic pump station, the abnormal detection of the equipment operation time sequence data is an effective means for guaranteeing the stable operation of equipment and improving the use efficiency of the equipment.
The abnormal detection of the time sequence data of the aviation hydraulic pump station mainly comprises the steps of collecting data of a sensor, counting the number of the data in a period of time, calculating the distance between the data, calculating the density of the data and the like to detect whether abnormal conditions exist in the data or not, but the abnormal conditions exist in the data.
Disclosure of Invention
The main aim of the application is to provide a method, a device, equipment and a storage medium for detecting the abnormal time sequence of an aviation hydraulic pump station, which aim at solving the technical problems of low accuracy and long time for detecting the abnormal time sequence data of the aviation hydraulic pump station.
In order to achieve the above purpose, the present application provides a method for detecting timing sequence abnormality of an aviation hydraulic pump station, including:
acquiring time sequence data of operation of a target aviation hydraulic pump station, and preprocessing the time sequence data to obtain first detection data and first abnormal data;
classifying the data objects in the first detection data according to the working state of the target aviation hydraulic pump station to obtain a plurality of data class groups;
pruning the first detection data according to the k distance of the data object and the average k distance of the data class group to obtain second detection data and second abnormal data;
performing local outlier factor anomaly detection on the second detection data to obtain third anomaly data;
outputting the first, second and third abnormal data.
Optionally, the step of obtaining the time sequence data of the operation of the target aviation hydraulic pump station and preprocessing the time sequence data to obtain the first detection data and the first abnormal data includes:
performing data missing value processing on the time sequence data by using a local mean value interpolation method to obtain first preprocessing data;
judging whether the number of the sequences of the continuous zero values in the first preprocessing data is larger than a preset number threshold value, if so, removing the sequences of the continuous zero values larger than the number threshold value to obtain second preprocessing data;
and judging the size relation between each data object in the second preprocessing data and the first threshold value, outputting the first abnormal data if the data object is larger than the first threshold value, and outputting the first abnormal data if the data object is smaller than or equal to the first threshold value.
Optionally, the step of classifying the data object in the first detection data according to the working state of the target aviation hydraulic pump station to obtain a plurality of data class groups includes:
performing piecewise fitting on the first detection data by using a univariate linear regression algorithm to obtain fitted data;
performing breakpoint detection on the fitted data to obtain data breakpoints;
and carrying out K-means classification on the data objects in the first detection data according to the data breakpoint and the working state of the target aviation hydraulic pump station to obtain a plurality of data class groups.
Optionally, pruning the first detection data according to the k distance of the data object and the average k distance of the data class group to obtain second detection data and second abnormal data, which includes:
if the absolute value of the difference between the k distance of the data object and the average k distance of the data class group to which the data object belongs is smaller than or equal to a preset second threshold value, pruning the first detection data, and marking the first detection data as the second abnormal data;
and if the absolute value of the difference between the k distance of the data object and the average k distance of the data class group to which the data object belongs is larger than a preset second threshold value, marking the data object as the second detection data.
Optionally, pruning the first detection data according to the k distance of the data object and the average k distance of the data class group to obtain second detection data and second abnormal data, which includes:
obtaining the average k distance of the data category group by the following relation:
wherein,k–dist(c)representing the average k-distance of the data class group c,k–dist(i)the k-distance of data object i is represented, i being the data object in data class group c.
Optionally, the step of performing local outlier factor anomaly detection on the second detection data to obtain third anomaly data includes:
judging whether the absolute value of the difference between the local outlier factor of the data object and 1 is larger than a preset third threshold value;
if yes, outputting the third abnormal data.
Optionally, the step of performing local outlier factor anomaly detection on the second detection data to obtain third anomaly data includes:
the local outlier factor is obtained by the following relation:
wherein,for the reachable distance between data objects i and o, -/->For the local reachable density of data object i, < +.>Local outlier factor for data object i。
In addition, in order to realize above-mentioned purpose, this application still provides an aviation hydraulic pump station time sequence anomaly detection device, includes:
the first abnormal data acquisition module is used for acquiring time sequence data of operation of the target aviation hydraulic pump station, preprocessing the time sequence data and acquiring first detection data and first abnormal data;
the data category acquisition module is used for classifying the data objects in the first detection data according to the working state of the target aviation hydraulic pump station to obtain a plurality of data category groups;
the second abnormal data acquisition module is used for pruning the first detection data according to the k distance of the data object and the average k distance of the data class group to obtain second detection data and second abnormal data;
the third abnormal data acquisition module is used for carrying out local outlier factor abnormal detection on the second detection data to obtain third abnormal data;
the abnormal data output module is used for outputting the first abnormal data, the second abnormal data and the third abnormal data.
In addition, in order to achieve the above object, the present application further provides a production apparatus, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above method.
In addition, in order to achieve the above object, the present application further provides a computer readable storage medium, where a computer program is stored, and a processor executes the computer program to implement the above method.
The beneficial effects that this application can realize.
According to the method, the device, the equipment and the storage medium for detecting the time sequence abnormality of the aviation hydraulic pump station, the first detection data and the first abnormality data are obtained by acquiring the time sequence data of the operation of the target aviation hydraulic pump station and preprocessing the time sequence data; classifying the data objects in the first detection data according to the working state of the target aviation hydraulic pump station to obtain a plurality of data class groups; pruning the first detection data according to the k distance of the data object and the average k distance of the data class group to obtain second detection data and second abnormal data; performing local outlier factor anomaly detection on the second detection data to obtain third anomaly data; outputting the first, second and third abnormal data. The method comprises the steps of preprocessing time sequence data of an aviation hydraulic pump station, screening meaningless data and obvious abnormal data which do not meet industrial standards, classifying and dividing the preprocessed time sequence data according to working conditions, carrying out abnormal detection in the same type of data, pruning the detection process, shortening detection time, improving detection efficiency, greatly reducing the data quantity to be detected after the abnormal data are screened through the two detection processes, and carrying out local outlier factor detection, so that the accuracy of a local outlier factor detection method is maintained, the time complexity of the detection method is reduced, the detection speed is further improved, the abnormal detection result is rapidly output, technicians are helped to accurately and timely master abnormal conditions in the operation process of equipment, the use efficiency of the aviation hydraulic pump station equipment is improved, and the safety and smoothness of aircraft assembly operation are ensured.
Drawings
FIG. 1 is a schematic diagram of a production facility of a hardware operating environment according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a method for detecting timing sequence abnormality of an aviation hydraulic pump station according to an embodiment of the present application;
fig. 3 is a schematic diagram of a functional module of an abnormal timing sequence detecting device of an aviation hydraulic pump station according to an embodiment of the present application.
The realization, functional characteristics and advantages of the present application will be further described with reference to the embodiments, referring to the attached drawings.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The main solutions of the embodiments of the present application are: according to the method, the device, the equipment and the storage medium for detecting the time sequence abnormality of the aviation hydraulic pump station, the time sequence data of the operation of the target aviation hydraulic pump station are obtained, and the time sequence data are preprocessed to obtain first detection data and first abnormality data; classifying the data objects in the first detection data according to the working state of the target aviation hydraulic pump station to obtain a plurality of data class groups; pruning the first detection data according to the k distance of the data object and the average k distance of the data class group to obtain second detection data and second abnormal data; performing local outlier factor anomaly detection on the second detection data to obtain third anomaly data; outputting the first, second and third abnormal data.
In the prior art, the hydraulic pump station is required to be used for installing, debugging, detecting and the like of an aircraft hydraulic system in the aircraft final assembly, and because the aviation hydraulic pump station system has the characteristics of high pressure, large flow and the like, the aviation hydraulic pump station system has higher requirements on the surrounding environment in the use process, a large amount of heat is easily generated in the use process, heat is required to be dissipated in time, and meanwhile, the pollution degree of oil is required to be smaller, so that the filter screen is prevented from being blocked, abnormal in pressure fluctuation and the like. Once the operation process of the hydraulic pump station is abnormal, the conditions of suspending tasks, planning delay and the like are caused by light weight, the products are damaged, and even operation safety accidents occur. Aiming at the abnormal problems of overhigh temperature, serious oil pollution, abnormal pressure fluctuation, lower liquid level than a working value and the like in the use process of the hydraulic pump station, the abnormal detection of the equipment operation time sequence data is an effective means for guaranteeing the stable operation of equipment and improving the use efficiency of the equipment.
The abnormal detection of the time sequence data of the aviation hydraulic pump station mainly comprises the steps of collecting data of a sensor, counting the number of the data in a period of time, calculating the distance between the data, calculating the density of the data and the like, and detecting whether abnormal conditions exist in the data or not, but the problems of detecting errors and overlong detecting time exist.
Therefore, the method and the device have the advantages that the time sequence data of the aviation hydraulic pump station are preprocessed, meaningless data and obvious abnormal data which do not meet the industrial standard are screened, the preprocessed time sequence data are classified and divided according to the working condition, abnormal detection is carried out in the same type of data, meanwhile, the detection process is pruned, the detection time can be shortened, the detection efficiency is improved, after the abnormal data are screened through the detection for two times, the data to be detected is greatly reduced, the local outlier factor detection is carried out, the accuracy of the local outlier factor detection method is reserved, the time complexity of the detection method is reduced, the detection speed is further improved, the abnormal detection result is rapidly output, the technical staff is helped to accurately and timely master the abnormal condition in the operation process of the equipment, the use efficiency of the aviation hydraulic pump station equipment is improved, and the safety and smoothness of the aircraft general assembly operation are ensured.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a production device of a hardware running environment according to an embodiment of the present application.
As shown in fig. 1, the production apparatus may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 is not limiting of the production apparatus and may include more or fewer components than shown, or certain components may be combined, or a different arrangement of components.
As shown in fig. 1, an operating system, a data storage module, a network communication module, a user interface module, and an electronic program may be included in the memory 1005 as one type of storage medium.
In the production facility shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the production equipment can be arranged in the production equipment, and the production equipment calls the timing sequence abnormality detection device of the aviation hydraulic pump station stored in the memory 1005 through the processor 1001 and executes the timing sequence abnormality detection method of the aviation hydraulic pump station.
Referring to fig. 2, based on the hardware device of the foregoing embodiment, an embodiment of the present application provides a method for detecting a timing anomaly of an aviation hydraulic pump station, including:
s10: acquiring time sequence data of operation of a target aviation hydraulic pump station, and preprocessing the time sequence data to obtain first detection data and first abnormal data;
in the specific implementation process, the time sequence data refer to key data of the PLC of the aviation hydraulic pump station, including oil supply pressure, oil tank temperature, oil tank liquid level, oil return pressure, system flow and time.
And storing the key data into a time sequence database, and acquiring the time sequence data of the operation of the target aviation hydraulic pump station from the time sequence database during detection. And converting the time and date format data into long format class data, and storing the long format class data and other time sequence data in a local disk file system in a TXT format.
And reading the TXT data into a two-dimensional array, wherein the rows of the array represent the pressure state of the hydraulic pump station at a certain moment, and the columns of the array represent the observed values of one pressure at all moments.
As an optional implementation manner, the step of obtaining the time sequence data of the operation of the target aviation hydraulic pump station and preprocessing the time sequence data to obtain the first detection data and the first abnormal data includes: performing data missing value processing on the time sequence data by using a local mean value interpolation method to obtain first preprocessing data; judging whether the number of the sequences of the continuous zero values in the first preprocessing data is larger than a preset number threshold value, if so, removing the sequences of the continuous zero values larger than the number threshold value to obtain second preprocessing data; and judging the size relation between each data object in the second preprocessing data and the first threshold value, outputting the first abnormal data if the data object is larger than the first threshold value, and outputting the first abnormal data if the data object is smaller than or equal to the first threshold value.
In the specific implementation process, a local mean interpolation method is used for carrying out data missing value processing on time series data:wherein->Representing the predicted value at time t, n representing looking backward at time t,/>An observation value indicating the i-th time; traversing each element in the array, and filling the missing elements with the average value of the first 10 data at the current moment for the missing value; sequencing the array of behavior units from small to large according to time, and converting the time into timestamp numbers; the time sequence data processed by the missing value is first preprocessing data.
Counting the number and the positions of time sequence data with continuous zero values in the first preprocessing data, wherein the overlong continuous zero value sequence is unnecessary to detect, and the nonsensical data needs to be removed so as to increase the detection efficiency, and determining the sequence length needing to be removed according to the actual use condition. In this embodiment, taking oil supply pressure data as an example, the number threshold is set to 120, sequences with consecutive zero values exceeding 120 are removed, and the remaining time-series data is reserved as second pre-processing data.
Performing preliminary anomaly detection on the second preprocessed data, and if the time sequence data is larger than a first threshold set according to the guiding process file, setting the first threshold to 54Mpa in the embodiment, and adding the first anomaly data as anomaly data; and if the data is smaller than or equal to the first detection data, the data is output as the first detection data, and the number of the data to be detected is primarily reduced.
S20: classifying the data objects in the first detection data according to the working state of the target aviation hydraulic pump station to obtain a plurality of data class groups;
in the specific implementation process, the working state of the target aviation hydraulic pump station refers to the working state of the hydraulic oil vehicle, and the method comprises the following steps: ready state, refuel state, steady voltage state, pressure release state. The data objects are the time sequence data in the previous step, and the data objects are classified and divided, so that the subsequent abnormality detection is carried out in the same type of data, the detection time can be shortened, the detection efficiency is improved, and the accuracy of the subsequent detection processing is also improved.
As an optional implementation manner, the step of classifying the data objects in the first detection data according to the working state of the target aviation hydraulic pump station to obtain a plurality of data class groups includes: performing piecewise fitting on the first detection data by using a univariate linear regression algorithm to obtain fitted data; performing breakpoint detection on the fitted data to obtain data breakpoints; and carrying out K-means classification on the data objects in the first detection data according to the data breakpoint and the working state of the target aviation hydraulic pump station to obtain a plurality of data class groups.
In the specific implementation process, a univariate linear regression algorithm is adopted to perform piecewise linear fitting on the first detection data; performing breakpoint detection on the fitted data, finding all data breakpoints, and dividing the data object by using the data breakpoints; dividing the segmentation data into four types by adopting K-means according to the working state of the target aviation hydraulic pump station: the method comprises the steps of preparing a state, adding fuel, stabilizing pressure and releasing pressure, so that each data object in the first detection data has a corresponding belonging category.
S30: pruning the first detection data according to the k distance of the data object and the average k distance of the data class group to obtain second detection data and second abnormal data;
in the specific implementation process, the k distance of each data object is calculated according to the class, the average k distance of the corresponding data class group is calculated according to the k distance of each data object, whether pruning processing is carried out or not is judged by using the average k distance of each data class group, and the detection time of abnormal data is reduced.
As an optional implementation manner, the step of pruning the first detection data according to the k distance of the data object and the average k distance of the data class group to obtain second detection data and second abnormal data includes: if the absolute value of the difference between the k distance of the data object and the average k distance of the data class group to which the data object belongs is smaller than or equal to a preset second threshold value, pruning the first detection data, and marking the first detection data as the second abnormal data; and if the absolute value of the difference between the k distance of the data object and the average k distance of the data class group to which the data object belongs is larger than a preset second threshold value, marking the data object as the second detection data.
In a specific implementation process, the embodiment sets a second threshold to be 0.3 according to an actual process and a historical test conclusion, and if the absolute value of the difference between the k distance of the data object and the average k distance of the data class group to which the data object belongs is smaller than or equal to 0.3, pruning is required to be performed on the abnormal data, and the second abnormal data is added; and if the detection data is more than 0.3, adding second detection data for further detection.
As another alternative embodiment, the step of pruning the first detection data according to the k distance of the data object and the average k distance of the data class group to obtain second detection data and second abnormal data includes: obtaining the average k distance of the data category group by the following relation:
wherein,k–dist(c)representing the average k-distance of the data class group c,k–dist(i)the k-distance of data object i is represented, i being the data object in data class group c.
In the implementation process, the k distance of the data object i is denoted as k-dist (i) =dist (i, o), and since the k distance of any one data object in one data set is a unique value, the following two conditions are satisfied at the same time:
at least k objects q epsilon S\ { i } in the set S are dist (i, q) less than or equal to dist (i, o);
at most k-1 objects q εS\ { i } have dist (i, q) < dist (i, o) in set S;
where set S is a data set of a data class group, q is other data objects in the data set than i, and o is a data object in the data set that is equal to the k distance of i.
S40: performing local outlier factor anomaly detection on the second detection data to obtain third anomaly data;
in a specific implementation process, the local outlier factor detection method (Local Outlier Factor, LOF algorithm) is an unsupervised outlier detection method, and is a representative algorithm in the outlier detection method based on density, the outlier factor is the average density of the positions of the sample points around a sample point to the density of the positions of the sample point, when the outlier factor of the sample point is greater than 1, the density of the positions of the sample points is less than the density of the positions of the samples around the sample point, and the outlier is more likely. The algorithm has higher detection accuracy, but in industrial practical application, the data to be detected is very much, the time consumption is more, and the complexity is very high. After the second detection data of the method passes through the twice abnormal data detection and screening to screen out the abnormal data, the data to be detected is greatly reduced, and then the local outlier factor detection is carried out, so that the accuracy is ensured, and the time complexity is reduced.
As an optional implementation manner, the step of performing local outlier factor anomaly detection on the second detection data to obtain third anomaly data includes: judging whether the absolute value of the difference between the local outlier factor of the data object and 1 is larger than a preset third threshold value; if yes, outputting the third abnormal data.
In the specific implementation process, a third threshold value is set to be 0.2 according to the actual process and the historical test conclusion, whether the absolute value of the difference between the local outlier factors of the data objects and 1 is larger than 0.2 or not is the abnormal data, and the third abnormal data are added.
As another optional implementation manner, the step of performing local outlier factor anomaly detection on the second detection data to obtain third anomaly data includes: the local outlier factor is obtained by the following relation:
wherein,for the reachable distance between data objects i and o, -/->For the local reachable density of data object i, < +.>Is a local outlier factor of the data object i.
In the implementation, if the data object i is far from the data object o, the reachable distance between the two is the actual distance between them, and when they are close enough, the actual distance is the k distance of the data object o, namely:。
the local reachable density of the data object i is the reciprocal of the average reachable density of the k nearest neighbor of the data object i, namely the point-to-point in the k neighborhood of the data object iThe inverse of the average reachable distance from object i, namely:。
the local outlier factor of data object i is the average of the ratio of the local reachable densities of the neighborhood points of data object i to the local reachable densities of data object i, i.e。
S50: outputting the first, second and third abnormal data.
In the specific implementation process, combining the first abnormal data obtained through preliminary abnormal detection, the second abnormal data obtained through pruning treatment and the third abnormal data obtained through local outlier factor detection, and outputting the data value of the abnormal data and the corresponding time and other related attribute information, namely the time sequence abnormal detection result of the target aviation hydraulic pump station.
It should be understood that the foregoing is merely illustrative, and the technical solutions of the present application are not limited in any way, and those skilled in the art may perform the setting based on the needs in practical applications, and the present application is not limited herein.
Through the description, it is easy to find that, in this embodiment, through preprocessing the time sequence data of the aviation hydraulic pump station, meaningless data and obvious abnormal data which does not meet the industrial standard are screened out, through classifying and dividing the preprocessed time sequence data according to the working condition, abnormal detection is performed in the same kind of data, and pruning processing is performed in the detection process, so that the detection time can be shortened, the detection efficiency is improved, after the abnormal data are screened out through the detection twice, the data to be detected is greatly reduced, and then the local outlier factor detection is performed, so that the accuracy of the local outlier factor detection method is maintained, the time complexity of the detection method is reduced, the detection speed is further improved, the abnormal detection result is rapidly output, technicians are helped to accurately and timely grasp the abnormal condition in the operation process of the equipment, the use efficiency of the aviation hydraulic pump station equipment is improved, and the safety and smoothness of the aircraft assembly operation are ensured.
Referring to fig. 3, based on the same inventive concept, an embodiment of the present application further provides an abnormal timing detection device for an aviation hydraulic pump station, including:
the first abnormal data acquisition module is used for acquiring time sequence data of operation of the target aviation hydraulic pump station, preprocessing the time sequence data and acquiring first detection data and first abnormal data;
the data category acquisition module is used for classifying the data objects in the first detection data according to the working state of the target aviation hydraulic pump station to obtain a plurality of data category groups;
the second abnormal data acquisition module is used for pruning the first detection data according to the k distance of the data object and the average k distance of the data class group to obtain second detection data and second abnormal data;
the third abnormal data acquisition module is used for carrying out local outlier factor abnormal detection on the second detection data to obtain third abnormal data;
the abnormal data output module is used for outputting the first abnormal data, the second abnormal data and the third abnormal data.
It should be noted that, each module in the timing anomaly detection device of the hydraulic pump station in this embodiment corresponds to each step in the timing anomaly detection method of the hydraulic pump station in the foregoing embodiment, so the specific implementation of this embodiment may refer to the implementation of the timing anomaly detection method of the hydraulic pump station, and will not be described herein.
Furthermore, in an embodiment, an embodiment of the present application also provides a production apparatus, the apparatus including a processor, a memory, and a computer program stored in the memory, which when executed by the processor, implements the steps of the method in the foregoing embodiment.
Furthermore, in an embodiment, the embodiments of the present application further provide a computer storage medium, on which a computer program is stored, which when being executed by a processor, implements the steps of the method in the previous embodiments.
In some embodiments, the computer readable storage medium may be FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; but may be a variety of devices including one or any combination of the above memories. The computer may be a variety of computing devices including smart terminals and servers.
In some embodiments, the executable instructions may be in the form of programs, software modules, scripts, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and they may be deployed in any form, including as stand-alone programs or as modules, components, subroutines, or other units suitable for use in a computing environment.
As an example, the executable instructions may, but need not, correspond to files in a file system, may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a hypertext markup language (HTML, hyper Text Markup Language) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).
As an example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices located at one site or, alternatively, distributed across multiple sites and interconnected by a communication network.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system 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 system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
From the above description of embodiments, it will be clear to a person skilled in the art that the above embodiment method may be implemented by means of software plus a necessary general hardware platform, but may of course also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. read-only memory/random-access memory, magnetic disk, optical disk), comprising instructions for causing a multimedia terminal device (which may be a mobile phone, a computer, a television receiver, or a network device, etc.) to perform the method described in the embodiments of the present application
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.
Claims (8)
1. The method for detecting the abnormal time sequence of the aviation hydraulic pump station is characterized by comprising the following steps of:
acquiring time sequence data of operation of a target aviation hydraulic pump station, and preprocessing the time sequence data to obtain first detection data and first abnormal data; the step of acquiring the time sequence data of the operation of the target aviation hydraulic pump station and preprocessing the time sequence data to obtain first detection data and first abnormal data comprises the following steps: performing data missing value processing on the time sequence data by using a local mean value interpolation method to obtain first preprocessing data; judging whether the number of the sequences of the continuous zero values in the first preprocessing data is larger than a preset number threshold value, if so, removing the sequences of the continuous zero values larger than the number threshold value to obtain second preprocessing data; judging the size relation between each data object in the second preprocessing data and a first threshold value, outputting the first abnormal data if the data object is larger than the first threshold value, and outputting the first abnormal data if the data object is smaller than or equal to the first threshold value;
classifying the data objects in the first detection data according to the working state of the target aviation hydraulic pump station to obtain a plurality of data class groups; the step of classifying the data objects in the first detection data according to the working state of the target aviation hydraulic pump station to obtain a plurality of data class groups comprises the following steps: performing piecewise fitting on the first detection data by using a univariate linear regression algorithm to obtain fitted data; performing breakpoint detection on the fitted data to obtain data breakpoints; according to the data breakpoint and the working state of the target aviation hydraulic pump station, carrying out K-means classification on the data objects in the first detection data to obtain a plurality of data class groups;
pruning the first detection data according to the k distance of the data object and the average k distance of the data class group to obtain second detection data and second abnormal data;
performing local outlier factor anomaly detection on the second detection data to obtain third anomaly data;
outputting the first, second and third abnormal data.
2. The method for detecting abnormal time sequence of an aviation hydraulic pump station according to claim 1, wherein the step of pruning the first detection data to obtain second detection data and second abnormal data according to the k distance of the data object and the average k distance of the data class group comprises the following steps:
if the absolute value of the difference between the k distance of the data object and the average k distance of the data class group to which the data object belongs is smaller than or equal to a preset second threshold value, pruning the first detection data, and marking the first detection data as the second abnormal data;
and if the absolute value of the difference between the k distance of the data object and the average k distance of the data class group to which the data object belongs is larger than a preset second threshold value, marking the data object as the second detection data.
3. The method for detecting abnormal time sequence of an aviation hydraulic pump station according to claim 1, wherein the step of pruning the first detection data to obtain second detection data and second abnormal data according to the k distance of the data object and the average k distance of the data class group comprises the following steps:
obtaining the average k distance of the data category group by the following relation:
wherein,k–dist(c)representing the average k-distance of the data class group c,k–dist(i)the k-distance of data object i is represented, i being the data object in data class group c.
4. The method for detecting abnormal time sequence of an aviation hydraulic pump station according to claim 1, wherein the step of performing local outlier factor abnormality detection on the second detection data to obtain third abnormal data comprises the steps of:
judging whether the absolute value of the difference between the local outlier factor of the data object and 1 is larger than a preset third threshold value;
if yes, outputting the third abnormal data.
5. The method for detecting abnormal time sequence of an aviation hydraulic pump station according to claim 1, wherein the step of performing local outlier factor abnormality detection on the second detection data to obtain third abnormal data comprises the steps of:
the local outlier factor is obtained by the following relation:
wherein,for the reachable distance between data objects i and o, -/->For the local reachable density of data object i, < +.>Is a local outlier factor of the data object i.
6. An abnormal detection device of time sequence of aviation hydraulic pump station, which is characterized by comprising:
the first abnormal data acquisition module is used for acquiring time sequence data of operation of the target aviation hydraulic pump station, preprocessing the time sequence data and acquiring first detection data and first abnormal data; the step of acquiring the time sequence data of the operation of the target aviation hydraulic pump station and preprocessing the time sequence data to obtain first detection data and first abnormal data comprises the following steps: performing data missing value processing on the time sequence data by using a local mean value interpolation method to obtain first preprocessing data; judging whether the number of the sequences of the continuous zero values in the first preprocessing data is larger than a preset number threshold value, if so, removing the sequences of the continuous zero values larger than the number threshold value to obtain second preprocessing data; judging the size relation between each data object in the second preprocessing data and a first threshold value, outputting the first abnormal data if the data object is larger than the first threshold value, and outputting the first abnormal data if the data object is smaller than or equal to the first threshold value;
the data category acquisition module is used for classifying the data objects in the first detection data according to the working state of the target aviation hydraulic pump station to obtain a plurality of data category groups; the step of classifying the data objects in the first detection data according to the working state of the target aviation hydraulic pump station to obtain a plurality of data class groups comprises the following steps: performing piecewise fitting on the first detection data by using a univariate linear regression algorithm to obtain fitted data; performing breakpoint detection on the fitted data to obtain data breakpoints; according to the data breakpoint and the working state of the target aviation hydraulic pump station, carrying out K-means classification on the data objects in the first detection data to obtain a plurality of data class groups;
the second abnormal data acquisition module is used for pruning the first detection data according to the k distance of the data object and the average k distance of the data class group to obtain second detection data and second abnormal data;
the third abnormal data acquisition module is used for carrying out local outlier factor abnormal detection on the second detection data to obtain third abnormal data;
the abnormal data output module is used for outputting the first abnormal data, the second abnormal data and the third abnormal data.
7. A production apparatus comprising a memory and a processor, said memory having stored therein a computer program, said processor executing said computer program to implement the method of any of claims 1-5.
8. A computer readable storage medium, having stored thereon a computer program, the computer program being executable by a processor to implement the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210294001.6A CN114648227B (en) | 2022-03-23 | 2022-03-23 | Method, device, equipment and storage medium for detecting abnormal time sequence of aviation hydraulic pump station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210294001.6A CN114648227B (en) | 2022-03-23 | 2022-03-23 | Method, device, equipment and storage medium for detecting abnormal time sequence of aviation hydraulic pump station |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114648227A CN114648227A (en) | 2022-06-21 |
| CN114648227B true CN114648227B (en) | 2024-03-15 |
Family
ID=81996146
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210294001.6A Active CN114648227B (en) | 2022-03-23 | 2022-03-23 | Method, device, equipment and storage medium for detecting abnormal time sequence of aviation hydraulic pump station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114648227B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115526241A (en) * | 2022-09-13 | 2022-12-27 | 成都飞机工业（集团）有限责任公司 | Real-time abnormity detection method, device, equipment and medium for aviation hydraulic pump station |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005195081A (en) * | 2004-01-06 | 2005-07-21 | Daikin Ind Ltd | Hydraulic power unit |
| CN102216534A (en) * | 2008-12-26 | 2011-10-12 | 日立建机株式会社 | Diagnostic information providing system for construction machine |
| JP2012230703A (en) * | 2012-07-19 | 2012-11-22 | Hitachi Ltd | Abnormality detection method and system |
| CN106575117A (en) * | 2014-12-15 | 2017-04-19 | 日立建机株式会社 | System for diagnosing oil properties in working machine |
| CN107848747A (en) * | 2015-07-17 | 2018-03-27 | 三菱电机株式会社 | The safety device of hydraulic pressure elevator and the enabling traveling method for detecting abnormality of hydraulic pressure elevator |
| CN109978379A (en) * | 2019-03-28 | 2019-07-05 | 北京百度网讯科技有限公司 | Time series data method for detecting abnormality, device, computer equipment and storage medium |
| WO2020019403A1 (en) * | 2018-07-26 | 2020-01-30 | 平安科技（深圳）有限公司 | Electricity consumption abnormality detection method, apparatus and device, and readable storage medium |
| CN112182056A (en) * | 2019-07-02 | 2021-01-05 | 中移(苏州)软件技术有限公司 | Data detection method, device, equipment and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3217335A1 (en) * | 2016-03-11 | 2017-09-13 | Deutsche Telekom AG | Method and system for generating a training model for fabricating synthetic data and for fabricating synthetic data |
| JP7087530B2 (en) * | 2018-03-23 | 2022-06-21 | コベルコ建機株式会社 | Exhaust gas abnormality detector |
| FR3106907B1 (en) * | 2020-01-31 | 2022-02-11 | Thales Sa | ELECTRONIC DEVICE FOR CALCULATING CENTRALIZED DISSEMINATION OF THE STATE(S) OF AN AIRCRAFT, AVIONIC ASSEMBLY, METHOD, AND ASSOCIATED COMPUTER PROGRAM |
-
2022
- 2022-03-23 CN CN202210294001.6A patent/CN114648227B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005195081A (en) * | 2004-01-06 | 2005-07-21 | Daikin Ind Ltd | Hydraulic power unit |
| CN102216534A (en) * | 2008-12-26 | 2011-10-12 | 日立建机株式会社 | Diagnostic information providing system for construction machine |
| JP2012230703A (en) * | 2012-07-19 | 2012-11-22 | Hitachi Ltd | Abnormality detection method and system |
| CN106575117A (en) * | 2014-12-15 | 2017-04-19 | 日立建机株式会社 | System for diagnosing oil properties in working machine |
| CN107848747A (en) * | 2015-07-17 | 2018-03-27 | 三菱电机株式会社 | The safety device of hydraulic pressure elevator and the enabling traveling method for detecting abnormality of hydraulic pressure elevator |
| WO2020019403A1 (en) * | 2018-07-26 | 2020-01-30 | 平安科技（深圳）有限公司 | Electricity consumption abnormality detection method, apparatus and device, and readable storage medium |
| CN109978379A (en) * | 2019-03-28 | 2019-07-05 | 北京百度网讯科技有限公司 | Time series data method for detecting abnormality, device, computer equipment and storage medium |
| CN112182056A (en) * | 2019-07-02 | 2021-01-05 | 中移(苏州)软件技术有限公司 | Data detection method, device, equipment and storage medium |
Non-Patent Citations (7)
| Title |
|---|
| Anomaly detection based on multivariate data for the aircraft hydraulic system;Hongsheng Yan etc.;SageJournals;第235卷(第05期);全文 * |
| Research on Anomaly Detection of Civil Aircraft Hydraulic System Based on Multivariate Monitoring Data;HongSheng Yan etc.;2019 IEEE AUTOTESTCON;全文 * |
| 一种改进的局部离群数据检测算法;段培永等;黑龙江大学自然科学学报(第04期);全文 * |
| 三峡水电厂700MW发电机组内冷水系统渗漏监测研究;陈勇强等;大电机技术(第02期);全文 * |
| 基于密度的异常数据检测算法GSWCLOF;李少波等;计算机工程与应用(第19期);全文 * |
| 基于重要点的飞机发动机数据异常子序列检测;杨慧等;计算机工程与设计(第09期);全文 * |
| 工业过程数据异常检测的改进局部离群因子法;何九虎等;计算机与应用化学(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114648227A (en) | 2022-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114548832B (en) | Wind power equipment state evaluation method and system based on big data | |
| CN111641519B (en) | Abnormal root cause positioning method, device and storage medium | |
| CN113283630A (en) | Air quality prediction method, device, equipment and computer readable storage medium | |
| CN111309539A (en) | Abnormity monitoring method and device and electronic equipment | |
| CN114648227B (en) | Method, device, equipment and storage medium for detecting abnormal time sequence of aviation hydraulic pump station | |
| CN112001520A (en) | Weather forecasting method and device, computer equipment and storage medium | |
| CN112383891A (en) | Equipment registration method and device based on object model automatic matching | |
| CN112417734A (en) | Wind speed correction method and device based on geographic information of wind power plant | |
| CN115600891A (en) | Big data analysis method and system applied to production monitoring of water-based acrylic resin | |
| CN113988325A (en) | Power system fault early warning method and device, terminal equipment and storage medium | |
| CN110232130B (en) | Metadata management pedigree generation method, apparatus, computer device and storage medium | |
| CN112148566A (en) | Monitoring method and device of computing engine, electronic equipment and storage medium | |
| CN112163012A (en) | Power grid line fault phase selection method and device, electronic equipment and storage medium | |
| CN112183827A (en) | Method, device, equipment and storage medium for predicting express monthly pickup quantity | |
| CN115062879B (en) | Method, device and equipment for acquiring index parameters of wind turbine generator | |
| CN116679139A (en) | Cable replacement monitoring system and method | |
| CN115760486A (en) | Method, device and equipment for estimating temporary construction scale and readable storage medium | |
| CN114987773A (en) | Method, device, equipment and medium for identifying performance abnormity of aircraft hydraulic system | |
| CN110968929A (en) | Wind power plant wind speed prediction method and device and electronic equipment | |
| CN115375039A (en) | Industrial equipment fault prediction method and device, electronic equipment and storage medium | |
| CN113343479A (en) | Method and device for calculating service life of equipment | |
| EP4071570A1 (en) | Prediction system, information processing device, and information processing program | |
| CN113065234A (en) | Batch reliability risk level assessment method and system for intelligent electric meters | |
| CN114996519B (en) | Data processing method, device, electronic equipment, storage medium and product | |
| CN115598309B (en) | Method and system for monitoring and early warning of lead content in atmospheric environment |
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 |