CN117585554A - Equipment inspection method and inspection system - Google Patents
Equipment inspection method and inspection system Download PDFInfo
- Publication number
- CN117585554A CN117585554A CN202410003436.XA CN202410003436A CN117585554A CN 117585554 A CN117585554 A CN 117585554A CN 202410003436 A CN202410003436 A CN 202410003436A CN 117585554 A CN117585554 A CN 117585554A
- Authority
- CN
- China
- Prior art keywords
- inspection
- target
- data
- inspection data
- calculating
- 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.)
- Granted
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 232
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000002159 abnormal effect Effects 0.000 claims abstract description 30
- 230000005856 abnormality Effects 0.000 claims description 54
- 238000010606 normalization Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 abstract description 6
- 238000012423 maintenance Methods 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 8
- 230000008859 change Effects 0.000 description 4
- 230000002596 correlated effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0018—Devices monitoring the operating condition of the elevator system
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0018—Devices monitoring the operating condition of the elevator system
- B66B5/0025—Devices monitoring the operating condition of the elevator system for maintenance or repair
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0018—Devices monitoring the operating condition of the elevator system
- B66B5/0031—Devices monitoring the operating condition of the elevator system for safety reasons
-
- 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
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Maintenance And Inspection Apparatuses For Elevators (AREA)
Abstract
The invention relates to the field of elevator equipment inspection, in particular to an equipment inspection method and an inspection system. The method comprises the steps of obtaining inspection data of elevator equipment; constructing an isolated forest for each dimension data of the target inspection data respectively, and calculating the target structural difference of the target inspection data according to the reference position of the target dimension data of the target inspection data in the corresponding isolated forest; calculating the confidence coefficient of the target structural difference, and acquiring an abnormal degree weight of the target inspection data according to the target structural difference and the confidence coefficient of the target inspection data; and carrying out weighted calculation on the abnormal score of each piece of inspection data according to the abnormal degree weight, updating the inspection period according to the calculation result, and generating and transmitting an updated inspection period signal. By the technical scheme, invalid inspection can be avoided, maintenance personnel can conveniently and correctly maintain the elevator, and safe operation of the elevator is ensured.
Description
Technical Field
The present invention relates generally to the field of elevator equipment inspection. More particularly, the invention relates to a device inspection method and an inspection system.
Background
Elevators are essential for their safe operation as indispensable vertical transport means for high-rise buildings and modern buildings. The traditional elevator inspection work mainly relies on manual periodic inspection, and the mode has the defects of fixed inspection period, low efficiency, incapability of finding hidden danger in time and the like, so that along with the development of technology, a system for adaptively calculating the inspection period through real-time detection of elevator equipment is needed.
Currently, various parameters are involved in elevator operation, such as speed, load, temperature, vibration, etc. Fluctuations within the normal range of these parameters reflect the normal operating conditions of the elevator, while abnormal fluctuations may be indicative of a potential failure or risk. Therefore, by monitoring these parameters in real time and performing anomaly analysis on these parameters, potential problems of the elevator can be effectively predicted and prevented.
In the prior art, for a traditional isolated forest, the weight of each data point in a plurality of isolated trees is the same, and in the process of detecting equipment, abnormal influence is caused on certain dimension data due to the influence of certain external factors, so that the abnormal degree of the data is increased, but the data point is pseudo abnormal data, namely the data point is a normal data point, and the data point is misjudged as the normal data point due to the influence of the external factors.
Disclosure of Invention
In order to solve one or more of the above technical problems, the present invention provides an equipment inspection method and an inspection system. To this end, the present invention provides solutions in various aspects as follows.
An equipment inspection method comprises the following steps: acquiring inspection data of elevator equipment in one day through a preset acquisition interval, wherein the inspection data comprises a plurality of dimension data; constructing an isolated forest for each dimension data of the target inspection data, wherein one dimension data corresponds to one isolated forest; acquiring a reference position of target dimension data of the target inspection data in a corresponding isolated forest, traversing all dimension data, and calculating a target structural difference of the target inspection data; constructing a window with a preset size, enabling the target inspection data to be located at the middle position of the window, and calculating the confidence coefficient of the target structural difference based on the target structural difference and the structural differences of other inspection data in the window; calculating an abnormality degree weight of the target inspection data based on the confidence coefficient and the target structural difference; acquiring the abnormality degree of the target inspection data according to the isolated forest, and acquiring the weighted abnormality degree of the target inspection data based on the abnormality degree and the abnormality degree weight; and calculating inspection cycle update parameters according to the weighted abnormal degree of all the inspection data in one day, generating and transmitting updated inspection cycle signals, and guiding the inspection work of the elevator equipment.
In one embodiment, the calculating the target structural differences of the target inspection data includes the steps of: the isolated forest comprises a target isolated tree and other isolated trees; acquiring the position of the target dimension data in the target isolated tree; calculating a distance between the location and a root node of the target orphan tree; traversing the other isolated trees, and calculating the average value of the distance of the target dimension data in each isolated tree as the reference position of the target dimension data in the isolated forest; traversing all dimension data of the target inspection data, calculating the variance of the reference position of each dimension data, and carrying out standard normalization on the variance; and taking the standard normalized variance as a target structural difference of the target inspection data.
In one embodiment, calculating the confidence of the target structural difference comprises the steps of: constructing a window with a preset size, and enabling the target inspection data to be located at the middle position of the window; calculating the confidence of the target structural difference based on the target structural difference and the structural differences of other inspection data in the window, wherein the confidence meets the relation:
wherein,indicate->Confidence of structural difference of individual inspection data, +.>Indicate->Structural differences of individual inspection data, +.>Indicate->Mean value of structural differences of all inspection data in window where individual inspection data are located, +.>Indicate->Total number of inspection data in window where each inspection data is located, < >>Indicate->The (th) in the window where the individual inspection data is located>Personal inspection data,/->Indicate->Structural differences in individual inspection data.
In one embodiment, the degree of abnormality weight satisfies the relationship:
wherein,indicate->Abnormality degree weight of individual inspection data, < ->Indicate->Confidence of structural difference of individual inspection data, +.>Indicate->Structural differences in individual inspection data.
In one embodiment, the step of obtaining the weighted abnormality degree of the target patrol data includes the steps of: obtaining abnormal scores of the target dimension data in the isolated forest of the target inspection data; traversing each dimension data, and calculating the mean value of the anomaly score of each dimension data as the anomaly degree of the target inspection data; calculating the abnormality degree of the target patrol data based on the abnormality degree and the abnormality degree weight, wherein the abnormality degree of the target patrol data satisfies a relation:
wherein,indicate->Degree of weighted abnormality of individual patrol data, +.>Indicate->Abnormality degree weight of individual inspection data, < ->Indicate->Degree of abnormality of each inspection data.
In one embodiment, the calculating the inspection cycle update parameter includes the steps of: acquiring inspection data in one day based on the preset acquisition interval; calculating the weighted abnormality degree of each inspection data; calculating an inspection period updating parameter through a preset parameter abnormal threshold value, wherein the inspection period updating parameter meets the relation:
wherein,update parameters representing the inspection cycle,/->Representing a preset parameter anomaly threshold value, +.>And the average value of the weighted abnormality degree of all the inspection data in one day is represented.
The invention has the following technical effects:
according to the constructed isolated forest, the abnormal degree weight of each inspection data is calculated according to the structural difference in the isolated forest divided by the same dimension characteristic data and the isolated forest divided by different dimension characteristic inspection data, the abnormal score of each inspection data is calculated according to the abnormal degree weight and the abnormal degree of each inspection data, and finally the inspection period of the elevator equipment is updated according to the abnormal score result, so that invalid inspection can be avoided, maintenance personnel can conveniently and correctly maintain the elevator, and safe operation of the elevator is ensured.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the invention are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
fig. 1 is a flowchart of a device inspection method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of an equipment inspection system according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. 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.
It should be understood that when the terms "first," "second," and the like are used in the claims, the specification and the drawings of the present invention, they are used merely for distinguishing between different objects and not for describing a particular sequential order. The terms "comprises" and "comprising" when used in the specification and claims of the present invention are taken to specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The invention provides a device inspection method. As shown in fig. 1, a method for inspecting equipment includes steps S1 to S4, which are described in detail below.
S1, acquiring inspection data of elevator equipment.
Specifically, in the process of inspecting elevator equipment, the inspection period needs to be updated according to the data change in the elevator operation process, the preset acquisition interval of elevator inspection data is usually required, the preset acquisition interval is set by a person skilled in the art according to a specific scene, and by way of example, the preset acquisition interval is set to be 2 seconds.
In one embodiment, the inspection data for the elevator installation includes, but is not limited to: operating parameters such as current, voltage, vibration frequency and the like of the elevator motor; the time of each door opening and closing process of the elevator, wherein the door opening and closing time refers to the time spent by the elevator door from the beginning of opening (closing) to the complete opening (closing); the instantaneous speed of the elevator going up and down. A physical quantity represents one dimension, and the number of dimensions is not limited in the present invention.
The specific acquisition method of the inspection data comprises the following steps: acquiring current of an elevator motor by using a current sensor, acquiring voltage of the elevator motor by using a voltage sensor, and acquiring vibration frequency of the elevator motor by using a vibration sensor; the open/close state of the door is detected by providing a door magnetic sensor inside the car door for every time the door is opened/closed of the elevator, thereby recording the open/close time of the door (the door magnetic sensor usually uses a magnetic element such as a magnetic spring or a magnet to sense the state of the door by detecting the change of the magnetic field of the door; the instantaneous speed of the elevator car while it is running is obtained by arranging a speed sensor above the elevator car.
S2, constructing an isolated forest for each dimension data of the target inspection data respectively, and calculating the target structural difference of the target inspection data according to the reference position of the target dimension data of the target inspection data in the corresponding isolated forest.
Specifically, when the data are monitored, if the elevator data at a certain moment are abnormal, the abnormal degree of each dimension data index at the moment is higher, so that an isolated tree needs to be constructed by utilizing an isolated forest algorithm according to each dimension data in the acquired inspection data.
It should be noted that, in the inspection data collected at any moment, if the data is normal, the node positions of the multidimensional data of the inspection data in the isolated forest corresponding to each dimension are low, otherwise if the data is abnormal, the node positions of the multidimensional data of the inspection data in the isolated forest corresponding to each dimension are high. When external factor interference occurs, data in certain dimensions are changed, the dimension data of the inspection data in the isolated forest is abnormal, the abnormality of the dimension data of the inspection data is caused by the interference of external environment factors, namely, the abnormality of the dimension data is only in a pseudo-abnormal state, and when the positions of the multi-dimension data of any one inspection data in the corresponding isolated forest are approximately the same, the possibility that the inspection data is pseudo-abnormal inspection data is lower; when the difference of the positions of the multidimensional data of any one inspection data in the corresponding isolated forest is large, the probability that the inspection data is pseudo-abnormal inspection data is large. It is therefore necessary to calculate structural differences of the inspection data in different isolated forests from the positions of the multidimensional data of the inspection data in different isolated forests.
In one embodiment, the inspection data of the elevator equipment in one day is obtained in one day unit according to the preset acquisition interval in step S1, each dimension data is constructed into an isolated forest, and for any one dimension data, by taking current as an example, all current data in one day are constructed into one isolated forest, wherein the isolated forest comprises a plurality of isolated trees, the number of the isolated trees is not limited, and the more the number of the isolated trees is, the more accurate the calculation result is. So that it is possible to provide the above-mentioned structure. The same dimension data in all the inspection data in one day corresponds to one isolated forest. According to the classification threshold value generated randomly by the isolated forest, the same dimension data in all the inspection data in one day is classified to obtain one isolated tree, and it is noted that multiple groups of classification threshold values can be generated simultaneously by the isolated forest, so that multiple isolated trees can be generated.
Constructing an isolated forest for the target dimension data, acquiring the position of the target dimension data in the target isolated tree, calculating the distance between the position and the root node of the target isolated tree, traversing other isolated trees, and calculating the average value of the distance of the target dimension data in each isolated tree as the reference position of the target dimension data in the isolated forest. Traversing all dimension data of all target inspection data, calculating the variance of the reference position of each dimension data, carrying out standard normalization on the variance, and taking the standard normalized variance as the target structural difference of the target inspection data.
And S3, calculating the confidence coefficient of the target structural difference, and acquiring the abnormality degree weight of the target inspection data according to the target structural difference and the confidence coefficient of the target inspection data.
In one embodiment, it should be noted that, for the inspection data of the elevator equipment collected at any time, there may be some changes in data of some dimensions due to the influence of external factors, for example, for the voltage and current data of the elevator motor, as the elevator continues to run, the temperature of the elevator motor gradually increases, the higher the temperature is, the smaller the resistance in the motor is, at this time, the current in the motor becomes larger, that is, the fluctuation of data of other dimensions in the data point is smaller, and the change of current data is larger, if in an isolated forest, the positions of data of other dimensions except for the "current" dimension in the corresponding isolated forest are closer, but for the "current" dimension data, the positions in the isolated forest are larger than the differences of the data of other dimensions of the data point, but the data point is only pseudo-abnormal data due to the influence of external factors, so that the degree weight of abnormality of each data point needs to be calculated according to the structural difference of the data point in each tree, that the degree of abnormality of each data point is corrected according to the structural difference of each data point in each isolated tree.
In one embodiment, a window of a preset size is constructed, which can be set by one skilled in the art according to the scene, and exemplary, the present invention sets the window size toNamely, 11 pieces of inspection data are included in the window, so that the target inspection data are positioned at the middle position of the window, namely, 5 pieces of inspection data exist before and after the 6 th position in the window, and the 11 pieces of inspection data are continuous inspection data acquired sequentially according to time at preset acquisition intervalsThe front part is marked before the target inspection data are acquired, and the rear part is marked after the target inspection data are acquired; if the number of inspection data in front of or behind the target inspection data is less than 5, at this time, the data is generally at the beginning of the data detection or at the moment when the data detection is about to end, that is, at the edge moment, the position of the target inspection data in the window is moved, so that the data in front of or behind the target inspection data is completely divided into the window, and for example, only 1 data in front of the target inspection data, the position of the target inspection data is 2, and 9 data in behind the target inspection data.
Calculating the confidence coefficient of the target structural difference based on the target structural difference and the structural differences of other inspection data in the window, wherein the confidence coefficient meets the relation:
wherein,indicate->Confidence of structural difference of individual inspection data, +.>Indicate->Structural differences of individual inspection data, +.>Indicate->Mean value of structural differences of all inspection data in window where individual inspection data are located, +.>Indicate->In the window where the inspection data are locatedTotal number of inspection data->Indicate->The (th) in the window where the individual inspection data is located>Personal inspection data,/->Indicate->Structural differences in individual inspection data. />Expressed as natural constant->An exponential function of the base.
The values of (1) are positively correlated with the differences between the target inspection data and other inspection data, the possibility that the target inspection data is pseudo-abnormal data, and the confidence level of the target structural difference is negatively correlated.
The structural difference and the possibility that the inspection data are pseudo-abnormal data are positively correlated, the confidence level and the possibility that the inspection data are pseudo-abnormal inspection data are negatively correlated, namely the higher the confidence level is, the higher the possibility that the inspection data with large structural difference are pseudo-abnormal data is, so that the inspection data with low confidence level and large structural difference are required to have low abnormality degree weight, thereby reducing the abnormality score of the inspection data and avoiding erroneous judgment.
Calculating an abnormality degree weight of the target inspection data based on the confidence coefficient and the target structural difference, wherein the abnormality degree weight satisfies a relation:
wherein,indicate->Abnormality degree weight of individual inspection data, < ->Indicate->Confidence of structural difference of individual inspection data, +.>Indicate->Structural differences in individual inspection data. />Representing a standard normalization function.
And S4, carrying out weighted calculation on the abnormal score of each inspection data according to the abnormal degree weight, updating the inspection period according to the calculation result, and generating and transmitting an updated inspection period signal.
In one embodiment, a weighted degree of anomaly of the target patrol data is obtained: obtaining an abnormal score of target dimension data of target inspection data in an isolated forest, wherein the abnormal score is obtained by utilizing the isolated forest as the prior art, which is not repeated herein; traversing each dimension data, and calculating the mean value of the anomaly scores of each dimension data as the anomaly degree of the target inspection data; calculating the abnormality degree of the target inspection data based on the abnormality degree and the abnormality degree weight, wherein the abnormality degree of the target inspection data satisfies the relation:
wherein,indicate->Degree of weighted abnormality of individual patrol data, +.>Indicate->Abnormality degree weight of individual inspection data, < ->Indicate->Degree of abnormality of each inspection data.
For abnormal inspection data, if the weighted abnormality degree of the continuous inspection data is higher, the state of the equipment is abnormal, and the inspection period needs to be shortened, namely the parameter of the inspection period is reduced.
Calculating the inspection cycle update parameters includes: acquiring inspection data in one day based on a preset acquisition interval; calculating the weighted abnormality degree of each inspection data; calculating an inspection period updating parameter through a preset parameter abnormal threshold value, wherein the inspection period updating parameter meets the relation:
wherein,update parameters representing the inspection cycle,/->Representing a preset parameter anomaly threshold value, +.>And the average value of the weighted abnormality degree of all the inspection data in one day is represented. />Representing a standard normalization function.
If it isThe inspection cycle parameter is smaller than 1, and the inspection cycle is shortened; if it isThe inspection period is unchanged; />And the inspection cycle parameter is larger than 1, and the inspection cycle is prolonged.
And obtaining inspection cycle updating parameters through calculation of the weighted abnormal degree of all inspection data in one day, wherein the inspection cycle updating parameters are used for updating a preset initial inspection cycle, and the preset initial inspection cycle is two hours. The initial inspection period is multiplied by the inspection period updating parameter and is rounded upwards, so that the updated inspection period parameter can be obtained, and the updated inspection period is used as the inspection period of the next day in the future.
The embodiment of the invention also discloses a device inspection system, referring to fig. 2, comprising a processor and a memory, wherein the memory stores computer program instructions, and the computer program instructions realize a device inspection method according to the invention when being executed by the processor.
The above system further comprises other components well known to those skilled in the art, such as a communication bus and a communication interface, the arrangement and function of which are known in the art and therefore are not described in detail herein.
In the context of this patent, the foregoing memory may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, the computer readable storage medium may be any suitable magnetic or magneto-optical storage medium, such as, for example, resistance change Memory RRAM (Resistive Random Access Memory), dynamic Random Access Memory DRAM (Dynamic Random Access Memory), static Random Access Memory SRAM (Static Random-Access Memory), enhanced dynamic Random Access Memory EDRAM (Enhanced Dynamic Random Access Memory), high-Bandwidth Memory HBM (High-Bandwidth Memory), hybrid storage cube HMC (Hybrid Memory Cube), etc., or any other medium that may be used to store the desired information and that may be accessed by an application, a module, or both. Any such computer storage media may be part of, or accessible by, or connectable to, the device.
While various embodiments of the present invention have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Many modifications, changes, and substitutions will now occur to those skilled in the art without departing from the spirit and scope of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in practicing the invention.
The above embodiments are not intended to limit the scope of the present invention, so: all equivalent changes in structure, shape and principle of the invention should be covered in the scope of protection of the invention.
Claims (7)
1. The equipment inspection method is characterized by comprising the following steps of:
acquiring inspection data of elevator equipment in one day through a preset acquisition interval, wherein the inspection data comprises a plurality of dimension data;
constructing an isolated forest for each dimension data of the target inspection data, wherein one dimension data corresponds to one isolated forest;
acquiring a reference position of target dimension data of the target inspection data in a corresponding isolated forest, traversing all dimension data, and calculating a target structural difference of the target inspection data;
constructing a window with a preset size, enabling the target inspection data to be located at the middle position of the window, and calculating the confidence coefficient of the target structural difference based on the target structural difference and the structural differences of other inspection data in the window;
calculating an abnormality degree weight of the target inspection data based on the confidence coefficient and the target structural difference;
acquiring the abnormality degree of the target inspection data according to the isolated forest, and acquiring the weighted abnormality degree of the target inspection data based on the abnormality degree and the abnormality degree weight;
and calculating inspection cycle update parameters according to the weighted abnormal degree of all the inspection data in one day, generating and transmitting updated inspection cycle signals, and guiding the inspection work of the elevator equipment.
2. The method of claim 1, wherein calculating the target structural difference of the target inspection data comprises:
the isolated forest comprises a target isolated tree and other isolated trees;
acquiring the position of the target dimension data in the target isolated tree;
calculating a distance between the location and a root node of the target orphan tree;
traversing the other isolated trees, and calculating the average value of the distance of the target dimension data in each isolated tree as the reference position of the target dimension data in the isolated forest;
traversing all dimension data of the target inspection data, calculating the variance of the reference position of each dimension data, and carrying out standard normalization on the variance;
and taking the standard normalized variance as a target structural difference of the target inspection data.
3. The method of equipment inspection according to claim 1, wherein calculating the confidence level of the target structural difference comprises the steps of:
constructing a window with a preset size, and enabling the target inspection data to be located at the middle position of the window;
calculating the confidence of the target structural difference based on the target structural difference and the structural differences of other inspection data in the window, wherein the confidence meets the relation:
wherein,indicate->Confidence of structural difference of individual inspection data, +.>Indicate->Structural differences of individual inspection data, +.>Indicate->Mean value of structural differences of all inspection data in window where individual inspection data are located, +.>Indicate->Total number of inspection data in window where each inspection data is located, < >>Indicate->Window with inspection dataFirst->Personal inspection data,/->Indicate->Structural differences in individual inspection data.
4. The equipment inspection method according to claim 1, wherein the abnormality degree weight satisfies the relation:
wherein,indicate->Abnormality degree weight of individual inspection data, < ->Indicate->Confidence of structural difference of individual inspection data, +.>Indicate->Structural differences in individual inspection data.
5. The equipment inspection method according to claim 1, wherein obtaining the weighted abnormality degree of the target inspection data comprises the steps of:
obtaining abnormal scores of the target dimension data in the isolated forest of the target inspection data;
traversing each dimension data, and calculating the mean value of the anomaly score of each dimension data as the anomaly degree of the target inspection data;
calculating the abnormality degree of the target patrol data based on the abnormality degree and the abnormality degree weight, wherein the abnormality degree of the target patrol data satisfies a relation:
wherein,indicate->Degree of weighted abnormality of individual patrol data, +.>Indicate->The abnormality degree weight of each inspection data,indicate->Degree of abnormality of each inspection data.
6. The method for inspecting equipment according to claim 1, wherein the step of calculating inspection cycle update parameters includes the steps of:
acquiring inspection data in one day based on the preset acquisition interval;
calculating the weighted abnormality degree of each inspection data;
calculating an inspection period updating parameter through a preset parameter abnormal threshold value, wherein the inspection period updating parameter meets the relation:
wherein,update parameters representing the inspection cycle,/->Representing a preset parameter anomaly threshold value, +.>And the average value of the weighted abnormality degree of all the inspection data in one day is represented.
7. A device inspection system, comprising:
a processor; and a memory storing computer instructions for a device inspection method, which when executed by the processor, cause the device to perform a device inspection method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410003436.XA CN117585554B (en) | 2024-01-02 | 2024-01-02 | Equipment inspection method and inspection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410003436.XA CN117585554B (en) | 2024-01-02 | 2024-01-02 | Equipment inspection method and inspection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117585554A true CN117585554A (en) | 2024-02-23 |
| CN117585554B CN117585554B (en) | 2024-05-24 |
Family
ID=89918547
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410003436.XA Active CN117585554B (en) | 2024-01-02 | 2024-01-02 | Equipment inspection method and inspection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117585554B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118200950A (en) * | 2024-05-17 | 2024-06-14 | 武汉众诚华鑫科技有限公司 | Method and system for inspecting telecommunication base station |
| CN118628161A (en) * | 2024-08-12 | 2024-09-10 | 浪潮智慧供应链科技(山东)有限公司 | Supply chain demand prediction method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113420073A (en) * | 2021-08-23 | 2021-09-21 | 平安科技（深圳）有限公司 | Abnormal sample detection method based on improved isolated forest and related equipment |
| CN113762350A (en) * | 2021-08-12 | 2021-12-07 | 南京星云数字技术有限公司 | Abnormal data detection method and device, computer equipment and storage medium |
| US20220291654A1 (en) * | 2021-03-11 | 2022-09-15 | Harbin Engineering University | Online monitoring method of nuclear power plant system based on isolation forest method and sliding window method |
-
2024
- 2024-01-02 CN CN202410003436.XA patent/CN117585554B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220291654A1 (en) * | 2021-03-11 | 2022-09-15 | Harbin Engineering University | Online monitoring method of nuclear power plant system based on isolation forest method and sliding window method |
| CN113762350A (en) * | 2021-08-12 | 2021-12-07 | 南京星云数字技术有限公司 | Abnormal data detection method and device, computer equipment and storage medium |
| CA3170154A1 (en) * | 2021-08-12 | 2023-02-12 | 10353744 Canada Ltd. | Anomalous data detecting method, device, computer equipment, and storage medium |
| CN113420073A (en) * | 2021-08-23 | 2021-09-21 | 平安科技（深圳）有限公司 | Abnormal sample detection method based on improved isolated forest and related equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118200950A (en) * | 2024-05-17 | 2024-06-14 | 武汉众诚华鑫科技有限公司 | Method and system for inspecting telecommunication base station |
| CN118628161A (en) * | 2024-08-12 | 2024-09-10 | 浪潮智慧供应链科技(山东)有限公司 | Supply chain demand prediction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117585554B (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117585554B (en) | Equipment inspection method and inspection system | |
| JP6871877B2 (en) | Information processing equipment, information processing methods and computer programs | |
| CN110188015B (en) | Host access relation abnormal behavior self-adaptive detection device and monitoring method thereof | |
| CN117992895B (en) | Oil and gas pipeline area risk monitoring method and system based on big data | |
| CN112232495A (en) | Prediction model training method, device, medium and computing equipment | |
| CN117807550B (en) | Intelligent quantitative detection method and system for building fire-fighting facilities | |
| CN116756493A (en) | Data management method for security and fire control finger collecting platform | |
| CN116956197B (en) | Deep learning-based energy facility fault prediction method and device and electronic equipment | |
| CN117906376B (en) | Method and system for monitoring carbon emission of rotary kiln | |
| CN118330408A (en) | Intelligent cable life prediction method and system based on data analysis | |
| CN118311429B (en) | Generator fault detection method and device based on power plant | |
| CN111476965B (en) | Method for constructing fire detection model, fire detection method and related equipment | |
| CN118133059B (en) | Intelligent security risk detection method and system based on digital twinning | |
| CN117970858B (en) | Medical equipment monitoring method and system based on Internet of things | |
| CN115719294A (en) | Indoor pedestrian flow evacuation control method and system, electronic device and medium | |
| Xu et al. | An improved LOF outlier detection algorithm | |
| CN117909930A (en) | Compressor stall prediction method, device, equipment and medium based on LSTM neural network | |
| CN117346079A (en) | Gas leakage concentration monitoring and early warning method and system | |
| CN116028930A (en) | Defense detection method and system for energy data in Internet of things | |
| CN114046816B (en) | Sensor signal fault diagnosis method based on lightweight gradient lifting decision tree | |
| CN115830516A (en) | Computer neural network image processing method for battery detonation detection | |
| CN117873838B (en) | Method and system for monitoring ambient temperature of telecommunication equipment | |
| CN118585012B (en) | Cold chain warehouse temperature monitoring method and system | |
| CN118503886B (en) | Method and system for predicting fault state of power information processing equipment | |
| CN118523963B (en) | Power information network security risk assessment method and system |
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 |