CN113762347B - Sliding door body health degree assessment method and device - Google Patents
Sliding door body health degree assessment method and device Download PDFInfo
- Publication number
- CN113762347B CN113762347B CN202110904179.3A CN202110904179A CN113762347B CN 113762347 B CN113762347 B CN 113762347B CN 202110904179 A CN202110904179 A CN 202110904179A CN 113762347 B CN113762347 B CN 113762347B
- Authority
- CN
- China
- Prior art keywords
- door body
- time
- displacement curve
- sliding
- training
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application discloses a sliding door body health degree assessment method and device. According to the technical scheme provided by the embodiment of the application, the time-displacement curve sample of the sliding of the door body is obtained; labeling the obtained time-displacement curve sample through a statistical learning model to obtain a corresponding time-displacement curve label sample; constructing state characteristics according to the time-displacement curve label sample, and inputting the state characteristics into a logistic regression model for training to obtain a door body health degree evaluation model; and inputting a corresponding time-displacement curve of the sliding door body of the sliding door to be tested when the sliding door body slides into the door body health degree evaluation model to evaluate the door body health degree. According to the technical scheme provided by the embodiment of the application, the problem of inaccurate evaluation of the health degree of the sliding door body can be solved, and the evaluation accuracy of the health degree of the sliding door body is improved.
Description
Technical Field
The embodiment of the application relates to the technical field of subway shielding door systems, in particular to a sliding door body health degree assessment method and device.
Background
The subway shielding door system is a safety device applied to urban rail transit, and is equipment arranged on the edge of a station platform to separate the area of the station platform from the train movement area. With the rapid development of urban rail transit in China in recent years, the safety problem of passengers riding is always the primary focus in all subway construction. The reliability and safety of the subway shielding door, which is an important subsystem directly related to the safety of passengers, are naturally one of the important concerns of subway operation departments.
The sliding door in the shielding door system is used as a key channel for isolating and communicating trains and platforms, and whether the sliding door can normally operate is not only related to subway operation efficiency but also related to passenger safety. In the actual operation process, factors influencing the normal operation of the sliding door are very complicated, such as the roller of the sliding door travelling trolley is damaged, the guide shoe of the sliding door is damaged, the sliding door travelling trolley is scratched with a track, the toothed belt is excessively loose and excessively tight, and the sliding door is excessively small in clearance between the sliding door and the ground sill, the upright post, the lintel and the like caused by the extrusion of passengers, which are common causes of the sliding door faults. When the sliding door is degraded to a certain extent, if the sliding door cannot be found and excluded in time, the sliding door has a great influence on the safety operation of the subway, and even accidents endangering the personal safety of passengers can occur. Therefore, how to evaluate the health status of the sliding door of the shielding door has very important significance for the safe operation of the subway.
The current door health assessment method can be mainly divided into two types of unsupervised learning and supervised learning. In the unsupervised learning portal health assessment method, a baseline standard is established based on historical normal data, and then a measurement model or rule is established to describe the difference between the existing data and the baseline standard so as to carry out health assessment; this method depends on whether an actual fault has occurred or not, and the fault data is very small relative to the fault-free data in the actual scenario, in which case the baseline criteria are not objectively accurate. In the supervised learning method, firstly, marking is carried out through manual rules to distinguish positive and negative samples of historical data, and then, a logistic regression model is input to carry out health assessment. The sliding door health assessment method by labeling with manual rules relies on the experience level of engineers, and thus the assessment results are not objectively accurate.
Disclosure of Invention
The embodiment of the application provides a sliding door body health degree assessment method and device, which can solve the problem of inaccurate sliding door body health degree assessment and improve the sliding door body health degree assessment accuracy.
In a first aspect, an embodiment of the present application provides a sliding door body health assessment method, including:
acquiring a time-displacement curve sample of sliding of a door body;
labeling the obtained time-displacement curve sample through a statistical learning model to obtain a corresponding time-displacement curve label sample;
constructing state characteristics according to the time-displacement curve label sample, and inputting the state characteristics into a logistic regression model for training to obtain a door body health degree evaluation model;
and inputting a corresponding time-displacement curve of the sliding door body of the sliding door to be tested when the sliding door body slides into the door body health degree evaluation model to evaluate the door body health degree.
Further, the statistical learning model is a 3 sigma statistical learning model;
correspondingly, the obtained time-displacement curve sample is labeled through a statistical learning model to obtain a corresponding time-displacement curve label sample, which is specifically:
and marking the positive and negative labels of the obtained time-displacement curve samples through a 3 sigma statistical learning model to obtain corresponding time-displacement curve positive and negative label samples, wherein the time-displacement curve positive label samples correspond to healthy door body time-displacement curve samples, and the time-displacement curve negative label samples correspond to sub-healthy door body time-displacement curve samples.
Further, the positive and negative label marking is performed on the obtained time-displacement curve sample through the 3 sigma statistical learning model, specifically:
calculating an average value u and a standard deviation sigma of the total door opening time or the total door closing time of a door body in a time-displacement curve sample;
marking a curve of the total door opening time or the total door closing time of the door body within the range of [ u-3 sigma, u+3 sigma ] as a healthy door body time-displacement curve, and marking a sample label as positive;
the curve of the total door opening time or the total door closing time of the door body, which is not in the range of [ u-3 sigma, u+3 sigma ] is marked as a sub-health door body time-displacement curve, and the sample label is marked as negative.
Further, the status feature is a time interval for the door body to slide to a plurality of preset positions;
correspondingly, the method comprises the steps of constructing state characteristics according to the time-displacement curve label sample, inputting the state characteristics into a logistic regression model for training to obtain a door body health evaluation model, wherein the method comprises the following specific steps:
inputting the state characteristics into a logistic regression model for training, and determining the value of training parameters according to training results;
and determining a door body health degree evaluation model according to the value of the training parameter.
Further, the logistic regression model isWherein x is the time interval between the sliding of the door body to a plurality of preset positions, x= (t) 1 ,t 2 ,...,t n ) Omega is training parameter, omega= (omega) 1 ,ω 2 ,...,ω n ) B is a constant value, y is the curve health degree, and the value range is [0,1]The unhealthy curve y value is denoted 0 and the healthy curve y value is denoted 1.
Further, the training is performed by inputting the state characteristics into a logistic regression model to obtain a door body health evaluation model, which specifically comprises:
state feature x= (t) 1 ,t 2 ,...,t n ) Inputting the training parameters into a logistic regression model for training, and determining the value of the training parameters omega according to the training results;
substituting the value of the training parameter omega into a logistic regression model to obtain a door body health degree evaluation model.
Further, the time-displacement curve corresponding to the sliding door body of the sliding door to be tested during sliding is input into the door body health evaluation model to evaluate the door body health, specifically:
and inputting the state characteristics of the corresponding door body time-displacement curve when the door body of the sliding door to be tested slides into the door body health evaluation model, and outputting the health degree of the corresponding curve to evaluate the door body health degree.
In a second aspect, an embodiment of the present application provides a sliding door body health assessment device, including:
the sample acquisition module is used for acquiring a time-displacement curve sample of sliding of the door body;
the statistical learning module is used for marking the obtained time-displacement curve sample through a statistical learning model to obtain a corresponding time-displacement curve label sample;
the training module is used for constructing state characteristics according to the time-displacement curve label sample, inputting the state characteristics into a logistic regression model for training, and obtaining a door body health degree assessment model;
and the evaluation module is used for inputting a time-displacement curve corresponding to the sliding of the door body of the sliding door to be tested into the door body health evaluation model to evaluate the door body health.
In a third aspect, an embodiment of the present application provides an electronic device, including:
a memory and one or more processors;
the memory is used for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the sliding door body health assessment method as described in the first aspect.
In a fourth aspect, embodiments of the present application provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are for performing the sliding door body health assessment method of the first aspect.
According to the method, the curve sample is labeled through the statistical learning model, the label sample is trained through the logistic regression model to obtain the door body health degree assessment model, and the door body sliding curve to be detected is subjected to health degree assessment according to the door body health degree assessment model. By adopting the technical means, the sample data can be labeled through the statistical learning model, so that the problem that the manual label labeling is inefficient and subjective can be avoided, and the working efficiency and objectivity of the sample label labeling are improved. In addition, the door body health degree evaluation model obtained by training the label sample through the logistic regression model carries out health degree evaluation on the door body curve to be detected, so that the corresponding health degree value can be directly output, and the accuracy and the visual effect of the sliding door body health degree evaluation are improved.
Drawings
Fig. 1 is a flowchart of a sliding door body health evaluation method according to an embodiment of the present application;
FIG. 2 is a diagram illustrating an exemplary process for obtaining a door health assessment model according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a door time-displacement curve according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a sliding door body health evaluation device according to a second embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the following detailed description of specific embodiments thereof is given with reference to the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the application and not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the matters related to the present application are shown in the accompanying drawings. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently, or at the same time. Furthermore, the order of the operations may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figures. The processes may correspond to methods, functions, procedures, subroutines, and the like.
The sliding door body health evaluation method and device provided by the application aim to label sample data through a statistical learning model, so that the problem that manual label labeling is inefficient and subjective can be avoided, and the working efficiency and objectivity of sample label labeling are improved. In addition, the door body health degree evaluation model obtained by training the label sample through the logistic regression model carries out health degree evaluation on the door body curve to be detected, so that the corresponding health degree value can be directly output, and the accuracy and the visual effect of the sliding door body health degree evaluation are improved. Compared with the traditional sliding door health degree assessment mode, the method is generally carried out on the basis of data with frequent faults, is not suitable for the situation that the fault data are relatively few in actual scenes, and is usually carried out through marking by manual rules when the health degree assessment is carried out by using a supervised learning method, and the method depends on the experience level of engineers, so that the final assessment result is not objective and accurate and is low in efficiency. Based on the above, the sliding door body health degree evaluation method is provided, so that the problems of accuracy and applicability in the existing sliding door body health degree evaluation process are solved.
Embodiment one:
fig. 1 is a flowchart of a sliding door body health assessment method according to an embodiment of the present application, where the sliding door body health assessment method provided in the embodiment may be implemented by a sliding door body health assessment device, and the sliding door body health assessment device may be implemented by software and/or hardware, and the sliding door body health assessment device may be configured by two or more physical entities or may be configured by one physical entity.
Referring to fig. 1 and 2, the sliding door body health evaluation method specifically includes:
s101, acquiring a time-displacement curve sample of sliding of the door body.
Specifically, referring to the a diagram in fig. 2, time and displacement data during the door opening and closing process of a plurality of sliding door bodies are detected through a sensor, and data processing is performed on the obtained time and displacement data to obtain corresponding door body sliding time-displacement curve samples. Based on the subsequent need for machine learning training, the obtained door sliding time-displacement curve samples should be as much as possible, and the training results will be more accurate.
S102, labeling the obtained time-displacement curve sample through a statistical learning model to obtain a corresponding time-displacement curve label sample.
The statistical learning model is various, and specifically can be a 3 sigma statistical learning model; correspondingly, the obtained time-displacement curve sample is labeled through a statistical learning model to obtain a corresponding time-displacement curve label sample, which is specifically: and marking the positive and negative labels of the obtained time-displacement curve samples through a 3 sigma statistical learning model to obtain corresponding time-displacement curve positive and negative label samples, wherein the time-displacement curve positive label samples correspond to healthy door body time-displacement curve samples, and the time-displacement curve negative label samples correspond to sub-healthy door body time-displacement curve samples.
Further, referring to the b graph in fig. 2, the positive and negative labels of the obtained time-displacement curve samples are labeled by using a 3 sigma statistical learning model, specifically: calculating an average value u and a standard deviation sigma of the total door opening time or the total door closing time of a door body in a time-displacement curve sample; marking a curve of the total door opening time or the total door closing time of the door body within the range of [ u-3 sigma, u+3 sigma ] as a healthy door body time-displacement curve, and marking a sample label as positive; the curve of the total door opening time or the total door closing time of the door body, which is not in the range of [ u-3 sigma, u+3 sigma ] is marked as a sub-health door body time-displacement curve, and the sample label is marked as negative.
By way of example, by acquiring a time-displacement curve of sliding a door body of a sliding door for a plurality of times, counting the time for each curve to finish a door opening or door closing process, calculating the total time for a time-displacement curve sample to finish a door opening or door closing process, and calculating the average value u and the standard deviation sigma of the total time for the door body to open or close in the corresponding time-displacement curve sample according to the total time. Assuming that a sliding door of a subway opens and closes 1 ten thousand times, a time-displacement curve of the sliding door sliding for 1 ten thousand times is obtained, and an average value u and a standard deviation sigma of the sliding time for 1 ten thousand times are calculated. Comparing each time of opening and closing the door for 1 ten thousand times with [ u-3 sigma, u+3 sigma ] according to the average value u and standard deviation sigma of the calculated time, marking a curve of the total door opening time or the total door closing time within the range of [ u-3 sigma, u+3 sigma ] as a healthy door body time-displacement curve, marking a sample label as positive, and taking the label as 1; and marking a curve of which the total door opening time or total door closing time is not in the range of [ u-3 sigma, u+3 sigma ] as a sub-health door body time-displacement curve, marking a sample label as negative, and taking the label as 0.
S103, constructing state features according to the time-displacement curve label samples, and inputting the state features into a logistic regression model for training to obtain a door body health degree assessment model.
Specifically, referring to the c diagram in fig. 2, the state features are time intervals in which the door body slides to a plurality of preset positions; correspondingly, the method comprises the steps of constructing state characteristics according to the time-displacement curve label sample, inputting the state characteristics into a logistic regression model for training to obtain a door body health evaluation model, wherein the method comprises the following specific steps: inputting the state characteristics into a logistic regression model for training, and determining the value of training parameters according to training results; and determining a door body health degree evaluation model according to the value of the training parameter.
Further, the logistic regression model isWherein x is the time interval between the sliding of the door body to a plurality of preset positions, x= (t) 1 ,t 2 ,...,t n ) Omega is training parameter, omega= (omega) 1 ,ω 2 ,...,ω n ) B is a constant value, y is the curve health degree, and the value range is [0 ],1]The unhealthy curve y value is represented as 0, the healthy curve y value is represented as 1, the sub-healthy curve y is represented as (0, 1), the curve health degree is represented as 0 when the y value is represented as 0, the curve health degree is represented as 100% when the y value is represented as 1, and the higher the value is, the higher the curve health degree is when the y value is between 0 and 1.
Further, the state feature x= (t 1 ,t 2 ,...,t n ) Inputting the training parameters into a logistic regression model for training, and determining the value of the training parameters omega according to the training results; substituting the value of the training parameter omega into a logistic regression model to obtain a door body health degree evaluation model.
Exemplary, referring to FIG. 3, n sliding door sliding displacement designated positions are preset, 5 displacement positions are preset, and the time spent by the door sliding to the designated positions is calculated to obtain corresponding time intervals t 1 -t 5 The time-consuming variable x= (t 1 ,t 2 ,t 3 ,t 4 ,t 5 ) And inputting the logic regression model to train to obtain a door body health degree evaluation model, wherein the value range is from 0 to 1.
For example, assuming that the door body needs to slide by 1 meter when opening the door, n sliding door sliding displacement designated positions are preset, and n=5 is assumed, that is, 5 sliding door sliding displacement designated positions are preset, wherein the designated positions are respectively 0.2 meter, 0.4 meter, 0.6 meter, 0.8 meter and 1 meter positions. Recording the time intervals of sliding the door body to the positions of 0.2 meter, 0.4 meter, 0.6 meter, 0.8 meter and 1 meter respectively, namely t when sliding from 0 meter to 0.2 meter 1 T when sliding from 0.2 meter to 0.4 meter 2 T when sliding from 0.4 meter to 0.6 meter 3 T when sliding from 0.6 meter to 0.8 meter 4 T when sliding from 0.8 meter to 1 meter 5 ，t 1 -t 5 Constituent state characteristics x= (t) 1 ,t 2 ,t 3 ,t 4 ,t 5 ). State feature x= (t) 1 ,t 2 ,t 3 ,t 4 ,t 5 ) Inputting the training in the logistic regression model to obtain the door body health degree evaluation modelIn which the training parameter omega is known as trueAnd outputting a curve health degree y value by a fixed value, wherein the y value ranges from 0 to 1.
S104, inputting a corresponding time-displacement curve of the sliding door body of the sliding door to be tested when the sliding door body slides into the door body health degree evaluation model to evaluate the door body health degree.
Specifically, the state characteristics of the corresponding door body time-displacement curve when the door body of the sliding door to be tested slides are input into the door body health evaluation model, and the corresponding curve health degree is output so as to evaluate the door body health degree.
Further, the state characteristics of the corresponding door body time-displacement curve when the door body of the sliding door to be detected slides are input into the door body health assessment model, the corresponding curve health degree is output, the health degree range is between 0 and 1, the specific health degree value of the corresponding curve can be output, the curve health degree is better depicted, the granularity of the door body health degree assessment result display is reduced, and the door body health degree assessment result is more refined.
And carrying out label marking on the curve sample through the statistical learning model, training the label sample through the logistic regression model to obtain a door body health degree evaluation model, and carrying out health degree evaluation on the door body sliding curve to be detected according to the door body health degree evaluation model. By adopting the technical means, the sample data can be labeled through the statistical learning model, so that the problem that the manual label labeling is inefficient and subjective can be avoided, and the working efficiency and objectivity of the sample label labeling are improved. In addition, the door body health degree evaluation model obtained by training the label sample through the logistic regression model carries out health degree evaluation on the door body curve to be detected, so that the corresponding health degree value can be directly output, and the accuracy and the visual effect of the sliding door body health degree evaluation are improved.
Embodiment two:
based on the above embodiments, fig. 4 is a schematic structural diagram of a sliding door body health evaluation device according to a second embodiment of the present application. Referring to fig. 4, the sliding door body health evaluation device provided in this embodiment specifically includes: a sample acquisition module 21, a statistical learning module 22, a training module 23 and an evaluation module 24.
The sample acquiring module 21 is configured to acquire a time-displacement curve sample of sliding of the door body;
the statistical learning module 22 is configured to label the obtained time-displacement curve sample by using a statistical learning model to obtain a corresponding time-displacement curve label sample;
the training module 23 is configured to construct a state feature according to the time-displacement curve label sample, and input the state feature into a logistic regression model for training to obtain a door body health evaluation model;
and the evaluation module 24 is used for inputting a time-displacement curve corresponding to the sliding of the door body of the sliding door to be tested into the door body health evaluation model to evaluate the door body health.
And carrying out label marking on the curve sample through the statistical learning model, training the label sample through the logistic regression model to obtain a door body health degree evaluation model, and carrying out health degree evaluation on the door body sliding curve to be detected according to the door body health degree evaluation model. By adopting the technical means, the sample data can be labeled through the statistical learning model, so that the problem that the manual label labeling is inefficient and subjective can be avoided, and the working efficiency and objectivity of the sample label labeling are improved. In addition, the door body health degree evaluation model obtained by training the label sample through the logistic regression model carries out health degree evaluation on the door body curve to be detected, so that the corresponding health degree value can be directly output, and the accuracy and the visual effect of the sliding door body health degree evaluation are improved.
The sliding door body health degree evaluation device provided in the second embodiment of the present application may be used to execute the sliding door body health degree evaluation method provided in the first embodiment, and has corresponding functions and beneficial effects.
Embodiment III:
an electronic device according to a third embodiment of the present application, referring to fig. 5, includes: processor 31, memory 32, communication module 33, input device 34 and output device 35. The number of processors in the electronic device may be one or more and the number of memories in the electronic device may be one or more. The processor, memory, communication module, input device, and output device of the electronic device may be connected by a bus or other means.
The memory 32 is used as a computer readable storage medium for storing software programs, computer executable programs and modules, such as program instructions/modules corresponding to the sliding door health assessment method according to any embodiment of the present application (e.g., a sample acquisition module, a statistical learning module, a training module and an assessment module in the sliding door health assessment device). The memory may mainly include a memory program area and a memory data area, wherein the memory program area may store an operating system, at least one application program required for a function; the storage data area may store data created according to the use of the device, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, the memory may further include memory remotely located with respect to the processor, the remote memory being connectable to the device through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The communication module 33 is used for data transmission.
The processor 31 executes various functional applications of the apparatus and data processing by running software programs, instructions and modules stored in the memory, i.e., implements the sliding door body health assessment method described above.
The input means 34 may be used to receive entered numeric or character information and to generate key signal inputs related to user settings and function control of the device. The output means 35 may comprise a display device such as a display screen.
The electronic device provided by the above-mentioned embodiment can be used for executing the sliding door body health degree evaluation method provided by the above-mentioned embodiment, and has corresponding functions and beneficial effects.
Embodiment four:
the present embodiments also provide a storage medium containing computer executable instructions, which when executed by a computer processor, are for performing a sliding door body health assessment method comprising: acquiring a time-displacement curve sample of sliding of a door body; labeling the obtained time-displacement curve sample through a statistical learning model to obtain a corresponding time-displacement curve label sample; constructing state characteristics according to the time-displacement curve label sample, and inputting the state characteristics into a logistic regression model for training to obtain a door body health degree evaluation model; and inputting a corresponding time-displacement curve of the sliding door body of the sliding door to be tested when the sliding door body slides into the door body health degree evaluation model to evaluate the door body health degree.
Storage media-any of various types of memory devices or storage devices. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk or tape devices; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, lanbas (Rambus) RAM, etc.; nonvolatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in a first computer system in which the program is executed, or may be located in a second, different computer system connected to the first computer system through a network such as the internet. The second computer system may provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations (e.g., in different computer systems connected by a network). The storage medium may store program instructions (e.g., embodied as a computer program) executable by one or more processors.
Of course, the storage medium containing the computer executable instructions provided in the embodiments of the present application is not limited to the sliding door body health assessment method described above, and may also perform the relevant operations in the sliding door body health assessment method provided in any embodiment of the present application.
The sliding door body health degree evaluation device, the storage medium and the electronic device provided in the above embodiments may execute the sliding door body health degree evaluation method provided in any embodiment of the present application, and technical details not described in detail in the above embodiments may be referred to the sliding door body health degree evaluation method provided in any embodiment of the present application.
The foregoing description is only of the preferred embodiments of the present application and the technical principles employed. The present application is not limited to the specific embodiments described herein, but is capable of numerous obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the present application. Therefore, while the present application has been described in connection with the above embodiments, the present application is not limited to the above embodiments, but may include many other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the claims.
Claims (9)
1. A sliding door body health assessment method, comprising:
acquiring a time-displacement curve sample of sliding of a door body;
labeling the obtained time-displacement curve sample through a statistical learning model to obtain a corresponding time-displacement curve label sample;
constructing state characteristics according to the time-displacement curve label sample, and inputting the state characteristics into a logistic regression model for training to obtain a door body health degree evaluation model;
inputting a corresponding time-displacement curve of a door body of the sliding door to be tested when the door body slides into the door body health evaluation model to evaluate the door body health;
the state features are the time intervals of the door body sliding to a plurality of preset positions;
correspondingly, the method comprises the steps of constructing state characteristics according to the time-displacement curve label sample, inputting the state characteristics into a logistic regression model for training to obtain a door body health evaluation model, wherein the method comprises the following specific steps:
inputting the state characteristics into a logistic regression model for training, and determining the value of training parameters according to training results;
and determining a door body health degree evaluation model according to the value of the training parameter.
2. The sliding door body health assessment method according to claim 1, wherein the statistical learning model is a 3σ statistical learning model;
correspondingly, the obtained time-displacement curve sample is labeled through a statistical learning model to obtain a corresponding time-displacement curve label sample, which is specifically:
and marking the positive and negative labels of the obtained time-displacement curve samples through a 3 sigma statistical learning model to obtain corresponding time-displacement curve positive and negative label samples, wherein the time-displacement curve positive label samples correspond to healthy door body time-displacement curve samples, and the time-displacement curve negative label samples correspond to sub-healthy door body time-displacement curve samples.
3. The sliding door body health evaluation method according to claim 2, wherein the positive and negative labels of the obtained time-displacement curve samples are marked by a 3 sigma statistical learning model, specifically:
calculating an average value u and a standard deviation sigma of the total door opening time or the total door closing time of a door body in a time-displacement curve sample;
marking a curve of the total door opening time or the total door closing time of the door body within the range of [ u-3 sigma, u+3 sigma ] as a healthy door body time-displacement curve, and marking a sample label as positive;
the curve of the total door opening time or the total door closing time of the door body, which is not in the range of [ u-3 sigma, u+3 sigma ] is marked as a sub-health door body time-displacement curve, and the sample label is marked as negative.
4. According to claim 1The sliding door body health degree assessment method is characterized in that the logistic regression model is thatWherein x is the time interval between the sliding of the door body to a plurality of preset positions, x= (t) 1 ,t 2 ,...,t n ) Omega is training parameter, omega= (omega) 1 ,ω 2 ,...,ω n ) B is a constant value, y is the curve health degree, and the value range is [0,1]The unhealthy curve y value is denoted 0 and the healthy curve y value is denoted 1.
5. The sliding door body health assessment method according to claim 4, wherein the training is performed by inputting the state features into a logistic regression model to obtain a door body health assessment model, specifically:
state feature x= (t) 1 ,t 2 ,...,t n ) Inputting the training parameters into a logistic regression model for training, and determining the value of the training parameters omega according to the training results;
substituting the value of the training parameter omega into a logistic regression model to obtain a door body health degree evaluation model.
6. The sliding door body health evaluation method according to claim 5, wherein the time-displacement curve corresponding to sliding the door body of the sliding door to be tested is input into the door body health evaluation model to evaluate the door body health, specifically:
and inputting the state characteristics of the corresponding door body time-displacement curve when the door body of the sliding door to be tested slides into the door body health evaluation model, and outputting the health degree of the corresponding curve to evaluate the door body health degree.
7. A sliding door body health assessment device, comprising:
the sample acquisition module is used for acquiring a time-displacement curve sample of sliding of the door body;
the statistical learning module is used for marking the obtained time-displacement curve sample through a statistical learning model to obtain a corresponding time-displacement curve label sample;
the training module is used for constructing state characteristics according to the time-displacement curve label sample, inputting the state characteristics into a logistic regression model for training, and obtaining a door body health degree assessment model;
the evaluation module is used for inputting a time-displacement curve corresponding to the sliding of the door body of the sliding door to be tested into the door body health evaluation model to evaluate the door body health;
the state features are the time intervals of the door body sliding to a plurality of preset positions;
correspondingly, the training module is further used for inputting the state characteristics into a logistic regression model for training, and determining the value of the training parameters according to the training result;
and determining a door body health degree evaluation model according to the value of the training parameter.
8. An electronic device, comprising:
a memory and one or more processors;
the memory is used for storing one or more programs;
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-6.
9. A storage medium containing computer executable instructions which, when executed by a computer processor, are for performing the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110904179.3A CN113762347B (en) | 2021-08-06 | 2021-08-06 | Sliding door body health degree assessment method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110904179.3A CN113762347B (en) | 2021-08-06 | 2021-08-06 | Sliding door body health degree assessment method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113762347A CN113762347A (en) | 2021-12-07 |
| CN113762347B true CN113762347B (en) | 2023-08-08 |
Family
ID=78788677
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110904179.3A Active CN113762347B (en) | 2021-08-06 | 2021-08-06 | Sliding door body health degree assessment method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113762347B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800139A (en) * | 2018-12-18 | 2019-05-24 | 东软集团股份有限公司 | Server health degree analysis method, device, storage medium and electronic equipment |
| CN111860671A (en) * | 2020-07-28 | 2020-10-30 | 中山大学 | Classification model training method and device, terminal equipment and readable storage medium |
| CN112723069A (en) * | 2020-12-16 | 2021-04-30 | 长沙慧联智能科技有限公司 | Elevator door running state monitoring method and system based on TOF visual detection |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020096099A1 (en) * | 2018-11-09 | 2020-05-14 | 주식회사 루닛 | Machine learning method and device |
-
2021
- 2021-08-06 CN CN202110904179.3A patent/CN113762347B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800139A (en) * | 2018-12-18 | 2019-05-24 | 东软集团股份有限公司 | Server health degree analysis method, device, storage medium and electronic equipment |
| CN111860671A (en) * | 2020-07-28 | 2020-10-30 | 中山大学 | Classification model training method and device, terminal equipment and readable storage medium |
| CN112723069A (en) * | 2020-12-16 | 2021-04-30 | 长沙慧联智能科技有限公司 | Elevator door running state monitoring method and system based on TOF visual detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113762347A (en) | 2021-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zheng et al. | Bayesian hierarchical modeling of the non-stationary traffic conflict extremes for crash estimation | |
| CN106960568B (en) | Generate method, medium and system based on probabilistic traffic congestion index | |
| US10282679B2 (en) | Information processing apparatus, program, and information processing method | |
| Zheng et al. | Application of extreme value theory for before-after road safety analysis | |
| Zhao et al. | Optimal condition-based maintenance policy with delay for systems subject to competing failures under continuous monitoring | |
| CN112330591A (en) | Steel rail surface defect detection method and device capable of achieving sample-less learning | |
| Liu et al. | Empirical study of driver responses during the yellow signal phase at six Maryland intersections | |
| CN106354995A (en) | Predicting method based on Lagrange interpolation and time sequence | |
| Winkler et al. | Optimizing for recall in automatic requirements classification: An empirical study | |
| CN109934433A (en) | A kind of personnel ability's appraisal procedure, device and cloud service platform | |
| US20220036984A1 (en) | Identifying and indexing discriminative features for disease progression in observational data | |
| CN110598999B (en) | Traffic travel analysis method, system and storage medium based on individual data | |
| CN112632179B (en) | Model construction method, device, storage medium and equipment | |
| CN106779224A (en) | It is a kind of to predict the method and system that probability is enrolled in college entrance examination | |
| CN113361690A (en) | Water quality prediction model training method, water quality prediction device, water quality prediction equipment and medium | |
| CN113536611B (en) | Method for checking correctness of autonomous traffic system architecture based on discrete simulation | |
| Zheng et al. | Validating the Bayesian hierarchical extreme value model for traffic conflict-based crash estimation on freeway segments with site-level factors | |
| CN111752833B (en) | Software quality system approval method, device, server and storage medium | |
| CN114021840A (en) | Channel switching strategy generation method and device, computer storage medium and electronic equipment | |
| CN113762347B (en) | Sliding door body health degree assessment method and device | |
| Zorn et al. | Replacing energy simulations with surrogate models for design space exploration | |
| CN113919432A (en) | Classification model construction method, data classification method and device | |
| Jeong et al. | Constructing an Audio Dataset of Construction Equipment from Online Sources for Audio-Based Recognition | |
| Zhou et al. | Urban Rail Transit Train Dwell Time Analysis Based on Random Forest Algorithm: A Case Study on the Beidajie Station of the Xi’an Metro in China | |
| CN115543702A (en) | Multi-source solid state disk collaborative fault diagnosis method, system, equipment and medium |
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 |