Elevator intelligent analysis system and method based on big data analysis

Abstract

The application relates to the technical field of quality detection, in particular to an elevator intelligent analysis system and method based on big data analysis, which evaluates and warns the safety of elevator riding through multiple steps, acquires elevator operation data, steel wire rope wear condition and personnel behavior characteristic condition, respectively evaluates personnel behavior risk and elevator behavior risk based on personnel behavior characteristics and elevator operation and steel wire rope condition, wherein the personnel behavior risk evaluation analyzes abnormalities from horizontal and vertical moving projection images in combination with weight condition, the elevator behavior risk evaluation quantitatively analyzes horizontal and vertical swing amplitude and frequency and steel wire rope strength, and then riding matching analysis is performed through the evaluation results of the two, the advantage lies in comprehensively considering elevator operation factors and personnel behavior, comprehensively and quantitatively evaluating elevator riding abnormal conditions, and facilitating the timely discovery of potential safety hazards and the taking of measures to ensure passenger safety.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of quality detection, and in particular to an elevator intelligent analysis system and method based on big data analysis. BACKGROUND

[0002] The widespread use of elevators has brought about safety problems that cannot be ignored. During the operation of the elevator, mechanical, electrical, control and other complex systems are involved, and any failure in any link can lead to the occurrence of safety accidents. In recent years, elevator safety accidents have occurred from time to time, such as sudden elevator falling, door system failure trapping people, abnormal shaking during operation, etc. These accidents not only pose a serious threat to the life safety of passengers, but also arouse the high attention of the society to the safety of elevators. The safety problem of elevators has become an important issue related to the safety of people's life and property and social stability.

[0003] At present, most elevator safety evaluation technologies mainly focus on the monitoring of elevator's own operating parameters such as speed, acceleration, floor position, etc. These technologies can detect the basic operating state of the elevator to a certain extent, but ignore the influence of other important factors on the safety of the elevator. For example, the elevator steel wire rope is a key component of the elevator operation, and its wear condition is directly related to the carrying capacity and running stability of the elevator, but the existing technology does not monitor the wear condition of the steel wire rope comprehensively and deeply, and often can only conduct periodic manual inspection, which is difficult to grasp the actual state of the steel wire rope in real time. In addition, the behavior of people in the elevator also affects the safety of the elevator, such as the degree of crowding and abnormal jumping of people, which may cause the imbalance or damage of the elevator, but the existing technology rarely takes the behavior of people into the elevator safety evaluation system. In the actual process of riding the elevator, there is a mutual influence between the running state of the elevator and the behavior of people. Different elevator running states have different requirements for the behavior of people, and the behavior of people will in turn affect the running safety of the elevator. However, the existing technology lacks analysis of the matching between the running state of the elevator and the behavior of people, and cannot accurately evaluate the safety of passengers riding the elevator according to the actual running condition of the elevator and the behavior characteristics of people. For example, when the elevator appears slight shaking, different personnel behaviors (such as standing still, violent jumping, etc.) have different influences on the safety of riding, but the existing technology cannot effectively analyze and warn this matching situation.

[0004] In view of this, the present application proposes an elevator intelligent analysis system and method based on big data analysis. SUMMARY

[0005] In order to overcome the defects and deficiencies proposed in the background art, the present application provides an elevator intelligent analysis system and method based on big data analysis.

[0006] In order to achieve the above purpose, the present application adopts the following technical solutions:

[0007] In a first aspect, the application provides an elevator intelligent analysis method based on big data analysis, comprising the following steps:

[0008] Step S1, obtaining elevator operation data, elevator steel wire rope wear condition, and personnel behavior feature condition in the elevator;

[0009] Step S2, performing personnel behavior risk assessment based on the personnel behavior feature condition, and the angle feature of the behavior direction and the elevator operation direction;

[0010] Step S3, performing elevator behavior risk assessment based on the corresponding elevator operation data and the elevator steel wire rope wear condition;

[0011] Step S4, performing ride matching analysis based on the personnel behavior risk assessment result and the elevator behavior risk assessment result;

[0012] Step S5, performing passenger ride early warning based on the ride matching analysis result.

[0013] In an implementation manner of the application, the swing condition data of each direction in the elevator operation process, the safety swing amplitude condition and the safety swing frequency condition set when the elevator is manufactured, and the swing condition of each direction can be obtained through a swing sensor, the elevator steel wire rope wear condition is obtained by a machine vision module in the process of lifting the steel wire rope to obtain the image on the surface of the steel wire rope, identify the surface image condition and the number of broken wires of the corresponding steel wire rope, the personnel behavior feature condition in the elevator is the movement condition of the personnel in the elevator and the weight condition of the personnel, wherein the movement behavior condition is obtained by a corresponding video acquisition module to acquire the movement behavior image condition of the corresponding personnel in the elevator, and the weight condition of the personnel is obtained by a weighing device when the personnel enters the elevator, and the obtained data is stored in a corresponding storage component in real time.

[0014] In an implementation manner of the application, the personnel behavior risk assessment in step S2 comprises the following specific steps:

[0015] S21, obtaining the movement behavior image condition of the personnel in the elevator, constructing a three-dimensional movement model of the elevator and the personnel, obtaining the personnel movement projection image in the horizontal direction of the elevator and the personnel movement projection image in the vertical direction, obtaining the personnel movement projection image in the horizontal and vertical directions of the elevator by obtaining the movement behavior image condition of the personnel in the elevator and constructing the three-dimensional movement model, and then obtaining the movement trajectory and the spatial position change of the personnel in the elevator, which can comprehensively and intuitively present the movement trajectory and the spatial position change of the personnel in the elevator, and such multi-dimensional image data provides a rich and reliable basis for subsequent precise analysis of personnel movement abnormalities, which helps to capture personnel movement features from different perspectives and improves the accuracy and comprehensiveness of the analysis;

[0016] S22, performing personnel lateral movement abnormality analysis based on the personnel movement projection image of the personnel relative to the elevator in the lateral direction and the weight condition of the personnel, wherein the personnel lateral movement abnormality analysis process is: obtaining the intersection area of the movement projection images of the personnel in the lateral direction at adjacent times, dividing the intersection area by the area of the part of the movement projection images of the personnel in the lateral direction at the corresponding time to obtain the image stagnation condition of the corresponding adjacent times, subtracting the image stagnation condition from 1 to obtain the image movement condition, integrating the image movement condition over time and dividing the integral by the time length to obtain the lateral movement influence of the corresponding personnel; obtaining the weight influence of the personnel based on the ratio of the weight of the personnel to the safe weight, multiplying the lateral movement influence result of the corresponding personnel by the corresponding weight influence to obtain the lateral movement abnormality analysis result of the corresponding personnel, performing lateral movement abnormality analysis based on the personnel lateral movement projection image and the weight condition, and comprehensively considering two key factors of personnel movement and weight. By calculating the image stagnation condition and the movement condition, the activity level of the personnel in the lateral direction can be quantified; by introducing the weight influence factor, the different influences of personnel movement of different weights on the elevator operation are further considered, and the lateral movement abnormality analysis result obtained by combining the two can more accurately determine whether the personnel movement in the lateral direction in the elevator is abnormal.

[0017] S23, performing personnel longitudinal movement abnormality analysis based on the personnel movement projection image of the personnel relative to the elevator in the longitudinal direction and the weight condition of the personnel, wherein the personnel longitudinal movement abnormality analysis process is: obtaining the intersection area of the movement projection images of the personnel in the longitudinal direction at adjacent times, dividing the intersection area by the area of the part of the movement projection images of the personnel in the longitudinal direction at the corresponding time to obtain the image stagnation condition of the corresponding adjacent times, subtracting the image stagnation condition from 1 to obtain the image movement condition, integrating the image movement condition over time and dividing the integral by the time length to obtain the longitudinal movement influence of the corresponding personnel; obtaining the weight influence of the personnel based on the ratio of the weight of the personnel to the safe weight, multiplying the longitudinal movement influence result of the corresponding personnel by the corresponding weight influence to obtain the longitudinal movement abnormality analysis result of the corresponding personnel, performing longitudinal movement abnormality analysis based on the personnel longitudinal movement projection image and the weight condition, and comprehensively evaluating the abnormality condition of the personnel longitudinal movement in the elevator.

[0018] In an implementation manner of the present application, the risk assessment in the step S3 comprises the following specific steps:

[0019] S31, obtaining the swing condition of the corresponding directions of the elevator, simultaneously obtaining the surface image condition of the steel wire rope of the elevator and the number of broken wires of the corresponding steel wire rope, and comprehensively obtaining the key running state information of the elevator in multiple aspects. The swing condition of each direction can directly reflect the stability of the elevator during operation.

[0020] S32, obtain the corresponding elevator lateral swing amplitude and swing frequency, respectively divide the elevator lateral swing amplitude, swing frequency and the corresponding swing safety value to obtain the lateral amplitude danger value and the lateral frequency danger value, and obtain the elevator lateral swing danger by weighted sum of the lateral amplitude danger value and the lateral frequency danger value, quantify the danger of the elevator lateral swing, obtain the danger value by dividing the lateral swing amplitude and frequency by the safety value, and then perform weighted sum, which can comprehensively consider the influence of the swing amplitude and frequency on the elevator safety, so that the danger degree of the elevator lateral swing can be represented by a specific value, and the safety condition of the elevator lateral operation can be intuitively understood by the staff;

[0021] S33, obtain the corresponding elevator longitudinal swing amplitude and longitudinal swing frequency, and simultaneously obtain the corresponding steel wire rope surface image and the corresponding number of broken wires of the steel wire rope, and perform elevator longitudinal danger assessment, wherein the elevator longitudinal danger assessment process comprises: obtaining the longitudinal swing amplitude and the longitudinal swing frequency of the elevator longitudinal, respectively dividing the elevator longitudinal swing amplitude, the swing frequency and the corresponding swing safety value to obtain the longitudinal amplitude danger value and the longitudinal frequency danger value, and obtaining the elevator longitudinal swing danger by weighted sum of the longitudinal amplitude danger value and the longitudinal frequency danger value; simultaneously obtaining the corresponding steel wire rope surface image and the corresponding number of broken wires of the steel wire rope, obtaining the strength of the steel wire rope at the corresponding time based on the steel wire rope surface image, the production strength of the steel wire rope and the number of broken wires of the corresponding steel wire rope through a deep learning neural network model, setting the ratio of the steel wire rope safety strength and the strength of the steel wire rope at the corresponding time as the steel wire rope danger value, and obtaining the elevator longitudinal danger by weighted sum of the steel wire rope danger value and the elevator longitudinal swing danger.

[0022] In an implementation manner of the present application, the ride matching analysis in the step S4 comprises the following specific contents:

[0023] S41, respectively obtain the lateral movement abnormality analysis result, the longitudinal movement abnormality analysis result, the elevator lateral swing danger and the elevator longitudinal swing danger;

[0024] S42. By multiplying the results of the lateral movement anomaly analysis with the lateral swaying hazard of the elevator, a lateral matching anomaly is obtained. By multiplying the results of the longitudinal movement anomaly analysis with the longitudinal swaying hazard of the elevator, a longitudinal matching anomaly is obtained. The results of the lateral matching anomaly and the longitudinal matching anomaly are then weighted and summed to obtain the riding matching anomaly result. This step, by multiplying the results of the lateral and longitudinal movement anomaly analysis with the swaying hazard in the corresponding direction, obtains the lateral and longitudinal matching anomalies, and then weighted and sums the two to obtain the riding matching anomaly result. This comprehensively considers the lateral and longitudinal movement anomalies of the elevator as well as the swaying hazard, and comprehensively and quantitatively assesses the abnormal situation of elevator riding. It provides an intuitive and accurate reference for elevator safety management and maintenance, and facilitates the timely detection of potential safety hazards and the taking of corresponding measures. The safety of elevator riding is affected by the lateral and longitudinal movement status and the swaying situation. The results of the movement anomaly analysis are combined with the swaying hazard for calculation.

[0025] In one implementation of this application, the passenger travel warning in step S5 includes the following specific content:

[0026] The abnormal ride matching result is compared with the corresponding abnormal ride matching threshold. If the abnormal ride matching result is greater than or equal to the corresponding abnormal ride matching threshold, it indicates that the passenger is in danger. The passenger is reminded of the danger and the amplitude of the movement is reduced or a mismatch warning is issued. If the abnormal ride matching result is less than the corresponding abnormal ride matching threshold, it indicates that the passenger is safe.

[0027] Secondly, this application also provides an elevator intelligent analysis system based on big data analysis, including:

[0028] The data acquisition module acquires data on elevator operation, elevator wire rope wear, and the behavioral characteristics of people in the elevator.

[0029] The behavioral hazard assessment module assesses the behavioral hazards of people in the elevator based on their behavioral characteristics and the angle between their behavioral direction and the direction of elevator operation.

[0030] The elevator hazard assessment module assesses the behavioral hazards of the elevator based on the corresponding elevator operation data and the wear condition of the elevator wire rope.

[0031] The ride matching analysis module performs ride matching analysis based on the results of personnel behavior risk assessment and elevator behavior risk assessment.

[0032] The verification and processing module issues passenger travel warnings based on the travel matching analysis results.

[0033] In a third aspect, the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program that can be invoked by the processor, and the processor executes the elevator intelligent analysis method based on big data analysis by invoking the computer program stored in the memory.

[0034] In a fourth aspect, the present application provides a computer readable storage medium storing instructions, which, when executed on a computer, cause the computer to execute the elevator intelligent analysis method based on big data analysis.

[0035] Compared with the prior art, the present application has the following advantages and beneficial effects:

[0036] The present application evaluates and warns the elevator ride safety through multiple steps. Firstly, the elevator operation data, the steel wire rope wear condition and the personnel behavior characteristic condition are obtained. Then, the personnel behavior risk assessment and the elevator behavior risk assessment are performed based on the personnel behavior characteristic and the elevator operation and the steel wire rope condition respectively. The personnel behavior risk assessment analyzes the abnormality from the horizontal and vertical moving projection image combined with the weight condition. The elevator behavior risk assessment quantitatively analyzes the horizontal and vertical swing amplitude and frequency and the steel wire rope strength. After that, the ride matching analysis is performed through the evaluation results of the two. The advantage is that the elevator ride abnormality condition is comprehensively and quantitatively evaluated by comprehensively considering the elevator operation multiple factors and the personnel behavior, which provides an intuitive and accurate reference for the elevator safety management and maintenance, facilitates the timely discovery of potential safety hazards and the taking of measures to protect the passenger safety. BRIEF DESCRIPTION OF DRAWINGS

[0037] Other features, objects and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments, made with reference to the accompanying drawings:

[0038] Figure 1 FIG. 1 is a schematic diagram of the overall process of the method embodiment 1 of the present application;

[0039] Figure 2 FIG. 2 is a schematic diagram of the S2 step of the method embodiment 1 of the present application;

[0040] Figure 3 FIG. 3 is a schematic diagram of the S3 step of the method embodiment 1 of the present application;

[0041] Figure 4 FIG. 4 is a schematic diagram of the structure of the system embodiment 2 of the present application;

[0042] Figure 5 FIG. 5 is a schematic diagram of the neural network model construction. DETAILED DESCRIPTION

[0043] In order to make the above objectives, characteristics and advantages of the present application more apparent, a detailed description of the specific embodiments of the present application will be given below with reference to the accompanying drawings.

[0044] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. The present application, however, can be practiced in other ways different from those described herein without departing from the scope of the present application, and it can be understood that similar modifications will be made by those skilled in the art without departing from the spirit of the present application, and therefore the present application is not limited to the specific embodiments disclosed below.

[0045] Secondly, "one embodiment" or "an embodiment" referred to herein means that a specific feature, structure or characteristic can be included in at least one implementation of the present application. "In one embodiment" appearing in different places in the specification does not mean the same embodiment, nor does it mean an embodiment that is separate from or mutually exclusive with other embodiments. Embodiment 1

[0046] As shown in the figure, the present embodiment provides an elevator intelligent analysis method based on big data analysis, specifically including the following steps: Figures 1 to 3

[0047] Step S1, obtaining elevator operation data, elevator steel wire rope wear condition and personnel behavior feature condition in the elevator;

[0048] In the present embodiment, the swing condition data corresponding to each direction in the elevator operation process, the safety swing amplitude condition set when the elevator is delivered from the factory and the safety swing frequency condition, in general, the horizontal swing amplitude is considered to be a relatively safe and reasonable range when the normal operation does not exceed ±5mm, the common requirement is that the swing frequency does not exceed 1 to 2Hz, which can be obtained from the factory setting, and the swing condition corresponding to each direction can be obtained through the swing sensor, the steel wire rope wear condition is obtained by the machine vision module in the process of lifting the steel wire rope to obtain the image of the surface of the steel wire rope, identify the surface image condition and the number of broken wires corresponding to the steel wire rope, which can be obtained through image processing software, the machine vision detection of the elevator steel wire rope wear mainly includes the following steps: real-time collection of surface images during the operation of the steel wire rope through high-resolution industrial cameras, and uniform light source is used to eliminate reflection interference; highlight the defect features by using image preprocessing (denoising, enhancement, ROI extraction), and then identify the broken wire and wear area through a deep learning model (such as YOLO), and count the number and position of broken wires, the personnel behavior feature condition in the elevator is the motion condition of the personnel in the elevator and the weight condition of the personnel, wherein the motion behavior condition is collected by the corresponding video acquisition module to collect the motion behavior image condition of the corresponding personnel in the elevator, and the weight condition of the personnel is obtained by weighing the personnel when entering the elevator through the weighing device, and the obtained data is stored in the corresponding storage component in real time; ​

[0049] Step S2, based on the behavior characteristics of the person in the elevator, the behavior direction and the angle characteristics of the elevator running direction to evaluate the dangerousness of the behavior of the person;

[0050] In this embodiment, the dangerousness of the behavior of the person in step S2 includes the following specific steps:

[0051] S21, acquire the moving behavior image situation of the person in the elevator, construct a three-dimensional moving model of the elevator and the person, acquire the horizontal moving projection image and the vertical moving projection image of the person relative to the elevator, by acquiring the moving behavior image situation of the person in the elevator and constructing the three-dimensional moving model, and then obtaining the horizontal and vertical moving projection images of the person in the elevator, the motion trajectory and the spatial position change of the person in the elevator can be presented comprehensively and intuitively, such multi-dimensional image data provides a rich and reliable basis for subsequent precise analysis of the motion abnormality of the person, which helps to capture the motion characteristics of the person from different perspectives, improves the accuracy and comprehensiveness of the analysis, the motion of the person in the elevator is a complex motion in three-dimensional space, a simple two-dimensional image is difficult to completely describe the motion situation, constructing a three-dimensional moving model can accurately model the relative position and motion relationship between the person and the elevator, and the horizontal and vertical projection images are effective simplification and information extraction of three-dimensional motion in a certain direction, which conforms to the scientific principle of analyzing complex motion in different dimensions;

[0052] S22, performing personnel lateral movement abnormality analysis based on the personnel movement projection image of the personnel relative to the lateral direction of the elevator and the weight condition of the personnel, wherein the personnel lateral movement abnormality analysis process is: obtaining an intersection area of the movement projection images of the personnel in the lateral direction at adjacent times, dividing the intersection area by an area of a part where the movement projection images of the personnel in the lateral direction at the corresponding times are combined together to obtain an image stagnation condition corresponding to the adjacent times, subtracting the image stagnation condition from 1 to obtain an image movement condition, integrating the image movement condition over time and dividing the integral by a time length to obtain a lateral movement influence of the corresponding personnel; obtaining a weight influence of the personnel based on a ratio of the weight of the personnel to a safe weight, and multiplying the lateral movement influence result of the corresponding personnel and the corresponding weight influence to obtain a lateral movement abnormality analysis result of the corresponding personnel; performing lateral movement abnormality analysis based on the personnel lateral movement projection image and the weight condition, and comprehensively considering two key factors of personnel movement and weight. By calculating the image stagnation condition and the movement condition, the activity level of the personnel in the lateral direction can be quantified; by introducing the weight influence factor, the different influences of personnel with different weights on the operation of the elevator are further considered; and the lateral movement abnormality analysis result obtained by combining the two can more accurately determine whether the lateral movement of the personnel in the elevator is abnormal, thereby providing more targeted reference for ensuring the safe operation of the elevator. The lateral movement of the personnel in the elevator will affect the balance and operation stability of the elevator, and the influence of personnel with different weights on the same movement is different. The calculation of the image stagnation and the movement condition can reflect the dynamic change of the lateral movement of the personnel, the ratio of the weight to the safe weight can measure the potential influence of the weight of the personnel on the elevator, and the multiplication of the two comprehensively considers the movement and weight factors, which conforms to the logic of multi-factor analysis of the safe operation of the elevator;

[0053] S23, performing personnel longitudinal movement abnormality analysis based on the personnel movement projection image of the personnel relative to the longitudinal direction of the elevator and the weight condition of the personnel, wherein the personnel longitudinal movement abnormality analysis process is: obtaining an intersection area of the movement projection images of the personnel in the longitudinal direction at adjacent times, dividing the intersection area by an area of a part where the movement projection images of the personnel in the longitudinal direction at the corresponding times are combined together to obtain an image stagnation condition corresponding to the adjacent times, subtracting the image stagnation condition from 1 to obtain an image movement condition, integrating the image movement condition over time and dividing the integral by a time length to obtain a longitudinal movement influence of the corresponding personnel; obtaining a weight influence of the personnel based on a ratio of the weight of the personnel to a safe weight, and multiplying the longitudinal movement influence result of the corresponding personnel and the corresponding weight influence to obtain a longitudinal movement abnormality analysis result of the corresponding personnel; performing longitudinal movement abnormality analysis based on the personnel longitudinal movement projection image and the weight condition, and comprehensively evaluating the abnormality of the longitudinal movement of the personnel in the elevator. By quantifying the longitudinal image movement condition and introducing the weight influence factor, the longitudinal movement abnormality analysis result obtained is helpful for timely discovering the abnormal movement of the personnel in the longitudinal direction, such as sudden up-and-down jumping, thereby warning the potential risk that may affect the safe operation of the elevator in advance.

[0054] Step S3, evaluating the behavior risk of the elevator based on the corresponding elevator operation data and the elevator wire rope wear condition;

[0055] In this embodiment, the risk evaluation in step S3 includes the following specific steps:

[0056] S31, obtaining the swing condition of the corresponding directions of the elevator, and obtaining the wire rope surface image condition and the number of broken wires of the corresponding wire rope, comprehensively obtaining the key operation state information of the elevator in multiple aspects. The swing condition in each direction can directly reflect the stability of the elevator during operation, and can help to find out whether the elevator has abnormal swinging in time, which may imply that the guide rail, suspension system and other components have problems. The wire rope surface image and the number of broken wires are important basis for evaluating the safety performance of the wire rope. The wire rope is a key load-bearing component of the elevator, and its condition is directly related to the safety of the elevator. Early detection of the damage condition of the wire rope helps to prevent serious accidents;

[0057] S32, obtaining the lateral swing amplitude and the swing frequency condition of the corresponding elevator, dividing the lateral swing amplitude and the swing frequency condition of the elevator by the corresponding swing safety value respectively to obtain the lateral amplitude risk value and the lateral frequency risk value, and obtaining the lateral swing risk of the elevator by weighted sum of the lateral amplitude risk value and the lateral frequency risk value, quantifying the risk of the lateral swing of the elevator. By dividing the lateral swing amplitude and frequency by the safety value to obtain the risk value, and then performing weighted sum, the influence of the swing amplitude and frequency on the safety of the elevator can be considered comprehensively. In this way, the risk degree of the lateral swing of the elevator can be represented by a specific value, which is convenient for the staff to intuitively understand the safety condition of the lateral operation of the elevator, and to take corresponding maintenance or repair measures in time. Swing amplitude and frequency are important indicators for measuring the stability of the lateral operation of the elevator. Swing amplitude and frequency exceeding the safety value will increase the risk of elevator operation. The method of weighted sum can reasonably allocate the weight according to the importance of different factors to the safety of the elevator;

[0058] S33, the longitudinal swing amplitude and the longitudinal swing frequency of the corresponding elevator are obtained, and the corresponding steel wire surface image condition and the corresponding number of broken wires of the steel wire are obtained, and the longitudinal danger of the elevator is evaluated, wherein the longitudinal danger evaluation process of the elevator includes: obtaining the longitudinal swing amplitude and the longitudinal swing frequency of the elevator, respectively dividing the longitudinal swing amplitude and the swing frequency of the elevator by the corresponding swing safety value to obtain the longitudinal amplitude danger value and the longitudinal frequency danger value respectively, and obtaining the longitudinal swing danger of the elevator by weighted sum of the longitudinal amplitude danger value and the longitudinal frequency danger value; at the same time, the corresponding steel wire surface image condition and the corresponding number of broken wires of the steel wire are obtained, the strength condition of the steel wire at the corresponding time is obtained based on the steel wire surface image condition, the production strength of the steel wire and the number of broken wires of the corresponding steel wire through the deep learning neural network model, the ratio of the safety strength of the steel wire to the strength condition of the steel wire at the corresponding time is set as the steel wire danger value, and the longitudinal danger of the elevator is obtained by weighted sum of the steel wire danger value and the longitudinal swing danger of the elevator; wherein, as shown in Figure 5 the specific content of the deep learning neural network model is: obtaining the historical steel wire surface image condition, the production strength of the steel wire and the number of broken wires of the corresponding steel wire, and the strength condition of the corresponding steel wire, constructing the deep learning neural network with the input of the steel wire surface image condition, the production strength of the steel wire and the number of broken wires of the corresponding steel wire, and the output of the strength condition of the steel wire; the historical data is divided into 9:1 training set and 15% test set; the 90% weight and bias training set is input into the deep learning neural network model for training to obtain the initial deep learning neural network model; the 10% weight and bias test set is used to test the initial deep learning neural network model, and the output of the initial deep learning neural network model that meets the maximum steel wire strength accuracy is taken as the deep learning neural network model, on the one hand, like the transverse swing evaluation, the longitudinal amplitude danger value and the longitudinal frequency danger value are calculated and weighted summed to quantify the danger of the longitudinal swing of the elevator; on the other hand, the deep learning neural network model is used to evaluate the strength condition of the steel wire by combining the steel wire surface image, the production strength and the number of broken wires, and the steel wire danger value is obtained, and finally the longitudinal danger of the elevator is obtained by weighted sum of the two, which comprehensively considers the safety condition of the elevator operation and the key components, so that the evaluation result is more accurate and comprehensive, and more reliable basis is provided for the safety management of the elevator;

[0059] Step S4, ride matching analysis is performed through the personnel behavior danger evaluation result and the elevator behavior danger evaluation result;

[0060] In this embodiment, the ride matching analysis in step S4 includes the following specific contents:

[0061] S41, respectively, obtain the transverse movement abnormality analysis result, the longitudinal movement abnormality analysis result, the elevator transverse swing danger and the elevator longitudinal swing danger;

[0062] S42, obtain the transverse matching abnormality by multiplying the transverse movement abnormality analysis result and the elevator transverse swing danger, and obtain the longitudinal matching abnormality by multiplying the longitudinal movement abnormality analysis result and the elevator longitudinal swing danger, and obtain the ride matching abnormality result by weighted sum of the transverse matching abnormality result and the longitudinal matching abnormality result, this step can comprehensively consider the transverse and longitudinal movement abnormality and the swing danger, comprehensively and quantitatively evaluate the abnormality of the elevator ride, provide intuitive and accurate reference for the elevator safety management and maintenance, facilitate to find potential safety hazards and take corresponding measures, the safety of the elevator ride is jointly affected by the transverse and longitudinal movement state and the swing condition, the movement abnormality analysis result and the swing danger are combined for calculation, which conforms to the scientific principle of comprehensive evaluation of elevator safety, and the weighted sum can reasonably allocate the weight according to the importance of the abnormality in different directions to the influence on the safety of the elevator ride, so that the evaluation result is more in line with the actual situation, and is consistent with the industry standard and method of elevator safety evaluation;

[0063] Step S5, passenger ride warning based on the ride matching analysis result; including the following specific contents:

[0064] The obtained ride matching abnormality result is compared with the corresponding ride matching abnormality threshold value, if the ride matching abnormality result is greater than or equal to the corresponding ride matching abnormality threshold value, it indicates that the passenger ride is dangerous, the passenger is reminded to ride, the action amplitude is reduced or the mismatch warning is given, and if the ride matching abnormality result is less than the corresponding ride matching abnormality threshold value, it indicates that the passenger ride is safe.

[0065] The values of the weights and the thresholds in the embodiment are obtained through experiments on historical data, and the specific experimental steps are as follows: obtaining historical elevator operation data, elevator wire rope wear condition and elevator personnel behavior characteristic condition, and whether the corresponding scene in history occurs dangerous condition, substituting the historical elevator operation data, elevator wire rope wear condition and elevator personnel behavior characteristic condition into the corresponding steps of the application to obtain the final ride matching abnormality result, and importing the ride matching abnormality result and the result of whether the corresponding scene occurs dangerous condition into fitting software (such as matlab) for data fitting iteration, and outputting the value of the set parameter that conforms to the maximum dangerous condition occurrence accuracy;

[0066] This embodiment offers the following advantages: It assesses and provides early warnings for elevator safety through a multi-step process. First, it acquires elevator operation data, steel cable wear data, and personnel behavior characteristics. Then, it conducts both personnel behavior hazard assessment and elevator behavior hazard assessment based on personnel behavior characteristics and elevator operation and steel cable conditions. The personnel behavior hazard assessment analyzes anomalies using lateral and longitudinal movement projection images combined with weight data. The elevator behavior hazard assessment quantifies the lateral and longitudinal sway amplitude and frequency, as well as the steel cable strength. Finally, it performs a ride matching analysis based on the results of both assessments. The advantage lies in comprehensively considering multiple factors related to elevator operation and personnel behavior, providing a comprehensive and quantitative assessment of abnormal elevator ride conditions. This offers an intuitive and accurate reference for elevator safety management and maintenance, facilitating the timely detection of potential safety hazards and enabling measures to be taken to ensure passenger safety. Example 2

[0067] like Figure 4 As shown, this embodiment provides an elevator intelligent analysis system based on big data analysis for implementing the elevator intelligent analysis method based on big data analysis in Embodiment 1. Specifically, it includes: a data acquisition module for acquiring elevator operation data, elevator wire rope wear, and passenger behavior characteristics; a behavior hazard assessment module for assessing passenger behavior hazard based on passenger behavior characteristics and the angle between the behavior direction and the elevator's operating direction; an elevator hazard assessment module for assessing elevator behavior hazard based on corresponding elevator operation data and elevator wire rope wear; a passenger matching analysis module for performing passenger matching analysis based on the passenger behavior hazard assessment results and the elevator behavior hazard assessment results; and a verification processing module for issuing passenger riding warnings based on the passenger matching analysis results. The specific steps of each module in this embodiment are the same as those in the method embodiment of Embodiment 1, and will not be repeated here. Example 3

[0068] An electronic device according to an embodiment of this application includes a processor and a memory. The memory stores a computer program that can be called by the processor. The processor executes an elevator intelligent analysis method based on big data analysis by calling the computer program stored in the memory. It should be noted that all computer programs for the elevator intelligent analysis method based on big data analysis are implemented using the C language. Example 4

[0069] This embodiment proposes a computer-readable storage medium on which an erasable and rewritable computer program is stored.

[0070] When the computer program runs on the computer device, it causes the computer device to execute the aforementioned elevator intelligent analysis method based on big data analysis.

[0071] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, the above-described embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, and the like, which includes one or more available medium collections. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0072] Those skilled in the art can clearly understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed in the present application can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0073] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device, and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0074] In several embodiments provided in the present application, it should be understood that the disclosed system, device, and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of units is only one, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices, or units, which can be electrical, mechanical, or other forms.

[0075] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0076] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit.

[0077] In the description of the present specification, the description referring to the terms "one embodiment", "example", "specific example" and the like means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are contained in at least one embodiment or example of the present application. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0078] The basic principles and main features of the present application and the advantages of the present application are shown and described above. It should be understood by those skilled in the art that the present application is not limited by the above embodiments, and the above embodiments and descriptions in the specification are only to illustrate the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements of the present application can be made, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. An elevator intelligent analysis method based on big data analysis, characterized by, The method comprises the following steps: Step S1, obtaining elevator operation data, elevator steel wire rope wear condition, and personnel behavior feature condition in the elevator; Step S2, performing personnel behavior risk assessment based on the behavior feature condition of the personnel in the elevator, and the angle feature of the behavior direction and the elevator operation direction; Step S3, performing elevator behavior risk assessment based on the corresponding elevator operation data and the elevator steel wire rope wear condition; Step S4, performing ride matching analysis based on the personnel behavior risk assessment result and the elevator behavior risk assessment result; Step S5, performing passenger ride warning based on the ride matching analysis result. The personnel behavior risk assessment comprises the following specific steps: An image of the motion behavior of the personnel in the elevator is obtained, a three-dimensional movement model of the elevator and the personnel is constructed, a personnel movement projection image in the horizontal direction relative to the elevator and a personnel movement projection image in the vertical direction are obtained; A personnel horizontal movement abnormality analysis is performed based on the personnel movement projection image in the horizontal direction relative to the elevator and the body weight of the personnel, wherein the personnel horizontal movement abnormality analysis process is as follows: the area of the intersection part of the personnel horizontal movement projection images of adjacent times is divided by the part area of the combined personnel horizontal movement projection images of the corresponding times to obtain the image stagnation condition of the corresponding adjacent times, the image movement condition is obtained by subtracting the image stagnation condition from 1, the horizontal movement influence of the corresponding personnel is obtained by integrating the image movement condition over time and dividing by the time length, the body weight influence of the personnel is obtained based on the ratio of the body weight of the personnel to the safe body weight, and the horizontal movement abnormality analysis result of the corresponding personnel is obtained by multiplying the horizontal movement influence result of the corresponding personnel and the corresponding body weight influence; A personnel vertical movement abnormality analysis is performed based on the personnel movement projection image in the vertical direction relative to the elevator and the body weight of the personnel. The risk assessment comprises the following specific steps: The swing condition of each direction of the elevator is obtained, and the surface image condition of the elevator steel wire rope and the number of broken wires of the corresponding steel wire rope are obtained; The horizontal swing amplitude and the swing frequency condition of the corresponding elevator are obtained, the horizontal swing amplitude and the swing frequency condition are respectively divided by the corresponding swing safety value to obtain a horizontal amplitude danger value and a horizontal frequency danger value, and the horizontal amplitude danger value and the horizontal frequency danger value are weighted and summed to obtain the horizontal swing danger of the elevator; The vertical swing amplitude and the vertical swing frequency condition of the corresponding elevator are obtained, the surface image condition of the corresponding steel wire rope and the number of broken wires of the corresponding steel wire rope are obtained, and the vertical danger of the elevator is evaluated.

2. The big data analysis based elevator intelligent analysis method according to claim 1, characterized by, The elevator longitudinal danger evaluation process comprises: obtaining the longitudinal swing amplitude and the longitudinal swing frequency of the elevator longitudinal direction, dividing the elevator longitudinal swing amplitude and the swing frequency by the corresponding swing safety value respectively to obtain the longitudinal amplitude danger value and the longitudinal frequency danger value, and obtaining the elevator longitudinal swing danger by weighted summation of the longitudinal amplitude danger value and the longitudinal frequency danger value; meanwhile, the surface image of the corresponding steel wire rope and the number of broken wires of the corresponding steel wire rope are obtained, the strength of the steel wire rope at the corresponding time is obtained based on the surface image of the steel wire rope, the production strength of the steel wire rope and the number of broken wires of the corresponding steel wire rope through a deep learning neural network model, the ratio of the safety strength of the steel wire rope to the strength of the steel wire rope at the corresponding time is set as the steel wire rope danger value, and the elevator longitudinal danger is obtained by weighted summation of the steel wire rope danger value and the elevator longitudinal swing danger.

3. The big data analysis based elevator intelligent analysis method according to claim 2, characterized by, The ride matching analysis comprises the following specific contents: The transverse movement abnormality analysis result, the longitudinal movement abnormality analysis result, the elevator transverse swing danger and the elevator longitudinal swing danger are obtained respectively; The transverse matching abnormality is obtained by multiplying the transverse movement abnormality analysis result and the elevator transverse swing danger, and the longitudinal matching abnormality is obtained by multiplying the longitudinal movement abnormality analysis result and the elevator longitudinal swing danger; the transverse matching abnormality result and the longitudinal matching abnormality result are weighted and summed to obtain the ride matching abnormality result.

4. The big data analysis based elevator intelligent analysis method according to claim 3, characterized by, The passenger ride prewarning comprises the following specific contents: The obtained ride matching abnormality result is compared with the corresponding ride matching abnormality threshold value, if the ride matching abnormality result is greater than or equal to the corresponding ride matching abnormality threshold value, it indicates that the passenger ride is dangerous, the passenger is reminded of the ride danger, the action amplitude is reduced or the non-matching prewarning is performed, and if the ride matching abnormality result is less than the corresponding ride matching abnormality threshold value, it indicates that the passenger ride is safe.

5. The big data analysis based elevator intelligent analysis method according to claim 4, characterized by, The swing situation data of each direction during the elevator operation, the safety swing amplitude and the safety swing frequency set when the elevator is delivered, the elevator steel wire rope wear condition, the surface image of the steel wire rope is obtained by the machine vision module during the lifting of the steel wire rope, the surface image and the number of broken wires of the corresponding steel wire rope are identified, and the motion behavior of the personnel in the elevator and the weight of the personnel are the personnel behavior characteristics in the elevator, wherein the motion behavior of the corresponding personnel in the elevator is collected by the corresponding video acquisition module to obtain the motion behavior image situation, and the data obtained is stored in the corresponding storage component in real time.

6. An elevator intelligent analysis system based on big data analysis for implementing the elevator intelligent analysis method based on big data analysis according to any one of claims 1 to 5, characterized by, The system comprises: A data acquisition module for acquiring the elevator operation data, the elevator steel wire rope wear condition and the personnel behavior characteristics in the elevator; A behavior danger evaluation module for evaluating the behavior danger of the personnel in the elevator based on the behavior characteristics of the personnel in the elevator, the angle characteristics of the behavior direction and the elevator operation direction; An elevator danger evaluation module for evaluating the behavior danger of the elevator based on the corresponding elevator operation data and the elevator steel wire rope wear condition; A ride matching analysis module for performing ride matching analysis based on the behavior danger evaluation result of the personnel and the behavior danger evaluation result of the elevator. The collation processing module performs passenger ride early warning based on the ride matching analysis result.

7. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program which can be invoked by the processor; characterized in that the processor executes the elevator intelligent analysis method based on big data analysis as claimed in any one of claims 1-5 by invoking the computer program stored in the memory.

Images