Intelligent elevator analysis system and method based on big data analysis

Abstract

The invention relates to the technical field of quality detection, in particular to an intelligent elevator analysis system and method based on big data analysis. According to the technical scheme, elevator taking safety is evaluated and early warned through multiple steps, firstly, elevator running condition data, steel wire rope abrasion conditions and personnel behavior characteristic conditions are obtained; then, personnel behavior risk assessment and elevator behavior risk assessment are conducted on the basis of personnel behavior characteristics and elevator operation and steel wire rope conditions, and according to personnel behavior risk assessment, abnormity is analyzed from transverse and longitudinal movement projection images in combination with the body weight condition; according to the elevator behavior risk assessment, quantitative analysis is conducted on transverse and longitudinal swing amplitude and frequency and steel wire rope strength, then taking matching analysis is conducted through the two assessment results, and the elevator behavior risk assessment method has the advantages that elevator running factors and personnel behaviors are comprehensively considered, and the elevator taking abnormal situation is comprehensively and quantitatively assessed; potential safety hazards can be conveniently found in time, and measures are taken to guarantee passenger safety.

Description

Technical Field

[0001] This application relates to the field of quality inspection technology, and in particular to an intelligent elevator analysis system and method based on big data analysis. Background Technology

[0002] The widespread use of elevators has brought about significant safety issues. Elevator operation involves multiple complex systems, including mechanical, electrical, and control systems; a malfunction in any of these systems can lead to an accident. In recent years, elevator accidents have occurred frequently, such as sudden elevator drops, door system malfunctions trapping passengers, and abnormal shaking during operation. These accidents not only pose a serious threat to passengers' lives but have also raised widespread public concern about elevator safety. Elevator safety has become a crucial issue concerning the safety of people's lives and property and social stability.

[0003] Currently, most elevator safety assessment technologies focus primarily on monitoring the elevator's own operating parameters, such as speed, acceleration, and floor position. While these technologies can detect the basic operating status of the elevator to a certain extent, they neglect the impact of other important factors on elevator safety. For example, the elevator steel cable, as a critical component of elevator operation, directly affects the elevator's load-bearing capacity and operational stability due to its wear. However, current technologies for monitoring steel cable wear are not comprehensive or in-depth enough, often relying on periodic manual inspections and failing to grasp the actual condition of the steel cable in real time. Furthermore, the behavior of people inside the elevator also affects elevator safety. For instance, crowding levels and abnormal bouncing can lead to elevator imbalance or damage. However, current technologies rarely incorporate human behavior factors into the elevator safety assessment system. In actual elevator use, there is a reciprocal relationship between the elevator's operating status and human behavior. Different elevator operating states require different human behaviors, and human behavior, in turn, affects elevator safety. However, current technologies lack a matching analysis between elevator operating states and human behavior, making it impossible to accurately assess passenger safety based on the actual elevator operation and human behavioral characteristics. For example, when an elevator shakes slightly, different behaviors (such as standing still or jumping violently) have different effects on passenger safety, but current technology cannot effectively analyze and provide early warnings for such passenger matching situations.

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

[0005] To overcome the defects and shortcomings mentioned in the background technology, this application provides an elevator intelligent analysis system and method based on big data analysis.

[0006] To achieve the above objectives, this application adopts the following technical solution: Firstly, this application provides an elevator intelligent analysis method based on big data analysis, including the following steps: Step S1: Obtain elevator operation data, elevator wire rope wear data, and information on the behavioral characteristics of people in the elevator; Step S2: Conduct a risk assessment of personnel behavior based on the behavioral characteristics of people in the elevator and the angular characteristics of the behavioral direction relative to the elevator's direction of travel; Step S3: Assess the elevator's behavioral hazards based on the corresponding elevator operation data and the wear condition of the elevator wire rope; Step S4: Conduct a ride matching analysis based on the results of the personnel behavior hazard assessment and the elevator behavior hazard assessment; Step S5: Issue passenger travel warnings based on the travel matching analysis results.

[0007] In one implementation of this application, the data on the swaying in each direction during elevator operation, the safe swaying amplitude set at the time of elevator manufacture, and the safe swaying frequency are obtained. The swaying in each direction can be acquired by a sway sensor. The wear of the elevator wire rope is obtained by a machine vision module by acquiring images of the wire rope surface during the lifting and lowering process, identifying the surface image and the number of broken wires in the corresponding wire rope. The characteristics of personnel behavior in the elevator include the movement and weight of the personnel. The movement behavior is acquired by a corresponding video acquisition module, which captures images of the movement behavior of the corresponding personnel in the elevator. The weight of the personnel is obtained by weighing the personnel when they enter the elevator, and the acquired data is stored in real time in the corresponding storage component.

[0008] In one implementation of this application, the personnel behavior hazard assessment in step S2 includes the following specific steps: S21. Obtain images of people's movement behavior in the elevator, construct a three-dimensional movement model of the elevator and people, and obtain projection images of people's movement in the horizontal and vertical directions relative to the elevator. By obtaining images of people's movement behavior in the elevator and constructing a three-dimensional movement model, we can obtain projection images of people's movement in the elevator in the horizontal and vertical directions. This can comprehensively and intuitively present the movement trajectory and spatial position changes of people in the elevator. This multi-dimensional image data provides a rich and reliable foundation for subsequent accurate analysis of abnormal movement of people, and helps to capture the movement characteristics of people from different perspectives, thereby improving the accuracy and comprehensiveness of the analysis. S22. Anomaly analysis of lateral movement of personnel is performed based on the projected images of personnel movement relative to the elevator's lateral direction and their weight. The process involves: dividing the area of ​​the intersecting portion of the lateral movement projection images of personnel at adjacent time points by the combined area of ​​the lateral movement projection images at the corresponding time points to obtain the image stagnation status at those adjacent time points; subtracting the image stagnation status from 1 to obtain the image movement status; and integrating the image movement status over time and dividing by the duration to obtain the lateral movement impact of the corresponding personnel. The ratio of a person's weight to their safe weight is used to obtain the weight impact; multiplying the lateral movement impact result by the corresponding weight impact yields the lateral movement anomaly analysis result. This lateral movement anomaly analysis, based on the projected images of personnel movement and their weight, comprehensively considers two key factors: personnel movement and weight. By calculating the image stagnation and movement status, the activity level of personnel in the lateral direction can be quantified. Introducing the weight impact factor further considers the different impacts that the movement of people of different weights may have on elevator operation. Combining these two factors allows for a more accurate determination of whether the lateral movement of personnel within the elevator is abnormal. S23. Based on the projection image of personnel movement relative to the elevator longitudinal direction and the personnel's weight, an anomaly analysis of personnel longitudinal movement is performed. The process of personnel longitudinal movement anomaly analysis is as follows: the intersection area of ​​personnel longitudinal movement projection images at adjacent time points is obtained by dividing it by the combined area of ​​personnel longitudinal movement projection images at the corresponding time points to obtain the image stagnation status at the corresponding adjacent time points. The image movement status is obtained by subtracting the image stagnation status from 1. The longitudinal movement impact of the corresponding personnel is obtained by integrating the image movement status over time and dividing it by the duration. The weight impact of the personnel is obtained based on the ratio of the personnel's weight to the safe weight. The longitudinal movement impact result of the corresponding personnel is obtained by multiplying the corresponding weight impact result by the corresponding weight impact result. The longitudinal movement anomaly analysis of the personnel longitudinal movement projection image and weight status can comprehensively assess the anomalies of personnel longitudinal movement in the elevator.

[0009] In one implementation of this application, the hazard assessment in step S3 includes the following specific steps: S31. Obtain the swaying status of the elevator in each direction, and simultaneously obtain images of the elevator wire rope surface and the number of broken wires, comprehensively acquiring key operational status information of the elevator from multiple aspects. The swaying status in each direction directly reflects the stability of the elevator during operation; S32. Obtain the corresponding lateral sway amplitude and sway frequency of the elevator. Divide the lateral sway amplitude and sway frequency by the corresponding sway safety value to obtain the lateral amplitude hazard value and lateral frequency hazard value, respectively. Then, sum the lateral amplitude hazard value and lateral frequency hazard value with weights to obtain the lateral sway hazard of the elevator. This quantifies the lateral sway hazard of the elevator. By dividing the lateral sway amplitude and frequency by the safety value to obtain the hazard value, and then summing them with weights, the impact of the two key factors of sway amplitude and frequency on elevator safety can be comprehensively considered. In this way, a specific numerical value can be used to represent the degree of danger of the lateral sway of the elevator, which makes it easier for staff to intuitively understand the safety status of the elevator's lateral operation. S33. Obtain the longitudinal sway amplitude and frequency of the corresponding elevator, and simultaneously obtain the surface image of the corresponding wire rope and the number of broken wires in the corresponding wire rope. Conduct a longitudinal hazard assessment of the elevator. The longitudinal hazard assessment process includes: obtaining the longitudinal sway amplitude and frequency of the elevator; dividing the longitudinal sway amplitude and frequency by the corresponding sway safety value to obtain the longitudinal amplitude hazard value and longitudinal frequency hazard value, respectively; and weighted summing the longitudinal amplitude hazard value and longitudinal frequency hazard value to obtain the longitudinal sway hazard of the elevator; simultaneously obtaining the surface image of the corresponding wire rope and the number of broken wires in the corresponding wire rope; based on the surface image of the wire rope, the production strength of the wire rope, and the number of broken wires in the corresponding wire rope, obtaining the strength of the wire rope at the corresponding time using a deep learning neural network model; setting the ratio of the wire rope safety strength to the strength of the wire rope at the corresponding time as the wire rope hazard value; and weighted summing the wire rope hazard value and the longitudinal sway hazard of the elevator to obtain the longitudinal hazard of the elevator.

[0010] In one implementation of this application, the ride matching analysis in step S4 includes the following specific contents: S41. Obtain the results of the lateral movement anomaly analysis, the results of the longitudinal movement anomaly analysis, the lateral swaying hazard of the elevator, and the longitudinal swaying hazard of the elevator, respectively. 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.

[0011] In one implementation of this application, the passenger travel warning in step S5 includes the following specific content: 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.

[0012] Secondly, this application also provides an elevator intelligent analysis system based on big data analysis, including: The data acquisition module acquires data on elevator operation, elevator wire rope wear, and the behavioral characteristics of people in the elevator. 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. 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. The ride matching analysis module performs ride matching analysis based on the results of personnel behavior risk assessment and elevator behavior risk assessment. The verification and processing module issues passenger travel warnings based on the travel matching analysis results.

[0013] Thirdly, this application provides an electronic device comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes an elevator intelligent analysis method based on big data analysis by calling the computer program stored in the memory.

[0014] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform an elevator intelligent analysis method based on big data analysis.

[0015] Compared with the prior art, this application has the following advantages and beneficial effects: This application employs a multi-step approach to assess and provide early warnings regarding elevator safety. First, it acquires data on elevator operation, wire rope wear, and passenger behavior. Then, based on these passenger behavior characteristics and the elevator's operation and wire rope conditions, it conducts both passenger behavior hazard assessments and elevator behavior hazard assessments. The passenger 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 wire rope strength. Finally, it performs a passenger matching analysis using the results of both assessments. The advantage of this approach is that it comprehensively considers multiple factors related to elevator operation and passenger behavior, providing a comprehensive and quantitative assessment of abnormal elevator riding situations. 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. Attached Figure Description

[0016] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a schematic diagram of the overall process of Embodiment 1 of the method of this application; Figure 2 This is a schematic diagram of step S2 of embodiment 1 of the method of this application; Figure 3 This is a schematic diagram of step S3 in embodiment 1 of the method of this application; Figure 4 This is a schematic diagram of the structure of embodiment 2 of the system in this application; Figure 5 A schematic diagram of constructing a neural network model. Detailed Implementation

[0017] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the specific embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0018] Many specific details are set forth in the following description in order to provide a full understanding of this application. However, this application may also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the spirit of this application. Therefore, this application is not limited to the specific embodiments disclosed below.

[0019] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of this application. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments. Example 1

[0020] like Figures 1 to 3 As shown, this embodiment provides an intelligent elevator analysis method based on big data analysis, which specifically includes the following steps: Step S1: Obtain elevator operation data, elevator wire rope wear data, and information on the behavioral characteristics of people in the elevator; In this embodiment, the data includes the swaying in each direction during elevator operation, the safe swaying amplitude set at the factory, and the safe swaying frequency. Generally, a horizontal swaying amplitude not exceeding ±5 mm during normal operation is considered a safe and reasonable range. A common requirement is a swaying frequency not exceeding 1 to 2 Hz, which can be obtained from the factory settings. The swaying in each direction can be acquired using sway sensors. The wear of the elevator wire rope is detected by a machine vision module acquiring images of the wire rope surface during its ascent and descent, identifying the surface condition and the number of broken wires. This can be achieved using image processing software. This machine vision detection method detects the wear of the elevator wire rope. The main steps include: acquiring surface images in real time during the operation of the wire rope using a high-resolution industrial camera, and eliminating reflective interference with a uniform light source; highlighting defect features using image preprocessing (denoising, enhancement, ROI extraction), and then identifying broken wires and wear areas using a deep learning model (such as YOLO), and counting the number and location of broken wires; and identifying the behavior characteristics of people in the elevator, including their movement and weight. The movement behavior is captured by the corresponding video acquisition module, and the weight is obtained by weighing people when they enter the elevator, with the data stored in real time in the corresponding storage component. Step S2: Conduct a risk assessment of personnel behavior based on the behavioral characteristics of people in the elevator and the angular characteristics of the behavioral direction relative to the elevator's direction of travel; In this embodiment, the personnel behavior hazard assessment in step S2 includes the following specific steps: S21. Obtain images of people's movement behavior in the elevator, construct a three-dimensional movement model of the elevator and people, and obtain projection images of people's movement in the horizontal and vertical directions relative to the elevator. By obtaining images of people's movement behavior in the elevator and constructing a three-dimensional movement model, we can obtain projection images of people's movement in the elevator in the horizontal and vertical directions. This can comprehensively and intuitively present the movement trajectory and spatial position changes of people in the elevator. This multi-dimensional image data provides a rich and reliable foundation for subsequent accurate analysis of abnormal movement of people. It helps to capture the movement characteristics of people from different perspectives and improve the accuracy and comprehensiveness of the analysis. The movement of people in the elevator is a complex movement in three-dimensional space. Simple two-dimensional images are difficult to fully describe its movement. Constructing a three-dimensional movement model can accurately model the relative position and movement relationship between people and the elevator. The horizontal and vertical projection images are an effective simplification and information extraction of three-dimensional movement in a specific direction, which is in line with the scientific principle of multi-dimensional analysis of complex movements. S22. Anomaly analysis of lateral movement of personnel is performed based on the projection images of personnel movement relative to the elevator laterally and the personnel's weight. The process of anomaly analysis of lateral movement of personnel is as follows: the area of ​​the intersection of the projection images of personnel movement laterally at adjacent time points is obtained by dividing the area of ​​the combined portion of the projection images of personnel movement laterally at the corresponding time points. The image stagnation status at the corresponding adjacent time points is obtained by subtracting the image stagnation status from 1. The lateral movement status is obtained by integrating the image movement status over time and dividing it by the duration. The weight influence of personnel is obtained based on the ratio of personnel weight to safe weight. The lateral movement influence result of the corresponding personnel is obtained by multiplying the corresponding weight influence result by the corresponding weight influence result. The lateral movement anomaly analysis is performed based on the projection images of personnel movement laterally and the weight status, comprehensively considering two key factors: personnel movement and weight. By calculating image stagnation and movement, the level of lateral movement activity of personnel can be quantified. Introducing the influence of weight further considers the different impacts that the movement of personnel of different weights may have on elevator operation. The lateral movement anomaly analysis results obtained by combining the two can more accurately determine whether the lateral movement of personnel in the elevator is abnormal, providing a more targeted reference for ensuring the safe operation of elevators. The lateral movement of personnel in the elevator will affect the balance and operational stability of the elevator, and the impact will be different for personnel of different weights under the same movement conditions. The calculation of image stagnation and movement can reflect the dynamic changes of personnel's lateral movement. The ratio of weight to safe weight can measure the potential impact of personnel weight on the elevator. Multiplying the two comprehensively considers the factors of movement and weight, which is in line with the logic of multi-factor analysis of elevator operation safety. S23. Based on the projection images of personnel movement relative to the elevator's longitudinal direction and their weight, anomaly analysis of longitudinal movement is performed. The process involves: obtaining the intersection area of ​​the projection images of personnel movement in the longitudinal direction at adjacent times, dividing it by the combined area of ​​the projection images at the corresponding times to obtain the image stagnation at those adjacent times; subtracting the image stagnation from 1 to obtain the image movement; integrating the image movement over time and dividing by the duration to obtain the longitudinal movement impact of the corresponding person; obtaining the weight impact based on the ratio of a person's weight to their safe weight; and multiplying the longitudinal movement impact result by the corresponding weight impact to obtain the longitudinal movement anomaly analysis result. This analysis of longitudinal movement projection images and weight allows for a comprehensive assessment of abnormal longitudinal movements of personnel within the elevator. By quantifying the movement of the longitudinal images and incorporating the influence of weight, the resulting longitudinal movement anomaly analysis helps to promptly detect abnormal longitudinal movements of personnel, such as sudden vertical jumps, thereby providing early warning of potential risks that may affect the safe operation of the elevator. Step S3: Assess the elevator's behavioral hazards based on the corresponding elevator operation data and the wear condition of the elevator wire rope; In this embodiment, the hazard assessment in step S3 includes the following specific steps: S31. Obtain the swaying status of the elevator in each direction, along with images of the elevator wire rope surface and the number of broken wires, comprehensively acquiring key operational status information of the elevator from multiple perspectives. The swaying status in each direction directly reflects the stability of the elevator during operation, helping to promptly detect any abnormal shaking, which may indicate problems with components such as the guide rails or suspension system. The wire rope surface image and the number of broken wires are crucial for assessing the safety performance of the wire rope. The wire rope is a critical load-bearing component in elevator operation, and its condition directly affects elevator safety. Early detection of wire rope damage helps prevent serious accidents. S32. Obtain the corresponding lateral sway amplitude and sway frequency of the elevator. Divide the lateral sway amplitude and sway frequency by the corresponding sway safety value to obtain the lateral amplitude hazard value and lateral frequency hazard value, respectively. Calculate the lateral sway hazard value and lateral frequency hazard value by weighted summation to obtain the lateral sway hazard of the elevator. This quantifies the lateral sway hazard of the elevator. By dividing the lateral sway amplitude and frequency by the safety value to obtain the hazard value, and then performing weighted summation, the impact of the two key factors of sway amplitude and frequency on elevator safety can be comprehensively considered. This allows a specific numerical value to represent the degree of danger of the elevator's lateral sway, making it easier for staff to intuitively understand the safety status of the elevator's lateral operation and take timely maintenance or repair measures. Sway amplitude and frequency are important indicators for measuring the stability of elevator lateral operation. Sway amplitude and frequency exceeding the safety value will increase the risk of elevator operation. The weighted summation method can reasonably allocate weights according to the importance of different factors on elevator safety. S33. Obtain the longitudinal sway amplitude and frequency of the corresponding elevator, and simultaneously obtain the surface image of the corresponding wire rope and the number of broken wires in the corresponding wire rope. Perform a longitudinal hazard assessment of the elevator. The longitudinal hazard assessment process includes: obtaining the longitudinal sway amplitude and frequency of the elevator; dividing the longitudinal sway amplitude and frequency by the corresponding sway safety value to obtain the longitudinal amplitude hazard value and longitudinal frequency hazard value, respectively; and weighted summing the longitudinal amplitude hazard value and longitudinal frequency hazard value to obtain the longitudinal sway hazard of the elevator; simultaneously obtaining the surface image of the corresponding wire rope and the number of broken wires in the corresponding wire rope; based on the surface image of the wire rope, the production strength of the wire rope, and the number of broken wires, obtaining the strength of the wire rope at the corresponding time using a deep learning neural network model; setting the ratio of the wire rope safety strength to the strength of the wire rope at the corresponding time as the wire rope hazard value; and weighted summing the wire rope hazard value with the longitudinal sway hazard of the elevator to obtain the longitudinal hazard of the elevator. Figure 5As shown, the specific content of the deep learning neural network model is as follows: It acquires historical images of the wire rope surface, the production strength of the wire rope, and the corresponding number of broken wires, along with the corresponding strength of the wire rope. A deep learning neural network is constructed with the wire rope surface image, production strength, and number of broken wires as input, and the wire rope strength as output. The historical data is divided into a 9:1 training set and a 15% test set. 90% of the weights and biases from the training set are input into the deep learning neural network model for training, resulting in the initial deep learning neural network model. The initial deep learning neural network model is then tested using the 10% weights and biases from the test set. Testing was conducted, and the initial deep learning neural network model output, which satisfied the maximum accuracy of the wire rope strength, was used as the deep learning neural network model. On the one hand, similar to the lateral sway assessment, the longitudinal amplitude hazard value and the longitudinal frequency hazard value were calculated and weighted to quantify the hazard of the elevator's longitudinal sway. On the other hand, the deep learning neural network model was used to assess the strength of the wire rope by combining the wire rope surface image, production intensity, and number of broken wires, thus obtaining the wire rope hazard value. Finally, the two values ​​were weighted and summed to obtain the elevator's longitudinal hazard. This comprehensive approach, taking into account the safety status of elevator operation and key components, made the assessment results more accurate and comprehensive, providing a more reliable basis for elevator safety management. Step S4: Conduct a ride matching analysis based on the results of the personnel behavior hazard assessment and the elevator behavior hazard assessment; In this embodiment, the ride matching analysis in step S4 includes the following specific contents: S41. Obtain the results of the lateral movement anomaly analysis, the results of the longitudinal movement anomaly analysis, the lateral swaying hazard of the elevator, and the longitudinal swaying hazard of the elevator, respectively. S42. By multiplying the results of the lateral movement anomaly analysis with the lateral sway hazard of the elevator, a lateral matching anomaly is obtained. By multiplying the results of the longitudinal movement anomaly analysis with the longitudinal sway 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 sway hazard in the corresponding direction, respectively, to obtain the lateral and longitudinal matching anomalies, and then weighting and summing the two to obtain the riding matching anomaly result, can comprehensively consider the lateral and longitudinal movement anomalies of the elevator as well as the sway hazard, and comprehensively and quantitatively assess the abnormal situation of elevator riding. This 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 sway situation. The calculation by combining the movement anomaly analysis results with the sway hazard conforms to the scientific principle of comprehensive assessment of elevator safety. The weighted summation method can reasonably allocate weights according to the importance of the abnormal situation in different directions on the safety of elevator riding, making the assessment results more in line with the actual situation and consistent with the industry standards and methods of elevator safety assessment. Step S5: Issue passenger travel warnings based on travel matching analysis results; including the following specific content: 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.

[0021] In this embodiment, the values ​​of weight and threshold are obtained through experiments using historical data. The specific experimental steps are as follows: obtain historical elevator operation data, elevator wire rope wear, and personnel behavior characteristics in the elevator, as well as the results of whether dangerous situations occurred in the corresponding historical scenarios. Substitute the historical elevator operation data, elevator wire rope wear, and personnel behavior characteristics in the elevator into the corresponding steps of this application to obtain the final ride matching anomaly result. Import the ride matching anomaly result and the results of whether dangerous situations occurred in the corresponding scenarios into fitting software (such as MATLAB) for data fitting iteration, and output the values ​​of the set parameters that meet the accuracy of the maximum dangerous situation occurrence. 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

[0022] 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

[0023] 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

[0024] This embodiment proposes a computer-readable storage medium on which an erasable and rewritable computer program is stored. 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.

[0025] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A 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, all or part of the processes or functions according to the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network and / or wireless network. A computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives (SSDs).

[0026] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0027] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0028] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only one method, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0029] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0030] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0031] In the description of this specification, the references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0032] The foregoing has shown and described the basic principles, main features, and advantages of this application. Those skilled in the art should understand that this application is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of this application. Various changes and modifications can be made to this application without departing from the spirit and scope thereof, and all such changes and modifications fall within the scope of this application as claimed. The scope of protection of this application is defined by the appended claims and their equivalents.

Claims

1. An elevator intelligent analysis method based on big data analysis, characterized in that, Includes the following steps: Step S1: Obtain elevator operation data, elevator wire rope wear data, and information on the behavioral characteristics of people in the elevator; Step S2: Conduct a risk assessment of personnel behavior based on the behavioral characteristics of people in the elevator and the angular characteristics of the behavioral direction relative to the elevator's direction of travel; Step S3: Assess the elevator's behavioral hazards based on the corresponding elevator operation data and the wear condition of the elevator wire rope; Step S4: Conduct a ride matching analysis based on the results of the personnel behavior hazard assessment and the elevator behavior hazard assessment; Step S5: Issue passenger travel warnings based on the travel matching analysis results.

2. The elevator intelligent analysis method based on big data analysis according to claim 1, characterized in that, The personnel behavior hazard assessment includes the following specific steps: Acquire images of people's movement behavior in the elevator, construct a 3D movement model of the elevator and people, and obtain projection images of people's movement in the horizontal direction and in the vertical direction relative to the elevator. Anomaly analysis of lateral movement of personnel is conducted based on the projected images of personnel movement relative to the elevator lateral direction and the personnel's weight. The process of anomaly analysis is as follows: the area of ​​the intersection of the lateral movement projection images of personnel at adjacent time points is obtained by dividing it by the area of ​​the combined portion of the lateral movement projection images of personnel at the corresponding time points to obtain the image stagnation at the corresponding adjacent time points. The image movement is obtained by subtracting the image stagnation by 1. The lateral movement impact of the corresponding personnel is obtained by integrating the image movement over time and dividing it by the duration. The weight impact of personnel is obtained based on the ratio of personnel weight to safe weight. The anomaly analysis result of the lateral movement impact of the corresponding personnel is obtained by multiplying the corresponding weight impact. Anomaly analysis of longitudinal movement of people is performed based on the projected images of people moving relative to the elevator longitudinally and the people's weight.

3. The elevator intelligent analysis method based on big data analysis according to claim 2, characterized in that, The risk assessment includes the following specific steps: The system obtains the swaying of the elevator in each direction, as well as the surface image of the elevator wire rope and the number of broken wires in the corresponding wire rope. Obtain the corresponding lateral sway amplitude and sway frequency of the elevator. Divide the lateral sway amplitude and sway frequency of the elevator by the corresponding sway safety value to obtain the lateral amplitude hazard value and lateral frequency hazard value respectively. Then, sum the lateral amplitude hazard value and lateral frequency hazard value by weight to obtain the lateral sway hazard of the elevator. The longitudinal sway amplitude and frequency of the corresponding elevator are obtained, along with images of the corresponding wire rope surface and the number of broken wires, to conduct a longitudinal hazard assessment of the elevator.

4. The elevator intelligent analysis method based on big data analysis according to claim 3, characterized in that, The elevator longitudinal hazard assessment process includes: acquiring the longitudinal swing amplitude and frequency of the elevator; dividing the longitudinal swing amplitude and frequency by the corresponding swing safety value to obtain the longitudinal amplitude hazard value and longitudinal frequency hazard value, respectively; and weighted summing the longitudinal amplitude hazard value and longitudinal frequency hazard value to obtain the elevator longitudinal swing hazard; simultaneously acquiring the surface image of the corresponding wire rope and the number of broken wires in the corresponding wire rope; based on the wire rope surface image, the production strength of the wire rope, and the number of broken wires, obtaining the strength of the wire rope at the corresponding time using a deep learning neural network model; setting the ratio of the wire rope's safe strength to the strength of the wire rope at the corresponding time as the wire rope hazard value; and weighted summing the wire rope hazard value with the elevator longitudinal swing hazard to obtain the elevator longitudinal hazard.

5. The elevator intelligent analysis method based on big data analysis according to claim 4, characterized in that, The ride matching analysis includes the following specific components: The results of the lateral movement anomaly analysis, the results of the longitudinal movement anomaly analysis, the lateral sway hazard of the elevator, and the longitudinal sway hazard of the elevator were obtained respectively. The lateral matching anomaly is obtained by multiplying the lateral movement anomaly analysis result with the lateral swaying hazard of the elevator, and the longitudinal matching anomaly is obtained by multiplying the longitudinal movement anomaly analysis result with the longitudinal swaying hazard of the elevator. The lateral matching anomaly result and the longitudinal matching anomaly result are then weighted and summed to obtain the riding matching anomaly result.

6. The elevator intelligent analysis method based on big data analysis according to claim 5, characterized in that, The passenger travel warning includes the following specific details: 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.

7. The elevator intelligent analysis method based on big data analysis according to claim 6, characterized in that, The data includes the swaying in each direction during elevator operation, the safe swaying amplitude and frequency set at the factory, and the wear of the elevator wire rope. The machine vision module acquires images of the wire rope surface during its lifting process to identify the surface image and the number of broken wires. The human behavior characteristics in the elevator include the movement and weight of the people in the elevator. The movement behavior data is acquired by a corresponding video acquisition module, which captures images of the movement behavior of the people in the elevator, and the acquired data is stored in real time in the corresponding storage component.

8. An elevator intelligent analysis system based on big data analytics, used to implement the elevator intelligent analysis method based on big data analytics as described in any one of claims 1-7, characterized in that, The system includes: The data acquisition module acquires data on elevator operation, elevator wire rope wear, and the behavioral characteristics of people in the elevator. 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. 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. The ride matching analysis module performs ride matching analysis based on the results of personnel behavior risk assessment and elevator behavior risk assessment. The verification and processing module issues passenger travel warnings based on the travel matching analysis results.

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

Images