Elevator health state assessment method, device and equipment and storage medium
Through multi-dimensional evaluation and intelligent decision-making, combined with expert rules, machine learning and artificial intelligence, the problem of single dimensions of elevator health assessment is solved, the comprehensive evaluation of elevator health status and the scientific setting of maintenance cycle are achieved, and maintenance is improved The accuracy and timeliness of the work.
Patent Information
- Application Number
- CN202411435416.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-14
- Publication Date
- 2024-11-26
AI Technical Summary
The existing elevator health assessment technology has a single evaluation dimension and is difficult to comprehensively and accurately reflect the true health status of the elevator, resulting in a lack of targeted and effective maintenance strategies.
By building a multi-dimensional elevator health status assessment system, data on various indicator dimensions of the elevator are obtained, and analysis is used using expert rules engines, machine learning models and artificial intelligence algorithms to comprehensively evaluate the health status of the elevator, and maintenance period is determined based on the scoring results.
It has achieved a comprehensive and accurate assessment of the health status of the elevator, dynamically adjusted the maintenance cycle, improved the accuracy and timeliness of maintenance work, and provided a clear maintenance basis for elevator managers.
Smart Images

Figure CN119018738A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent supervision technology, and in particular to an elevator health status assessment method, device, equipment and storage medium. Background Art
[0002] With the acceleration of urbanization, high-rise buildings are increasing day by day. As a vertical transportation tool, the safety, reliability and operating efficiency of elevators are directly related to people's daily life quality and public safety. Therefore, real-time monitoring and evaluation of the health status of elevators, timely detection of potential faults, and formulation of scientific and reasonable maintenance strategies have become important issues that need to be urgently addressed in the elevator industry.
[0003] The current elevator health assessment technology has the problem of a single assessment dimension, and most assessment methods only focus on certain specific aspects of the elevator. This one-sided assessment method is difficult to fully and accurately reflect the true health status of the elevator, resulting in the lack of pertinence and effectiveness in the formulation of maintenance strategies.
[0004] Therefore, how to provide a system that can comprehensively and accurately evaluate the health of elevators to achieve reasonable maintenance of elevators is a technical problem that needs to be solved urgently. Summary of the invention
[0005] In view of this, the present application provides an elevator health status assessment method, device, equipment and storage medium, aiming to achieve accurate assessment of the elevator health status by constructing a comprehensive, multi-dimensional assessment system.
[0006] In a first aspect, the present application provides a method for evaluating the health status of an elevator, the method comprising:
[0007] Acquire data corresponding to each indicator dimension of the elevator, wherein the indicator dimension includes an indicator dimension representing an elevator health baseline and an indicator dimension representing an elevator health dynamic, wherein the indicator dimension representing an elevator health baseline includes indicators corresponding to each component of the elevator, and the indicator dimension representing an elevator health dynamic includes a fault feedback indicator dimension, a maintenance quality indicator dimension, a real-time operation indicator dimension, and an overall loss indicator dimension;
[0008] According to the data corresponding to each indicator dimension of the elevator, the data corresponding to each indicator dimension of the elevator is analyzed using an elevator health evaluation model to obtain a health status score result of each indicator dimension; the elevator health evaluation model includes one or more of an expert rule engine, a machine learning model and an artificial intelligence algorithm;
[0009] The health status score results of each indicator dimension are weighted to obtain the overall health score of the elevator;
[0010] The maintenance period of the elevator is determined according to the overall health score.
[0011] Optionally, the health status score result of the indicator dimension representing the elevator health baseline is obtained by:
[0012] Obtaining inspection data of each component of the elevator, wherein each component of the elevator at least includes a traction machine component, a wire rope component, a control cabinet, a car, a floor car door device, a guide rail guide shoe, a safety clamp and a speed limiter;
[0013] Analyzing the inspection data using an expert rule engine to obtain a health status score result of each component of the elevator; the expert rule engine includes a pre-set rule set for identifying the health status of each component;
[0014] Based on the health status scoring results of the elevator components, the health status scoring results of the indicator dimensions of the elevator health baseline are obtained.
[0015] Optionally, the elevator components also include a guide wheel and a return rope wheel, a counterweight and a counterweight frame, a compensation device, a traveling cable and a buffer.
[0016] Optionally, obtaining the health status scoring result of the indicator dimension of the elevator health baseline based on the health status scoring result of each component of the elevator includes:
[0017] Presetting a health score weight for each component of the elevator;
[0018] Based on the preset health score weights of the elevator components and the health status score results of the elevator components, the health status score results of the indicator dimensions of the elevator health baseline are obtained.
[0019] Optionally, the health status score result of the indicator dimension characterizing the dynamic health of the elevator is obtained by:
[0020] For the fault feedback index, the fault data of the elevator is obtained through the Internet of Things device, and the fault data is analyzed by the expert rule engine to obtain the fault type, and the fault type is classified according to the fault type to obtain the health status score result of the fault feedback index dimension;
[0021] For the maintenance quality index, the maintenance records and preset maintenance standards are obtained, and the maintenance items, maintenance dates and single maintenance duration are scored using a machine learning model to obtain the health status score results of the maintenance quality index dimension; the maintenance records include maintenance items, maintenance dates and single maintenance duration;
[0022] For real-time operation indicators, the elevator operation status data is obtained through the IoT devices and surveillance cameras on the elevator. According to the operation status data, the data features are extracted using the signal decomposition algorithm, and the health status score results of the real-time operation indicator dimension are obtained through the degradation model; the degradation model is pre-built based on the historical operation status data of each component; the elevator operation status data at least includes vibration, operation speed, and noise simulation data;
[0023] For the overall loss index, the operating years, average daily operating times and operating duration of the elevator are obtained, and the loss curve is fitted based on the operating years, average daily operating times and operating duration of the elevator based on artificial intelligence to obtain the health status score result of the overall loss index dimension.
[0024] Optionally, the method further comprises:
[0025] The maintenance strategy of the elevator is determined according to the health status score result corresponding to any indicator dimension of each indicator dimension.
[0026] Optionally, the weight value of the weighted processing is calculated based on an entropy method or a hierarchical analysis method;
[0027] Among them, when the entropy method is used, the weight of each indicator is obtained, and the weight of each target indicator is positively correlated with the influence of each target indicator on the health score;
[0028] or,
[0029] When using the hierarchical analysis method, the weight of each indicator is obtained, and its weight value is determined according to the degree of influence of each target indicator on the health score.
[0030] In a second aspect, the present application provides an elevator health status assessment device, the device comprising:
[0031] An acquisition module, used to acquire data corresponding to each indicator dimension of the elevator, wherein the indicator dimension includes an indicator dimension representing an elevator health baseline and an indicator dimension representing an elevator health dynamic. The indicator dimension representing an elevator health baseline includes indicators corresponding to each component of the elevator, and the indicator dimension representing an elevator health dynamic includes a fault feedback indicator dimension, a maintenance quality indicator dimension, a real-time operation indicator dimension, and an overall loss indicator dimension;
[0032] An acquisition module is used to analyze the data corresponding to each indicator dimension of the elevator using an elevator health evaluation model according to the data corresponding to each indicator dimension of the elevator, so as to obtain a health status score result of each indicator dimension; the elevator health evaluation model includes one or more of an expert rule engine, a machine learning model and an artificial intelligence algorithm;
[0033] A scoring module is used to perform weighted processing on the health status scoring results of each indicator dimension to obtain an overall health score of the elevator;
[0034] The determination module is used to determine the maintenance period of the elevator according to the overall health score.
[0035] In a third aspect, the present application provides a device, comprising a memory and a processor, wherein the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device executes the elevator health status assessment method described in any one of the first aspects above.
[0036] In a fourth aspect, the present application provides a computer storage medium having codes stored therein. When the codes are executed, a device executing the codes implements the elevator health status assessment method described in any one of the first aspects above.
[0037] The present application provides a method for evaluating the health status of an elevator. The method includes: obtaining data corresponding to each indicator dimension of the elevator, the indicator dimension includes an indicator dimension that characterizes the baseline of the elevator health and an indicator dimension that characterizes the dynamics of the elevator health, the indicator dimension that characterizes the baseline of the elevator health includes indicators corresponding to each component of the elevator, and the indicator dimension that characterizes the dynamics of the elevator health includes a fault feedback indicator dimension, a maintenance quality indicator dimension, a real-time operation indicator dimension, and an overall loss indicator dimension; according to the data corresponding to each indicator dimension of the elevator, the elevator health evaluation model is used to analyze the data corresponding to each indicator dimension of the elevator to obtain the health status score results of each indicator dimension; the elevator health evaluation model includes one or more of an expert rule engine, a machine learning model, and an artificial intelligence algorithm; the health status score results of each indicator dimension are weighted to obtain the overall health score of the elevator; according to the overall health score, the maintenance cycle of the elevator is determined. In this way, by comprehensively using multi-dimensional evaluation, intelligent decision-making, and dynamic adjustment of the maintenance cycle, the evaluation of the health status of the elevator is more comprehensive and accurate, and the maintenance cycle of the elevator is determined according to the health score, which provides a clear and definite maintenance basis for elevator managers, making the maintenance work more accurate and timely. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] In order to more clearly illustrate the technical solutions in this embodiment or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0039] Figure 1 A method flow chart of an elevator health status assessment method provided in an embodiment of the present application;
[0040] Figure 2 A flowchart of a possible implementation method of step S102 provided in an embodiment of the present application;
[0041] Figure 3 A schematic diagram of elevator level division is provided for an embodiment of the present application;
[0042] Figure 4 A flowchart of another possible implementation method of step S102 provided in an embodiment of the present application;
[0043] Figure 5a An elevator health model provided in an embodiment of the present application;
[0044] Figure 5b A schematic diagram of an application of an elevator health status assessment method provided in an embodiment of the present application;
[0045] Figure 6 A schematic diagram of the structure of an elevator health status assessment device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0046] Current elevator health assessment technologies generally face the problem of a single assessment dimension. Most assessment methods only focus on certain specific aspects of the elevator, such as physical parameters during operation (vibration, temperature, humidity, etc.), while ignoring the actual operating status of other core components within the elevator system (such as traction machines, wire ropes, etc.), as well as the impact of the elevator's historical operating data (such as operating years, number of operations, operating hours, etc.) and external factors (such as use environment, maintenance management, etc.) on the health of the elevator. This one-sided assessment method is difficult to fully and accurately reflect the true health status of the elevator, which may lead to the lack of pertinence and effectiveness in the formulation of maintenance strategies.
[0047] In view of this, the present application provides a method for evaluating the health status of an elevator. It includes: obtaining data corresponding to each indicator dimension of the elevator, the indicator dimension includes an indicator dimension that characterizes the baseline of the elevator health and an indicator dimension that characterizes the dynamics of the elevator health, the indicator dimension that characterizes the baseline of the elevator health includes indicators corresponding to each component of the elevator, and the indicator dimension that characterizes the dynamics of the elevator health includes a fault feedback indicator dimension, a maintenance quality indicator dimension, a real-time operation indicator dimension, and an overall loss indicator dimension; according to the data corresponding to each indicator dimension of the elevator, using the elevator health evaluation model to analyze the data corresponding to each indicator dimension of the elevator, and obtain the health status score results of each indicator dimension; the elevator health evaluation model includes one or more of an expert rule engine, a machine learning model, and an artificial intelligence algorithm; weighting the health status score results of each indicator dimension to obtain the overall health score of the elevator; and determining the maintenance cycle of the elevator according to the overall health score.
[0048] In this way, by comprehensively using multi-dimensional evaluation, intelligent decision-making and dynamic adjustment of maintenance cycles, the assessment of the health status of the elevator is more comprehensive and accurate, and the maintenance cycle of the elevator is determined according to the health score, providing elevator managers with a clear and definite maintenance basis, making maintenance work more accurate and timely.
[0049] It should be noted that the embodiments of the present application do not limit the execution subject of the elevator health status assessment. For example, the method of the embodiments of the present application can be applied to data processing devices such as terminal devices or servers. The terminal device can be a smart phone, a computer, a personal digital assistant (PDA) or a tablet computer. The server can be an independent server, a cluster server or a cloud server.
[0050] In order to be able to understand the characteristics and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0051] Figure 1 A method flow chart of the elevator health status assessment method provided in the embodiment of the present application, see Figure 1 The elevator health status assessment method provided in the embodiment of the present application may include:
[0052] S101, obtaining data corresponding to each indicator dimension of the elevator.
[0053] In this embodiment, various data required by the elevator in the health status assessment process are first collected. These data cover the indicator dimensions that characterize the elevator health baseline and the indicator dimensions that characterize the elevator health dynamics. Among them, the indicator dimensions that characterize the elevator health baseline include the indicators corresponding to each component of the elevator, and the indicator dimensions that characterize the elevator health dynamics include the fault feedback indicator dimension, the maintenance quality indicator dimension, the real-time operation indicator dimension, and the overall loss indicator dimension.
[0054] Specifically, the indicators corresponding to each component of the elevator usually reflect the basic performance and status of each key component of the elevator (such as traction system, control system, door system, safety device, etc.). The data source may include the design parameters of the elevator, the technical specifications provided by the manufacturer, historical maintenance records, and direct inspection of the status of elevator components.
[0055] S102, analyzing the data corresponding to each indicator dimension of the elevator using an elevator health evaluation model according to the data corresponding to each indicator dimension of the elevator to obtain a health status score result of each indicator dimension.
[0056] In this embodiment, the collected data will be input into the elevator health assessment model for analysis and processing. The elevator health assessment model is a comprehensive platform that integrates expert rule engines, machine learning models, and artificial intelligence algorithms, and can automatically complete tasks such as data analysis, health status scoring, and decision-making recommendation generation. That is, the elevator health assessment model includes one or more of the expert rule engines, machine learning models, and artificial intelligence algorithms.
[0057] Specifically, first, the data is cleaned and preprocessed, including noise removal, missing value filling, data standardization and other steps to ensure the accuracy and consistency of the data. Key features are extracted from the preprocessed data, which will be used for subsequent health status scoring and model training.
[0058] Taking into account that different indicators correspond to different data features, in this embodiment, since the elevator health assessment model integrates an expert rule engine, a machine learning model, and an artificial intelligence algorithm, different indicators can be analyzed in different ways.
[0059] Among them, the expert rule engine refers to the use of the knowledge and experience of domain experts to build a series of rules to evaluate the health status of elevators. These rules may be based on specific thresholds (such as failures exceeding a certain value are considered unhealthy), logical relationships (such as failures of multiple components at the same time indicate that there is a problem with the system), etc.
[0060] Machine learning models refer to the use of machine learning models to make predictions for situations that are difficult to judge with simple rules. Common models include regression models (used to predict continuous health scores), classification models (classifying elevator status into categories such as healthy, sub-healthy, and unhealthy), etc. Training these models requires a large amount of historical data and labels, as well as appropriate model tuning strategies.
[0061] Artificial intelligence algorithms refer to the use of more advanced artificial intelligence technologies, such as deep learning, reinforcement learning, etc., to handle complex elevator health assessment problems. These algorithms can automatically learn complex patterns from data and make more accurate predictions.
[0062] It should be noted that, in order to improve the accuracy of the assessment, the results of expert rules, machine learning models and artificial intelligence algorithms can be integrated. For example, expert rules can be used for preliminary screening, and then machine learning models can be used for fine-grained evaluation, and finally the optimization suggestions of artificial intelligence algorithms can be combined to obtain the final health status score. This application does not limit this.
[0063] In this embodiment, a clear evaluation report is provided to explain the scoring basis of each indicator dimension and the judgment logic of the overall health status, so that elevator managers and maintenance personnel can understand and take corresponding measures.
[0064] In an alternative embodiment, Figure 2 A possible implementation flow chart of step S102 provided in an embodiment of the present application. Figure 2 As shown, the health status score result of the indicator dimension characterizing the elevator health baseline provided in the embodiment of the present application is obtained by the following method:
[0065] S1021, obtaining inspection data of each component of the elevator.
[0066] In this embodiment, the elevator includes multiple components, including core components and non-core components. When evaluating the elevator, the health status of the core components can be considered, that is, the elevator components at least include the traction machine component, the wire rope component, the control cabinet, the car, the floor car door device, the guide rail guide shoe, the safety clamp and the speed limiter. In an optional embodiment, the non-core components of the elevator can also be comprehensively considered, that is, the elevator components can also include components such as the guide wheel and the anti-ropes wheel, the counterweight and the counterweight frame, the compensation device, the accompanying cable and the buffer. Figure 3 A schematic diagram of elevator level division is provided for an embodiment of the present application. Figure 3 As shown, the elevator can be pre-divided into hierarchical components and parts according to the structure of the elevator. For example, core component 1 is a traction machine component, and the corresponding parts include a traction machine, a traction wheel, etc. It should be noted that the above hierarchical division can also be applied to other indicators.
[0067] The inspection data of each component of the elevator can be obtained by the elevator inspector carrying necessary tools, such as EVA vibration tester (for measuring vibration), infrared thermometer (for detecting temperature abnormalities), illuminance meter (for evaluating lighting conditions), vernier caliper (for measuring size and degree of wear), etc., and going to the elevator site for inspection.
[0068] Specifically, according to the requirements of the parts inspection method, the elevator inspectors use tools to inspect the elevator's core components such as the traction machine assembly, wire rope assembly, control cabinet, car, floor door device, guide rail guide shoe, safety clamp and speed limiter one by one. The inspection content includes but is not limited to vibration level, temperature, degree of wear, functional integrity, etc. The data obtained during the inspection process shall be recorded in detail, including analog data (such as vibration value, temperature value) and observation results (such as wear condition, whether the function is normal). It should be noted that the above tools can be networked devices, and the above data can be uploaded via the Internet.
[0069] S1022, analyzing the inspection data using an expert rule engine to obtain health status scoring results of each component of the elevator.
[0070] In this embodiment, the expert rule engine includes a pre-set rule set for identifying the health status of each component. Table 1 is a rule set comparison table provided in the embodiment of the present application.
[0071] Table 1
[0072]
[0073]
[0074]
[0075] Combined with the above table, the rule set involves multiple aspects such as vibration threshold, temperature range, wear standard, etc. The collected inspection data is compared with the conditions in the rule set, and the health status of each component is judged based on the matching results. For example, if the vibration value of the traction machine exceeds the set threshold, it may be judged as unhealthy. Based on the health status of the component, a health status score is generated for each component using a preset scoring mechanism. The score may be in a percentage system, a graded system, or other forms to intuitively reflect the health of the component.
[0076] S1023, based on the health status scoring results of the elevator components, obtain the health status scoring results of the indicator dimensions of the elevator health baseline.
[0077] In an optional embodiment, obtaining the health status scoring results of the indicator dimensions of the elevator health baseline based on the health status scoring results of each component of the elevator may include: presetting the health scoring weights for each component of the elevator; and obtaining the health status scoring results of the indicator dimensions of the elevator health baseline based on the preset health scoring weights of each component of the elevator and the health status scoring results of each component of the elevator.
[0078] In this embodiment, different weights are assigned to each component according to its importance and influence on the overall operation of the elevator. For example, core components such as traction machines and control cabinets may have higher weights. The health status score of each component is multiplied by its corresponding weight, and then summed to obtain a comprehensive score of the elevator in the health baseline indicator dimension. This score reflects the overall health of the elevator in the baseline state.
[0079] In an optional embodiment, in addition to outputting the comprehensive scoring result, the detailed scores and rectification suggestions of each component can also be integrated and output to provide decision support for elevator managers and maintenance personnel. Table 2 is a comprehensive scoring result table provided in an embodiment of the present application.
[0080] Table 2
[0081]
[0082]
[0083] In this embodiment, when the insurance industry insures an elevator, the elevator health assessment of the related technology usually obtains the current status of the elevator from the original data of the elevator or infers from a single dimension, and then performs insurance and monitoring of subsequent insurance items. However, the current status of the elevator obtained from the original data of the elevator or inferred from a single dimension is not accurate enough to clarify the actual health of the current elevator. Therefore, the embodiment of the present application introduces an indicator dimension that characterizes the health baseline of the elevator to obtain a health status scoring result that characterizes the health baseline of the elevator, scores the actual status of the current elevator to obtain the basic status of the current elevator, and the health assessment method established in combination with the indicator dimension that characterizes the health baseline of the elevator can make subsequent monitoring of subsequent elevators more accurate.
[0084] S103, weighting the health status score results of each indicator dimension to obtain the overall health score of the elevator.
[0085] In this embodiment, weighted processing means that when calculating the comprehensive score, different weights are given according to the importance or influence of each indicator dimension. This is because in actual applications, different indicator dimensions may have different degrees of influence on the overall health status of the elevator. For example, the status of the core components of the elevator may have a greater impact on the health of the elevator than the maintenance quality or real-time operation data.
[0086] Once the weights of each indicator dimension are determined, first, the individual health status scores of each indicator dimension are obtained according to the analysis results of the elevator health assessment model in step S102. Then, each individual score is multiplied by its corresponding weight to obtain a weighted score. This step ensures that the contribution of different indicator dimensions in the overall score matches their importance. Finally, all weighted scores are added together to obtain the overall health score of the elevator. This score is a quantitative result that integrates all indicator dimension information and can fully reflect the health status of the elevator.
[0087] The overall health score formula provided in the embodiment of the present application is as follows:
[0088]
[0089] Among them, q i is the corresponding indicator weight, g i is the corresponding indicator health status scoring result, and i represents the indicator dimension. The embodiment of the present application may include 5 indicator dimensions, specifically an indicator dimension characterizing the elevator health baseline and an indicator dimension characterizing the elevator health dynamics, wherein the indicator dimension characterizing the elevator health dynamics specifically includes a fault feedback indicator dimension, a maintenance quality indicator dimension, a real-time operation indicator dimension, and an overall loss indicator dimension.
[0090] In an optional embodiment, the weight value of the weighted processing can be calculated in a variety of ways. The weight value of the weighted processing provided in the embodiment of the present application is calculated based on the entropy method or the hierarchical analysis method.
[0091] Among them, when the entropy method is used, the weight of each indicator is obtained, and the weight of each target indicator is positively correlated with the degree of influence of each target indicator on the health score; or, when the hierarchical analysis method is used, the weight of each indicator is obtained, and its weight value is determined according to the degree of influence of each target indicator on the health score.
[0092] Specifically, the following five indicators are assumed: an indicator characterizing the elevator health baseline, a fault feedback indicator, a maintenance quality indicator, a real-time operation indicator, and an overall loss indicator.
[0093] Using the entropy method, the original data of each indicator is standardized, and for each indicator, the entropy value e is calculated. j , the entropy value indicates the discreteness of the data. Based on the entropy value, the information entropy weight w of each indicator is calculated. j As the corresponding indicator weight. The larger the weight, the greater the impact of the indicator on the health score. Multiply the score of each indicator by its corresponding weight, and then sum them up to get the overall health score of the elevator.
[0094] In this embodiment, the entropy method determines the weights based on the information content of the data itself, avoiding the influence of subjective judgment and making the determination of the weights more objective and fair.
[0095] The hierarchical analysis method is used to determine the hierarchical relationship between the indicators. According to the expert judgment, a pairwise comparison matrix between the indicators is constructed. Based on the pairwise comparison matrix, the weight vector of each indicator is obtained by solving the eigenvalue and eigenvector. A consistency ratio test is performed to ensure the consistency of the comparison matrix. The score of each indicator is multiplied by its corresponding weight, and then summed to obtain the overall health score of the elevator.
[0096] In this embodiment, the hierarchical analysis method constructs a hierarchical relationship between indicators, ensures the logic and structure between indicators, provides a clear decision-making process and result explanation through pairwise comparison matrix and consistency test, and the hierarchical analysis method can adjust the importance of indicators according to actual conditions, making the evaluation closer to actual needs.
[0097] S104, determining the maintenance period of the elevator according to the overall health score.
[0098] In this embodiment, first, the overall health score of the elevator is obtained from step S103. This score is a weighted result that combines various indicator dimensions of the elevator (including baseline indicators and dynamic indicators) and can fully reflect the current health status of the elevator.
[0099] Next, the obtained overall health score can be compared with the preset maintenance cycle standards. These standards are usually based on the best practices, safety regulations and recommendations of the elevator industry, and are designed to ensure that the elevator is properly maintained in different health states. Based on the comparison results, the maintenance cycle of the elevator is determined.
[0100] In an optional embodiment, the maintenance period is set according to the following principles:
[0101] Health score below 60 points: It means that the health status of the elevator is not up to standard, there are major safety hazards or performance problems, and the maintenance cycle needs to be shortened to strengthen monitoring and maintenance. Therefore, the maintenance cycle is adjusted to once every 10 days.
[0102] Health score 60 to 80 points: The health status of the elevator is acceptable, but there is still room for improvement. Maintenance is carried out according to normal standards, that is, maintenance is carried out every 15 days.
[0103] Health score of 80-90 points: indicates that the elevator is in good health, stable operation and reliable performance. The maintenance cycle can be appropriately extended to reduce maintenance costs while keeping the elevator in good condition. Therefore, the maintenance cycle is adjusted to once every 30 days.
[0104] Health score of 90 points or above: indicates that the elevator is in excellent health and requires little intervention. In order to further optimize maintenance costs, the maintenance cycle can be further extended to once every 45 days.
[0105] Finally, the corresponding maintenance plan can also be output according to the determined maintenance cycle. This plan can include the specific time, content, responsible person and other information of each maintenance to ensure the smooth progress of the maintenance work. Through step S104, the maintenance cycle of the elevator is set scientifically and reasonably, which not only ensures the safe operation of the elevator, but also optimizes the maintenance cost. At the same time, this step also provides a clear guiding direction for subsequent maintenance work. It should be noted that the above specific scores and maintenance cycle time are only used as exemplary explanations. In the actual application process, the specific values may be adjusted according to the actual situation. In addition, the above scores can also be expressed by other parameters, such as S or excellent, A or good, B or general, C or poor, etc.
[0106] In an optional embodiment, the method further includes: determining a maintenance strategy for the elevator according to a health status score result corresponding to any indicator dimension of each indicator dimension.
[0107] In the evaluation of elevator health status, multiple indicator dimensions are usually considered, such as the indicator dimension that represents the elevator health baseline, the fault feedback indicator dimension, the maintenance quality indicator dimension, the real-time operation indicator dimension, and the overall loss indicator dimension. Each indicator dimension will calculate a health status score based on its corresponding evaluation criteria and data. These scores reflect the health status of the elevator in different aspects.
[0108] In this embodiment, in addition to comprehensively considering these scores, it is also possible to pay special attention to the problematic parts in any indicator dimension to determine the maintenance strategy of the elevator. For example: if the health status score of a certain indicator dimension is much lower than that of other dimensions, it means that there may be more serious problems in this dimension, so maintenance and maintenance need to be given priority. According to the scoring results, specific maintenance measures can be formulated. For example, if the electrical system scores low, it may be necessary to check the circuit, replace aging electrical components, or debug and optimize the system. Through regular health status assessments, potential problems of the elevator can be predicted, and preventive maintenance measures can be taken in advance to avoid failures and improve the reliability and safety of the elevator's operation. During the execution of the maintenance strategy, feedback information can be continuously collected, and the strategy can be adjusted and optimized according to actual conditions to ensure continuous improvement of maintenance work and continuous improvement of the health status of the elevator.
[0109] In this way, by comprehensively using multi-dimensional evaluation, intelligent decision-making and dynamic adjustment of maintenance cycles, the assessment of the health status of the elevator is more comprehensive and accurate, and the maintenance cycle of the elevator is determined according to the health score, providing elevator managers with a clear and definite maintenance basis, making maintenance work more accurate and timely.
[0110] In the embodiment of the present application, the above Figure 1 There are multiple possible implementations of step S102, which are described below. It should be noted that the implementations described below are only exemplary and do not represent all implementations of the embodiments of the present application.
[0111] Figure 4 A flowchart of another possible implementation method of step S102 provided in an embodiment of the present application. Figure 4 As shown, the health status score results of the indicator dimension that characterizes the dynamic health of the elevator are obtained in the following way:
[0112] S1024, for the fault feedback index, the fault data of the elevator is obtained through the Internet of Things device, the fault data is analyzed by the expert rule engine to obtain the fault type, and the fault type is classified according to the fault type to obtain the health status score result of the fault feedback index dimension.
[0113] In this embodiment, the operation status of the elevator is monitored in real time through IoT devices installed in the elevator system (such as sensors, surveillance cameras, data acquisition modules in the control cabinet, etc.). These devices can capture various parameters in the operation of the elevator, including but not limited to speed, acceleration, current, voltage, temperature, switch status, etc., as well as fault codes generated by the control cabinet and control board. Once an abnormality or failure occurs in the elevator, the IoT device will immediately capture the relevant data and prepare for subsequent processing.
[0114] After the fault data is acquired, it is transferred to the expert rule engine for processing. The expert rule engine is a software system that integrates industry expert knowledge, historical fault cases, and statistical analysis methods. It can analyze the received fault data according to a preset set of rules (these rules are usually based on the best practices of elevator maintenance, the manufacturer's recommendations, and the accumulated experience in actual operation). The purpose of this step is to identify specific fault types, such as door system failure, control system failure, motor failure, guide rail failure, etc.
[0115] After identifying the fault type, the expert rule engine will classify the fault according to factors such as the severity of the fault, the scope of impact, and the difficulty of repair. Generally, faults can be divided into several levels, such as minor faults (which do not affect the safe use of the elevator, but may affect the comfort of passengers), general faults (which need to be repaired in time to avoid affecting the normal operation of the elevator), major faults (which may cause the elevator to stop operating and affect safety), etc. The classification standards can be adjusted according to the specific elevator model, usage environment, and the actual situation of the maintenance team.
[0116] Based on the fault type and classification results, the expert rule engine calculates a health score for the fault feedback indicator dimension. This score is usually a numerical value that quantifies the health of the elevator in the current fault state. The score may vary depending on the fault level. For example, a minor fault may only slightly affect the score, while a major fault may cause a significant drop in the score.
[0117] In addition, based on the fault type and classification, the expert rule engine will also provide corresponding maintenance suggestions and solutions to help the maintenance team quickly locate the problem and take appropriate repair measures. These suggestions and solutions may involve specific operating steps, required tools or spare parts, and safety precautions.
[0118] S1025, for the maintenance quality index, obtain the maintenance records and preset maintenance standards, use the machine learning model to score the maintenance items, maintenance dates and single maintenance duration, and obtain the health status score results of the maintenance quality index dimension.
[0119] In this embodiment, the maintenance records of the elevator are collected, which generally include the maintenance time interval, the single maintenance duration, the maintenance date and the corresponding maintenance items. At the same time, the system also needs a set of preset maintenance standards, which are formulated based on the elevator manufacturer's recommendations, industry specifications, safety regulations and maintenance practice experience to measure the quality and compliance of maintenance work.
[0120] Before inputting maintenance records and preset standards into the machine learning model, data preprocessing is required. This includes cleaning data (removing duplicate, erroneous or inconsistent records), formatting data (ensuring that the data format meets the model input requirements), and possible feature engineering (extracting features that are useful for evaluating maintenance quality, such as the complexity of maintenance items, the rationality of maintenance time, etc.).
[0121] Next, the preprocessed maintenance data is scored using the trained machine learning model. This model may be based on supervised learning. It has been trained on a data set containing known maintenance quality labels and has learned how to infer the quality of maintenance from features such as maintenance items, maintenance dates, and single maintenance duration. It should be noted that the specific type of model can be selected according to actual conditions, such as decision trees, random forests, gradient boosting machines (such as XGBoost, LightGBM), or neural networks. These models can capture complex patterns and relationships in maintenance data and give quantitative scores for maintenance quality based on them.
[0122] The score given by the model represents the quantitative result of the maintenance quality. Based on this score, the health status of the maintenance quality indicator dimension can be further evaluated. The health status can be a continuous value (such as a score from 0 to 100) or a level based on a certain threshold (such as excellent, good, average, poor, and very poor).
[0123] In addition to providing maintenance quality scores, the system can also provide corresponding rectification suggestions based on the model's analysis results. These suggestions may include adjusting maintenance intervals, optimizing maintenance items, and strengthening maintenance personnel training, etc., aiming to help the maintenance team improve maintenance quality, reduce elevator failures, and improve elevator reliability and economic benefits.
[0124] S1026, for real-time operation indicators, the elevator operation status data is obtained through the Internet of Things devices and monitoring cameras on the elevator. Based on the operation status data, the data features are extracted using the signal decomposition algorithm, and the health status score results of the real-time operation indicator dimension are obtained through the degradation model.
[0125] In this embodiment, the degradation model is pre-constructed based on the historical operating status data of each component; the elevator operating status data at least includes vibration, operating speed, and noise simulation data.
[0126] Specifically, first, high-precision sensors and surveillance cameras are placed on the key core components of the elevator (such as the car, traction machine, control system, etc.). These sensors can measure and collect various analog data during the operation of the elevator in real time, including but not limited to:
[0127] Vibration of the car: an important indicator that reflects the smoothness of the elevator's operation. Abnormal vibration may indicate problems such as uneven guide rails and worn bearings. Response time: refers to the time from when the elevator responds to a passenger's call to when it starts moving. It is a key parameter for evaluating the elevator's response speed. Vibration of the traction machine: the traction machine is the power source of the elevator, and its vibration directly affects the elevator's operating stability and safety. Temperature rise: the traction machine, motor and other components will generate heat during operation. Excessive temperature rise may cause malfunctions or safety hazards. Operating speed: The elevator's operating speed must be kept within a safe range. Too fast or too slow may affect the comfort and safety of passengers. Noise: The noise level of the elevator during operation is also one of the important indicators for evaluating its operating status.
[0128] Since the collected raw data often contains noise and interference signals, filtering and isolation processing is required to improve the accuracy and reliability of the data. Next, the processed data is deeply analyzed using the signal decomposition algorithm embedded in the model (such as wavelet transform, empirical mode decomposition, etc.) to extract key features that can reflect the health status of the core components of the elevator. These features may include vibration frequency, amplitude, waveform changes, noise spectrum, etc.
[0129] Specifically, a degradation model can be pre-built based on the historical operating status data of each component. A degradation model is a mathematical model that describes the gradual degradation of component performance over time or as operating conditions change. By comparing current operating data with historical data, the degree of component degradation can be evaluated and its future performance can be predicted. The construction of a degradation model requires comprehensive consideration of multiple factors, such as the material, design, use environment, and maintenance status of the component.
[0130] Compare the real-time operation data with the degradation model to analyze the health status of each core component. According to the degree of degradation, the corresponding health status assessment results are given and converted into specific scoring values. The scoring value can be a continuous numerical range (such as 0-100 points) or a graded classification based on certain standards (such as excellent, good, medium, and poor).
[0131] In this embodiment, the real-time monitoring of the elevator operation status is achieved through IoT devices and surveillance cameras, and the health status score results are promptly fed back to the management personnel or maintenance team. Once an abnormality or potential problem is found, the system can immediately issue an alarm to remind relevant personnel to take necessary measures to deal with it, thereby ensuring the safe and reliable operation of the elevator.
[0132] S1027, for the overall loss index, obtain the operating years, average daily operating times and operating duration of the elevator, and fit the loss curve based on the operating years, average daily operating times and operating duration of the elevator based on artificial intelligence to obtain the health status score result of the overall loss index dimension.
[0133] In this embodiment, the key to the overall loss index is to quantify the performance degradation of the elevator due to mechanical wear and electrical loss during long-term use and associate it with the health score. This process not only relies on traditional expert experience, but also combines artificial intelligence methods, especially through data-driven models to more accurately evaluate the overall loss status of the elevator.
[0134] Specifically, first of all, it is necessary to collect key operating data of the elevator, including: service life: the number of years the elevator has been in use since its installation, which is an important indicator for evaluating the aging of the elevator; average daily operating time: the total average operating time of the elevator every day, reflecting the frequency of use and load of the elevator; average daily operating times: the average number of times the elevator is used every day, which is also used to evaluate the activity and potential wear of the elevator. These data can be obtained through various channels such as elevator management systems, IoT devices or maintenance records.
[0135] Based on the collected data, artificial intelligence technology is used to fit the loss curve. This process can use a variety of algorithms, such as using the least squares method for curve fitting. The least squares method is a mathematical optimization technique that finds the best function match for the data by minimizing the sum of squared errors.
[0136] Specifically, based on the physical characteristics of elevator loss and expert experience, a suitable mathematical model is selected to describe the relationship between elevator loss and operating years, average daily operating hours, and average daily operating times. This model may be a multivariate linear regression model, a polynomial regression model, or a more complex nonlinear model. Using the least squares method, the model parameters are estimated based on the collected data so that the sum of squared errors between the model prediction value and the actual observed value is minimized. By adjusting the model parameters, a curve is drawn showing the overall loss of the elevator changing with operating years, average daily operating hours, and average daily operating times.
[0137] Based on the fitted loss curve, a health status score can be assigned to the overall loss index of the elevator. This score can be set according to the specific shape and value range of the loss curve. For example, a loss threshold is set. When the loss of the elevator exceeds this threshold, it is considered to be in poor health and given a lower score. Or, based on the slope or change trend of the loss curve, the acceleration of the elevator loss can be evaluated and a corresponding score can be given.
[0138] The above introduces the elevator health status assessment method provided by the embodiment of the present application. The following is an exemplary description of the elevator health status assessment method in combination with a specific application scenario.
[0139] Figure 5aAn elevator health model is provided in an embodiment of the present application. As shown in FIG5 , the elevator health model includes five aspects: fault feedback, maintenance quality, real-time monitoring, elevator loss and parts inspection (i.e., indicators that characterize the elevator health baseline).
[0140] Among them, fault feedback includes fault level assessment, fault type identification and fault solution. Maintenance quality includes maintenance project specifications, maintenance time specifications and maintenance interval requirements. Implementation monitoring includes core component monitoring, data feature extraction and degradation model establishment. Elevator loss includes elevator operation data and overall degradation assessment. Parts inspection (i.e., indicators that characterize the baseline of elevator health) includes part hierarchy, part wear rating and part rectification suggestions.
[0141] The specific implementation method of the elevator health model refers to the contents recorded in the above steps S101 to S104, which will not be described here in detail.
[0142] The elevator health model can output results such as elevator health assessment, component health assessment, risk factor assessment traceability, maintenance recommendations and on-demand maintenance guidance.
[0143] Figure 5b A schematic diagram of an elevator health status assessment method application provided in an embodiment of the present application, combined with Figure 5b As shown, the elevator health status assessment method may include:
[0144] S11a: Obtain elevator fault data.
[0145] S11b: Determine whether there is a fault, if so, go to S11c, if not, go to S11d.
[0146] S11c: Fault type classification, go to S11e.
[0147] S11d: No points deduction required, proceed to S11g.
[0148] S11e: Deduct the corresponding score and go to S11g.
[0149] The corresponding points will be deducted based on the fault type classification.
[0150] S11f: Troubleshooting.
[0151] Determine the fault solution based on the fault type classification.
[0152] S11g: Fault feedback score.
[0153] S12a: Obtain elevator maintenance data.
[0154] S12b: Determine whether the maintenance meets the specifications. If so, go to step S12c; if not, go to step S12d.
[0155] S12c: No points deduction required, proceed to S12f.
[0156] S12d: Deduct the corresponding points and go to S12f.
[0157] S12e: Maintenance improvement suggestions.
[0158] S12f: Maintenance quality score.
[0159] S13a: Obtain core component monitoring data.
[0160] S13b: Signal decomposition and fractal dimension processing.
[0161] S13c: Constructing degradation model.
[0162] S13d: Core component degradation assessment.
[0163] S13e: Real-time monitoring score.
[0164] S14a: Obtain elevator operation statistics.
[0165] S14b: Loss-related model processing.
[0166] S14c: Deduct corresponding points based on the loss situation.
[0167] S14d: Overall loss score.
[0168] S15a: Obtain parts inspection data.
[0169] S15b: Determination of parts wear level.
[0170] S15c: Determine whether the wear is excessive, if so, go to step S15d, if not, go to step S15e.
[0171] S15d: Component health deduction, transfer to S15g.
[0172] S15e: No points will be deducted.
[0173] S15f: Corresponding rectification suggestions.
[0174] S15g: Part inspection score.
[0175] S16: Obtain an elevator health score by weighting based on the indicator weights.
[0176] S17: Determine whether it is less than or equal to 90. If so, go to step S18. If not, adjust the maintenance cycle to once every 45 days.
[0177] S18: Determine whether it is less than or equal to 80. If so, go to step S19. If not, adjust the maintenance cycle to once every 30 days.
[0178] S19: Determine whether it is less than or equal to 60. If so, go to step S20. If not, adjust the maintenance cycle to once every 15 days.
[0179] S20: The maintenance cycle is adjusted to once every 10 days.
[0180] The specific implementation methods of the above steps are described in the previous text and will not be repeated here.
[0181] Through the above embodiments, the health score of the elevator is obtained comprehensively from the elevator operation data, component characteristic data, parts wear status, maintenance and other external factors. The consideration angle is relatively comprehensive, the selected indicator distribution is more reasonable, and the various factors affecting the health of the elevator can be comprehensively examined. At the same time, through the health status score of each indicator, it is also possible to trace the risk factors that cause the elevator to be unhealthy, locate the problems that affect the current health of the elevator, and then combine the preset algorithm model and expert experience to give more reasonable and effective rectification suggestions. By constructing an elevator health assessment method based on the above indicators, it is highly interpretable, the logic is clear, and the results obtained are intuitive and easy to understand. The scoring method not only realizes the health status assessment, but also can provide effective theoretical basis and data support for ensuring the long-term effective operation of the elevator and reducing the elevator failure rate.
[0182] The above are some specific implementations of the elevator health status assessment method provided in the embodiment of the present application. Based on this, the present application also provides a corresponding device. The device provided in the embodiment of the present application will be introduced from the perspective of functional modularization.
[0183] See also Figure 6 The structure diagram of the elevator health status assessment device 600 is shown, and the device 600 includes an acquisition module 610, an acquisition module 620, a scoring module 630 and a determination module 640.
[0184] An acquisition module 610 is used to acquire data corresponding to each indicator dimension of the elevator, wherein the indicator dimension includes an indicator dimension representing an elevator health baseline and an indicator dimension representing an elevator health dynamic. The indicator dimension representing an elevator health baseline includes indicators corresponding to each component of the elevator, and the indicator dimension representing an elevator health dynamic includes a fault feedback indicator dimension, a maintenance quality indicator dimension, a real-time operation indicator dimension, and an overall loss indicator dimension.
[0185] An acquisition module 620 is used to analyze the data corresponding to each indicator dimension of the elevator using an elevator health evaluation model according to the data corresponding to each indicator dimension of the elevator to obtain a health status score result of each indicator dimension; the elevator health evaluation model includes one or more of an expert rule engine, a machine learning model, and an artificial intelligence algorithm;
[0186] The scoring module 630 is used to perform weighted processing on the health status scoring results of the indicator dimensions to obtain an overall health score of the elevator;
[0187] The determination module 640 is used to determine the maintenance period of the elevator according to the overall health score.
[0188] Optionally, the obtaining module 620 is specifically configured to:
[0189] Obtaining inspection data of each component of the elevator, wherein each component of the elevator at least includes a traction machine component, a wire rope component, a control cabinet, a car, a floor car door device, a guide rail guide shoe, a safety clamp and a speed limiter;
[0190] Analyzing the inspection data using an expert rule engine to obtain a health status score result of each component of the elevator; the expert rule engine includes a pre-set rule set for identifying the health status of each component;
[0191] Based on the health status scoring results of the elevator components, the health status scoring results of the indicator dimensions of the elevator health baseline are obtained.
[0192] Optionally, the elevator components also include a guide wheel and a return rope wheel, a counterweight and a counterweight frame, a compensation device, a traveling cable and a buffer.
[0193] Optionally, the obtaining module 620 is specifically configured to:
[0194] Presetting a health score weight for each component of the elevator;
[0195] Based on the preset health score weights of the elevator components and the health status score results of the elevator components, the health status score results of the indicator dimensions of the elevator health baseline are obtained.
[0196] Optionally, the obtaining module 620 is specifically configured to:
[0197] For the fault feedback index, the fault data of the elevator is obtained through the Internet of Things device, and the fault data is analyzed by the expert rule engine to obtain the fault type, and the fault type is classified according to the fault type to obtain the health status score result of the fault feedback index dimension;
[0198] For the maintenance quality index, the maintenance records and preset maintenance standards are obtained, and the maintenance items, maintenance dates and single maintenance duration are scored using a machine learning model to obtain the health status score results of the maintenance quality index dimension; the maintenance records include maintenance items, maintenance dates and single maintenance duration;
[0199] For real-time operation indicators, the elevator operation status data is obtained through the IoT devices and surveillance cameras on the elevator. According to the operation status data, the data features are extracted using the signal decomposition algorithm, and the health status score results of the real-time operation indicator dimension are obtained through the degradation model; the degradation model is pre-built based on the historical operation status data of each component; the elevator operation status data at least includes vibration, operation speed, and noise simulation data;
[0200] For the overall loss index, the operating years, average daily operating times and operating duration of the elevator are obtained, and the loss curve is fitted based on the operating years, average daily operating times and operating duration of the elevator based on artificial intelligence to obtain the health status score result of the overall loss index dimension.
[0201] Optionally, the device further includes a determining unit:
[0202] It is used to determine the maintenance strategy of the elevator according to the health status score result corresponding to any indicator dimension of each indicator dimension.
[0203] Optionally, the weight value of the weighted processing is calculated based on an entropy method or a hierarchical analysis method;
[0204] The scoring module is specifically used for:
[0205] When the entropy method is used, the weight of each indicator is obtained, and the weight of each target indicator is positively correlated with the degree of influence of each target indicator on the health score;
[0206] or,
[0207] When using the hierarchical analysis method, the weight of each indicator is obtained, and its weight value is determined according to the degree of influence of each target indicator on the health score.
[0208] The embodiments of the present application also provide corresponding devices and computer storage media for implementing the solutions provided by the embodiments of the present application.
[0209] The device includes a memory and a processor, the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device executes the elevator health status assessment method described in any embodiment of the present application.
[0210] The computer storage medium stores codes, and when the codes are executed, the device executing the codes implements the elevator health status assessment method described in any embodiment of the present application.
[0211] The "first" and "second" in the names such as "first" and "second" (if any) mentioned in the embodiments of the present application are only used as name identifiers and do not represent the first or second in order.
[0212] Through the description of the above implementation methods, it can be known that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a storage medium, such as a read-only memory (ROM) / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute the methods described in each embodiment of the present application or some parts of the embodiments.
[0213] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.
[0214] The above description is merely an exemplary embodiment of the present application and is not intended to limit the protection scope of the present application.
Claims
1. A method for evaluating the health status of an elevator, characterized in that: The method comprises: Acquire data corresponding to each indicator dimension of the elevator, wherein the indicator dimension includes an indicator dimension representing an elevator health baseline and an indicator dimension representing an elevator health dynamic, wherein the indicator dimension representing an elevator health baseline includes indicators corresponding to each component of the elevator, and the indicator dimension representing an elevator health dynamic includes a fault feedback indicator dimension, a maintenance quality indicator dimension, a real-time operation indicator dimension, and an overall loss indicator dimension; According to the data corresponding to each indicator dimension of the elevator, the data corresponding to each indicator dimension of the elevator is analyzed using an elevator health evaluation model to obtain a health status score result of each indicator dimension; the elevator health evaluation model includes one or more of an expert rule engine, a machine learning model and an artificial intelligence algorithm; The health status score results of each indicator dimension are weighted to obtain the overall health score of the elevator; The maintenance period of the elevator is determined according to the overall health score.
2. The elevator health status assessment method according to claim 1, characterized in that: The health status score results of the indicator dimension representing the elevator health baseline are obtained in the following way: Obtaining inspection data of each component of the elevator, wherein each component of the elevator at least includes a traction machine component, a wire rope component, a control cabinet, a car, a floor car door device, a guide rail guide shoe, a safety clamp and a speed limiter; Analyzing the inspection data using an expert rule engine to obtain a health status score result of each component of the elevator; the expert rule engine includes a pre-set rule set for identifying the health status of each component; Based on the health status scoring results of the elevator components, the health status scoring results of the indicator dimensions of the elevator health baseline are obtained.
3. The elevator health status assessment method according to claim 2, characterized in that: The elevator components also include a guide wheel and a reverse rope wheel, a counterweight and a counterweight frame, a compensation device, a traveling cable and a buffer.
4. The elevator health status assessment method according to claim 3, characterized in that: The health status scoring results of the indicator dimensions of the elevator health baseline are obtained based on the health status scoring results of the elevator components, including: Presetting a health score weight for each component of the elevator; Based on the preset health score weights of the elevator components and the health status score results of the elevator components, the health status score results of the indicator dimensions of the elevator health baseline are obtained.
5. The elevator health status assessment method according to claim 1, characterized in that: The health status score result of the indicator dimension representing the dynamic health of the elevator is obtained in the following way: For the fault feedback index, the fault data of the elevator is obtained through the Internet of Things device, and the fault data is analyzed by the expert rule engine to obtain the fault type, and the fault type is classified according to the fault type to obtain the health status score result of the fault feedback index dimension; For the maintenance quality index, the maintenance records and preset maintenance standards are obtained, and the maintenance items, maintenance dates and single maintenance duration are scored using a machine learning model to obtain the health status score results of the maintenance quality index dimension; the maintenance records include maintenance items, maintenance dates and single maintenance duration; For real-time operation indicators, the elevator operation status data is obtained through the IoT devices and surveillance cameras on the elevator. According to the operation status data, the data features are extracted using the signal decomposition algorithm, and the health status score results of the real-time operation indicator dimension are obtained through the degradation model; the degradation model is pre-built based on the historical operation status data of each component; the elevator operation status data at least includes vibration, operation speed, and noise simulation data; For the overall loss index, the operating years, average daily operating times and operating duration of the elevator are obtained, and the loss curve is fitted based on the operating years, average daily operating times and operating duration of the elevator based on artificial intelligence to obtain the health status score result of the overall loss index dimension.
6. The elevator health status assessment method according to claim 1, characterized in that: The method further comprises: The maintenance strategy of the elevator is determined according to the health status score result corresponding to any indicator dimension of each indicator dimension.
7. The method according to claim 1, characterized in that The weight value of the weighted processing is calculated based on the entropy method or the hierarchical analysis method; Among them, when the entropy method is used, the weight of each indicator is obtained, and the weight of each target indicator is positively correlated with the degree of influence of each target indicator on the health score; or, When using the hierarchical analysis method, the weight of each indicator is obtained, and its weight value is determined according to the degree of influence of each target indicator on the health score.
8. An elevator health status assessment device, characterized in that: The device comprises: An acquisition module, used to acquire data corresponding to each indicator dimension of the elevator, wherein the indicator dimension includes an indicator dimension representing an elevator health baseline and an indicator dimension representing an elevator health dynamic. The indicator dimension representing an elevator health baseline includes indicators corresponding to each component of the elevator, and the indicator dimension representing an elevator health dynamic includes a fault feedback indicator dimension, a maintenance quality indicator dimension, a real-time operation indicator dimension, and an overall loss indicator dimension; An acquisition module is used to analyze the data corresponding to each indicator dimension of the elevator using an elevator health evaluation model according to the data corresponding to each indicator dimension of the elevator, so as to obtain a health status score result of each indicator dimension; the elevator health evaluation model includes one or more of an expert rule engine, a machine learning model and an artificial intelligence algorithm; A scoring module is used to perform weighted processing on the health status scoring results of each indicator dimension to obtain an overall health score of the elevator; The determination module is used to determine the maintenance period of the elevator according to the overall health score.
9. A device, comprising a memory and a processor, wherein the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes, so that the device executes the elevator health status assessment method according to any one of claims 1 to 8.
10. A computer storage medium, wherein a code is stored in the computer storage medium. When the code is executed, a device executing the code implements the elevator health status assessment method according to any one of claims 1 to 8.
Citation Information
Cited By
Elevator health state evaluation method and system based on big data
CN119513728A
Elevator risk early warning management method and system
CN119648207A
Elevator on-demand maintenance method based on dynamic prediction
CN119873545A
Elevator health degree assessment method based on big data analysis
CN119873546A
Elevator safety circuit contact health management method and system
CN122464324A
