Method, system and storage medium for construction of an elevator component performance model

Abstract

The present application relates to the technical field of elevator component performance analysis, and particularly relates to a method and system for constructing an elevator component performance model and a storage medium. The method comprises the following steps: collecting elevator usage records and performing flow spectrum modeling to generate start-stop spectrum features and elevator usage pattern features, then performing component response analysis on the usage pattern features to obtain dynamic characteristic indexes and calculate independent performances of components, reconstructing an elevator interaction network according to the independent performances and the usage pattern features, calculating energy consumption distribution of the elevator, obtaining overall parameters of the elevator and performing framework simulation, calculating framework movement performance loss, projecting the simulation framework based on the independent performances of the components, and evaluating interaction performance, so as to construct an elevator component performance model. The present application realizes an elevator component performance model construction method which can accurately depict start-stop spectrum features and energy consumption distribution of an elevator, and dynamically evaluate component response characteristics and interaction performance.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of elevator component performance analysis, and in particular to a method and system for constructing an elevator component performance model and a storage medium. BACKGROUND

[0002] Traditional elevator maintenance relies on experience and regular inspection, making it difficult to achieve real-time monitoring and efficient management, and unable to effectively deal with sudden failures, reducing the safety and efficiency of elevator use. To improve the intelligent level and maintenance efficiency of elevators, a systematic method is urgently needed to construct an elevator component performance model to achieve dynamic monitoring and performance analysis of each component. Although existing elevator performance evaluation techniques have improved the safety and efficiency of elevator operation to some extent, they often lack in-depth analysis of the actual use of elevators, and single performance testing cannot fully reflect the performance of elevators under different use modes, especially under high-frequency use or complex environments, where the performance of elevator components changes more significantly. Traditional methods cannot timely capture these changes, leading to decision-making errors or improper maintenance, increasing operating costs and accident risks. Therefore, a more accurate and scientific elevator performance model needs to be established through comprehensive multi-dimensional data analysis. SUMMARY

[0003] Therefore, it is necessary to provide a method and system for constructing an elevator component performance model and a storage medium to solve at least one of the above technical problems.

[0004] To achieve the above-mentioned purpose, the method for constructing an elevator component performance model comprises the following steps:

[0005] Step S1: Collecting elevator usage records; performing flow spectrum modeling on the elevator usage records to generate start-stop spectrum features; and performing flow-frequency collaborative fitting to obtain elevator usage mode features;

[0006] Step S2: Analyzing the elevator usage mode features for component response to obtain dynamic characteristic indexes; and calculating component independent performance based on the dynamic characteristic indexes;

[0007] Step S3: Reconstructing an elevator interaction network according to the component independent performance and the elevator usage mode features; and calculating elevator energy consumption distribution based on the elevator usage mode features and the elevator interaction network;

[0008] Step S4: Obtaining elevator overall parameters; performing elevator framework simulation on the elevator overall parameters; and calculating framework movement performance loss based on the simulated elevator framework;

[0009] Step S5: projecting component positions on the simulation elevator framework based on component independent performance, and evaluating component interaction performance according to the component position projection, the component independent performance and the elevator energy consumption distribution; and constructing an elevator component performance model according to the component independent performance, the component interaction performance and the framework movement performance loss.

[0010] The application realizes multi-dimensional analysis of the running state of the elevator by collecting the elevator use records, the flow spectrum modeling provides a basis for identifying the start-stop characteristics of the elevator, the results of the flow-frequency collaborative fitting reveal the use mode characteristics of the elevator, which lays a scientific basis for performance analysis of components, the acquisition of dynamic characteristics indexes can deeply understand the response behavior of each component in the running process, the calculation of component independent performance provides data support for maintenance and upgrading of the elevator, the reconstruction of the elevator interaction network enhances the control of the overall running state of the elevator system, the energy consumption distribution calculated based on the use mode characteristics of the elevator provides a practical basis for energy saving improvement, the acquisition of overall parameters and the combination of framework simulation effectively analyze the performance of the elevator framework, which helps to identify and reduce energy loss in the running process, the component position projection can clearly indicate the relative position of each component in the whole, which provides visual data for interaction performance evaluation, the constructed elevator component performance model accurately reflects the performance of each component in actual work, which provides a reliable reference for subsequent fault prediction and performance optimization, and overall improves the running efficiency and safety of the elevator, and provides strong support for intelligent management of the elevator system.

[0011] Preferably, step S1 comprises the following steps:

[0012] Step S11: collecting the elevator use records; and extracting the elevator use flow in the elevator use records;

[0013] Step S12: dividing the elevator use flow into time windows to obtain time-period use flow; and inferring the flow periodicity mode according to the time-period use flow;

[0014] Step S13: detecting outliers of the flow periodicity mode, setting the outlier threshold to 2.5 times the standard deviation, and eliminating outliers to generate a purified flow mode; and extracting historical start-stop frequency data in the elevator use records;

[0015] Step S14: performing statistical filtering processing on the historical start-stop frequency, and performing frequency domain conversion to obtain start-stop spectrum characteristics;

[0016] Step S15: identifying the peak value of the start-stop spectrum characteristics and marking it as a key frequency feature point; and performing flow spectrum collaborative analysis on the purified flow mode and the key frequency feature point to obtain flow-frequency correlation data;

[0017] Step S16: Extract the distribution data of co-variables based on the flow-frequency correlation data, and perform working condition fitting based on the distribution data of co-variables to obtain the elevator usage pattern characteristics.

[0018] This invention achieves accurate estimation of elevator usage by collecting elevator usage records and extracting flow data. Time window segmentation effectively identifies usage flow in different time periods. The inference of flow periodic patterns supports scientific analysis of elevator usage behavior. Outlier detection and removal improve the accuracy and reliability of the data. Purified flow patterns provide a clearer foundation for subsequent analysis. Extraction of historical start-stop frequency data provides important evidence for understanding elevator start-stop characteristics. The application of statistical filtering and frequency domain conversion techniques effectively extracts start-stop spectrum features. Peak identification and marking of key frequency feature points provide important references for analysis. The realization of flow spectrum collaborative analysis increases the depth of understanding of the relationship between flow and frequency. The extraction of collaborative variable distribution data provides a comprehensive evaluation of elevator performance under different operating conditions. The elevator usage pattern features obtained by operating condition fitting provide strong support for further system optimization and performance improvement. Overall, this invention enhances the intelligence and scientific nature of elevator monitoring and management.

[0019] Preferably, step S2 includes the following steps:

[0020] Step S21: Decompose the component load of the elevator usage mode characteristics, and query the component response characteristics in the elevator usage mode characteristics based on the component load data;

[0021] Step S22: Identify the component transfer function based on the component response characteristics and component load data; perform pole and zero analysis on the component transfer function and map dynamic characteristic indicators;

[0022] Step S23: Determine the stability boundary based on the dynamic characteristic index, and divide the component stability range according to the stability boundary;

[0023] Step S24: Identify key operating parameters of dynamic characteristic indicators based on the component's stability range to obtain key operating parameters of the component; perform performance curve fitting on the key operating parameters of the component to generate independent performance of the component.

[0024] This invention decomposes the load on elevator components based on their usage patterns, enabling in-depth analysis of the load conditions of each component during actual operation. This provides crucial data for identifying component response characteristics. The combination of component response characteristics and load data helps accurately identify the component's transfer function, thus reflecting its dynamic characteristics. Pole-zero analysis lays the foundation for a deeper understanding of dynamic performance. The mapping of dynamic characteristic indicators provides an intuitive representation for component performance evaluation. The determination of stability boundaries ensures a comprehensive analysis of the stability of elevator components under different operating conditions. The effectively defined component stability range provides guidance for subsequent performance optimization. The identification of key operating parameters further enhances the understanding of component operating states. The component-independent performance data generated by performance curve fitting provides a reliable quantitative basis for elevator maintenance and upgrades. Overall, this invention improves the accuracy and practicality of the elevator performance model, promoting the intelligent development and management efficiency improvement of the elevator industry.

[0025] Preferably, the elevator frame simulation of the overall elevator parameters in step S4 includes:

[0026] The overall parameters of the elevator are expanded along the feature dimensions to obtain a hierarchical set of parameters.

[0027] Constraint coupling and integration are performed on the hierarchical set of parameters to generate parameter-related data;

[0028] The frame mechanical load is projected onto the parameter correlation data to obtain the frame load distribution. The load types include static load, which ranges from 1.0 to 1.5 times the rated load; dynamic load, which ranges from 0.2 to 0.5 times the rated load; and impact load, which ranges from 0.1 to 0.3 times the rated load.

[0029] The rigidity requirements of the frame components are obtained by mapping the rigidity requirements of the components based on the load distribution of the frame.

[0030] Identify the main load-bearing component parameters of the elevator's overall parameters;

[0031] The geometric characteristics of the load-bearing components are determined based on the parameters of the main load-bearing components, and stress distribution analysis is performed based on the geometric characteristics of the load-bearing components to obtain load-bearing stress distribution data.

[0032] Three-dimensional simulation of the parameters of the main load-bearing components is performed, and stress deformation simulation of the simulated load-bearing components is performed based on the load-bearing stress distribution data to generate simulated deformable load-bearing components;

[0033] Identify the parameters of the outer contact surface components of the elevator as a whole;

[0034] Determine the outer end contact area of ​​the outer end contact surface component parameters, and filter the prominent component parameters of the outer end contact surface component parameters based on the outer end contact area;

[0035] Based on the parameters of the simulated deformable load-bearing components and protruding components, the morphology of elevator components is simulated to obtain the reconstructed morphology of elevator components.

[0036] Based on the rigidity requirements of the frame components, component topology matching is performed on the reconstructed elevator component shape to obtain the matched elevator component;

[0037] Elevator frame simulation is performed based on matched elevator components, where the number of nodes in the simulation model is 1000-10000 and the simulation time step is 0.01-0.1 seconds.

[0038] This invention expands the overall parameters of the elevator by characteristic dimensions, forming a hierarchical parameter set that provides comprehensive data support for subsequent analysis. Constraint coupling integration enables efficient expression of relationships between parameters, and the generated parameter correlation data provides a solid foundation for frame mechanics analysis. The application of frame mechanics load projection allows for the systematic consideration of the influence of different types of loads. The setting of static loads, dynamic loads, and impact loads ensures the effectiveness of the model under various working conditions. The mapping of component rigidity requirements provides a scientific basis for elevator component design. The identification of parameters of major load-bearing components ensures the targeted nature of the analysis. The determination of geometric features and stress distribution analysis provide detailed data for the performance evaluation of load-bearing components. Three-dimensional simulation and stress deformation simulation accurately... The simulation reproduced the performance of the components under actual working conditions. The identification of the parameters of the outer end contact surface components and the determination of the outer end contact area helped to screen out key components. The parameters of these prominent components can better reflect the actual working state in the simulation. The realization of the reconstructed elevator component morphology provides an intuitive model for optimized design. The topological matching of the rigidity requirements of the frame components to the reconstructed morphology ensures the rationality of the elevator components in the overall design. Setting the number of nodes in the simulation model between 1,000 and 10,000 improves the accuracy of the calculation. The setting of the time step provides the necessary detail for the simulation of dynamic behavior. Overall, it improves the design efficiency and performance optimization of the elevator system and provides important theoretical support and practical guidance for the innovative development of future elevator technology.

[0039] Preferably, the calculation of frame movement performance loss based on simulated elevator frame in step S4 includes:

[0040] The structural degrees of freedom of the simulated elevator frame are expanded to obtain the frame degree of freedom data;

[0041] The motion mode of the elevator frame is calibrated based on the frame degree-of-freedom data;

[0042] Based on the motion mode of the elevator frame, the force mapping transformation of the simulated elevator frame is performed to generate the frame motion reference.

[0043] Extract the energy distribution of the contact surface in the frame motion reference, and infer the frame contact area based on the energy distribution of the contact surface;

[0044] Dynamically fit the friction force in the contact area of ​​the frame to generate frame friction force data;

[0045] Power consumption reduction is performed on the frame friction force matrix to obtain frame friction response data;

[0046] The frame friction response data is used to distribute the moment of the supporting components to obtain the frame support force data;

[0047] Based on the force data of the frame support, the resistance characteristics of the frame are mapped;

[0048] Performance degradation is calculated based on the frame drag characteristics, and the degradation effect is accumulated based on the performance degradation data to generate frame movement performance loss.

[0049] This invention, by unfolding the structural degrees of freedom of a simulated elevator frame, can identify the frame's motion capabilities and limitations, providing a necessary data foundation for dynamic performance evaluation. The calibration of the frame's degrees of freedom data facilitates accurate identification of the elevator frame's motion modes. The implementation of force mapping transformation enables a comprehensive analysis of the frame's force state during motion. The generated frame motion benchmark lays the foundation for subsequent energy distribution extraction. The extraction of contact surface energy distribution helps identify energy loss in the frame's contact area, providing a basis for dynamic fitting of friction forces. The generation of frame friction force data can reflect the friction loss of the elevator during operation in detail. Power consumption reduction and the aggregation and querying of the friction force matrix provide quantitative data for overall performance analysis. The torque distribution of supporting components ensures the rationality and balance of forces on different components. The mapping of frame support force data can clearly present the resistance characteristics of the frame during motion. Based on these resistance characteristics, performance degradation calculation can quantify changes in frame performance and provide data support for future design optimization through the accumulation of degradation effects. Overall, this improves the understanding of elevator frame movement performance and provides important technical guidance for reducing energy consumption and improving operating efficiency.

[0050] Preferably, step S5 includes the following steps:

[0051] Step S51: Disassemble the elevator component units of the simulated elevator frame; perform component unit matching based on the independent performance of the elevator component units to obtain the matching relationship;

[0052] Step S52: Project the independent performance of the components onto the simulated elevator frame based on the matching relationship to obtain the component position projection;

[0053] Step S53: Calculate component energy consumption based on component location projection and elevator energy consumption distribution, and derive component network performance based on component energy consumption data and overall elevator parameters; evaluate component interaction performance based on component network performance and component independent performance.

[0054] Step S54: Decompose the independent performance data of the component into functional blocks to obtain the component functional blocks; fit the energy efficiency response of the component functional blocks to obtain the component energy efficiency distribution;

[0055] Step S55: Perform global correlation and aggregation on the component energy efficiency distribution data to obtain component performance data; perform output performance integration based on component performance data and component interaction performance to obtain integrated output performance;

[0056] Step S56: Construct an elevator component performance model based on the integrated output performance and frame movement performance loss.

[0057] This invention enables more detailed component analysis by breaking down the elevator component units of the simulated elevator frame. The matching relationships between component units provide a reasonable basis for the independent performance of each component. Projecting the independent performance of each component onto the simulation frame clearly identifies the role of each component in the overall structure. The implementation of component position projection lays the foundation for component energy consumption calculation, enabling the quantification of energy consumption of each component during operation based on energy distribution, providing data support for optimizing the overall elevator performance. The evaluation of component network performance helps to understand the interaction of each component during elevator operation. The decomposition of functional blocks makes component performance evaluation more systematic. The implementation of energy efficiency response fitting reveals the energy efficiency performance of components under different operating conditions. The correlation and aggregation of component energy efficiency distribution data ensures a comprehensive evaluation of component overall performance. The generation of integrated output performance provides a key reference for the optimized design of the elevator system. By combining integrated output performance with frame movement performance loss, a more accurate elevator component performance model can be constructed, providing scientific guidance for performance improvement and resource optimization of the elevator system.

[0058] The present invention also provides a system for constructing a performance model for elevator components, for executing the method for constructing a performance model for elevator components as described above, the system comprising:

[0059] The spectrum modeling module is used to collect elevator usage records; perform flow spectrum modeling on the elevator usage records to generate start-stop spectrum features; and perform flow-frequency co-fitting to obtain elevator usage pattern features.

[0060] The dynamic analysis module is used to analyze the component response characteristics of elevator usage patterns to obtain dynamic characteristic indicators; and to calculate the independent performance of components based on the dynamic characteristic indicators.

[0061] The interactive network module is used to reconstruct the elevator interactive network based on the independent performance of components and the characteristics of elevator usage patterns; and to calculate the elevator energy consumption distribution based on the characteristics of elevator usage patterns and the elevator interactive network.

[0062] The frame simulation module is used to obtain the overall parameters of the elevator; to perform elevator frame simulation based on the overall elevator parameters; and to calculate the frame movement performance loss based on the simulated elevator frame.

[0063] The model building module is used to project the component positions of the simulated elevator frame based on the component independent performance, and evaluate the component interaction performance based on the component position projection, component independent performance, and elevator energy consumption distribution; and to build an elevator component performance model based on the component independent performance, component interaction performance, and frame movement performance loss.

[0064] This invention achieves in-depth analysis of elevator operating characteristics through the collection and analysis of elevator usage records. The generated start-stop spectrum features provide data support for understanding elevator usage patterns. The results of flow-frequency co-fitting reveal the elevator's operating patterns, which helps optimize elevator operating strategies. The component response analysis capability of the dynamic analysis module improves the understanding of the working status of various elevator components. The calculation of dynamic characteristic indicators makes the evaluation of component performance more scientific and systematic. The construction of the interactive network module provides a modeling basis for the interaction between various components of the elevator system. The effectively calculated elevator energy consumption distribution supports energy-saving retrofitting and optimization design. The frame simulation module evaluates the working performance of the elevator frame through the acquisition of overall parameters and simulation analysis. The accurately calculated frame movement performance loss provides a basis for elevator operation and maintenance. The model building module constructs an elevator component performance model that covers the mutual influence and comprehensive performance between various components by evaluating component position projection and interaction performance. This provides comprehensive data support and decision-making basis for the intelligent management and optimization of the elevator system, improving the overall efficiency and stability of elevator operation and promoting the continuous improvement and development of the elevator system.

[0065] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed, implements the method for constructing a performance model of elevator components as described in any of the above claims.

[0066] This invention enables the efficient execution of a method for constructing performance models of elevator components by storing a computer program. The executableness of the program ensures the automation and standardization of the model construction process, improving computational efficiency and accuracy. The stored program can flexibly adapt to the characteristics of different elevator systems, enabling personalized parameter settings and analysis. Leveraging the powerful computing capabilities of the computer system, it can perform large-scale data processing and analysis, thereby improving the reliability and timeliness of elevator usage data. The modular design of the program makes the connection between various functional modules smoother, facilitating subsequent maintenance and upgrades. The computer-readable implementation also supports compatibility with multiple platforms and devices, improving the application scope and convenience, effectively meeting the needs of intelligent elevator management and optimization, and providing theoretical and practical basis for the efficient operation and sustainable development of elevator systems. Attached Figure Description

[0067] Fig. 1 This is a flowchart illustrating the steps involved in constructing a performance model for elevator components.

[0068] Fig. 2 This is a detailed flowchart illustrating the implementation steps of step S2;

[0069] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0070] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0071] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0072] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0073] To achieve the above objectives, please refer to Figs. 1-2 A method for constructing a performance model for elevator components includes the following steps:

[0074] Step S1: Collect elevator usage records; perform flow spectrum modeling on the elevator usage records to generate start-stop spectrum features; perform flow-frequency co-fitting to obtain elevator usage pattern features;

[0075] Step S2: Analyze the component response characteristics of the elevator usage mode to obtain dynamic characteristic indicators; calculate the independent performance of the components based on the dynamic characteristic indicators;

[0076] Step S3: Reconstruct the elevator interaction network based on the independent performance of components and the characteristics of elevator usage patterns; calculate the elevator energy consumption distribution based on the characteristics of elevator usage patterns and the elevator interaction network;

[0077] Step S4: Obtain the overall elevator parameters; perform elevator frame simulation based on the overall elevator parameters; calculate the frame movement performance loss based on the simulated elevator frame;

[0078] Step S5: Project the component positions onto the simulated elevator frame based on the component independent performance, and evaluate the component interaction performance based on the component position projection, component independent performance, and elevator energy consumption distribution; construct an elevator component performance model based on the component independent performance, component interaction performance, and frame movement performance loss.

[0079] This invention achieves multi-dimensional analysis of elevator operating status by collecting elevator usage records. Flow spectrum modeling provides a foundation for identifying elevator start-stop characteristics. The results of flow-frequency co-fitting reveal elevator usage pattern characteristics, laying a scientific basis for component performance analysis. The acquisition of dynamic characteristic indicators allows for in-depth understanding of the response behavior of each component during operation. The calculation of independent component performance provides data support for elevator maintenance and upgrades. Reconstructing the elevator interaction network enhances the control over the overall elevator system operating status. The energy consumption distribution calculated based on elevator usage pattern characteristics provides a practical basis for energy-saving improvements. The acquisition of overall parameters combined with framework simulation effectively analyzes the performance of the elevator framework, helping to identify and reduce energy loss during operation. Component position projection clearly indicates the relative position of each component in the whole, providing visualized data for interactive performance evaluation. The constructed elevator component performance model accurately reflects the performance of each component in actual work, providing a reliable reference for subsequent fault prediction and performance optimization. Overall, it improves the operating efficiency and safety of the elevator and provides strong support for the intelligent management of the elevator system.

[0080] In this embodiment of the invention, the method for constructing a performance model for elevator components includes the following steps:

[0081] Step S1: Collect elevator usage records; perform flow spectrum modeling on the elevator usage records to generate start-stop spectrum features; perform flow-frequency co-fitting to obtain elevator usage pattern features;

[0082] In this embodiment, when collecting elevator usage records, a data acquisition device is installed in the core unit of the elevator control system. The acquisition device includes a high-precision time-series recording chip, a data buffer module, and a data transmission module. The high-precision time-series recording chip timestamps each elevator start and stop at millisecond levels. The data buffer module stores continuous start and stop data for short periods. The data transmission module transmits the buffered data to the central storage unit at fixed time intervals. All recorded data includes, but is not limited to, elevator start and stop times, elevator floors, elevator load weight, elevator door opening time, elevator door closing time, and elevator direction of travel. All data is stored in a standardized format and in a database according to time sequence. Simultaneously, the collected data is modeled using a flow spectrum and a Short-Time Fourier Transform (STFT). The Short-Time Fourier Transform (SFT) method decomposes the time series of elevator operation status to obtain start-stop signals with different frequency components. Window function optimization improves the time-frequency resolution of the SFT, resulting in high-resolution start-stop spectral features. Subsequently, flow-frequency co-fitting is performed on these start-stop spectral features. First, a Poisson flow model of elevator start-stop events is established, mapping the elevator start-stop sequence to a time window and calculating the start-stop frequency per unit time. Then, a nonlinear regression method is used to co-optimize the start-stop spectral features and the flow model, yielding elevator usage mode features. These features include different categories such as high-frequency start-stop mode, low-frequency start-stop mode, load-sensitive start-stop mode, and inertial start-stop mode. Parameters for each mode are quantified and stored. A hierarchical clustering algorithm is used to classify and organize the elevator usage mode features, ultimately resulting in an elevator usage mode feature library.

[0083] Step S2: Analyze the component response characteristics of the elevator usage mode to obtain dynamic characteristic indicators; calculate the independent performance of the components based on the dynamic characteristic indicators;

[0084] In this embodiment, when analyzing the component response characteristics of elevator usage modes, the time series data of each mode in the elevator usage mode feature library is first extracted and subjected to Discrete Wavelet Transform (DWT) to extract the response signals of key elevator components (traction machine, guide rail, car, door system, speed governor, etc.) under each mode. Time and frequency domain features are extracted from the response signals, and the Hilbert-Huang Transform (HHT) method is used to perform envelope analysis on the non-stationary signals to obtain the instantaneous amplitude, instantaneous frequency, and their changing trends of each component. Based on the extracted dynamic response features, the Support Vector Regression (SVR) algorithm is used to establish the mapping relationship between elevator usage mode characteristics and component dynamic characteristics. The component dynamic characteristic indicators under each mode are predicted and stored. Subsequently, the independent performance of the components is calculated based on the dynamic characteristic indicators, and a Recurrent Neural Network (RNN) is used. A recurrent neural network (RNN) is used to model the dynamic characteristics of components in a time series manner. During training, a Long Short-Term Memory (LSTM) network is used for parameter optimization to calculate independent performance parameters such as the component's operational stability, load adaptability, and fatigue wear rate.

[0085] Step S3: Reconstruct the elevator interaction network based on the independent performance of components and the characteristics of elevator usage patterns; calculate the elevator energy consumption distribution based on the characteristics of elevator usage patterns and the elevator interaction network;

[0086] In this embodiment, when reconstructing the elevator interaction network based on the independent performance of components and the characteristics of elevator usage patterns, a component-pattern adjacency matrix is ​​first constructed. The rows of the matrix represent different elevator components, the columns represent different usage patterns, and the elements in the matrix are the independent performance scores of the components in that pattern. A graph convolutional neural network (GCN) is used to extract features from the component-pattern adjacency matrix to obtain a high-dimensional representation vector of the component interaction relationship. The interaction strength between components is calculated using cosine similarity to generate an elevator interaction network topology graph. Subsequently, the elevator energy consumption distribution is inferred based on the elevator usage pattern characteristics and the elevator interaction network. First, the centrality indices of different components in the interaction network are calculated based on the topology graph, including degree centrality, betweenness centrality, and eigenvector centrality. Then, a Markov decision process (MDP) is used to model the state transition model of the elevator energy consumption distribution. Bayesian updates are performed on the energy consumption in different states to finally obtain the component-level energy consumption distribution matrix.

[0087] Step S4: Obtain the overall elevator parameters; perform elevator frame simulation based on the overall elevator parameters; calculate the frame movement performance loss based on the simulated elevator frame;

[0088] In this embodiment, when obtaining the overall elevator parameters, basic parameters from the elevator operation database are called, including the elevator rated load, elevator rated speed, elevator guide rail spacing, elevator balance coefficient, elevator traction ratio, etc., and combined with the independent performance data of components and elevator interactive network data, a complete elevator system parameter set is established. Then, the elevator frame is simulated based on the overall elevator parameters. The finite element analysis (FEA) method is used to simulate and calculate the stress on the elevator frame. First, the elevator frame is meshed, and a non-uniform mesh refinement strategy is used during the meshing process. Mesh refinement is performed in stress concentration areas (such as guide rail connection points, suspension points, etc.) to ensure calculation accuracy. Then, the frame movement performance loss is calculated based on the simulated elevator frame. During the calculation, multiple factors such as friction loss, structural deformation loss, and energy conversion loss are considered. The Coulomb friction model is used to calculate the friction loss between the guide rail and the car, the elastoplastic deformation theory is used to calculate the strain energy loss of the frame structure, and the power balance method is used to calculate the energy loss of the traction system.

[0089] Step S5: Project the component positions onto the simulated elevator frame based on the component independent performance, and evaluate the component interaction performance based on the component position projection, component independent performance, and elevator energy consumption distribution; construct an elevator component performance model based on the component independent performance, component interaction performance, and frame movement performance loss.

[0090] In this embodiment, when projecting component positions onto the simulated elevator frame based on component-independent performance, the simulated elevator frame is first transformed to map the positions of each component to a standardized three-dimensional coordinate system. The weighted centroid method is used to calculate the relative position weights of the components within the frame, and interpolation is performed on the component position projections to ensure data continuity and smoothness. Subsequently, the component interaction performance is evaluated based on component position projections, component-independent performance, and elevator energy consumption distribution. First, a non-parametric kernel density estimation (KDE) method is used to calculate the interaction probability density of components under different operating modes. Then, a Markov random field (MRF) method is used to model the cooperative influence relationships between components, ultimately obtaining the component interaction performance matrix, which is stored in the database. Next, an elevator component performance model is constructed based on component-independent performance, component interaction performance, and frame movement performance loss. First, a component feature space is constructed based on component-independent performance, and Principal Component Analysis (PCA) is used. The elevator component performance model is then constructed by performing dimensionality reduction using the Component Analysis (PPC) method to extract the principal components of component performance. Subsequently, a component collaborative performance model is established by combining the component interaction performance matrix. The elevator component performance evaluation model is trained using a deep neural network (DNN), and the model parameters are corrected based on the frame movement performance loss. Finally, a complete elevator component performance model is output.

[0091] Preferably, step S1 includes the following steps:

[0092] Step S11: Collect elevator usage records; extract elevator usage flow from the elevator usage records;

[0093] Step S12: Divide the elevator usage flow into time windows to obtain time-segmented usage flow; infer the periodicity pattern of the flow based on the time-segmented usage flow.

[0094] Step S13: Detect outliers in the periodic flow pattern, set the outlier threshold to 2.5 times the standard deviation, remove outliers, and generate a purified flow pattern; extract historical start-stop frequency data from the elevator usage records;

[0095] Step S14: Perform statistical filtering on the historical start and stop frequencies and perform frequency domain transformation to obtain the start and stop spectrum characteristics;

[0096] Step S15: Identify the peak values ​​of the start-stop spectrum characteristics and mark them as key frequency feature points; perform flow spectrum collaborative analysis on the purification flow mode and key frequency feature points to obtain flow-frequency correlation data;

[0097] Step S16: Extract the distribution data of co-variables based on the flow-frequency correlation data, and perform working condition fitting based on the distribution data of co-variables to obtain the elevator usage pattern characteristics.

[0098] In this embodiment, when collecting elevator usage records, a data acquisition device is installed in the central unit of the elevator control system. The data acquisition device includes a high-precision time synchronization module, a status sensing module, a data storage module, and a data transmission module. The high-precision time synchronization module uses GPS (Global Positioning System) timing technology to synchronously record elevator status changes with microsecond-level accuracy. The status sensing module includes start / stop detection sensors, load sensors, door status sensors, and running direction detection sensors. Each sensor's sampling frequency is set to 200Hz. The data storage module uses a ring buffer storage structure to store data for the most recent 24 hours. The data transmission module uses an Ethernet connection to transmit data to the central storage unit every 5 minutes. The stored data includes elevator start time, elevator stop time, elevator floor, elevator load weight, elevator door opening time, elevator door closing time, and elevator running direction. The data is stored in a time-series format in the database. Subsequently, elevator usage records were analyzed to extract elevator usage flow, defined as the number of elevator starts and stops per unit time. A sliding window method was used for calculation, with a window length of 30 minutes and a sliding step size of 5 minutes. The number of starts and stops within all time windows was calculated, generating an elevator usage flow data sequence. When segmenting the elevator usage flow into time windows, the time window length was initially set to 1 hour, and the elevator usage flow sequence was divided into multiple time windows according to chronological order. The mean, variance, and median of the flow data within each time window were calculated and stored in the database. Then, based on the time-segmented usage flow, the periodicity pattern of the flow was inferred using a Fast Fourier Transform (FFT). The Fast Fourier Transform (FFT) is used to calculate the dominant frequency component of the flow sequence and extract the period corresponding to the highest power spectral density. The phase alignment of the flow sequence under this period is calculated, and the period with the highest phase alignment is taken as the dominant period of the elevator flow periodicity pattern. Subsequently, an Auto-Regressive Moving Average (ARMA) model is used to fit the periodicity pattern to calculate the flow change trend in future periods. When detecting outliers in the flow periodicity pattern, the Local Outlier Factor (LOF) method is used to calculate the local outlier score of the flow data in each time window, and the outlier threshold is set to 2.Five standard deviations were used to generate a purification flow pattern, which was then stored in the database after removing all time windows where scores exceeded the threshold. Subsequently, historical start-stop frequency data was extracted from elevator usage records. The calculation method involved performing time-series statistics on elevator start-stop events, calculating the start-stop frequency every minute, and storing the start-stop frequencies within all time windows to generate a historical start-stop frequency data sequence. When performing statistical filtering on the historical start-stop frequencies, a median filtering method was used to eliminate sudden outliers. The median filtering window length was set to 5 minutes. The start-stop frequencies of all time windows were filtered, and then frequency domain transformation was performed using Short-Time Fourier Transform (STFT). The short-time Fourier transform (SFT) is used to calculate the time-frequency characteristics of start-stop frequencies within different time windows. A Hanning window function is employed to improve spectral resolution, and the power spectral density is calculated to obtain start-stop spectral characteristics. When identifying peak values ​​of these characteristics, a peak detection algorithm is used to calculate the first derivative of the power spectral density curve, and all frequency points with zero derivatives and negative second derivatives are located. These frequency points are marked as key frequency feature points and stored in a database. Subsequently, a flow-frequency co-analysis is performed on the purification flow mode and key frequency feature points. The mutual information method is used to calculate the correlation between the purification flow mode and key frequency feature points, and flow-frequency correlation data is calculated based on this correlation. When extracting covariate distribution data from the flow-frequency correlation data, kernel density estimation (KDE) is used to calculate the probability density function of the flow-frequency correlation data, and covariate distribution data is generated based on the probability density function. Finally, operating condition fitting is performed based on the covariate distribution data, using a Gaussian mixture model (GMM). The Gaussian mixture model (GMM) is used to perform cluster analysis on the distribution data of co-variables and calculate the elevator usage probability under different operating conditions, ultimately obtaining the elevator usage pattern characteristics.

[0099] Preferably, step S2 includes the following steps:

[0100] Step S21: Decompose the component load of the elevator usage mode characteristics, and query the component response characteristics in the elevator usage mode characteristics based on the component load data;

[0101] Step S22: Identify the component transfer function based on the component response characteristics and component load data; perform pole and zero analysis on the component transfer function and map dynamic characteristic indicators;

[0102] Step S23: Determine the stability boundary based on the dynamic characteristic index, and divide the component stability range according to the stability boundary;

[0103] Step S24: Identify key operating parameters of dynamic characteristic indicators based on the component's stability range to obtain key operating parameters of the component; perform performance curve fitting on the key operating parameters of the component to generate independent performance of the component.

[0104] In this embodiment, when performing component load decomposition on elevator usage mode characteristics, the flow-frequency correlation data in the elevator usage mode characteristics is first obtained. Then, the working status of key elevator components is analyzed based on the elevator operation log. These key components include the traction machine, elevator guide rails, elevator brake, and elevator balancing system. A load decomposition model based on operating status identification is used to convert the elevator usage mode characteristics into instantaneous load data for each component. The load decomposition model uses rigid body dynamics equations to calculate the force state of each component. Assuming the elevator car mass is 1000kg, the rated load capacity is 800kg, the traction machine drive power is 22kW, and the traction ratio is set... The load ratio was set to 2:1. The output torque of the traction machine was calculated. The force state of the elevator guide rail was calculated using a contact stiffness model, the force of the brake was calculated using a braking friction model, and the tension distribution of the balancing system was calculated using a wire rope tension distribution model. The calculated component load data was stored in a database. Then, based on the component load data, the component response characteristics in the elevator usage mode characteristics were queried. The dynamic coupling relationship between the load change of each component and the elevator usage mode characteristics was calculated using a time series cross-correlation analysis method. Based on the sliding window cross-correlation, the response lag time of the load change of each component to the elevator start and stop frequency was calculated. The calculation accuracy of the lag time was set to 0.In one second, when identifying the component transfer function based on component response characteristics and component load data, the least squares method is used to estimate the transfer function parameters. The transfer function is represented by a second-order system model, in the form G(s)=(Kω_n^2) / (s^2+2ζω_ns+ω_n^2), where K is the gain coefficient, ω_n is the system natural frequency, and ζ is the damping ratio. The least squares method is used to calculate the optimal estimates of K, ω_n, and ζ, and the calculated transfer function is stored in the database. Subsequently, pole and zero analysis is performed on the component transfer function. The Laplace transform is used to calculate the system pole locations, calculate the real and imaginary parts of the poles, and analyze the pole distribution to determine the system stability. The state-space method is used to calculate the system zero locations, analyze the distribution of system zeros, and calculate the degree of influence of zeros on the system response. Then, dynamic characteristic index mapping is performed to extract the component's natural frequency, damping ratio, and other parameters. When determining the stability boundary based on dynamic characteristic indicators for resonant frequency and frequency response characteristics, the Nyquist criterion is used to calculate the system stability margin. The calculation method involves plotting the Nyquist curve of the system and analyzing its encirclement relative to the (-1,0) point. Gain margin and phase margin are calculated, with a gain margin threshold of 6 dB and a phase margin threshold of 45 degrees. The stability range of the system is then determined using the Lyapunov method. A Lyapunov function V(x) is established, its derivative dV / dt is calculated, and the sign of dV / dt is determined. If dV / dt is less than zero, the system is in a stable state; if dV / dt is greater than zero, the system is in an unstable state. Based on the stability judgment results, the component stability range is divided. When identifying key operating parameters of dynamic characteristic indicators based on the component stability range, Support Vector Regression (SVR) is used. Support Vector Regression (SVR) calculates the mapping relationship between dynamic characteristic indices and stability range. Input features are dynamic characteristic indices, including natural frequency, damping ratio, resonant frequency, and frequency response characteristics. Output is the stability range. A Radial Basis Function (RBF) kernel function is used for regression calculation to optimize the SVR model parameters, which are then stored in a database. Subsequently, performance curves are fitted to key operating parameters of the component. The least squares curve fitting method is used to calculate the relationship curve between key operating parameters and component performance. The order of the fitted curve is set to a third-order polynomial. Fitting parameters are calculated and stored in the database, ultimately generating the component's independent performance.

[0105] Preferably, the reconstruction of the elevator interaction network based on the independent performance of components and the characteristics of elevator usage patterns in step S3 includes:

[0106] Elevator operation data is derived based on elevator usage pattern characteristics;

[0107] The elevator operation data is broken down to obtain the operation data of the elevator components;

[0108] Component dependency analysis is performed on the elevator component operation data to obtain the dependencies between components;

[0109] The causal direction of the dependencies between components is determined, and the component subordination relationship is identified based on the causal direction.

[0110] Reconstruct the elevator interaction network based on the independent performance of components and the subordinate relationships between components.

[0111] In this embodiment, elevator operation data is derived based on elevator usage pattern characteristics. A time-series data processing method is used to perform time-series analysis on the elevator usage pattern characteristics, setting the time window size to 10 minutes. A sliding window method is used to extract feature sequences, calculate the car's running time distribution, and set the range of a single car running time to 5-60 seconds. The elevator start-stop frequency is calculated, setting the range to 0.1-2 times / minute. Fourier transform is used to calculate the operating cycle characteristics, setting the main frequency range to 0.01-0.5Hz. The obtained elevator operation data is stored and then decomposed to obtain elevator component operation data. A rule-based decomposition method is used, setting the decomposition rule as the mapping relationship between operation data and component working states. The elevator start-stop signals are parsed and mapped to the control system response, setting the control system response time range to 0.01-0.1 seconds. The car acceleration signal is parsed, setting the maximum car acceleration to 1.5 m / s². 2The process involves analyzing the braking system status, setting the operating current range of the braking system to 0.5-5A, performing component dependency analysis on elevator component operating data to obtain inter-component dependencies, calculating the temporal correlation between components using dynamic correlation analysis with a correlation threshold of 0.8, calculating the causal relationship between components using Granger causality analysis with a significance level of 0.05, calculating the causal effect of traction machine power changes on car speed changes, and calculating the impact of guide rail friction changes on car vibration. A directed graph model is used to construct a component dependency network with 10-50 network nodes to store inter-component dependencies, locating the causal direction of inter-component dependencies, and identifying component subordination relationships based on the causal direction. Structural equation modeling (SEM) is used to calculate causal paths with path coefficients ranging from 0.1-0.9, and a Directional Bayesian network (DBN) is employed. Using a directional Bayesian network (GNMB) to infer causal directions, with a confidence level of 95%, the causal direction of changes in car mass on changes in traction machine load is calculated. The impact of braking system response time on car stopping accuracy is calculated, and component dependency relationships are generated. Based on the independent performance of components and component dependency relationships, the elevator interaction network is reconstructed. A weighted directed graph method is used to construct the elevator component interaction topology, with weights ranging from 0.1 to 1. The interaction strength between each component is calculated, with an interaction strength threshold of 0.5. A graph theory method is used to calculate the clustering coefficient of the interaction network, with clustering coefficients ranging from 0.2 to 0.8. The network centrality is calculated, with centrality ranging from 0.1 to 0.9, and finally, the elevator interaction network is generated.

[0112] Of particular importance, the reconstruction of the elevator interaction network based on the independent performance of components and the dependency relationship of components includes:

[0113] Convert the component hierarchy into a hierarchical tree structure;

[0114] A hybrid feature space is obtained by fusing and mapping the subordinate tree structure and the independent performance of components.

[0115] An interactive topology framework is constructed based on a hybrid feature space, and the interaction strength of components is analyzed based on the interactive topology framework.

[0116] Based on the component dependency relationship, the directional weight of the component interaction strength is adjusted to obtain the asymmetric interaction strength;

[0117] Component links are sorted according to the intensity of asymmetric interaction to generate a ranking of key interaction links;

[0118] Elevator components are connected based on the ranking of key interactive links, and an interactive topology of elevator components is constructed based on the connected elevator components.

[0119] Centrality calculation is performed on the interaction topology of elevator components to obtain the node importance distribution;

[0120] Identifying key elevator components based on node importance distribution;

[0121] Reconstruct the elevator interaction network based on key elevator components and their interaction topology.

[0122] In this embodiment, the component dependency relationships are transformed into a dependency tree structure. A Directed Acyclic Graph (DAG) is used to model the dependency relationships of elevator components, with the root node being the elevator frame and child nodes including guide rails, car, counterweight, traction machine, control cabinet, door system, etc. Hierarchical clustering is used to classify the component dependency relationships, with a hierarchy depth of 3-5 levels. An adjacency matrix is ​​used to store the connection relationships between components, with a matrix dimension of N×N, where N is the total number of components. A depth-first search (DFS) method is used to traverse the component dependency tree, with a search depth not exceeding 6 levels, ultimately generating a component dependency tree structure. The dependency tree structure and the independent performance of the components are fused and mapped to obtain a hybrid feature space. Feature embedding is used to numerically process the independent performance of the components, with an embedding dimension of 10-50 dimensions, and a Gaussian kernel function is used. A nonlinear mapping is applied to the component performance data using a kernel function with a width of 0.1-1.0. Principal Component Analysis (PCA) is used to reduce the dimensionality of the fused feature data, with a principal component contribution rate threshold of 85%-95%. Cosine Similarity is used to calculate the feature similarity between components, with a similarity threshold of 0.75-1.0, ultimately generating a hybrid feature space. An interaction topology framework is constructed based on this hybrid feature space, and the interaction strength of components is analyzed based on this framework. A Graph Neural Network (GNN) is used to model the interaction relationships between components, with 3-5 layers. A random walk method is used to sample the interaction network, with a walk step size of 5-10. Node embedding is used to encode the interaction features of components, with an embedding dimension of 16-64. Link prediction is used... The Prediction method is used to calculate the interaction strength of components, setting the interaction strength range to 0-1, and finally obtaining the interaction topology framework. The directional weights of the component interaction strengths are adjusted based on the component hierarchy to obtain the asymmetric interaction strength. A directed graph is used to store the component interaction data, with the initial edge weight set to 1.0. PageRank is used to calculate the importance of components in the interaction topology, and the damping coefficient is set to 0.85. Normalized Mutual Information (NMI) is used to calculate component interaction weights, with a weight range of 0.1-1.0. Information Entropy is used to directionally adjust the interaction strength, with an entropy range of 0.01-0.1, ultimately generating asymmetric interaction strengths. Component links are sorted based on these asymmetric interaction strengths to generate a ranking of key interaction links. A ranking algorithm is used to prioritize the interaction links, with the ranking criteria including interaction strength, component importance, and structural stability. The Top-K method is used to select key interaction links, with K set to 10-50. A bidirectional sorting method is used to optimize the interaction links, with the optimization objective being maximum interaction stability. The Analytic Hierarchy Process (AHP) is employed. The process calculates the weights of different ranking factors, setting the weight range to 0.2-0.8, and finally obtains the ranking of key interaction links. Elevator components are connected based on the ranking of key interaction links, and an elevator component interaction topology is constructed based on the connected elevator components. The Dijkstra shortest path algorithm is used to calculate the optimal connection path between elevator components, setting the path weight as the reciprocal of the interaction strength. An adjacency list is used to store the connection information of elevator components, setting the maximum capacity of the adjacency list to N×N, where N is the total number of components. A sparse matrix is ​​used to store the interaction topology data, setting the sparsity threshold to 0.1-0.3. The minimum spanning tree (MST) method is used to optimize the connection structure of elevator components, finally constructing the elevator component interaction topology. The centrality of the elevator component interaction topology is calculated to obtain the node importance distribution. Degree centrality is used to calculate the connectivity of each component in the topology structure, setting the degree range to 1-20. Betweenness centrality is used... Centrality is used to calculate the influence of each component in the interaction path, with the betweenness factor set to a range of 0.01-0.5. Eigenvector centrality is used to calculate the global importance of each component, with the eigenvector centrality set to a range of 0.1-1.0. Closeness is used to calculate the tightness between components, with the calculation range set to 0.05-0.95. Finally, the node importance distribution is obtained. Based on the node importance distribution, key elevator components are identified. The K-Means clustering method is used to classify the components, with the number of categories set to 3-5. The LOF (Local Outlier Factor) method is used to identify abnormal components, with the outlier factor threshold set to 1.5-2.5. The weighted scoring method is used to calculate the score of key components, with the scoring criteria set as centrality score, interaction strength score, and connection stability score. The threshold filtering method is used to select key components, with the filtering threshold set to 0.7-1.0. Finally, key elevator components are identified. The elevator interaction network is reconstructed based on the key elevator components and the elevator component interaction topology. The local reconstruction method is used to optimize the elevator interaction topology, with the optimization objective set as minimum transmission loss. The global optimization method is used to calculate the optimal network structure, with optimization parameters including node stability, interaction path redundancy, and energy consumption. Dynamic weighting is used. The edge weights in the elevator interaction network are adjusted using a weighting method, with a dynamic adjustment range of 0.1-1.0. Connectivity analysis is then used to calculate the connectivity of the elevator interaction network, with a connectivity threshold of 0.8-1.0. Finally, the elevator interaction network is reconstructed.

[0123] Preferably, the step S3, which involves calculating the elevator energy consumption distribution based on elevator usage pattern characteristics and elevator interaction network, includes:

[0124] Identify the key connection framework of the elevator interaction network;

[0125] Redundant paths are identified in the associated connection skeleton to obtain a set of backup paths;

[0126] Construct the elevator interaction network topology based on the key connection skeleton and the set of backup paths;

[0127] Elevator energy consumption is mapped based on elevator usage pattern characteristics, and the elevator interaction network topology is connected based on elevator energy consumption. The energy data is then used to identify the distribution of elevator energy consumption.

[0128] In this embodiment, the key connection skeleton of the elevator interaction network is identified. Principal Component Analysis (PCA) is performed on the elevator interaction network using a topology dimensionality reduction method. The threshold for the variance contribution rate of the principal components is set to 90%. Key component connections are screened, and the minimum spanning tree (MST) method is used to construct the skeleton connection structure. The weights are calculated based on the energy flow intensity between elevator components, and the energy flow intensity is calculated as the power transfer ratio. The threshold range is set to 0.05-0.5. This yields the key connection skeleton. Redundant paths are identified in the associated connection skeletons to obtain a set of alternative paths. A breadth-first search (BFS) method is used to traverse the elevator interaction network, with a path search depth of 3-5 layers. The maximum flow minimum cut (Max-Flow) method is then employed. The Min-Cut method is used to calculate path redundancy. Maximum flow is calculated as component energy transfer rate, which is then calculated as energy consumption ratio, with a range of 0.1-0.9. All paths meeting redundancy conditions are identified, and a set of backup paths is stored. The elevator interaction network topology is constructed based on the key connection skeleton and the set of backup paths. A Weighted Directed Graph (WDR) method is used for topology modeling, with 10-50 nodes and edge weights calculated as energy transfer efficiency, which is calculated as the input-output power ratio, with a range of 0.6-0.95. Network connectivity is calculated using the shortest path optimization method, specifically Dijkstra's algorithm based on energy loss, with an energy loss range of 1-10%. The final elevator interaction network topology is generated. Elevator usage pattern characteristics are mapped to elevator energy consumption, and connection energy mapping is performed on the elevator interaction network topology based on elevator energy consumption. Time-series regression analysis is then used. The method calculates the trend of elevator energy consumption changes, setting the regression window size to 30 minutes. It calculates the energy consumption distribution of the traction machine, setting the traction machine energy consumption range to 1-10kW. It also calculates the power consumption of the control system, setting the control system power range to 0.1-2kW. Power flow analysis is used to calculate the energy transmission relationship of each component, setting the power transmission efficiency range to 0.7-0.98. Connection energy data is generated, and the elevator energy consumption distribution is identified based on this data. Finally, a power density calculation method is used to calculate the energy consumption density of elevator components, setting the power density calculation method as the power consumption ratio per unit volume, with the power consumption ratio range to 0.5-5kW / m². 3The energy consumption of elevator components is classified using a hierarchical clustering method. The number of classification layers is set to 3-5 layers. The energy consumption ratio of each layer is calculated. The energy consumption ratio is calculated by comparing the power consumption of each layer with the total power. Finally, elevator energy consumption distribution data is generated.

[0129] Preferably, the elevator frame simulation of the overall elevator parameters in step S4 includes:

[0130] The overall parameters of the elevator are expanded along the feature dimensions to obtain a hierarchical set of parameters.

[0131] Constraint coupling and integration are performed on the hierarchical set of parameters to generate parameter-related data;

[0132] The frame mechanical load is projected onto the parameter correlation data to obtain the frame load distribution. The load types include static load, which ranges from 1.0 to 1.5 times the rated load; dynamic load, which ranges from 0.2 to 0.5 times the rated load; and impact load, which ranges from 0.1 to 0.3 times the rated load.

[0133] The rigidity requirements of the frame components are obtained by mapping the rigidity requirements of the components based on the load distribution of the frame.

[0134] Identify the main load-bearing component parameters of the elevator's overall parameters;

[0135] The geometric characteristics of the load-bearing components are determined based on the parameters of the main load-bearing components, and stress distribution analysis is performed based on the geometric characteristics of the load-bearing components to obtain load-bearing stress distribution data.

[0136] Three-dimensional simulation of the parameters of the main load-bearing components is performed, and stress deformation simulation of the simulated load-bearing components is performed based on the load-bearing stress distribution data to generate simulated deformable load-bearing components;

[0137] Identify the parameters of the outer contact surface components of the elevator as a whole;

[0138] Determine the outer end contact area of ​​the outer end contact surface component parameters, and filter the prominent component parameters of the outer end contact surface component parameters based on the outer end contact area;

[0139] Based on the parameters of the simulated deformable load-bearing components and protruding components, the morphology of elevator components is simulated to obtain the reconstructed morphology of elevator components.

[0140] Based on the rigidity requirements of the frame components, component topology matching is performed on the reconstructed elevator component shape to obtain the matched elevator component;

[0141] Elevator frame simulation is performed based on matched elevator components, where the number of nodes in the simulation model is 1000-10000 and the simulation time step is 0.01-0.1 seconds.

[0142] In this embodiment, the overall parameters of the elevator are expanded into four dimensions using a multi-level feature classification method: physical properties, electrical characteristics, structural features, and environmental adaptability. Physical properties include material density, elastic modulus, tensile strength, and yield strength; electrical characteristics include motor power, current, voltage, and control signal type; structural features include frame dimensions, welding methods, and connection methods; and environmental adaptability includes temperature tolerance and humidity tolerance. During data processing, principal component analysis (PCA) is performed on the parameters of each dimension to extract highly correlated parameter sets. Singular value decomposition (SVD) is used to calculate the importance weights of the parameters, and parameters with weights greater than 0.8 are designated as core features. A hierarchical parameter set is constructed, stored in a multi-dimensional array format. Each parameter is stored in the corresponding array layer according to its physical, mechanical, electrical, or environmental properties, and access is achieved through a data index. All data is stored as double-precision floating-point numbers to ensure calculation accuracy. During the calculation process, a data normalization range is set so that all parameter values ​​fall within the [0,1] interval. The normalization calculation formula uses… Linear normalization, which involves subtracting the minimum value from the parameter value and then dividing by the difference between the maximum and minimum values, integrates the hierarchical parameter sets with constraints to generate parameter-related data. During constraint-coupled calculations, a finite constraint optimization method is used to establish a system of constraint equations for the data in each parameter hierarchical set. For example, for the thickness of the main beam of the frame, the constraints include the material yield strength, maximum working stress, and a safety factor. The calculation formula is that the main beam thickness equals the total load borne by the frame divided by the product of the main beam width and the yield strength, multiplied by the safety factor. During the constraint calculation process, the Lagrange multiplier method is used to solve the constraints. The optimization problem employs sparse matrix storage for the parameter constraint matrix to reduce computational complexity. QR decomposition is used to improve computational efficiency during the solution process. An association matrix is ​​established for all parameters, where each element represents the influence weight between two parameters. This weight is calculated through data fitting using the least squares method, with at least 1000 fitted data points to ensure computational accuracy. Variance analysis is performed on the fitting error, and parameters with variance exceeding a threshold are removed. Finite element analysis (FEA) is used to simulate the load on the elevator frame when projecting the frame mechanical load onto the parameter association data. First, a finite element model of the elevator frame is established, using four-node tetrahedral elements with a mesh size of 10mm. The material parameters for each component are set according to the steel structure's Young's modulus of 210GPa, Poisson's ratio of 0.3, and yield strength of 355MPa. Static loads, dynamic loads, and impact loads are applied to the finite element model, with the static load range set to 1.0-1 times the rated load.A dynamic load of 5 times the rated load is applied to the bottom contact surface of the car, using a uniformly distributed load mode. The dynamic load range is set to 0.2-0.5 times the rated load and applied to the connection point between the traction steel wire rope and the car using time history analysis. The impact load range is set to 0.1-0.3 times the rated load and applied to the buffer contact point. The impact response is simulated using transient analysis, employing ANSYS. Mechanical simulations were performed with a time step of 0.01s and a total simulation time of 10s. During the calculation, nodal stress, displacement, and acceleration data were recorded at each time step and stored in CSV format. The final output was frame load distribution data. When mapping component rigidity requirements based on the frame load distribution, high-stress areas of the elevator frame were first extracted. A stress threshold of 80% of the material's yield strength was set; areas with stress exceeding 284MPa were considered to have high rigidity requirements. Interpolation methods were used to calculate the rigidity requirement gradient to determine the rigidity requirement level of each component. For high-rigidity requirement areas, thicker plates or additional stiffeners were used to improve rigidity. For low-rigidity requirement areas, material usage was optimized to reduce weight and manufacturing costs. The main parameters of the overall elevator were identified. When determining the parameters of load-bearing components, the main load-bearing components, including guide rails, car base frame, counterweight frame, and traction machine base, are first identified based on the frame load distribution. Stress analysis is used to calculate the load percentage of each component, setting a threshold of 5% of the total load. Components with a load percentage exceeding 5% are considered main load-bearing components. MATLAB is used for calculation, inputting the load data of all components into a matrix. Principal component analysis (PCA) is then used to filter the main load-bearing components. Based on the parameters of the main load-bearing components, the geometric characteristics of the load-bearing components are determined, extracting the dimensional data of each component and constructing a 3D CAD model. ABAQUS is used for stress distribution analysis, setting the mesh size to 5mm. Actual operating loads are applied, and the stress distribution of each component is calculated and output. Abaqus Explicit is used for 3D simulation of the main load-bearing components, applying actual operating loads and calculating deformation based on the stress distribution data, with the simulation time step set to 0.005s, iterative calculation 1000 steps, finally output the deformation of the simulated load-bearing components, extract the outer end contact surface data from the overall elevator parameters, including the car bottom, sill, buffer contact surfaces, etc. Based on the elevator structural model, extract all components in contact with the external environment, and use computer vision methods to automatically identify the contact areas. The contact areas are segmented using image segmentation algorithms, and the parameters of the outer end contact surface components are determined by geometric analysis. The outer end contact area of ​​the outer end contact surface component parameters is determined, and when filtering the protruding component parameters of the outer end contact surface component parameters based on the outer end contact area, firstly, a 3D scanner is used to acquire the surface data of the outer end contact surface components, and point cloud processing software is used for surface reconstruction to calculate the contact area. Based on the contact area, a threshold is set to filter the protruding component parameters of the outer end contact surface components. When simulating the elevator component morphology based on the simulated deformation load-bearing components and protruding component parameters, CATIA modeling software is used to construct the elevator components. A morphological model was created and morphological simulation was performed using Abaqus software. Material properties, load conditions, and contact characteristics were defined to obtain the morphology of the reconstructed elevator components. When performing topological matching of the reconstructed elevator component morphology based on the rigidity requirements of the frame components, a constraint optimization-based topology matching method was used to optimize the component morphological data and perform matching calculations in conjunction with structural rigidity requirements, ultimately obtaining matched elevator components. When simulating the elevator frame based on the matched elevator components, a finite element simulation model containing 1000-10000 nodes was established, with a simulation time step set to 0.01-0.1 seconds. A dynamic solver was used for time-domain analysis, and the simulation results were finally obtained.

[0143] Preferably, the calculation of frame movement performance loss based on simulated elevator frame in step S4 includes:

[0144] The structural degrees of freedom of the simulated elevator frame are expanded to obtain the frame degree of freedom data;

[0145] The motion mode of the elevator frame is calibrated based on the frame degree-of-freedom data;

[0146] Based on the motion mode of the elevator frame, the force mapping transformation of the simulated elevator frame is performed to generate the frame motion reference.

[0147] Extract the energy distribution of the contact surface in the frame motion reference, and infer the frame contact area based on the energy distribution of the contact surface;

[0148] Dynamically fit the friction force in the contact area of ​​the frame to generate frame friction force data;

[0149] Power consumption reduction is performed on the frame friction force matrix to obtain frame friction response data;

[0150] The frame friction response data is used to distribute the moment of the supporting components to obtain the frame support force data;

[0151] Based on the force data of the frame support, the resistance characteristics of the frame are mapped;

[0152] Performance degradation is calculated based on the frame drag characteristics, and the degradation effect is accumulated based on the performance degradation data to generate frame movement performance loss.

[0153] In this embodiment, the structural degrees of freedom of the simulated elevator frame are expanded to obtain frame degree-of-freedom data. Finite Element Analysis (FEA) is used to discretize the elevator frame, setting the total number of nodes to 1000-10000. The degrees of freedom for each node are defined, including three-dimensional displacement and three-dimensional rotation. Constraints are applied to the fixed ends, hinge points, and sliding support positions of the frame, using the Lagrange multiplier method. The constraint reaction force is calculated using the method described by the constraint equation: [K]{U}={F}, where [K] is the frame stiffness matrix, {U} is the nodal displacement vector, and {F} is the external load vector. The convergence error is set to within 0.01 mm. The frame degree of freedom data is obtained, and the elevator frame motion mode is calibrated based on this data. Modal analysis is used to calculate the frame's natural vibration characteristics, with the natural frequency range set to 0.5-5 Hz. The mode shapes of each frame mode are calculated, and a Fourier transform is performed on the modal response. A frequency domain resolution of 0.1 Hz is set to calculate the dominant frequency component and modal morphology characteristics of the motion mode, obtaining the elevator frame motion mode data. Based on the elevator frame motion mode, a force mapping transformation is performed on the simulated elevator frame to generate the frame motion reference. The Newton-Euler equations are then used. The force state of the frame under traction, braking, and inertial forces was analyzed using an equation. The traction force range was set to 1.2-1.8 times the rated load, and the braking force range was set to 0.8-1.5 times the rated load. The force equilibrium state of the frame under different load conditions was calculated, and a force mapping matrix was established. The force distribution data was correlated with the frame structure to form a frame motion reference. The contact surface energy distribution in the frame motion reference was extracted, and the frame contact area was inferred based on the contact surface energy distribution. The energy transfer between the frame and the guide rails, car bottom, and other contact parts was calculated using contact mechanics analysis methods. The contact energy range was set to 10-500 joules. The contact area was refined using a finite element mesh method with a mesh size range of 1-5 mm. The energy density per unit area was calculated, and the contact area boundary was identified based on the energy density gradient. Dynamic fitting of the friction force in the frame contact area was performed to generate frame friction force data. The Coulomb friction model was used to calculate the friction force, and the friction force expression is: F f =μN, where μ is the coefficient of friction, F fFor friction force data, the range is set to 0.05-0.3, where N is the normal force. The Newton-Raphson method is used to calculate the dynamic curve of friction force versus time, with a time step range of 0.01-0.1 seconds. This generates frame friction force data. Power consumption is calculated from the frame friction force matrix to obtain frame friction response data. The principle of energy conservation is used to calculate friction power consumption, expressed as: P f =F f v, where v is the relative sliding velocity of the contact surfaces, P f For frictional power consumption data, the range of frictional power consumption was set to 1-50 watts. The total power consumption of the friction force matrix was calculated using matrix decomposition, with a calculation error range set within 0.01 watts. This yielded frame frictional response data. Torque distribution of the supporting components was then performed on the frame frictional response data to obtain frame support force data. The stress state of the supporting components was calculated using static equilibrium equations, with the support force range set to 100-5000 Newtons. Torque distribution was calculated using matrix operations, with a torque calculation error set within 0.01 Newton-meters. This generated frame support force data. Based on the frame support force data, the frame resistance characteristics were mapped, and fluid dynamics methods were used to calculate the elevator's operating process. During the process, air resistance was set to a range of 1-10 Newtons. Frictional resistance between the frame and the guide rail was calculated using tribological analysis, with a range of 10-500 Newtons. Air resistance, frictional resistance, and other mechanical resistances were accumulated to form the frame resistance characteristics. Performance degradation was calculated based on the frame resistance characteristics, and the degradation effect was accumulated based on the performance degradation data to generate the frame movement performance loss. The frame performance degradation trend was calculated using time series analysis, with a time step range of 1-10 hours. The accumulation of degradation effect was calculated using an integral method, with an accumulation error range of 0.01%, ultimately generating the frame movement performance loss.

[0154] Preferably, step S5 includes the following steps:

[0155] Step S51: Disassemble the elevator component units of the simulated elevator frame; perform component unit matching based on the independent performance of the elevator component units to obtain the matching relationship;

[0156] Step S52: Project the independent performance of the components onto the simulated elevator frame based on the matching relationship to obtain the component position projection;

[0157] Step S53: Calculate component energy consumption based on component location projection and elevator energy consumption distribution, and derive component network performance based on component energy consumption data and overall elevator parameters; evaluate component interaction performance based on component network performance and component independent performance.

[0158] Step S54: Decompose the independent performance data of the component into functional blocks to obtain the component functional blocks; fit the energy efficiency response of the component functional blocks to obtain the component energy efficiency distribution;

[0159] Step S55: Perform global correlation and aggregation on the component energy efficiency distribution data to obtain component performance data; perform output performance integration based on component performance data and component interaction performance to obtain integrated output performance;

[0160] Step S56: Construct an elevator component performance model based on the integrated output performance and frame movement performance loss.

[0161] In this embodiment, the elevator component units of the simulated elevator frame are disassembled. A topological decomposition method is used to analyze the structure of the elevator frame. The decomposition threshold is set as a component size greater than 50 mm or a mass greater than 1 kg. A connectivity matrix is ​​used to determine the structural coupling relationship between components, and the connection strength of each component is calculated. The connection strength threshold is set to 0.1-1.0 N·m. Based on the connection strength value, the elevator components are disassembled into independent units to obtain component unit data. Component unit matching is performed based on the independent performance of the elevator component units. A feature matching algorithm is used to calculate the independent performance vector of the components, with the vector dimension set to 10-50. The performance indicators of the elevator components, such as mass, stiffness, damping, and moment of inertia, are standardized. The K-Nearest Neighbors (KNN) classification method is used to calculate the component matching degree, with K set to 3-7 and the matching degree threshold set to 80%-100%. Matching relationships are generated. Based on the matching relationships, the independent performance of the components is projected onto the simulated elevator frame to obtain the component position projection. A geometric transformation matrix is ​​used. The spatial transformation relationship of the component relative to the frame is calculated using a matrix, with the rotation angle range of the transformation matrix set to 0-180 degrees. Homogeneous coordinate transformation is used to calculate the spatial mapping coordinates of the component in the simulated elevator frame, with a coordinate accuracy of 0.1 mm, obtaining the component's position projection data. Based on the component's position projection and the elevator's energy consumption distribution, the component's energy consumption is calculated. The component network performance is then derived based on the component's energy consumption data and overall elevator parameters. The energy balance equation is used to calculate the component's energy consumption: E = P·t, where E is the component's energy consumption in joules (J), P is the power in watts (W), and t is the running time in seconds (s), with the power measurement range set to 1-500 watts. Fourier series expansion is used to calculate the time series characteristics of the overall elevator energy consumption parameters, with the series expansion order set to 5-20. The component network performance is derived by combining the component's energy consumption data and overall elevator parameters, using a graph convolutional network (GCN). The network is used to calculate the energy transfer path between components. The number of network layers is set to 2-5 and the number of nodes is set to 50-500. The network performance data of the components is obtained. The interaction performance of the components is calculated based on the network performance and the independent performance of the components. The energy interaction process between the components is simulated by a Markov process, and the state transition probability threshold is set to 0.1-0.9. Obtain component interaction performance data, and perform functional block decomposition on the component independent performance data to obtain component functional blocks. Calculate the functional independence of components within the system using Functional Module Decomposition (FMD). Set the functional independence score range to 0-100 points and the score threshold to 50 points. Components with scores below the threshold are further decomposed into functional blocks. Calculate the functional similarity between components using Hierarchical Clustering (HCL). Set the similarity threshold to 80%-100% to obtain component functional block data. Fit the energy efficiency response of the component functional blocks to obtain the component energy efficiency distribution. Use Multiple Regression (MR) analysis. (Analysis) The relationship between component energy consumption and variables such as load and speed is calculated, with regression coefficients ranging from 0.1 to 10.0. The regression equation is: E = a·L + b·v + c, where E is component energy consumption in joules (J), L is load in newtons (N), v is speed in meters per second (m / s), and a, b, and c are regression coefficients. The least squares method is used to solve for the regression coefficients, with the calculation error range set within 0.1%. Component energy efficiency distribution data is obtained. Global correlation and aggregation of the component energy efficiency distribution data yields component performance data. Principal Component Analysis (PCA) is then used to analyze the data. The analysis method is used to calculate the main components of the component's energy efficiency characteristics. The contribution rate threshold for the principal components is set at 85%-95%. The top 3-5 principal components are extracted and globally aggregated. The K-Means clustering algorithm is used to calculate the component performance categories, with 3-7 clusters. Based on the component performance data and component interaction performance, output performance is integrated to obtain the integrated output performance. The weighted average method is used to calculate the comprehensive score of the component performance, with a weight range of 0.1-0.9. The Delphi method is used to calculate the weight coefficients, with 10-30 experts in the expert group. Weighted scores for different components are calculated and normalized, with a normalization interval of 0-1. Integrated output performance data is obtained. An elevator component performance model is constructed based on the integrated output performance and frame movement performance loss. The performance prediction model is trained using Support Vector Regression (SVR), with the kernel function set as Radial Basis Function (RBF) and the penalty parameter C set to a range of 0.The model error was set to within 1% (range 1-100). Cross-validation was used to calculate the model's generalization ability, with 5-10 folds used in the cross-validation process, ultimately yielding the elevator component performance model.

[0162] Of particular importance is the calculation of component energy consumption based on component location projection and elevator energy distribution, and the joint derivation of component network performance based on component energy consumption data and overall elevator parameters; the evaluation of component interaction performance based on component network performance and component independent performance includes:

[0163] Spatial correlation is performed on the component position projection data to obtain component topology connection data;

[0164] Energy transfer is tracked from component topology connection data, and elevator energy consumption distribution data is mapped based on the energy transfer path;

[0165] Analysis of component energy consumption characteristics based on elevator energy consumption distribution data;

[0166] Based on the energy consumption characteristics of components and the overall parameters of the elevator, the network association is reconstructed, and the system performance is collaboratively mapped to obtain the network performance of the components.

[0167] Feature decoupling is performed on the independent performance data of components to obtain component feature vectors;

[0168] Topology penetration analysis is performed on the component network performance to obtain the network flow structure;

[0169] The interaction potential energy of components is analyzed based on the network fluid structure and component feature vectors, and the interaction performance of components is mapped based on the interaction potential energy.

[0170] In this embodiment, spatial correlation is performed on the component position projection data to obtain component topology connection data. A three-dimensional coordinate mapping method is used to model the spatial position data of the elevator components, with a coordinate accuracy set to 0.1 mm. The positions of fixed components (such as guide rails and shaft walls) and moving components (such as the car and counterweight) of the elevator frame are calibrated using the Delaunay triangulation algorithm. Triangulation was used to calculate the shortest connection path between components, setting a path length threshold of 10-1000 mm. Topological analysis was performed on the spatial connections between adjacent components, using the K-Nearest Neighbors (KNN) method to define adjacency relationships, with K values ​​ranging from 3 to 7. The connection data was normalized, with a normalization range of 0-1, ultimately yielding the topological connection data of the elevator components. Energy transfer was tracked using this topological connection data, and elevator energy consumption distribution data was mapped based on the energy transfer paths. The energy conservation principle was used to calculate the energy transfer path between elevator components, setting a power loss threshold of 1-100 watts (W) per unit time. The finite difference method (FDM) was used to calculate the energy transfer rate, with a time step of 1-10 milliseconds. A Markov process was used to analyze the state of the energy transfer chain, with the state transition matrix dimension set to 5-20. Simulations of energy flow under different operating conditions were performed using Monte Carlo simulation. The simulation method is set to run 1000-10000 simulations, and regression analysis is performed on the simulation data. The goodness-of-fit R-value is set. 2With a threshold of 0.9-1.0, elevator energy consumption distribution data was obtained. Based on this data, component energy consumption characteristics were analyzed. Fourier transform was used to calculate the frequency domain characteristics of the component power consumption signal, with a transform order of 10-50. Power spectral density analysis (PSD) was used to calculate the component's energy distribution, with a frequency resolution of 0.1-5 Hz. Mutual information entropy was used to calculate the distribution characteristics of the component energy consumption data, with an entropy range of 0.1-1.0. Principal component analysis (PCA) was performed on the energy consumption characteristic data, with a principal component contribution rate threshold of 85%-95%. Finally, the energy consumption characteristics of the elevator components were obtained. Based on the component energy consumption characteristics and overall elevator parameters, network reconstruction was performed, and system performance was collaboratively mapped to obtain the component network performance. A weighted undirected graph was used. A graph (Graph) is constructed to represent the energy consumption network of the elevator components. The number of graph nodes is set to 50-500, and the edge weights range from 0.1-1.0. The Dijkstra Algorithm is used to calculate energy transmission paths, with power loss as the path cost function. Hierarchical clustering is used to classify the component energy consumption data, with 2-4 clustering layers. Dynamic Time Warping (DTW) is used to calculate the similarity of energy consumption data, with a similarity threshold of 0.8-1.0. System performance co-mapping is performed on the reconstructed energy consumption network, and a Deep Neural Network (DNN) is used to calculate system performance co-parameters. The network has 3-7 layers, with 100-500 hidden neurons. Finally, the network performance of the elevator components is obtained. Feature decoupling is performed on the independent performance data of each component to obtain component feature vectors. A Convolutional Neural Network (CNN) is then used to perform feature mapping. Spatial features of components are extracted using a network, with a convolution kernel size of 3×3. Temporal features of components are extracted using a Long Short-Term Memory (LSTM) network, with the number of LSTM units set to 50-200. The optimal feature subset of independent performance data of components is calculated using a feature selection algorithm, with the feature selection threshold set to 0.05-0.5. Finally, the feature vectors of the elevator components are obtained. Topological permeation analysis is performed on the network performance of the components to obtain the network fluid dynamics structure. Computational Fluid Dynamics (CFD) is used to calculate the flow characteristics of the elevator energy flow, with a mesh size of 0.1-1 mm. Finite Element Analysis (FEA) is used to calculate the stress distribution of the network topology, with a stress threshold of 10-100 MPa. The PageRank algorithm is used to calculate the network flow importance of the components, with a damping factor of 0.85. Time series analysis is performed on the fluid dynamics structure data, using an Autoregressive Moving Average (ARMA) model with an order of 1-5 to obtain the final network fluid dynamics structure of the elevator components. Based on the network fluid dynamics structure and component feature vectors, the interaction potential energy of the components is analyzed, and the interaction performance of the components is mapped based on the interaction potential energy. Hamiltonian mechanics is used to calculate the interaction potential energy of the components, and the total energy conservation condition of the system is set. Lagrangian mechanics is then applied. Mechanics were used to calculate the relative motion relationships between components. The generalized coordinate system was set to 3-6 dimensions. Particle Swarm Optimization (PSO) was employed to calculate the optimal interaction parameters of the components, with a particle swarm size of 50-200 particles. Feature extraction was performed on the interaction potential energy data, and Principal Component Analysis (PCA) was used to screen for the optimal interaction mode. The principal component contribution rate threshold was set at 85%-95%, ultimately yielding the interaction performance of the elevator components.

[0171] The present invention also provides a system for constructing a performance model for elevator components, for executing the method for constructing a performance model for elevator components as described above, the system comprising:

[0172] The spectrum modeling module is used to collect elevator usage records; perform flow spectrum modeling on the elevator usage records to generate start-stop spectrum features; and perform flow-frequency co-fitting to obtain elevator usage pattern features.

[0173] The dynamic analysis module is used to analyze the component response characteristics of elevator usage patterns to obtain dynamic characteristic indicators; and to calculate the independent performance of components based on the dynamic characteristic indicators.

[0174] The interactive network module is used to reconstruct the elevator interactive network based on the independent performance of components and the characteristics of elevator usage patterns; and to calculate the elevator energy consumption distribution based on the characteristics of elevator usage patterns and the elevator interactive network.

[0175] The frame simulation module is used to obtain the overall parameters of the elevator; to perform elevator frame simulation based on the overall elevator parameters; and to calculate the frame movement performance loss based on the simulated elevator frame.

[0176] The model building module is used to project the component positions of the simulated elevator frame based on the component independent performance, and evaluate the component interaction performance based on the component position projection, component independent performance, and elevator energy consumption distribution; and to build an elevator component performance model based on the component independent performance, component interaction performance, and frame movement performance loss.

[0177] This invention achieves in-depth analysis of elevator operating characteristics through the collection and analysis of elevator usage records. The generated start-stop spectrum features provide data support for understanding elevator usage patterns. The results of flow-frequency co-fitting reveal the elevator's operating patterns, which helps optimize elevator operating strategies. The component response analysis capability of the dynamic analysis module improves the understanding of the working status of various elevator components. The calculation of dynamic characteristic indicators makes the evaluation of component performance more scientific and systematic. The construction of the interactive network module provides a modeling basis for the interaction between various components of the elevator system. The effectively calculated elevator energy consumption distribution supports energy-saving retrofitting and optimization design. The frame simulation module evaluates the working performance of the elevator frame through the acquisition of overall parameters and simulation analysis. The accurately calculated frame movement performance loss provides a basis for elevator operation and maintenance. The model building module constructs an elevator component performance model that covers the mutual influence and comprehensive performance between various components by evaluating component position projection and interaction performance. This provides comprehensive data support and decision-making basis for the intelligent management and optimization of the elevator system, improving the overall efficiency and stability of elevator operation and promoting the continuous improvement and development of the elevator system.

[0178] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed, implements the method for constructing a performance model of elevator components as described in any of the above claims.

[0179] This invention enables the efficient execution of a method for constructing performance models of elevator components by storing a computer program. The executableness of the program ensures the automation and standardization of the model construction process, improving computational efficiency and accuracy. The stored program can flexibly adapt to the characteristics of different elevator systems, enabling personalized parameter settings and analysis. Leveraging the powerful computing capabilities of the computer system, it can perform large-scale data processing and analysis, thereby improving the reliability and timeliness of elevator usage data. The modular design of the program makes the connection between various functional modules smoother, facilitating subsequent maintenance and upgrades. The computer-readable implementation also supports compatibility with multiple platforms and devices, improving the application scope and convenience, effectively meeting the needs of intelligent elevator management and optimization, and providing theoretical and practical basis for the efficient operation and sustainable development of elevator systems.

Claims

1. A method for construction of an elevator component performance model, characterized by, Comprising the following steps: Step S1: Collecting elevator usage records; modeling the flow spectrum of the elevator usage records to generate start-stop spectrum features; Performing flow-frequency collaborative fitting to obtain elevator usage pattern features; Step S2: Analyzing the elevator usage pattern features for component response to obtain dynamic characteristic indicators; calculating component independent performance based on the dynamic characteristic indicators; Step S2 comprises the following steps: Step S21: Decomposing the elevator usage pattern features for component load, and querying the component response characteristics in the elevator usage pattern features based on the component load data; Step S22: Identifying component transfer functions based on the component response characteristics and the component load data; performing pole-zero analysis on the component transfer functions, and mapping dynamic characteristic indicators; Step S23: Determining stability boundaries based on the dynamic characteristic indicators, and dividing component stability ranges according to the stability boundaries; Step S24: Identifying key operating parameters of the dynamic characteristic indicators according to the component stability ranges to obtain component key operating parameters; fitting performance curves for the component key operating parameters to generate component independent performance; Step S3: Reconstructing an elevator interaction network according to the component independent performance and the elevator usage pattern features; calculating elevator energy consumption distribution based on the elevator usage pattern features and the elevator interaction network; Reconstructing the elevator interaction network comprises: Deriving elevator operation data according to the elevator usage pattern features; Splitting the elevator operation data to obtain elevator component operation data; Performing component dependency analysis on the elevator component operation data to obtain inter-component dependency relationships; Positioning the cause-effect direction of the inter-component dependency relationships, and identifying component subordination relationships based on the cause-effect direction; Reconstructing the elevator interaction network based on the component independent performance and the component subordination relationships; Calculating the elevator energy consumption distribution comprises: Identifying key connection skeletons of the elevator interaction network; Identifying redundant path sets of the associated connection skeletons to obtain backup paths; Constructing an elevator interaction network topology according to the key connection skeletons and the backup path sets; Mapping elevator energy consumption on the elevator usage pattern features, and mapping connection energy on the elevator interaction network topology based on the elevator energy consumption, and identifying the elevator energy consumption distribution based on the connection energy data; Step S4: Obtaining elevator overall parameters; simulating an elevator framework based on the elevator overall parameters; calculating framework movement performance loss based on the simulated elevator framework; wherein the method for obtaining the elevator overall parameters comprises calling elevator operation database including elevator rated load, elevator rated speed, elevator guide rail spacing, elevator balance coefficient, and elevator traction ratio basic parameters as the elevator overall parameters; Step S5: Projecting components on the simulated elevator framework based on the component independent performance, and evaluating component interaction performance according to the component position projection, the component independent performance, and the elevator energy consumption distribution; constructing an elevator component performance model according to the component independent performance, the component interaction performance, and the framework movement performance loss.

2. The method for construction of an elevator component performance model according to claim 1, characterized in that, Step S1 comprises the following steps: Step S11: Collecting elevator usage records; extracting elevator usage flow in the elevator usage records; Step S12: Dividing the elevator usage flow into time window segments to obtain time-periodic usage flow; inferring flow periodicity patterns according to the time-periodic usage flow; Step S13: Outlier detection is performed on the flow periodic pattern, the outlier threshold is set to 2.5 times the standard deviation, outliers are removed, and a purified flow pattern is generated; historical start-stop frequency data in the elevator usage record is extracted; Step S14: The historical start-stop frequency is statistically filtered and frequency domain converted to obtain start-stop frequency spectrum features; Step S15: Peaks of the start-stop frequency spectrum features are identified and marked as key frequency feature points; the purified flow pattern and the key frequency feature points are subjected to flow spectrum collaborative analysis to obtain flow-frequency correlation data; Step S16: Collaborative variable distribution data are extracted based on the flow-frequency correlation data, and working condition fitting is performed based on the collaborative variable distribution data to obtain elevator usage mode features.

3. The method for construction of an elevator component performance model according to claim 1, characterized in that, The elevator frame simulation based on the elevator overall parameters in step S4 includes: The elevator overall parameters are subjected to feature dimension expansion to obtain a parameter hierarchical set; The parameter hierarchical set is subjected to constraint coupling integration to generate parameter correlation data; The parameter correlation data are subjected to frame mechanics load projection to obtain frame load distribution, wherein the load types include static load, the range of which is 1.0-1.5 times the rated load, dynamic load, the range of which is 0.2-0.5 times the rated load, and impact load, the range of which is 0.1-0.3 times the rated load; Component rigidity demand is mapped according to the frame load distribution to obtain frame component rigidity demand; Main load-bearing member parameters of the elevator overall parameters are identified; The geometric features of the load-bearing members are determined based on the main load-bearing member parameters, and stress distribution analysis is performed according to the geometric features of the load-bearing members to obtain load-bearing stress distribution data; Three-dimensional simulation is performed on the main load-bearing member parameters, and stress deformation simulation is performed on the simulated load-bearing members based on the load-bearing stress distribution data to generate simulated deformation load-bearing members; External end contact surface member parameters of the elevator overall parameters are identified; External end contact areas of the external end contact surface member parameters are determined, and prominent member parameters of the external end contact surface member parameters are screened based on the external end contact areas; Elevator component morphology simulation is performed based on the simulated deformation load-bearing members and the prominent member parameters to obtain reconstructed elevator component morphology; Component topology matching is performed on the reconstructed elevator component morphology according to the frame component rigidity demand to obtain matched elevator components; Elevator frame simulation is performed based on the matched elevator components, wherein the number of nodes of the simulation model is 1000-10000, and the simulation time step is 0.01-0.1 seconds.

4. The method for construction of an elevator component performance model according to claim 1, characterized in that, The calculation of frame movement performance loss based on the simulated elevator frame in step S4 includes: The structure freedom degrees of the simulated elevator frame are expanded to obtain frame freedom degree data; The elevator frame movement mode is calibrated according to the frame freedom degree data; The simulated elevator frame is subjected to stress mapping transformation according to the elevator frame movement mode to generate a frame movement benchmark; Contact surface energy distribution in the frame movement benchmark is extracted, and frame contact areas are inferred based on the contact surface energy distribution; Frame friction force data are generated by dynamically fitting the frame contact areas; Frame friction response data are obtained by calculating the power consumption of the frame friction matrix. The frame friction response data is subjected to support member moment distribution to obtain frame support stress data; Frame resistance characteristics are mapped based on the frame support stress data; Performance degradation is calculated according to the frame resistance characteristics, and degradation effects are accumulated based on the performance degradation data to generate frame movement performance loss.

5. The method for construction of an elevator component performance model according to claim 1, characterized by, Step S5 includes the following steps: Step S51: split the elevator component units of the simulation elevator frame; based on the component units, component unit matching is performed on the component independent performance to obtain a matching relationship; Step S52: based on the matching relationship, the component independent performance is projected to the simulation elevator frame to obtain component position projection; Step S53: component energy consumption calculation is performed according to the component position projection and the elevator energy consumption distribution, and component network performance is jointly deduced based on the component energy consumption data and the overall parameters of the elevator; component interaction performance is evaluated based on the component network performance and the component independent performance; Step S54: the component independent performance data is subjected to functional block splitting to obtain component functional blocks; component energy efficiency distribution is obtained by fitting the energy efficiency response of the component functional blocks; Step S55: component performance data is obtained by globally correlating and aggregating the component energy efficiency distribution data; integrated output performance is obtained by integrating the output performance based on the component performance data and the component interaction performance; Step S56: an elevator component performance model is constructed according to the integrated output performance and the frame movement performance loss.

6. A system for construction of an elevator component performance model, characterized by The system for constructing an elevator component performance model for performing the method for constructing an elevator component performance model according to claim 1 comprises: A spectrum modeling module for collecting elevator usage records; performing flow spectrum modeling on the elevator usage records to generate start-stop spectrum characteristics; and performing flow-frequency collaborative fitting to obtain elevator usage mode characteristics; A dynamic analysis module for performing component response analysis on the elevator usage mode characteristics to obtain dynamic characteristic indicators; and deducing component independent performance based on the dynamic characteristic indicators; An interaction network module for reconstructing an elevator interaction network according to the component independent performance and the elevator usage mode characteristics; and deducing elevator energy consumption distribution based on the elevator usage mode characteristics and the elevator interaction network; A frame simulation module for obtaining overall parameters of the elevator; performing elevator frame simulation on the overall parameters of the elevator; and calculating frame movement performance loss based on the simulation elevator frame; A model construction module for performing component position projection on the simulation elevator frame based on the component independent performance; evaluating component interaction performance according to the component position projection, the component independent performance, and the elevator energy consumption distribution; and constructing an elevator component performance model according to the component independent performance, the component interaction performance, and the frame movement performance loss.

7. A computer readable storage medium storing a computer program, wherein the computer program comprises program instructions configured to cause a processor to perform the method according to any one of claims 1 to 6. The computer program, when executed, implements the method for constructing an elevator component performance model according to any one of claims 1 to 5.

Images