Elevator equipment health data driving evaluation method and system

Abstract

The invention relates to the technical field of elevator health, and discloses an elevator equipment health data driving evaluation method and system.The method comprises the steps that noise data of multi-source monitoring data in an elevator is filtered out, data format unification is conducted on the filtered data, and standardized monitoring data is obtained; constructing a health data stream based on the historical health database; performing differential analysis on the health data stream and a compliance data stream of a historical health database to obtain a health deviation detection quantity; when the elevator runs, the running state risk and the elevator taking environment risk of the elevator are comprehensively judged by taking the health deviation detection quantity as an evaluation reference, and a risk evaluation result is obtained; mapping the risk assessment result into a risk level table of the elevator to obtain a risk level; according to the risk level, a safety response action of the elevator is triggered, and the safety response action is coded into a response instruction to control safety operation of the elevator; according to the method, the accuracy of elevator equipment health data driving evaluation can be improved.

Description

Technical Field

[0001] This invention relates to the field of elevator health technology, and in particular to a data-driven assessment method and system for elevator equipment health. Background Technology

[0002] Existing technologies for elevator safety monitoring have significant shortcomings in data preprocessing and data stream construction. They fail to systematically filter noise and standardize the format of multi-source monitoring data, simply filtering out obvious noise or retaining the original data format. This results in invalid information and format chaos in the data, making it impossible to form standardized monitoring data and providing low-quality basic data for subsequent analysis. When constructing the data stream, they fail to combine historical health databases to hierarchically divide and strengthen the correlation between operational data and elevator environment data. They simply integrate the data in a disordered manner or arrange it in a single dimension, failing to reflect the differentiated importance of different data for safety monitoring and making it difficult to ensure logical consistency between data. The generated data stream lacks specificity and completeness and cannot accurately support safety assessments.

[0003] Existing technologies have significant shortcomings in elevator safety deviation detection and risk response. They fail to accurately calculate health deviation detection volumes by differentially analyzing health and compliance data streams, relying solely on single data thresholds to judge deviations. This fails to comprehensively capture multi-dimensional feature differences, resulting in insufficient accuracy in deviation detection results. Risk assessments do not comprehensively consider both operational status and the passenger environment, nor do they construct risk correlation maps for collaborative analysis. They only assess single risk types in isolation, leading to one-sided risk assessment results that fail to reflect the correlation between risks. Safety responses do not match corresponding action combinations based on risk levels, employing only fixed response patterns and failing to encode actions into standardized instructions. This results in low response specificity and execution efficiency, hindering timely and effective handling of safety risks and failing to adequately guarantee elevator safety. Summary of the Invention

[0004] This invention provides a data-driven assessment method and system for elevator equipment health to address the problems mentioned in the background section.

[0005] To achieve the above objectives, the present invention provides a data-driven assessment method for elevator equipment health, comprising: S1. Filter out the noise data from the multi-source monitoring data in the elevator, and unify the data format of the filtered data to obtain the standardized monitoring data of the elevator; S2. Based on the elevator's historical health database, the elevator's health data stream is constructed using the operational data from the standardized monitoring data as the first-level stream and the elevator riding environment data as the second-level stream. S3. Perform differential parsing on the health data stream and the compliant data stream of the historical health database to obtain the health deviation detection quantity of the elevator; S4. During elevator operation, the health deviation detection quantity is used as the evaluation benchmark to comprehensively determine the elevator's operating status risk and riding environment risk, and obtain the elevator's risk assessment result; S5. Map the risk assessment results to the risk level table of the elevator to obtain the risk level of the elevator; S6. Based on the risk level, trigger the elevator's safety response action and encode the safety response action into a response command to control the safe operation of the elevator.

[0006] In a preferred embodiment, the process of filtering out noise data from multi-source monitoring data in the elevator and standardizing the data format of the filtered data to obtain standardized monitoring data for the elevator includes: Receive elevator operating parameter data and elevator riding environment data, and integrate the operating parameter data and the elevator riding environment data into multi-source monitoring data of the elevator; By removing invalid data points from the multi-source monitoring data at different scales, the valid monitoring data of the elevator is obtained. The valid monitoring data is low-pass filtered to obtain the standard monitoring data of the elevator; The basic format of various types of data in the standardized monitoring data is unified to obtain the standardized monitoring data of the elevator.

[0007] In a preferred embodiment, the step of constructing the elevator's health data stream based on the elevator's historical health database, using operational parameter data from the standardized monitoring data as the first-level stream and elevator environment data as the second-level stream, includes: Based on the multiple data characteristics in the standardized monitoring data, the operating parameter data is divided into core operating parameters and auxiliary operating parameters; The core operating parameters are placed at the basic level, and the auxiliary operating parameters are placed at the top level to obtain the hierarchical operating data of the elevator; The elevator's hierarchical environmental data is obtained by placing environmental factors that directly affect safety in the elevator riding environment data at the priority level and placing indirect factors in the elevator riding environment data at the lag level. Using the hierarchical operational data as the first level and the hierarchical environmental data as the second level, the associated data group of the elevator is constructed. The associated data group is matched with the typical operating condition template of the historical health database in the elevator to obtain the matching result of the elevator. Based on the matching results, the logical consistency in the associated data group is calibrated to obtain the health data stream of the elevator.

[0008] In a preferred embodiment, constructing the elevator's associated data group, using the hierarchical operational data as the first level and the hierarchical environmental data as the second level, includes: The hierarchical operation data and the hierarchical environment data are divided into time windows to obtain the elevator's operation data segment and environment data segment; Within the same time window, the running data segment and the environmental data segment are correlated based on their matching degree to obtain the preliminary associated data group of the elevator; Based on typical operating scenarios in the historical health database, scenario identifiers are assigned to the preliminary associated data groups to obtain scenario-labeled data for the preliminary associated data groups; Based on the scene-labeled data, the correlation strength of key data in the preliminary correlation data group is strengthened to obtain the correlation data group of the elevator.

[0009] In a preferred embodiment, the step of performing differential analysis between the health data stream and the compliant data stream of the historical health database to obtain the health deviation detection quantity of the elevator includes: The health data stream is divided into multiple consecutive data segments to obtain the elevator's safety data segment set; Extract compliant data segments from the historical health database to obtain a set of compliant data segments from the historical health database; By identifying the key features between the safety data segment set and the compliance data segment set, the safety feature set and compliance feature set of the elevator are obtained. The safety feature set and the compliance feature set are compared by comparing the feature difference points to obtain the feature difference set of the elevator; The degree of difference in the feature difference set is evaluated to obtain multi-level difference results for the feature difference set. Based on the multi-level difference results, the feature difference set is coupled and analyzed to obtain the health deviation detection quantity of the elevator.

[0010] In a preferred embodiment, the step of performing coupled analysis on the feature difference set based on the multi-level difference results to obtain the elevator's health deviation detection quantity includes: Influence factor analysis is performed on the feature difference points in the feature difference set to determine the influence factor set of the feature difference points; Based on the multi-level difference results, a level weight coefficient is assigned to the feature difference points to obtain the level weight coefficient set of the feature difference points. Based on the set of grade weight coefficients, the deviation of the influencing factor set is calculated to obtain the preliminary deviation detection amount of the elevator. The calculation formula for the preliminary deviation detection amount is as follows: ; In the formula, This is the initial deviation detection amount. For the first The difference values ​​of each feature difference point For the first The influence factors of the influence factor set corresponding to each characteristic difference point. For the first The weight coefficients of the set of grade weight coefficients corresponding to each feature difference point. This represents the total number of the feature difference points; The preliminary deviation detection value is normalized to obtain the health deviation detection value of the elevator.

[0011] In a preferred embodiment, during elevator operation, the step of using the health deviation detection quantity as an evaluation benchmark to comprehensively determine the elevator's operational status risk and riding environment risk, and obtaining the elevator's risk assessment result, includes: Risk factors are identified in the health deviation detection data to obtain the risk factor classification results of the health deviation detection data; Logical judgment is made on the operational status-related deviations of the risk factor classification results to obtain the preliminary operational risk of the elevator; By mapping the environmental factor-related deviations of the risk factor classification results to risk characteristics, the preliminary environmental risk of the elevator can be obtained. Using the initial operational risks as risk nodes and the initial environmental risks as risk edges, a risk association graph of the elevator is constructed. Based on the risk correlation map, the preliminary operational risks and the preliminary environmental risks are synergistically integrated to obtain the risk assessment results of the elevator.

[0012] In a preferred embodiment, mapping the risk assessment results to the elevator's risk level table to obtain the elevator's risk level includes: The risk assessment results are analyzed in two dimensions to obtain the elevator's operational risk component and environmental risk component; The operational risk component and the environmental risk component are mapped to the risk level table of the elevator to determine the risk level range of the elevator; The risk level range is integrated according to a preset level fusion rule to obtain the risk level of the elevator.

[0013] In a preferred embodiment, triggering a safety response action of the elevator based on the risk level and encoding the safety response action into a response command to control the safe operation of the elevator includes: Based on the risk level, determine the response level of the elevator; Based on the aforementioned response level, a corresponding combination of safety response actions is matched from a preset safety response action library to obtain the elevator's action execution sequence; The control instruction is encoded into the sequence of actions to obtain the elevator's response instruction; The response command is sent to the elevator's control terminal to trigger the elevator's corresponding safety operation.

[0014] To address the above problems, the present invention also provides an elevator equipment health data-driven assessment system, the system comprising: The data standardization module is used to filter out noise data from multi-source monitoring data in the elevator and to unify the data format of the filtered data to obtain standardized monitoring data of the elevator. The health data stream construction module is used to construct the health data stream of the elevator based on the elevator's historical health database, using the operational data in the standardized monitoring data as the first-level stream and the elevator riding environment data as the second-level stream; The safety deviation detection module is used to perform differential parsing between the health data stream and the compliant data stream of the historical health database to obtain the health deviation detection quantity of the elevator. The risk assessment module is used to comprehensively determine the operational status risk and riding environment risk of the elevator when the elevator is running, based on the health deviation detection quantity as the assessment benchmark, and obtain the risk assessment result of the elevator. The risk level mapping module is used to map the risk assessment results to the risk level table of the elevator to obtain the risk level of the elevator. The safety response module is used to trigger the elevator's safety response action according to the risk level, and encode the safety response action into a response command to control the safe operation of the elevator.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention provides high-quality data support for elevator safety monitoring through standardized data processing and hierarchical data flow construction. It integrates elevator operating parameters and passenger environment data, removing invalid data, performing low-pass filtering, and standardizing formats to generate accurate, standardized monitoring data. Based on a historical health database, it divides operating and environmental data into different levels, strengthens the correlation of key data through time window matching and scene identification, and constructs a health data flow after calibrating logical consistency, comprehensively and systematically presenting the core information of elevator operation and the environment.

[0016] 2. This invention significantly improves the reliability and timeliness of elevator safety monitoring by leveraging precise deviation detection and tiered safety response. Through differential analysis of health and compliance data streams, it identifies feature differences and couples them to calculate the health deviation detection quantity. Using this quantity as a benchmark, a risk correlation graph is constructed to comprehensively determine both operational and environmental risks and map risk levels. Based on the risk level, corresponding safety response action combinations are matched, encoded into response commands, and sent to the control terminal, enabling rapid identification and precise handling of safety risks and comprehensively ensuring elevator safety. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a data-driven health assessment method for elevator equipment according to an embodiment of the present invention. Figure 2 A functional block diagram of an elevator equipment health data-driven assessment system provided in an embodiment of the present invention; 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

[0018] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] This application provides a data-driven assessment method for elevator equipment health. The execution entity of this data-driven assessment method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the data-driven assessment method for elevator equipment health can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0020] Reference Figure 1 The diagram shown is a flowchart illustrating a data-driven health assessment method for elevator equipment according to an embodiment of the present invention. In this embodiment, the data-driven health assessment method for elevator equipment includes: S1. Filter out the noise data from the multi-source monitoring data in the elevator, and unify the data format of the filtered data to obtain the standardized monitoring data of the elevator; In this embodiment of the invention, noise data from multi-source monitoring data in the elevator is filtered out, and the filtered data is formatted to obtain standardized monitoring data for the elevator, including: Receive elevator operating parameter data and elevator riding environment data, and integrate the operating parameter data and the elevator riding environment data into multi-source monitoring data of the elevator; By removing invalid data points from the multi-source monitoring data at different scales, the valid monitoring data of the elevator is obtained. The valid monitoring data is low-pass filtered to obtain the standard monitoring data of the elevator; The basic format of various types of data in the standardized monitoring data is unified to obtain the standardized monitoring data of the elevator.

[0021] By deploying various sensors and monitoring devices on the elevator, real-time data on elevator operation parameters and passenger environment are collected. Operational parameter data includes information directly related to elevator operation, such as elevator speed, car position, door open / close status, and traction machine operating status. Passenger environment data includes environmentally relevant information such as temperature, humidity, air quality, and lighting brightness inside the car. The collected data from both types are correlated and integrated according to timestamps to form multi-source monitoring data for the elevator, covering both elevator operation and environmental conditions.

[0022] The integrated multi-source monitoring data is checked item by item. Invalid data points are identified and removed based on the reasonable range of data values, logical correlation, and normal operating thresholds of the acquisition equipment. For operating parameter data, if a data point exceeds the maximum or minimum operating range designed by the equipment, or has obvious logical contradictions with parameter data at adjacent time points, it is determined to be an invalid data point. For elevator environment data, if a data point deviates significantly from the normal environmental value range, or remains unchanged for a long time and does not match the actual environmental perception, it is also determined to be an invalid data point. After screening and processing, the valid monitoring data of the elevator is obtained.

[0023] Low-pass filtering is employed to process the effective monitoring data. Low-pass filtering retains useful lower-frequency signals while attenuating or filtering out higher-frequency noise signals. Specifically, based on the time series of the data, a moving average is used to smooth the effective monitoring data, correlating the value of each data point with the average value of multiple adjacent data points. This reduces the impact of instantaneous noise fluctuations on data accuracy, resulting in a smoother data trend and ultimately obtaining standardized elevator monitoring data.

[0024] The process involves streamlining the original formats of various types of monitoring data, including differences in unit representation, numerical precision, and storage format. A unified unit standard is established for all types of data, converting the same type of data expressed in different units into a unified unit. Standardized numerical precision requirements are set, and values ​​exceeding or falling short of precision are rounded down or supplemented accordingly. All data is then structured according to a pre-defined storage format standard to ensure consistency in format across all data types, ultimately resulting in standardized, uniform, and orderly elevator monitoring data.

[0025] The beneficial effects are that by receiving and integrating elevator operating parameter data and passenger environment data into multi-source elevator monitoring data, it can comprehensively gather the core data required for elevator safety monitoring. Operating parameter data directly reflects the working status and operational stability of the elevator's core components, while passenger environment data reflects the safety and comfort conditions inside the car. After being linked and integrated by timestamp, these two data sets form a complete dataset covering both elevator operation and environmental dimensions, avoiding the one-sidedness of monitoring caused by single-dimensional data collection and providing comprehensive raw data support for subsequent data processing.

[0026] By removing invalid data points from multi-source monitoring data at different scales, valid elevator monitoring data can be obtained. This process filters out interference and ensures data quality. Based on reasonable value ranges, logical relationships, and equipment operating thresholds, invalid data that exceeds normal ranges, contains logical contradictions, or remains unchanged for a long time is accurately identified and removed. This avoids invalid data interfering with subsequent analysis results, ensuring that the retained data accurately reflects the actual operation and environmental conditions of the elevator, providing high-quality foundational data for noise filtering.

[0027] Low-pass filtering of effective monitoring data yields standardized elevator monitoring data, effectively reducing the impact of transient noise on data accuracy. Low-pass filtering, through a moving average method, retains the low-frequency useful signals reflecting the elevator's true state while attenuating high-frequency noise signals caused by equipment interference and transient fluctuations. This results in smoother data trends that better reflect reality, avoiding data distortion caused by noise and providing accurate and stable standardized data for a unified format.

[0028] Standardizing elevator monitoring data by unifying and standardizing the basic formats of various data types eliminates analytical obstacles caused by data format differences. By standardizing the units of measurement, numerical precision, and storage format, data from different sensors and of different types are converted into standardized structured data, avoiding the problem of data incompatibility due to format confusion. This makes the standardized monitoring data directly usable for constructing subsequent health data streams, significantly improving the efficiency and accuracy of data-driven health assessments of elevator equipment.

[0029] S2. Based on the elevator's historical health database, the elevator's health data stream is constructed using the operational data from the standardized monitoring data as the first-level stream and the elevator riding environment data as the second-level stream. In this embodiment of the invention, the step of constructing a health data stream for the elevator based on the elevator's historical health database, using operational parameter data from the standardized monitoring data as a first-level stream and elevator environment data as a second-level stream, includes: Based on the multiple data characteristics in the standardized monitoring data, the operating parameter data is divided into core operating parameters and auxiliary operating parameters; The core operating parameters are placed at the basic level, and the auxiliary operating parameters are placed at the top level to obtain the hierarchical operating data of the elevator; The elevator's hierarchical environmental data is obtained by placing environmental factors that directly affect safety in the elevator riding environment data at the priority level and placing indirect factors in the elevator riding environment data at the lag level. Using the hierarchical operational data as the first level and the hierarchical environmental data as the second level, the associated data group of the elevator is constructed. The associated data group is matched with the typical operating condition template of the historical health database in the elevator to obtain the matching result of the elevator. Based on the matching results, the logical consistency in the associated data group is calibrated to obtain the health data stream of the elevator.

[0030] The process of constructing the elevator's associated data group, using the hierarchical operational data as the first level and the hierarchical environmental data as the second level, includes: The hierarchical operation data and the hierarchical environment data are divided into time windows to obtain the elevator's operation data segment and environment data segment; Within the same time window, the running data segment and the environmental data segment are correlated based on their matching degree to obtain the preliminary associated data group of the elevator; Based on typical operating scenarios in the historical health database, scenario identifiers are assigned to the preliminary associated data groups to obtain scenario-labeled data for the preliminary associated data groups; Based on the scene-labeled data, the correlation strength of key data in the preliminary correlation data group is strengthened to obtain the correlation data group of the elevator.

[0031] A thorough analysis of the multi-data characteristics of operational parameters in standardized monitoring data is conducted. These characteristics include the degree of impact of the data on elevator safety, the close correlation with the working status of core components, and the sensitivity of data changes to elevator operational stability. Based on these characteristics, data that directly determines elevator operational safety, is directly related to the working status of core components such as the traction machine and car doors, and whose data changes have a significant impact on operational stability are classified as core operational parameters. Data that has a relatively small impact on elevator safety and is only used to supplement the working status of monitoring equipment or provide supplementary information about the operating environment are classified as auxiliary operational parameters, clearly distinguishing the functional positioning of the two types of operational parameters.

[0032] The hierarchical operational data construction logic is clearly defined, with ensuring the basic safe operation of elevators as the core principle, placing core operational parameters at the basic level. As the core data layer for elevator safety monitoring, the basic level prioritizes the collection, transmission, and analysis of data from this level to ensure real-time and accurate monitoring of core operational status. Simultaneously, auxiliary operational parameters are placed at the top level, with top-level data supplementing the basic level data to improve the comprehensive perception of elevator operational status. Together, these two levels form a clearly structured and prioritized hierarchical elevator operational data system.

[0033] A comprehensive analysis of the attributes of various environmental factors in elevator passenger environment data is conducted to determine whether each factor directly affects elevator operation safety or passenger safety. Environmental factors that directly impact safety, such as air quality data that severely exceeds standards and affects passenger health, and humidity data that may lead to electrical equipment malfunctions, are placed in a priority level. Priority data holds a core reference position in safety analysis. Environmental factors that do not directly affect safety, such as temperature data that slightly deviates from the comfort range but does not affect health, and lighting brightness adjustment data that does not affect equipment operation, are placed in a lagging level. Lagging data serves as a supplementary reference for safety assessment, thereby forming a hierarchical environmental data of elevators with a clear focus.

[0034] Following the hierarchical classification rules of health data streams, hierarchical operational data is designated as the first level, and hierarchical environmental data as the second level. Using timestamps as the link, hierarchical operational data and hierarchical environmental data within the same time dimension are paired and combined to ensure that each data set fully reflects the elevator's operational and environmental states at the corresponding moment. This pairing method constructs a hierarchical set of elevator-related data that combines both operational and environmental states, providing a structured data foundation for subsequent pattern matching.

[0035] The elevator's historical health database is retrieved. This database stores typical operating condition templates for elevators under different operating conditions. These templates include combinations of operating parameters and environmental data characteristics for various normal, abnormal, and fault conditions. The constructed associated data set is compared one by one with the typical operating condition templates in the historical health database. During the comparison, the focus is on the degree of fit between the associated data set and the template in core operating parameters and priority-level environmental data. At the same time, the matching of auxiliary operating parameters and lagging-level environmental data is also taken into account. Finally, the matching result of the elevator is obtained, and the operating condition type corresponding to the associated data set is determined.

[0036] Based on the operating condition type determined by the matching results, the logical consistency of the associated data group is calibrated against the normal logical relationships between data under that operating condition type. This involves checking for logical contradictions between core operating parameters and auxiliary operating parameters, such as core operating parameters indicating the elevator is running while auxiliary operating parameters indicate the equipment is stopped. Simultaneously, it verifies whether priority-level environmental data and hierarchical operating data conform to the usual correlation patterns under that operating condition, such as whether environmental vibration data under high-speed operation is within a reasonable logical range. Data with logical deviations are corrected and adjusted to ensure logical consistency among data within the associated data group and conformity to actual operating condition patterns, ultimately yielding the elevator's health data stream.

[0037] Based on the temporal continuity of elevator operation and the correlation of data changes, a fixed-length time window is set to synchronously divide the hierarchical operational data and hierarchical environmental data. During the division process, it is ensured that the start and end times of the time windows for both types of data are completely consistent. Each time window corresponds to a continuous segment of operational data and a segment of synchronous environmental data, forming the elevator's operational data segment and environmental data segment respectively, so that each segment of data can accurately correspond to the elevator's operation and environmental status within the same time period.

[0038] For the operational data segment and environmental data segment within the same time window, matching and correlation are performed from two dimensions: the time synchronization of data acquisition and the consistency of the scenario reflected by the data. The timestamps of each data point in the operational data segment are checked to ensure complete consistency with the corresponding data points in the environmental data segment, guaranteeing accurate matching of data in the time dimension. Simultaneously, the elevator operating status reflected in the operational data segment, such as start-up, acceleration, constant speed, and stopping, is analyzed to determine whether it conforms to the actual scenario logic with the environmental changes reflected in the environmental data segment. For example, is the change in vibration data inside the car during acceleration reasonable? Through this dual verification, a preliminary correlation data set for the elevator is formed.

[0039] Typical operating scenarios stored in the historical health database are retrieved. These scenarios cover various common operating conditions such as normal elevator start-stop, constant speed operation, door opening and closing, and fault alarms. Each typical operating scenario has a clear characteristic data identifier. The core operating parameters and priority level environmental data in the preliminary association data group are compared with the characteristic data of each typical operating scenario to identify the typical operating scenario with the most matching characteristics. A corresponding scenario identifier is assigned to this preliminary association data group. The identifier content directly reflects the type of operating scenario to which the data group belongs, forming the scenario label data of the preliminary association data group.

[0040] Based on the operational scenario types identified by the scenario-labeled data, we analyze the core data that plays a crucial role in the safe operation of elevators within these scenarios. This includes key indicators among the core operational parameters and core factors among the priority-level environmental data. By increasing the weight of these key data in the initial correlated data set, we strengthen the correlation logic between key data and other relevant data. For example, in a fault alarm scenario, we enhance the correlation strength between fault signal data and relevant operational parameter environmental data. This allows changes in key data to more clearly drive the correlation analysis of the entire data set, ultimately forming a closely linked and core-focused correlated data set for elevators.

[0041] The beneficial effects are that, based on the multiple data characteristics in standardized monitoring data, operational parameters are divided into core operational parameters and auxiliary operational parameters, which can accurately distinguish the impact weight of different operational data on elevator safety. By analyzing the correlation between data and the working status of core components, as well as their sensitivity to operational stability, the core operational parameters are identified as the key basis for safety monitoring, while auxiliary operational parameters serve as supplementary references. This avoids the shift in monitoring focus due to confusion about data importance and lays a clear data classification foundation for subsequent hierarchical data construction.

[0042] By placing core operating parameters at the basic level and auxiliary operating parameters at the top level, a hierarchical operating data structure for the elevator is obtained, enabling the establishment of a clearly prioritized operating data structure. The basic level prioritizes the collection, transmission, and analysis of core operating parameters, ensuring that the elevator's core operating status is captured accurately in real time. The top level serves as a supplementary level, improving the overall perception of the elevator's operating status. Together, they form a logically clear hierarchical system, preventing the obscuring of core information due to disordered data arrangement and improving the efficiency of operating data utilization.

[0043] By prioritizing environmental factors directly affecting safety and relegating indirect factors to a secondary level, we obtain hierarchical environmental data for elevators. This approach highlights critical safety information within the environmental data. Prioritized data focuses on core environmental factors impacting passenger health or equipment safety, ensuring this data holds a central position in safety analysis. Secondary data includes non-critical factors affecting only comfort, preventing non-core data from interfering with safety judgments. This makes environmental data analysis more targeted and aligns with the core needs of elevator safety monitoring.

[0044] By constructing a data set for the elevator using hierarchical operational data as the first level and hierarchical environmental data as the second level, deep coupling of operational and environmental data can be achieved. Pairing the two types of hierarchical data at the same moment using timestamps ensures that each data set fully reflects the elevator's operational and environmental states at that time, avoiding the biased safety analysis caused by isolated data. This forms a structured data set with both operational and environmental dimensions and clear hierarchical distinctions, providing an accurate data carrier for subsequent pattern matching.

[0045] By performing pattern matching between the associated data set and typical operating condition templates in the historical health database, the elevator's matching result can be obtained. This allows for the identification of the current operating condition type based on historical experience. The typical operating condition templates in the historical health database cover features of various scenarios, including normal, abnormal, and faulty conditions. By comparing the core features of the associated data set with those templates, the current operating condition of the elevator can be accurately determined, avoiding the problem of inaccurate judgment based solely on real-time data. This provides a clear operating condition reference for data logic calibration.

[0046] The elevator health data stream is obtained by calibrating the logical consistency of the associated data groups based on the matching results, ensuring the accuracy and reliability of the data stream. By comparing the normal logical relationships between data under the matching operating conditions, logical contradictions in the associated data groups are corrected, such as abnormal correlations between operating parameters and environmental data. This ensures that the logic between each data point in the data stream is self-consistent and conforms to the actual operating conditions, ultimately forming a complete, logically rigorous health data stream that can accurately support subsequent safety assessments, significantly improving the scientific rigor and effectiveness of elevator safety monitoring.

[0047] By dividing hierarchical operational data and hierarchical environmental data into time windows, elevator operational data segments and environmental data segments are obtained, enabling precise alignment of the two types of data in the time dimension. By setting fixed-length and synchronized time windows, it is ensured that each segment of operational data and its corresponding environmental data accurately reflects the elevator's operational and environmental status within the same time period, avoiding data correlation deviations caused by time misalignment. This provides a unified time-dimensional benchmark for subsequent data matching and correlation, making data correlation more timely and accurate.

[0048] By matching and associating operational and environmental data segments within the same time window, a preliminary associated data set for the elevator is obtained, establishing a direct correlation between operational and environmental data. Verifying the consistency of data timestamps ensures complete temporal synchronization between the two types of data. Simultaneously, analyzing the scenario logic of operational status and environmental changes, such as the reasonable changes in vibration data during elevator acceleration, verifies the reasonableness of data matching at the scenario level. This dual-verification process forms a preliminary associated data set, avoiding the problem of isolated data and providing a structured data foundation for subsequent scenario identification.

[0049] By assigning scenario identifiers to preliminary associated data groups based on typical operating scenarios in the historical health database, scenario-labeled data for these data groups is obtained, enabling precise correspondence between the data groups and actual operating scenarios. The typical operating scenarios in the historical health database cover various conditions such as normal elevator start-stop, constant speed operation, and fault alarms. By comparing the fit between the preliminary associated data groups and scenario characteristics, clear scenario attributes are assigned to the data groups, avoiding the problem of data groups containing only numerical values ​​without scenario meaning, and making subsequent data association strengthening more targeted.

[0050] By strengthening the correlation strength of key data in the initial correlation data group based on scene-labeled data, a correlation data group for elevators is obtained, which can highlight the core data value under different scenarios. Based on the scene identifier, key data that is crucial to safety in that scenario is identified, such as fault signals and related operating parameters in fault scenarios. By increasing the weight of key data, its correlation logic with other data is strengthened, allowing changes in key data to more clearly drive the analysis of the overall data group, preventing critical information from being buried. Ultimately, a closely correlated and core-focused correlation data group is formed, providing high-quality data units for the subsequent construction of health data streams, significantly improving the utilization efficiency and analytical accuracy of elevator safety monitoring data.

[0051] S3. Perform differential parsing on the health data stream and the compliant data stream of the historical health database to obtain the health deviation detection quantity of the elevator; In this embodiment of the invention, the step of performing differential parsing between the health data stream and the compliant data stream of the historical health database to obtain the health deviation detection quantity of the elevator includes: The health data stream is divided into multiple consecutive data segments to obtain the elevator's safety data segment set; Extract compliant data segments from the historical health database to obtain a set of compliant data segments from the historical health database; By identifying the key features between the safety data segment set and the compliance data segment set, the safety feature set and compliance feature set of the elevator are obtained. The safety feature set and the compliance feature set are compared by comparing the feature difference points to obtain the feature difference set of the elevator; The degree of difference in the feature difference set is evaluated to obtain multi-level difference results for the feature difference set. Based on the multi-level difference results, the feature difference set is coupled and analyzed to obtain the health deviation detection quantity of the elevator.

[0052] The process of performing coupled analysis on the feature difference set based on the multi-level difference results to obtain the health deviation detection quantity of the elevator includes: Influence factor analysis is performed on the feature difference points in the feature difference set to determine the influence factor set of the feature difference points; Based on the multi-level difference results, a level weight coefficient is assigned to the feature difference points to obtain the level weight coefficient set of the feature difference points. Based on the set of grade weight coefficients, the deviation of the influencing factor set is calculated to obtain the preliminary deviation detection amount of the elevator. The calculation formula for the preliminary deviation detection amount is as follows: ; In the formula, This is the initial deviation detection amount. For the first The difference values ​​of each feature difference point For the first The influence factors of the influence factor set corresponding to each characteristic difference point. For the first The weight coefficients of the set of grade weight coefficients corresponding to each feature difference point. This represents the total number of the feature difference points; The preliminary deviation detection value is normalized to obtain the health deviation detection value of the elevator.

[0053] Based on the changing patterns of elevator operating conditions and the continuity of data time series, the health data stream is segmented at fixed time intervals. During the segmentation process, it is ensured that each data segment can fully reflect the safety status of the elevator under a certain continuous operating condition, covering the hierarchical operating data and hierarchical environmental data corresponding to that condition. There is no overlap between the data segments and they are seamlessly connected, ultimately forming a set of elevator safety data segments containing multiple continuous data segments.

[0054] Compliant data streams that meet elevator safety operation standards are selected from the historical health database. These compliant data streams are then synchronously segmented according to the same segmentation rules and time intervals as the health data streams. Each compliant data segment corresponds to safe operation data under a specific standard elevator condition, ensuring consistency with the corresponding data segment in the safety data segment set in terms of time length and data dimensions. This results in a set of compliant data segments from the historical health database, providing a unified benchmark for subsequent feature comparisons.

[0055] Each data segment in the safety data set is analyzed in depth to extract key features reflecting the elevator's safety status, including trends in core operating parameters, numerical ranges of priority-level environmental data, and logical relationships between data. These key features from all data segments are then integrated to form a safety feature set for the elevator. Using the same feature extraction standards, features are extracted from each compliant data segment in the compliance data set to capture key operational and environmental characteristics of the elevator under compliant conditions. This is then compiled into a compliance feature set, ensuring a complete match between the feature dimensions of the two sets.

[0056] The safety feature set and the compliance feature set are compared one by one according to the corresponding data segments and feature dimensions. The numerical values, patterns of change, and logical relationships of each feature item are checked for consistency. For numerical features, it is determined whether they are within the reasonable range set by the compliance features; for trend features, it is analyzed whether their direction and magnitude of change are consistent with the compliance features; for logically related features, it is verified whether the relationship patterns between their data conform to compliance standards. All feature items that do not meet the compliance requirements are filtered out and categorized by data segments and feature dimensions to form a feature difference set for elevators.

[0057] A clear standard for assessing the degree of difference is established, evaluating each difference feature in the feature difference set from two core dimensions: the extent to which the feature deviates from the compliance range and the degree of impact of the difference feature on the safe operation of the elevator. Based on the different deviations and degrees of impact, the difference features are divided into different levels such as minor difference, moderate difference, and severe difference. Each level corresponds to a clear assessment basis and judgment standard. Through comprehensive assessment, multi-level difference results of the feature difference set are obtained, clearly presenting the severity of each type of difference.

[0058] Based on the difference levels determined by the multi-level difference results, the difference features within the feature difference set are coupled and analyzed in descending order of severity. The analysis focuses on the mutual influence between severe difference features, the correlation between moderate and severe differences, and the potential impact of minor differences on the overall safety status, integrating the combined effects of different levels of difference features. By combining the correspondence between differences and safety hazards in the historical health database, the coupling analysis results are transformed into quantitative indicators that accurately reflect the degree of elevator safety deviation, ultimately yielding the elevator's health deviation detection quantity.

[0059] This study delves into the mechanism by which each feature difference point in the feature difference set affects the safe operation of elevators, clarifying the types and scope of safety risks that each difference point may cause. By referencing elevator safety operation standards and historical failure cases, it assesses the degree of impact of the difference points on the operation of core elevator components, passenger safety, and overall system stability. Simultaneously, it identifies the interrelationships between the difference points, such as whether differences in a certain operating parameter exacerbate the impact of abnormal environmental data. These key factors related to these impacts are integrated to form a set of influencing factors for the feature difference points.

[0060] Based on the difference levels identified in the multi-level difference results, a corresponding level weight coefficient is assigned to each feature difference point. Feature difference points at the severe level are assigned the highest weight coefficient because they pose the greatest threat to elevator safety; feature difference points at the moderate level are assigned a medium weight coefficient; and feature difference points at the slight level are assigned the lowest weight coefficient. The allocation of weight coefficients strictly follows the principle that the higher the difference level, the greater the weight percentage, ensuring that the level weight coefficients accurately reflect the safety impact priority of the difference points, ultimately forming a set of level weight coefficients for the feature difference points.

[0061] Based on the set of grade weight coefficients, the influence factors of each characteristic difference point are correlated with the corresponding grade weight coefficients for calculation. For each influence factor, combined with its corresponding weight coefficient, the importance of the influence factor in the overall safety assessment is considered. By comprehensively superimposing the influence factors and their weight proportions of all characteristic difference points, the overall deviation degree corresponding to the influence factor set is quantitatively calculated. This quantitative result is the preliminary deviation detection quantity of the elevator, which initially reflects the deviation of the elevator's safety status from compliance standards.

[0062] A unified normalization method is adopted to convert the initial deviation detection quantities into a fixed numerical range. During the processing, the deviation benchmark value and limit safety deviation value under compliance status in the historical health database are referenced to determine a reasonable normalization interval. By adjusting the numerical scale of the initial deviation detection quantities, the influence of different dimensional differences on the numerical range of the detection quantities is eliminated, so that the final elevator health deviation detection quantities have a unified and comparable standard, and can accurately and intuitively reflect the degree of elevator safety deviation from compliance status.

[0063] No. The difference value of the nth feature difference point comes from the nth feature difference set. The comparison results of the first feature difference point with the corresponding feature in the compliance feature set. By comparing the first feature difference point in the security feature set with the corresponding feature in the compliance feature set. The numerical value, variation pattern, or logical relationship of each feature is compared one by one with the features of the same dimension in the compliance feature set, and the degree of deviation between the two is calculated. The quantitative result of this deviation is the first feature. The difference values ​​of each feature difference point.

[0064] No. The influencing factors corresponding to each characteristic difference point are derived from the influencing factor analysis of that characteristic difference point. In-depth analysis of the first... The mechanism by which these characteristic differences affect the operation of elevator core components, passenger safety, and system stability is analyzed by referring to elevator safety operation standards and historical failure cases. The types of safety risks that these differences may cause, their scope of impact, and their correlation with other differences are identified, and corresponding influencing factors are extracted.

[0065] No. The weight coefficients corresponding to each feature difference point are derived from the set of level weight coefficients. Based on the multi-level difference results, the weight coefficients for each feature difference point are derived from the set of level weight coefficients. For each feature difference point, the difference level to which it belongs is assigned a corresponding weight coefficient directly, based on the principle of assigning the highest weight to severe differences, the medium weight to moderate differences, and the lowest weight to slight differences, ensuring that the weight coefficient is consistent with the safety impact priority of the difference point.

[0066] The total number of feature difference points is the result obtained by counting all independent feature difference points in the feature difference set. This is achieved by meticulously counting the difference features categorized by data segment and feature dimension in the feature difference set, and then counting the number of all unique feature difference points.

[0067] The formula's significance lies in comprehensively considering the degree of difference, scope of influence, and safety priority of various feature difference points to accurately quantify the initial deviation of elevator safety status from compliance standards. The calculation process involves first multiplying the difference value of each feature difference point by its corresponding influence factor and weighting coefficient to obtain the weighted deviation contribution value for each feature difference point. Then, the weighted deviation contribution values ​​of all feature difference points are summed. Finally, the summation is divided by the total number of feature difference points to obtain the averaged initial deviation detection quantity. This calculation method reflects the degree of deviation of individual features through difference values, considers the actual scope of the difference through influence factors, highlights the safety priority of different levels of difference through weighting coefficients, and ultimately eliminates the influence of the number of difference points on the result through averaging. This allows the initial deviation detection quantity to comprehensively and objectively reflect the basic situation of the overall elevator safety deviation, providing a scientific quantitative basis for subsequent normalization processing.

[0068] The beneficial effect is that dividing the health data stream into multiple continuous data segments yields a set of elevator safety data segments, enabling the complete data stream to be broken down into unitized data suitable for analysis. By segmenting according to fixed time intervals or nodes of change in operating conditions, it ensures that each data segment fully reflects the safety status of the elevator during a continuous period or under specific operating conditions, avoiding the loss of local details due to the overall data stream, and providing structured and divisible basic data units for subsequent accurate comparison with compliance data.

[0069] Extracting compliant data segments from the historical health database yields a set of compliant data segments, providing a standardized reference benchmark for safety deviation detection. These compliant data segments are derived from historical records of elevator safe operation and are processed using the same segmentation rules as the safety data segment set, ensuring complete matching in time length and data dimensions. This avoids deviation detection errors caused by inconsistent reference standards and lays a unified compliance reference foundation for subsequent feature comparison and difference identification.

[0070] Identifying key features between the safety data segment set and the compliance data segment set yields the elevator's safety feature set and compliance feature set, enabling a focus on the core data dimensions affecting elevator safety. By extracting key features such as the changing trends of core operating parameters, the numerical range of priority-level environmental data, and the logical relationship patterns between data, and eliminating irrelevant and redundant information, the two feature sets accurately reflect the core differences between the safety and compliance states. This avoids low efficiency in difference identification due to feature extraction generalization and improves the targeting of deviation detection.

[0071] By comparing the safety feature set with the compliance feature set to identify differences, a feature difference set for elevators can be obtained. This allows for a systematic review of the specific deviations between safety data and compliance standards. By verifying the consistency of feature values, patterns of change, and logical relationships dimension by dimension and data segment by segment, all feature items that deviate from compliance requirements are categorized and organized. This avoids omissions of deviations in a single dimension or local area, forming a comprehensive and clear list of differences, providing a clear analytical framework for subsequent assessment of the degree of difference.

[0072] Assessing the degree of difference in the feature difference set yields multi-level difference results, enabling precise differentiation of the severity and risk priority of deviations. By setting assessment criteria such as deviation magnitude and impact range, the difference features are classified into different risk levels, clarifying which deviations have a significant impact on safety and which are minor deviations. This avoids wasting risk response resources by treating all differences equally and provides a basis for risk weighting in subsequent coupled analysis.

[0073] Based on the multi-level difference results, the elevator health deviation detection quantity is obtained by coupling and analyzing the feature difference set, which can comprehensively quantify the overall safety deviation of the elevator. By integrating the influence of differences at different levels and analyzing the interaction and superposition effects between differences, discrete difference features are transformed into unified quantitative indicators. This avoids misjudgment of the overall safety status caused by single difference assessment, allowing the health deviation detection quantity to accurately reflect the overall deviation of the elevator from compliance standards. This provides a scientific and reliable quantitative basis for subsequent risk assessment, significantly improving the accuracy and objectivity of elevator safety monitoring.

[0074] By conducting influencing factor analysis on the characteristic difference points within the characteristic difference set to determine the set of influencing factors, it is possible to deeply explore the actual impact of each difference point on elevator safety. By analyzing the scope and mechanism of the impact of these differences on the operation of core components, passenger safety, and system stability, and by combining historical failure cases, it is possible to clarify the types of safety risks that these differences may cause. This avoids focusing solely on the numerical value of the differences while ignoring their actual hazards, ensuring that the set of influencing factors accurately reflects the safety-related value of the difference points, and providing key impact dimensions for subsequent deviation calculations.

[0075] Based on the multi-level difference results, a set of level weight coefficients is obtained by assigning level weight coefficients to feature difference points, which can assign corresponding importance weights to difference points with different risk levels. Following the principle of assigning the highest weight to severe differences, the medium weight to moderate differences, and the lowest weight to slight differences, this ensures that the weight coefficients are directly linked to the degree of security threat posed by the difference points. This avoids weakening the core risks caused by equally weighting all difference points, allowing subsequent calculations to highlight the impact of high-risk differences and improve the risk sensitivity of deviation detection.

[0076] The initial deviation detection quantity of the elevator is obtained by calculating the deviation of the influencing factor set based on the set of grade weight coefficients. This allows for the quantitative integration of the impact of differences through a formula. The formula first multiplies the difference value, influencing factor, and weight coefficient of each characteristic difference point to obtain the weighted deviation contribution of a single difference point. Then, the contributions of all difference points are summed and averaged to eliminate the interference of the number of difference points on the result. This calculation method takes into account the magnitude, impact, and risk level of the difference, and the averaging process makes the result more objective, avoiding the excessive dominance of a single difference in the overall assessment, and accurately quantifying the basic level of elevator safety deviation.

[0077] Normalizing the initial deviation detection values ​​yields the elevator's health deviation detection values, eliminating assessment obstacles caused by differences in data dimensions. By referencing the deviation benchmarks and extreme safety deviations of compliance status in the historical health database, the initial deviation detection values ​​are transformed into a uniform numerical range, ensuring the comparability of health deviation detection values ​​for different elevators and monitoring periods, and avoiding misjudgments of deviation levels due to differences in the scale of the original data. The resulting health deviation detection values ​​accurately reflect the degree of deviation of the elevator from compliance standards and provide a unified and comparable quantitative basis for subsequent risk assessments, significantly improving the scientific rigor and practicality of elevator safety monitoring.

[0078] S4. During elevator operation, the health deviation detection quantity is used as the evaluation benchmark to comprehensively determine the elevator's operating status risk and riding environment risk, and obtain the elevator's risk assessment result; In this embodiment of the invention, the step of using the health deviation detection quantity as an evaluation benchmark to comprehensively determine the elevator's operational status risk and riding environment risk during elevator operation, and obtaining the elevator's risk assessment result, includes: Risk factors are identified in the health deviation detection data to obtain the risk factor classification results of the health deviation detection data; Logical judgment is made on the operational status-related deviations of the risk factor classification results to obtain the preliminary operational risk of the elevator; By mapping the environmental factor-related deviations of the risk factor classification results to risk characteristics, the preliminary environmental risk of the elevator can be obtained. Using the initial operational risks as risk nodes and the initial environmental risks as risk edges, a risk association graph of the elevator is constructed. Based on the risk correlation map, the preliminary operational risks and the preliminary environmental risks are synergistically integrated to obtain the risk assessment results of the elevator.

[0079] A thorough analysis of elevator safety deviations reflected in health deviation detection data, combined with elevator operation safety regulations and historical risk cases, identifies various risk factors constituting safety deviations. Based on the objects affected by these risk factors, they are categorized into two types: risk factors directly related to elevator operation status and risk factors related to the elevator riding environment. This ensures that the classification criteria for each type of risk factor are clear and their attribution is well-defined, ultimately yielding the risk factor classification results of the health deviation detection data.

[0080] For each deviation risk factor related to operational status in the risk factor classification results, we analyze its impact on the elevator's core operating components, the stability of operating parameters, and the consistency of operating logic. By comparing these deviations with the logical standards for normal elevator operation, we determine whether they will cause abnormalities in the elevator's starting, acceleration, and constant-speed stopping processes, whether they will affect the normal operation of core components such as the traction machine and car doors, and whether there is a potential for operational malfunctions. Through systematic logical judgment, we obtain the initial operational risks of the elevator.

[0081] We extract the deviation risk factors related to environmental factors from the risk factor classification results, and sort out the corresponding elevator environment characteristics, such as anomalies in air quality, temperature, humidity, and vibration. We then match these environmental deviation factors with a known environmental risk feature database to identify the types of safety hazards that each environmental deviation may cause, such as affecting the health of elevator passengers or deteriorating the operating environment of equipment. Through risk feature mapping, we obtain the preliminary environmental risk of the elevator.

[0082] Using initial operational risks as the core risk nodes in the risk correlation graph, each initial operational risk corresponds to an independent node, clearly identifying the source and core scope of the risk. Initial environmental risks serve as the risk edges connecting these risk nodes. The strength of the edge's correlation is determined by the degree of association between the initial environmental risks and initial operational risks; the closer the correlation, the more significant the impact represented by the edge. Using the overall safe operation logic of the elevator as a framework, the risk nodes and risk edges are arranged according to their actual relationships, constructing a complete risk correlation graph of the elevator that fully presents the interactions of various risks.

[0083] Based on the correlation relationships between risk nodes and risk edges presented in the risk correlation graph, this study analyzes the mutual influence and synergistic effects between initial operational risks and initial environmental risks. It considers whether initial operational risks will exacerbate the severity of initial environmental risks, and whether initial environmental risks will induce new initial operational risks or amplify existing operational risks, integrating the superimposed effects and comprehensive impacts of the two types of risks. Combining elevator safety assessment standards, a comprehensive determination is made of the risk level, scope of impact, and potential consequences after the synergistic effect, ultimately yielding a risk assessment result that comprehensively reflects the overall safety status of the elevator.

[0084] The beneficial effects are that identifying risk factors in health deviation detection data leads to a risk factor classification result, enabling the extraction of specific risk sources from quantified deviation data. By combining elevator safety operation standards with historical risk cases, the overall deviation reflected by health deviation detection data is refined into two categories of risk factors: those related to operational status and those related to the elevator riding environment. This avoids the problem of failing to pinpoint specific risk points by focusing only on overall deviation, providing a clear analytical object for subsequent multi-dimensional risk assessment.

[0085] Logically determining the operational status-related deviations in the risk factor classification results yields the initial operational risk of the elevator, enabling accurate assessment of safety hazards in the core operational aspects. By comparing the results with the logical standards for normal elevator operation, it analyzes whether operational risk factors lead to abnormal operation of core components, excessive fluctuations in operating parameters, or contradictions in operational logic, such as abnormal traction machine speed or car position deviation. This avoids overlooking potential faults due to ignoring operational logic anomalies, ensuring that the initial operational risk accurately reflects the safety status at the elevator operation level.

[0086] By mapping the environmental factor-related deviations from the risk factor classification results to risk characteristics, preliminary environmental risks of elevators can be obtained, enabling the systematic identification of safety threats in the elevator riding environment. By matching environmentally relevant risk factors with a known environmental risk feature database, the potential health risks to personnel or hidden dangers in the equipment operating environment caused by deviations such as excessive temperature and deteriorating air quality can be clearly identified. This avoids overlooking the long-term hazards due to seemingly minor environmental deviations, making the preliminary environmental risk assessment more targeted and safer.

[0087] By constructing a risk correlation map for elevators using initial operational risks as risk nodes and initial environmental risks as risk edges, the interaction relationships between risks can be intuitively presented. Risk nodes clearly mark the core risk points at the operational level, while risk edges reflect the intensity and correlation logic of environmental risks on operational risks, such as the aggravating effect of high humidity on the operational risks of electrical components. The graphical display avoids the limitations of isolated risk analysis, allowing staff to quickly grasp the risk transmission path and core risk sources.

[0088] The risk assessment results for elevators are obtained by synergistically integrating preliminary operational risks and preliminary environmental risks based on risk correlation maps, which can comprehensively consider the superposition effect and overall impact of the two types of risks. By analyzing the mutual reinforcement or constraint relationship between operational risks and environmental risks, comprehensive safety hazards that cannot be covered by a single risk assessment are integrated. For example, increased operational vibration may lead to excessive environmental noise and further affect personnel safety. Finally, a comprehensive and systematic risk assessment result is formed, avoiding safety decision-making biases caused by one-sided assessments, and providing a scientific and complete basis for subsequent risk level mapping and safety response.

[0089] S5. Map the risk assessment results to the risk level table of the elevator to obtain the risk level of the elevator; In this embodiment of the invention, mapping the risk assessment result to the risk level table of the elevator to obtain the risk level of the elevator includes: The risk assessment results are analyzed in two dimensions to obtain the elevator's operational risk component and environmental risk component; The operational risk component and the environmental risk component are mapped to the risk level table of the elevator to determine the risk level range of the elevator; The risk level range is integrated according to a preset level fusion rule to obtain the risk level of the elevator.

[0090] The risk assessment results are comprehensively broken down, and in-depth analysis is conducted from two fixed dimensions: elevator operation safety and elevator environment safety. Focusing on the operation safety dimension, risk information related to the working status of core elevator components, stability of operating parameters, and consistency of operating logic is extracted from the assessment results and integrated to form an elevator operation risk component that can separately reflect the safety status of the elevator operation. Simultaneously, for the elevator environment safety dimension, risk content related to environmental factors such as air quality, temperature, humidity, and vibration inside the elevator car is screened from the assessment results and compiled into an environmental risk component that specifically reflects the safety status of the elevator environment. This ensures that the risk components of the two dimensions do not overlap and completely cover the assessment results.

[0091] The elevator's risk level table was retrieved. This table pre-defined risk level classification standards for different safety conditions and clearly defined the mapping relationship between the quantitative ranges of operational risk and environmental risk and their corresponding levels. The analyzed operational risk components were compared one by one with the quantitative ranges of the operational risk dimensions in the risk level table to find the specific risk level intervals corresponding to each component. Using the same comparison method, the environmental risk components were matched with the quantitative ranges of the environmental risk dimensions in the risk level table to determine their corresponding risk level intervals. Finally, the elevator's risk level intervals were clarified, providing a clear basis for subsequent level integration.

[0092] The pre-defined risk level fusion rule is based on the core principle of "prioritizing higher risk levels and making comprehensive judgments." This means that when the risk level ranges corresponding to the operational risk component and the environmental risk component differ, the higher-level range is prioritized as the base risk level. If the two risk level ranges are the same, that range is directly determined as the final risk level. If the two ranges differ, while selecting the higher-level range, the final level is fine-tuned based on the risk level of the lower-level range to ensure that the impact of the high-risk dimension is highlighted while not ignoring the potential hazards of the low-risk dimension. By integrating the previously determined risk level ranges according to this rule, a risk level that comprehensively reflects the overall safety status of the elevator is obtained.

[0093] The beneficial effects are that by performing a two-dimensional analysis of the risk assessment results, the operational risk component and the environmental risk component of the elevator can be obtained, enabling precise breakdown of the core components of the risk assessment results. By focusing on the two key dimensions of elevator operation safety and passenger environment safety, operational risk information related to the operation of core components and the stability of operating parameters, as well as environmental risk information related to factors such as temperature and air quality inside the elevator car, are extracted from the assessment results. This avoids biases in risk level determination caused by confusion of risk dimensions, allowing the two types of risk components to clearly reflect the safety status of their respective dimensions, and providing a clear single-dimensional risk basis for subsequent level mapping.

[0094] Mapping operational and environmental risk components to an elevator risk level table determines the elevator's risk level range, providing a standardized reference level for each type of risk. The risk level table pre-defines level ranges corresponding to different risk levels. By comparing the two risk components with the quantitative ranges of their respective dimensions in the table, the respective level ranges for operational and environmental risks are clearly defined. This avoids subjective risk level judgments due to a lack of unified standards, ensuring the objectivity and consistency of level range determination and laying a precise foundation for subsequent level integration.

[0095] The risk level of an elevator is obtained by integrating risk level ranges according to preset risk level fusion rules, which comprehensively considers the impact of two types of risks to form a comprehensive final level. The preset rules are based on the principle of "prioritizing higher risks while considering the overall picture," emphasizing the impact of high-level risks on overall safety (e.g., matching high-risk levels when operational risks are high) while not neglecting the potential hazards of low-level risks. Reasonable fine-tuning ensures that no key safety information is overlooked during the risk level integration. This integration method avoids the one-sidedness of relying solely on a single-dimensional risk level for judgment, ensuring that the final risk level comprehensively reflects the combined safety status of the elevator's operation and environment. This provides an accurate and reliable basis for matching subsequent safety response actions, ensuring that safety responses are specifically tailored to the actual risk level of the elevator.

[0096] S6. Based on the risk level, trigger the elevator's safety response action and encode the safety response action into a response command to control the safe operation of the elevator.

[0097] In this embodiment of the invention, triggering a safety response action of the elevator based on the risk level, and encoding the safety response action into a response command to control the safe operation of the elevator, includes: Based on the risk level, determine the response level of the elevator; Based on the aforementioned response level, a corresponding combination of safety response actions is matched from a preset safety response action library to obtain the elevator's action execution sequence; The control instruction is encoded into the sequence of actions to obtain the elevator's response instruction; The response command is sent to the elevator's control terminal to trigger the elevator's corresponding safety operation.

[0098] Referring to the pre-defined response level classification standard, this standard clarifies the elevator safety response intensity and handling priority corresponding to different risk levels. Based on the determined elevator risk level, the corresponding response level is directly matched; the higher the risk level, the higher the response level, the more comprehensive the response measures, and the higher the handling priority. This ensures that the response level accurately corresponds to the severity of the risk level, clarifies the core execution standards for elevator safety response, and ultimately determines the elevator's response level.

[0099] The system retrieves a pre-defined safety response action library, which stores various safety response actions corresponding to different response levels. Each action has a clear execution purpose and operating procedure. Based on a defined response level, all appropriate safety response actions are selected from the library. These actions are then sorted and combined according to their logical execution order and urgency to form a complete, coherent operating procedure that meets the response level requirements. This procedure constitutes the elevator's action execution sequence, ensuring orderly execution and effective response to risks of the corresponding level.

[0100] Based on the instruction coding rules recognizable by the elevator control terminal, each safety response action in the action execution sequence is encoded one by one. During the encoding process, key information such as the execution content, execution parameters, and execution timing of each action is converted into an instruction format that the control terminal can parse, ensuring that each code uniquely corresponds to a safety response action and that the instruction information is complete and unambiguous. All codes are integrated in the order of the action execution sequence to form a clearly structured and logically coherent elevator response instruction, ensuring that the instruction accurately conveys the action execution requirements.

[0101] A stable connection is established between the response command sender and the elevator control terminal through the elevator's built-in communication transmission channel, ensuring the real-time and reliable transmission of commands. The encoded response command is sent to the control terminal according to the transmission method required by the communication protocol. After receiving the command, the control terminal decodes and parses it according to the encoding rules, extracting the corresponding safety response action and execution requirements for each command. Based on the parsing results, the control terminal sequentially triggers the corresponding safety operations of the elevator, such as adjusting the operating status, activating the alarm device, and controlling the door movement, enabling timely handling of elevator safety risks.

[0102] The beneficial effect is that determining the elevator's response level based on risk level establishes a precise correlation between risk and response. Different risk levels correspond to different degrees of safety threat. Through preset response level classification standards, risk levels are directly matched to corresponding response intensities and handling priorities. For example, high-risk levels correspond to emergency response levels, and low-risk levels correspond to routine response levels. This avoids resource waste or inadequate handling due to mismatches between response levels and risks, ensuring that response measures accurately match the severity of risks and providing clear execution standards for subsequent safety actions.

[0103] The elevator's action execution sequence is obtained by matching the corresponding safety response action combination from the preset safety response action library based on the response level, ensuring the professionalism and consistency of the response actions. The preset safety response action library stores standardized actions adapted to different response levels. Actions are filtered by response level and sorted according to logical order and urgency to form a complete execution flow, such as the "stop operation - start alarm - notify maintenance" sequence under the emergency response level. This avoids failures in handling due to arbitrary action selection or disordered order, ensuring that the action execution can efficiently respond to risks and improve the reliability of safety response.

[0104] Encoding the action execution sequence with control commands yields the elevator's response commands, enabling the conversion of response actions into equipment-recognizable signals. Based on the elevator control terminal's command encoding rules, the execution content, parameters, and timing of each action are converted into standardized digital commands. This ensures the command information is complete, unambiguous, and accurately parsed by the terminal, preventing actions from failing due to incompatible command formats. This streamlines the critical link of "risk assessment - action planning - equipment execution," providing technical support for triggering safe operations.

[0105] Sending response commands to the elevator's control terminal triggers corresponding safety operations, enabling real-time risk mitigation. Commands are transmitted via the elevator's built-in stable communication channel. Upon receiving the commands, the control terminal quickly decodes and executes them, such as adjusting the elevator's speed, controlling door opening and closing, and activating ventilation equipment. This ensures that safety response actions are promptly applied during elevator operation, preventing the escalation of risks due to command transmission delays or execution lags. Ultimately, this achieves rapid and effective handling of elevator safety risks, comprehensively protecting passenger safety and ensuring stable elevator operation.

[0106] like Figure 2 The diagram shown is a functional block diagram of an elevator equipment health data-driven assessment system provided in an embodiment of the present invention.

[0107] The elevator equipment health data-driven assessment system 100 described in this invention can be installed in an electronic device. Depending on the functions implemented, the elevator equipment health data-driven assessment system 100 may include a data standardization module 101, a health data stream construction module 102, a safety deviation detection module 103, a risk assessment module 104, a risk level mapping module 105, and a safety response module 106. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0108] In this embodiment, the functions of each module / unit are as follows: The data standardization module 101 is used to filter out noise data from multi-source monitoring data in the elevator and to unify the data format of the filtered data to obtain standardized monitoring data of the elevator. The health data flow construction module 102 is used to construct the health data flow of the elevator based on the elevator's historical health database, using the operational data in the standardized monitoring data as the first-level flow and the elevator riding environment data as the second-level flow. The safety deviation detection module 103 is used to perform differential analysis between the health data stream and the compliant data stream of the historical health database to obtain the health deviation detection quantity of the elevator. The risk assessment module 104 is used to comprehensively determine the operating status risk and riding environment risk of the elevator based on the health deviation detection quantity when the elevator is running, and obtain the risk assessment result of the elevator. The risk level mapping module 105 is used to map the risk assessment result to the risk level table of the elevator to obtain the risk level of the elevator. The safety response module 106 is used to trigger the safety response action of the elevator according to the risk level, and encode the safety response action into a response command to control the safe operation of the elevator.

[0109] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0110] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0111] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0112] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0113] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An elevator equipment health data driven assessment method, characterized by, The method comprises: S1. filtering noise data of multi-source monitoring data in the elevator, and unifying data formats of filtered data to obtain standardized monitoring data of the elevator; S2. based on a historical health database of the elevator, taking operation data in the standardized monitoring data as a first-level flow and taking elevator environment data as a second-level flow, constructing a health data flow of the elevator; S3. differentiating and analyzing the health data flow and a compliance data flow of the historical health database to obtain a health deviation detection quantity of the elevator; S4. during operation of the elevator, taking the health deviation detection quantity as an evaluation benchmark, comprehensively judging operation state risks and elevator environment risks of the elevator to obtain a risk evaluation result of the elevator; S5. mapping the risk evaluation result to a risk level table of the elevator to obtain a risk level of the elevator; S6. according to the risk level, triggering a safety response action of the elevator, and encoding the safety response action as a response instruction to control a safety operation of the elevator.

2. The method of claim 1, wherein, The filtering of noise data of multi-source monitoring data in the elevator and the unification of data formats of filtered data to obtain standardized monitoring data of the elevator comprise: receiving operation parameter data and elevator environment data of the elevator, and integrating the operation parameter data and the elevator environment data into multi-source monitoring data of the elevator; eliminating invalid data points of different scale data in the multi-source monitoring data to obtain effective monitoring data of the elevator; performing low-pass filtering on the effective monitoring data to obtain standard monitoring data of the elevator; unifying basic formats of various data in the standard monitoring data to obtain standardized monitoring data of the elevator.

3. The method of claim 1, wherein, The construction of a health data flow of the elevator based on a historical health database of the elevator, taking operation parameter data in the standardized monitoring data as a first-level flow and taking elevator environment data as a second-level flow, comprises: dividing the operation parameter data into core operation parameters and auxiliary operation parameters according to multiple data characteristics in the standardized monitoring data; placing the core operation parameters in a basic level and placing the auxiliary operation parameters in a top level to obtain hierarchical operation data of the elevator; placing environment factors directly affecting safety in the elevator environment data in a priority level and placing non-direct factors in the elevator environment data in a lag level to obtain hierarchical environment data of the elevator; taking the hierarchical operation data as a first level and taking the hierarchical environment data as a second level to construct a correlation data group of the elevator; performing pattern matching on the correlation data group and a typical working condition template of the historical health database of the elevator to obtain a post-matching result of the elevator; based on the post-matching result, calibrating logical consistency in the correlation data group to obtain a health data flow of the elevator.

4. The method of claim 3, wherein, The construction of a correlation data group of the elevator taking hierarchical operation data as a first level and taking hierarchical environment data as a second level comprises: The hierarchical operation data and the hierarchical environment data are time windowed to obtain operation data segments and environment data segments of the elevator; In the same time window, the operation data segments and the environment data segments are matched to obtain a preliminary associated data set of the elevator; According to a typical operation scene in the historical health database, scene identification is assigned to the preliminary associated data set to obtain scene marked data of the preliminary associated data set; Based on the scene marked data, the association strength of key data in the preliminary associated data set is strengthened to obtain an associated data set of the elevator.

5. The method of claim 1, wherein, The health deviation detection quantity of the elevator is obtained by differentiating the health data stream from the compliance data stream of the historical health database, including: The health data stream is divided into multiple continuous data segments to obtain a safety data segment set of the elevator; Compliance data segments in the historical health database are extracted to obtain a compliance data segment set of the historical health database; Key features between the safety data segment set and the compliance data segment set are identified to obtain a safety feature set and a compliance feature set of the elevator; The safety feature set and the compliance feature set are compared in terms of feature difference points to obtain a feature difference set of the elevator; The feature difference set is evaluated in terms of difference degree to obtain a multi-level difference result of the feature difference set; Based on the multi-level difference result, the feature difference set is coupled and analyzed to obtain the health deviation detection quantity of the elevator.

6. A method of elevator equipment health data driven assessment as defined in claim 5, wherein, The health deviation detection quantity of the elevator is obtained by coupling and analyzing the feature difference set based on the multi-level difference result, including: Influence factor analysis is performed on the feature difference points in the feature difference set to determine an influence factor set of the feature difference points; Based on the multi-level difference result, a level weight coefficient is assigned to the feature difference points to obtain a level weight coefficient set of the feature difference points; Based on the level weight coefficient set, the deviation degree of the influence factor set is calculated to obtain a preliminary deviation detection quantity of the elevator, wherein the calculation formula of the preliminary deviation detection quantity is as follows: ； In the formula, is the preliminary deviation detection quantity, is the difference value of the first feature difference point, is the influence factor corresponding to the first feature difference point, is the weight coefficient corresponding to the first feature difference point, is the total number of feature difference points. The preliminary deviation detection quantity is normalized to obtain the health deviation detection quantity of the elevator.

7. A method of elevator equipment health data driven assessment as defined in claim 1, wherein, The health deviation detection quantity is used as an evaluation benchmark to comprehensively determine the operation state risk and the elevator environment risk of the elevator to obtain a risk evaluation result of the elevator, including: Risk factor identification is performed on the health deviation detection quantity to obtain a risk factor classification result of the health deviation detection quantity; Logical judgment is performed on the operation state related deviation of the risk factor classification result to obtain a preliminary operation risk of the elevator; Risk feature mapping is performed on the environment factor related deviation of the risk factor classification result to obtain a preliminary environment risk of the elevator; The preliminary operation risk is taken as a risk node, and the preliminary environment risk is taken as a risk edge to construct a risk association graph of the elevator; Based on the risk association graph, the preliminary operation risk and the preliminary environment risk are synergistically fused to obtain a risk evaluation result of the elevator.

8. A method of elevator equipment health data driven assessment as defined in claim 1, wherein, The mapping of the risk assessment result into the risk level table of the elevator obtains the risk level of the elevator, and the method comprises the steps of: The risk assessment result is analyzed in two dimensions to obtain the operation risk component and the environment risk component of the elevator; The operation risk component and the environment risk component are mapped into the risk level table of the elevator to determine the risk level interval of the elevator; The risk level interval is integrated according to a preset level fusion rule to obtain the risk level of the elevator.

9. A method of elevator equipment health data driven assessment as defined in claim 1, wherein, According to the risk level, the safety response action of the elevator is triggered, and the safety response action is encoded into a response instruction to control the safety operation of the elevator, and the method comprises the steps of: According to the risk level, the response level of the elevator is determined; According to the response level, a corresponding safety response action combination is matched from a preset safety response action library to obtain an action execution sequence of the elevator; The action execution sequence is controlled and instructed to obtain the response instruction of the elevator; The response instruction is sent to the control terminal of the elevator to trigger the corresponding safety operation of the elevator.

10. An elevator equipment health data driven evaluation system for realizing the elevator equipment health data driven evaluation method of claim 1, and the system comprises: A data standardization module is used to filter out noise data of multi-source monitoring data in the elevator, and to unify the data format of the filtered data to obtain standardized monitoring data of the elevator; A health data flow construction module is used to construct the health data flow of the elevator based on the historical health database of the elevator, with operation data in the standardized monitoring data as a first level flow and with elevator environment data as a second level flow; A safety deviation detection module is used to differentially analyze the health data flow and the compliance data flow of the historical health database to obtain health deviation detection quantity of the elevator; A risk assessment module is used to determine the operation state risk and the elevator environment risk of the elevator based on the health deviation detection quantity as an evaluation reference to obtain the risk assessment result of the elevator; A risk level mapping module is used to map the risk assessment result into the risk level table of the elevator to obtain the risk level of the elevator; A safety response module is used to trigger the safety response action of the elevator according to the risk level, and to encode the safety response action into a response instruction to control the safety operation of the elevator.

Images