Elevator Brake Performance Testing Methods and Systems

Abstract

This application relates to the field of elevator braking technology and discloses a method and system for testing the performance of elevator brakes. The method includes: acquiring operational data before and after the braking command is triggered and forming braking behavior data segments; determining a short-time analysis interval from the triggering of the braking command until the speed first reaches zero, extracting first feature data and comparing it with historical stable features, and marking suspected anomalies; identifying continuous operational segments of braking followed by re-braking, extracting second and third feature data, and judging response consistency; dividing load state samples based on drive response features; statistically analyzing the distribution of first feature data and response consistency results under different loads, and analyzing cross-load consistency; and outputting a detection conclusion based on comprehensive multi-dimensional results. This method can accurately identify early transient anomalies, distinguish between occasional disturbances and true degradation, adapt to multiple load conditions, provide accurate basis for maintenance, and ensure elevator operational safety.

Description

Technical Field

[0001] This application relates to the field of elevator braking technology, specifically to a method and system for testing the performance of elevator brakes. Background Technology

[0002] As an indispensable vertical transportation tool in high-rise buildings, the safety of elevators directly affects the lives and property of users. The brake, as a core component of the elevator safety protection system, plays a crucial role in the normal braking and stopping of the elevator at each floor, and in emergency situations, it is essential for ensuring the safe operation of the elevator.

[0003] During the long-term service of elevators, the performance of the brakes will exhibit a gradual degradation due to various factors such as frictional loss, mechanical fatigue, and environmental corrosion. This process has significant operating condition correlation and transient concealment. In existing technologies, elevator brake performance testing methods mostly rely on the final result of a single braking operation or the braking capacity under fixed load conditions as the basis for judgment, which has obvious limitations: First, they ignore the dynamic behavior from the issuance of the braking command to the full establishment of braking force, making it difficult to capture early abnormal signals such as minute slippage and deceleration fluctuations within this short time interval. Although such abnormalities do not affect the immediate braking result, they may be the initial signs of performance degradation. Second, they lack an assessment of the consistency of the entire braking-release-re-braking process, making it impossible to effectively distinguish between anomalies caused by occasional operating condition disturbances and changes in the mechanical state of the brake (such as viscosity and hysteresis). Third, the tests are mostly conducted under fixed operating conditions such as rated load or no-load, which makes it difficult to reflect the stability of braking performance when the load changes dynamically during actual elevator operation. Some performance problems that only appear under heavy load or sudden load changes are easily missed.

[0004] The shortcomings of the aforementioned detection methods make it difficult for existing technologies to provide reliable early warnings before the brake performance deteriorates significantly. Problems are often not discovered until obvious brake failure or runaway signs appear, increasing the risk of elevator operation and failing to provide accurate guidance for maintenance work, resulting in delayed or excessive maintenance. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for testing the performance of elevator brakes, so as to solve the problems mentioned in the background art.

[0006] According to one aspect of this application, a method for testing the performance of an elevator brake is provided, comprising the following steps:

[0007] The system acquires operational data before and after each braking command is triggered, forming a braking behavior data segment, wherein the operational data includes the elevator's operating speed;

[0008] For each braking behavior data segment, a short analysis interval is determined from the time the braking command is triggered until the speed first reaches zero. The first feature data representing the dynamic response in the initial stage of braking establishment within this interval is extracted and compared with historical stable features. If the deviation continues, the corresponding braking behavior is marked as a suspected anomaly.

[0009] Before and after a suspected abnormal event, identify whether there is a continuous running segment where the brake is released and then braked again. If so, extract the second feature data of the brake release process and the third feature data of the re-braking process in the segment.

[0010] Compare the second feature data with the third feature data to determine the consistency of the response between brake release and re-brake. If the consistency is lower than the preset judgment range, record the result of inconsistent response.

[0011] Based on the driving response characteristics during elevator operation, each braking behavior data segment is divided into operating samples under at least two different load states;

[0012] For operating samples under different load conditions, the distribution of the first feature data and the response consistency results are statistically analyzed to analyze the cross-load consistency of the brake performance. If the abnormality is concentrated under a specific load or the load change causes the abnormality to intensify, it is determined that there is a load-related stability decrease.

[0013] Based on the comparison results of the first feature data, the response consistency judgment results, and the load-related stability analysis results, the brake performance test conclusion is output.

[0014] Preferably, the first feature data includes at least one of velocity decay continuity feature data, low-speed phase motion residue feature data, and deceleration change stability feature data; the continuous deviation specifically means that the current first feature data exceeds the historical stable feature range in a preset number of consecutive braking events, or the single exceedance exceeds a preset threshold.

[0015] Preferably, identifying whether there is a continuous operating segment where braking is released and then re-applied specifically means: if, within a preset time range before and after a suspected abnormal braking event, the time interval between two braking commands is less than a preset threshold, and there is a complete braking release process in between, then the segment of operating data is determined as a continuous braking operating segment.

[0016] Preferably, the second feature data includes at least one of: brake release delay time and speed establishment time; the third feature data includes at least one of: re-braking delay time and complete stop time.

[0017] Preferably, the method further includes: establishing a consistency determination interval based on data from the elevator's historical stable operation phases; calculating the difference between the brake release delay time and the re-braking delay time, and the ratio or difference between the speed establishment time and the complete stop time; comparing the difference or ratio with the corresponding consistency determination interval, and determining that the response is inconsistent when the difference or ratio exceeds the interval range.

[0018] Preferably, dividing each braking behavior data segment into operating samples under at least two different load conditions specifically involves using at least one of the stator current, output torque, or inverter output voltage of the elevator drive motor as input features, and dividing the braking behavior data segment into operating samples under light load, medium load, or heavy load conditions through a preset load condition determination model.

[0019] Preferably, analyzing the performance consistency of the brake under different load conditions specifically includes:

[0020] For the same type of feature data, calculate the mean difference under different load conditions;

[0021] Calculate the proportion of abnormal samples in the characteristic data under each load condition;

[0022] When the mean difference exceeds the preset proportion of the difference corresponding to the historical stable stage, or when the proportion of abnormal samples under a certain load state is significantly higher than that under other load states, it is determined that the brake performance has a load-related stability decline.

[0023] In another aspect, this application also provides an elevator brake performance testing system, comprising:

[0024] The data acquisition module acquires the operating data before and after each braking command is triggered, forming a braking behavior data segment, wherein the operating data includes the elevator running speed;

[0025] The suspected anomaly marking module determines a short analysis interval for each braking behavior data segment from the time the braking command is triggered until the speed first reaches zero. It extracts the first feature data representing the dynamic response in the initial stage of braking establishment within this interval and compares it with historical stable features. If the deviation continues, the corresponding braking behavior is marked as suspected anomaly.

[0026] The continuous braking segment identification and feature extraction module identifies whether there is a continuous running segment before and after a suspected abnormal event where the brake is released and then braked again. If so, it extracts the second feature data of the brake release process and the third feature data of the re-braking process in the segment.

[0027] The response consistency judgment module compares the second feature data with the third feature data to determine the response consistency between brake release and re-braking. If the consistency is lower than the preset judgment range, the response inconsistency result is recorded.

[0028] The load state segmentation module, based on the drive response characteristics during elevator operation, divides each braking behavior data segment into operating samples under at least two different load states.

[0029] The cross-load consistency analysis module statistically analyzes the distribution of the first feature data and response consistency results for operating samples under different load states, and analyzes the cross-load consistency of brake performance. If abnormal concentration or load change leads to aggravation of abnormality under a specific load, it is determined that there is a load-related stability decrease.

[0030] The comprehensive conclusion output module integrates the comparison results of the first feature data, the response consistency judgment results, and the load-related stability analysis results to output the brake performance test conclusion.

[0031] This application also provides a computer device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the elevator brake performance detection method as described above.

[0032] In another aspect, this application provides a computer-readable storage medium having stored thereon computer program instructions that can be executed by a processor to implement the elevator brake performance testing method described above.

[0033] In another aspect of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the elevator brake performance detection method as described above.

[0034] This application achieves accurate and comprehensive testing of elevator brake performance by constructing a detection process that includes early detection, mechanism confirmation, and operational condition verification. Through short-term analysis of the initial braking phase and extraction of three types of primary feature data, it can identify transient anomalies that are difficult to detect using traditional methods, enabling early warning. By utilizing the consistency analysis of the response between brake release and re-braking, it effectively distinguishes between occasional disturbances and actual performance degradation, improving the reliability of the judgment. Through multi-load state division and cross-load consistency analysis, it enhances adaptability to complex operating conditions and can detect performance problems under specific loads. This method can provide accurate degradation information before brake performance significantly declines, clearly identify the degradation stage, and provide targeted maintenance suggestions, optimizing maintenance timing, reducing the risk of brake failure, and ensuring elevator operational safety. Attached Figure Description

[0035] Figure 1This is a schematic diagram of an elevator brake performance testing method provided in an embodiment of this application;

[0036] Figure 2 A schematic diagram illustrating the process of extracting and analyzing the initial dynamic characteristics of braking provided in this application embodiment;

[0037] Figure 3 This is a schematic diagram of the first feature extraction process provided in an embodiment of this application;

[0038] Figure 4 This is a schematic diagram illustrating the extraction process of the second and third feature data provided in the embodiments of this application;

[0039] Figure 5 This is a schematic diagram of the response consistency judgment process provided in an embodiment of this application;

[0040] Figure 6 This is a schematic diagram of the operational load state partitioning process provided in an embodiment of this application;

[0041] Figure 7 A schematic diagram of the stability analysis process provided in the embodiments of this application;

[0042] Figure 8 A schematic diagram of an elevator brake performance testing system provided in this application embodiment;

[0043] Figure 9 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0044] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0045] It should be noted that all user information (including but not limited to user device information, user personal information, object information corresponding to device usage data, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, device usage data, etc.) involved in all embodiments of this application are information and data authorized by the user or fully authorized by all parties.

[0046] This application applies to the performance testing of brakes during normal operation of traction elevators. It can be deployed in the elevator control system, maintenance and testing terminal, or data processing unit connected to it. Implementation generally does not require adding new sensors or dedicated testing equipment, nor does it alter the elevator's original control structure and hardware configuration. It relies solely on the existing data acquisition and processing capabilities of the elevator control system, enabling execution in scenarios such as daily elevator operation, periodic maintenance and testing, or operational status assessment. This allows for continuous monitoring and accurate analysis of brake performance changes during long-term operation.

[0047] The implementation process of the elevator brake performance testing method described in this application will be described in detail below with reference to specific embodiments. It should be noted that this embodiment is only used to explain this application and is not intended to limit the scope of protection of this application. Conventional adjustments or substitutions of each step by those skilled in the art without departing from the concept of this application should be included in the scope of protection of this application.

[0048] like Figure 1 As shown in the figure, this application discloses a schematic diagram of an elevator brake performance testing method, which includes the following method steps:

[0049] S1: Acquire the running data before and after each braking command is triggered to form a braking behavior data segment, wherein the running data includes the elevator running speed;

[0050] S2: For each braking behavior data segment, a short analysis interval is determined from the time the braking command is triggered until the speed first reaches zero. The first feature data representing the dynamic response in the initial stage of braking establishment within this interval is extracted and compared with historical stable features. If the deviation continues, the corresponding braking behavior is marked as a suspected anomaly.

[0051] S3: Before and after a suspected abnormal event, identify whether there is a continuous running segment where the brake is released and then braked again. If so, extract the second feature data of the brake release process and the third feature data of the re-braking process in the segment.

[0052] S4: Compare the second feature data with the third feature data to determine the consistency of the response between brake release and re-brake. If the consistency is lower than the preset judgment range, record the result of inconsistent response.

[0053] S5: Based on the driving response characteristics during elevator operation, divide each braking behavior data segment into at least two types of operating samples under different load states;

[0054] S6: For operating samples under different load conditions, the distribution of the first feature data and the response consistency results are statistically analyzed to analyze the cross-load consistency of the brake performance. If the abnormality is concentrated under a specific load or the load change causes the abnormality to intensify, it is determined that there is a load-related stability decrease.

[0055] S7: Based on the comparison results of the first feature data, the response consistency judgment results, and the load-related stability analysis results, output the brake performance test conclusion.

[0056] In some embodiments, step S1 involves the acquisition of braking behavior data and identification of braking events. During normal elevator operation, operational data related to the braking process is acquired through the existing data interface of the elevator control system. This operational data includes at least the trigger signal of the braking command and its trigger time, elevator operating speed or equivalent motor speed feedback information, elevator operating direction information, and elevator operating status identification information. Specifically, the trigger signal of the braking command is used to accurately locate the starting point of the braking event; the elevator operating speed or motor speed feedback information is the core data source for subsequent analysis of braking dynamic characteristics; the operating direction information helps determine the force state of the brake during braking; and the operating status identification information can distinguish between different operating modes such as no-load, passenger-carrying, and maintenance, providing a basis for subsequent operating condition analysis.

[0057] Based on the acquired braking command trigger signals, all operational data undergoes time alignment processing to ensure consistency in the braking command trigger signals, speed feedback information, and operational direction information across the time dimension, avoiding distortion of analysis results due to data timing deviations. Each braking command trigger is used as the starting point of a braking event, and corresponding braking behavior data segments are segmented from the continuous operational data. To ensure the completeness of the analysis, each braking behavior data segment covers at least the stable operation phase before the braking command trigger and the stopping phase after braking. The stable operation phase data before the braking command trigger is used to establish a baseline reference, while the stopping phase data after braking is used to confirm the final braking effect, ensuring a comprehensive capture of the entire braking event process.

[0058] Optionally, during data acquisition, the raw data can be preliminarily filtered to remove abnormal noise caused by signal interference. For example, a moving average filtering algorithm can be used to process the motor speed feedback information to improve data reliability. The data acquisition frequency can be configured to match the raw data output frequency of the elevator control system to ensure complete capture of dynamic changes during braking and meet the accuracy requirements of subsequent feature extraction.

[0059] In some embodiments, step S2 involves the extraction and analysis of dynamic characteristics during the initial stage of brake establishment. In this embodiment, the short-time analysis interval, i.e., the micro-slip time window, refers to a preset short-time interval before the elevator speed is first determined to be zero after the braking command is issued. This interval is specifically used to characterize the dynamic behavior during the initial stage of brake establishment. This interval can accurately capture the transient response of the brake from the start of applying braking force to the complete establishment of braking force, providing data support for early anomaly identification.

[0060] Please see Figure 2 , Figure 2 This is a schematic diagram illustrating the process of extracting and analyzing the dynamic characteristics during the initial braking stage, as provided in an embodiment of this application. Specifically, it includes the following steps:

[0061] In S201, the short-time analysis interval is determined. For each obtained braking behavior data segment, the braking command trigger time is first extracted. And the moment when the elevator's operating speed is first determined to be zero. Based on the preset time window length rule, the short-term analysis interval for the initial stage of braking establishment is determined, i.e., this interval is... ,in This is the delay time for the braking command to take effect, used to exclude invalid data intervals between the issuance of the braking command and its actual implementation. A buffer time is used to determine when the speed returns to zero, thus eliminating the influence of measurement errors when the elevator speed is close to zero.

[0062] For example, The time can be configured from 0 to 100 milliseconds. The specific value is determined based on the command response delay characteristics of the elevator control system. For variable frequency control systems with faster response speeds, It can be set to a smaller value; The time interval can be configured from 0 to 50 milliseconds, with the specific value adjusted according to the accuracy of the speed measurement sensor. The total length of the short-time analysis interval can be flexibly adjusted according to the elevator's operating speed level. For elevators with a rated speed of 1.0-2.5 m / s, the total length can be set to 0.5-2 seconds to ensure complete coverage of the dynamic process during the initial braking setup, without omitting key transient information or including irrelevant data.

[0063] When determining the short-time analysis interval, the following constraints must be met: the start time of the interval is no earlier than the braking command trigger time, the end time is no later than the moment the elevator speed is first determined to be zero, and the interval length is no less than the preset minimum effective analysis time, for example, 0.3 seconds. If based on... and If the calculated interval length is less than the minimum effective analysis time, the interval length will be adjusted to the minimum effective analysis time to ensure the effectiveness and reliability of subsequent feature extraction.

[0064] In S202, speed data preprocessing is performed. Within a defined short-time analysis interval, the data on elevator speed changes over time are preprocessed to lay the foundation for feature extraction. First, the speed data is sorted chronologically to ensure the continuity of the data sequence and avoid the impact of data storage or transmission order errors on the analysis results. Then, the speed change between adjacent time points is calculated. ,in For the first The velocity value at each time point For the first The velocity value at each time point It is a positive integer.

[0065] Optionally, to remove random noise from the data, the velocity variation can be smoothed, for example, by using a moving average filter, taking adjacent values... The average of the velocity changes is taken as the velocity change at the current moment. The value can be adjusted according to the data acquisition frequency. When the acquisition frequency is 100Hz... The value can be set to 5-10. At the same time, the validity of the preprocessed speed data is checked, and outliers that are obviously outside the reasonable range are removed. For example, when the speed value at a certain moment differs from the speed value at an adjacent moment by more than a preset threshold (such as 50% of the rated speed), the data is determined to be an outlier and is completed using linear interpolation to ensure the continuity and validity of the data.

[0066] In S203, the first feature data is extracted. Based on the preprocessed velocity data, the first feature data characterizing the dynamic response in the initial stage of braking is extracted. This first feature data includes velocity decay continuity feature data, low-speed phase motion residual feature data, and deceleration change stability feature data. (See also...) Figure 3 , Figure 3 This is a schematic diagram of the first feature extraction process provided in an embodiment of this application. The specific extraction method is as follows:

[0067] In S2031, the continuity characteristic data of velocity decay is extracted. By analyzing the velocity-time curve, the continuity of the velocity decay process is determined. A velocity decay continuity index is defined. The calculation method is as follows: in, This represents the number of velocity data points within the short-time analysis interval. For the first The change in velocity over a time interval For the first The change in velocity over a time interval It is the ideal proportionality coefficient for the change in velocity, with a value of 1, representing a uniform and continuous velocity decay process. The smaller the value, the better the continuity of velocity decay; conversely, the larger the value, the more abrupt the velocity decay process is, and the poorer the continuity.

[0068] During the extraction process, if the absolute value of the speed change is less than the preset minimum change threshold within a certain time period, and the duration exceeds the preset duration, it is determined that the speed decay process is interrupted, and the speed decay continuity feature data is abnormal.

[0069] In S2032, residual motion characteristic data is extracted during the low-speed phase. When the elevator speed decreases below a preset low-speed threshold, the system analyzes whether there is speed fluctuation or residual slippage within this low-speed range. Residual motion indices are defined. The calculation method is as follows: in, This represents the number of speed data points within the low-speed range. For the first The velocity value at each time point This is the preset low-speed threshold. If... If the value is greater than the preset residual judgment threshold, it indicates that there is obvious residual slip in the low-speed range; if the velocity direction is reversed in the low-speed range, that is, the velocity values ​​at adjacent time points have opposite signs, the motion residual feature data is directly judged to be abnormal.

[0070] In S2033, deceleration variation stability feature data extraction is performed. Deceleration is calculated based on velocity variation. ,in The time interval between adjacent time points. Define the stability index for deceleration changes. The calculation method is as follows: in, For the first The deceleration over time intervals, For the first The deceleration over time intervals, The average deceleration within the short-time analysis interval. This represents the number of deceleration data points. The smaller the value, the more stable the deceleration change; if If the value is greater than the preset stability threshold, it indicates that there are abnormal fluctuations in the deceleration.

[0071] In S204, comparison with historical stable characteristics and identification of suspected anomalies are performed. Dynamic characteristic data of the elevator's braking during the initial stage of historical stable operation are pre-stored to establish a historical stable characteristic database. The historical stable operation stage can be selected as the first 3-6 months of the elevator's initial use, during which there are no braking-related fault records and the operating status is stable. For each type of first characteristic data in the historical stable characteristic database, its statistical distribution range is calculated, for example, using 3... The principle determines the normal range for each characteristic, that is, the normal range is... ,in The mean of historical feature data. The standard deviation of historical feature data.

[0072] The speed decay continuity characteristic data, low-speed phase motion residual characteristic data, and deceleration change stability characteristic data corresponding to the current braking event are compared with the corresponding normal ranges in the historical stable characteristic database. The continuous deviation specifically refers to the current first characteristic data exceeding the historical stable characteristic range in a predetermined number of consecutive braking events, or a single exceedance exceeding a predetermined threshold. For example, the speed decay continuity index for three consecutive braking events... Exceeding the normal range, or a single occurrence If the value exceeds 150% of the upper limit of the normal range, the braking event is determined to have abnormal dynamic characteristics in the early stage of braking establishment, and the braking event is marked as a suspected abnormal braking event.

[0073] This step precisely defines the short-term analysis interval during the initial stage of brake establishment and specifically extracts three types of primary feature data, solving the technical problem of difficulty in detecting transient anomalies during the initial stage of brake establishment in existing technologies. The principle is that although minor slippage, deceleration fluctuations, and other anomalies during the initial stage of brake establishment are short-lived and do not affect the final braking result, they reflect changes in the state of the brake friction pairs, spring mechanism, and mechanical clearances. Through a specialized short-term analysis interval and feature extraction method, these transient anomalies can be accurately captured. Potential anomalies can be detected before brake performance significantly deteriorates, preventing further performance degradation due to unidentified initial anomalies, and providing accurate detection targets for subsequent response consistency analysis and load-related stability analysis.

[0074] In some embodiments, step S3 involves screening and extracting feature data from continuous braking operation segments. Screening of continuous braking operation segments includes, after marking suspected abnormal braking events, screening continuous braking operation segments for response consistency analysis. From the braking behavior data segment sequence, operation data adjacent to the suspected abnormal braking event is extracted to determine whether there is an operation pattern where a braking command is triggered again shortly after brake release.

[0075] A preset threshold for the time interval between brake release and re-braking is established, for example, 30 seconds. When the interval between two braking commands is less than this threshold, and a complete brake release process exists in between (i.e., the elevator speed recovers from 0 to a stable operating speed), the corresponding operating data is identified as a continuous braking operation segment. This continuous braking operation segment must at least cover the release phase of the previous brake, the intermediate stable operating phase, and the braking phase of the subsequent brake to ensure that the response features of the brake release and re-braking processes can be completely extracted, providing comprehensive data support for subsequent consistency comparisons.

[0076] If no matching continuous braking segments are found within the preset search range before and after a suspected abnormal braking event, such as 5 braking events before and after, the situation is recorded, and subsequent judgments are based solely on other analysis results. If multiple matching continuous braking segments exist, the segment closest in time to the suspected abnormal braking event is selected as the input data for subsequent response consistency analysis to improve the correlation between the analysis results and the suspected abnormal event.

[0077] For details on the extraction of the second and third feature data, please refer to [link / reference needed]. Figure 4 , Figure 4 This is a schematic diagram illustrating the extraction process of the second and third feature data provided in an embodiment of this application. For the selected continuous braking operation segment, the second feature data of the brake release process and the third feature data of the re-braking process are extracted respectively. The second feature data includes the brake release delay time and the speed establishment time, and the third feature data includes the re-braking delay time and the complete stop time. Specifically, it includes:

[0078] In S401, the continuous braking operation segment is segmented. First, the continuous braking operation segment is segmented according to the operation phase, divided into a brake release phase and a re-braking phase. The start time of the brake release phase is the brake release command trigger time. The end point is when the elevator speed first reaches a stable operating speed. The moment The start time of the re-braking phase is the time when the re-braking command is triggered. The end time is the moment when the elevator speed is first determined to be zero. .

[0079] Among them, stable operating speed The determination method is as follows: when the fluctuation range of the elevator speed within a continuous preset time period, such as 1 second, is less than a preset fluctuation threshold, such as 5% of the rated speed, the average speed within that time period is determined to be the stable operating speed. If there are multiple stable operating stages in the continuous braking operation segment, the stable operating stage closest to the trigger time of the re-braking command is selected as the analysis object to ensure the correlation between the feature data and the re-braking process.

[0080] In S402, the second feature data is extracted: brake release delay time. The moment the brake release command is triggered. until the elevator speed begins to increase The time interval, i.e. Among them, the moment when the elevator speed begins to increase. The judgment criterion is: the increase in speed value at a certain moment compared to the speed value at the moment the brake release command is triggered (usually 0) exceeds the preset start threshold, for example, 0.02 m / s, and the speed value continues to rise for the next 3 consecutive time points, so as to eliminate misjudgment caused by instantaneous noise.

[0081] Speed ​​build time The moment the elevator begins to increase speed To reach a stable operating speed time The time interval, i.e. If the elevator fails to reach the preset stable operating speed during the brake release phase and instead directly enters the re-braking phase, the speed settling time will be [not specified]. The time interval between the moment the elevator speed begins to increase and the moment the braking command is triggered again is used to ensure that the feature data can fully reflect the response of the braking release process.

[0082] In S403, the third feature data is extracted. Re-braking delay time. The moment when the braking command is triggered again. until the elevator speed begins to decrease The time interval, i.e. The moment the elevator speed begins to decrease. The criterion for judgment is: the speed value at a certain moment compared to the speed value at the moment the braking command is triggered again (stable operating speed). If the reduction exceeds a preset descent threshold, such as 0.02 m / s, and the speed value continues to decrease for three consecutive time points, it ensures accurate capture of the initial response moment of re-braking.

[0083] Complete stop time The moment when the elevator speed begins to decrease The moment when the speed is first determined to be zero. The time interval, i.e. This time can directly reflect the braking response efficiency of the re-braking process.

[0084] This step involves screening continuous braking segments and specifically extracting second and third feature data, addressing the technical problem of existing technologies lacking a means to evaluate the overall consistency of the braking and release processes. The principle is that changes in the mechanical state of the brake, such as viscosity, mechanical stagnation, or response hysteresis, directly lead to differences in the response characteristics of the brake release and re-braking processes. By extracting the core time feature data of these two types of processes, this difference can be quantified. This provides accurate and effective feature data support for subsequent response consistency judgment, enabling the accurate capture of response differences between the brake release and re-braking processes. It lays the foundation for eliminating occasional operating condition disturbances and confirming the correlation between anomalies and changes in the brake's mechanical state, thus improving the reliability and accuracy of braking performance anomaly judgment.

[0085] In some embodiments, for step S4, the consistency judgment of the brake release and re-braking responses is performed. First, based on the continuous braking operation segments of the elevator during its historical stable operation phase, the corresponding second and third feature data are extracted to establish a historical consistency feature database. For each pair of corresponding feature data, namely brake release delay time and re-braking delay time, speed establishment time and complete stop time, the statistical distribution range of their differences is calculated, and the consistency judgment interval for each feature difference is determined using the 3σ principle, i.e., the consistency judgment interval is... ,in This represents the mean of the historical characteristic differences. This represents the standard deviation of historical characteristic differences.

[0086] The consistency judgment range is used to reflect the consistency level of the brake's response during brake release and re-braking under normal conditions. The range can be dynamically adjusted according to factors such as the elevator's model, operating years, and rated parameters. For example, for newly commissioned elevators, the range can be appropriately narrowed to improve the sensitivity of the judgment; for elevators with a longer operating history, the range can be appropriately widened to avoid misjudgments caused by the natural aging of the equipment.

[0087] Please see Figure 5 , Figure 5 This is a schematic diagram of the response consistency judgment process provided in an embodiment of this application. Specifically, it includes:

[0088] In S501, the consistency between the brake release delay time and the re-braking delay time is determined. The brake release delay time is calculated. With re-braking delay time The difference .Will Compare with the consistency judgment interval corresponding to the historical stable operation phase, if If the consistency judgment interval is within the range, then the response consistency of the pair of feature data is determined to be good; if If the data exceeds the consistency judgment range and the excess exceeds 20% of the upper limit of the range, then the response consistency of the pair of feature data is determined to be abnormal.

[0089] In S502, the consistency between velocity settling time and complete stop time is determined. Velocity settling time is calculated. With complete stop time ratio Or calculate the difference between the two. The calculation results are compared with the consistency judgment intervals corresponding to historical stable operation phases. If the ratio is... or difference If the data is within the consistency judgment range, the response consistency of the pair of feature data is considered good; if it exceeds the consistency judgment range and the excess exceeds 20% of the upper limit of the range, the response consistency of the pair of feature data is considered abnormal.

[0090] In S503, a comprehensive response consistency judgment is performed. Based on the consistency judgment results of the two pairs of characteristic data mentioned above, if the response consistency of at least one pair of characteristic data is judged to be abnormal, then a significant response inconsistency is determined between the brake release process and the re-braking process, and this inconsistency result is recorded. This result indicates that the discovered micro-slip anomaly is not caused by occasional operating condition disturbances, but is highly correlated with changes in the mechanical state of the brake, such as viscosity, hysteresis, and mechanical stagnation, providing mechanistic confirmation for subsequent load-related stability analysis.

[0091] This step constructs a consistency judgment interval based on historical data and achieves response consistency judgment by comparing the differences between two pairs of core feature data, solving the technical problem that existing technologies struggle to distinguish between occasional operating condition disturbances and actual performance degradation. The principle is that occasional operating condition disturbances typically only affect a single feature of a single process, while changes in the mechanical state of the brake can cause consistency anomalies in multiple pairs of feature data during brake release and re-braking processes. Through multi-dimensional consistency judgment, the impact of occasional disturbances can be effectively filtered out.

[0092] In some embodiments, step S5 involves classifying the operating load state. The drive response characteristics refer to the load-related parameters output by the drive system during elevator operation, including the stator current of the drive motor, output torque, and inverter output voltage. These parameters exhibit regular changes with the elevator's operating load and can serve as the basis for load state classification.

[0093] Please see Figure 6 , Figure 6 This is a schematic diagram of the operational load state partitioning process provided in an embodiment of this application. Specifically, it includes:

[0094] In S601, drive response characteristic data is acquired and preprocessed. Drive response characteristic data related to the operating load are acquired from the elevator control system, including but not limited to the stator current of the drive motor, output torque, and inverter output voltage. The acquisition frequency is consistent with the acquisition frequency of braking behavior data to ensure data timing synchronization, so as to accurately correlate the load state with braking behavior data segments in the future.

[0095] The collected drive response feature data is preprocessed to remove noise and outliers. Median filtering is used to filter current and voltage data, with a window size of 5-10 data points to remove random noise. For abnormal peak values ​​in torque data, such as those exceeding 150% of the rated torque, interpolation is used to replace them, avoiding the influence of abnormal data on the load state classification results. Simultaneously, the preprocessed data is normalized to convert drive response feature data of different magnitudes to the same numerical range, such as [0,1], to facilitate subsequent feature fusion and load state determination model training.

[0096] In S602, the load state determination model is constructed. Based on the preprocessed drive response feature data, a load state determination model is constructed to divide the braking behavior data segment into operating samples under at least two different load states. In this embodiment, it is specifically divided into three working conditions: light load, medium load, and heavy load. The light load condition refers to the elevator load being less than 30% of the rated load, the medium load condition refers to the elevator load being 30%-70% of the rated load, and the heavy load condition refers to the elevator load being greater than 70% of the rated load.

[0097] The load status determination model can be constructed using machine learning algorithms, such as support vector machines, random forests, or neural networks. In this embodiment, the random forest algorithm is preferred because it is robust, not prone to overfitting, and can handle high-dimensional data, making it suitable for elevator load status classification tasks.

[0098] Taking the random forest algorithm as an example, the model construction process is as follows: First, the drive response feature data of the elevator under known load conditions, such as load values ​​determined manually, is used as training samples. The input features are normalized stator current, output torque, inverter output voltage, etc., and the output labels are the corresponding load states, i.e., light load, medium load, and heavy load. Second, the training samples are divided into a training set and a validation set in a 7:3 ratio. The training set is used for model training, and the validation set is used for model parameter adjustment and performance evaluation. Then, the number of decision trees is set to 100-200, the maximum depth of each decision tree is 5-10 layers, and the minimum number of sample splits is 5-10. The model is trained using the training set, and the model parameters are adjusted using the validation set to improve the model's judgment accuracy. Finally, when the model's accuracy on the validation set reaches more than 90%, the model construction is completed, ensuring that the model has good classification performance.

[0099] In S603, the load state is segmented for braking behavior data segments. The drive response feature data corresponding to the current braking event is input into the trained load state determination model, and the model outputs the load state corresponding to the braking event. During the segmentation process, if the load state probability output by the model, for example, the probability of belonging to a heavy load condition, is lower than a preset probability threshold, such as 80%, then a comprehensive judgment is made by combining the load states of adjacent braking events. If the load states of adjacent braking events are both medium load, then the load state of the current braking event is determined to be medium load; if the load states of adjacent braking events are inconsistent, then the current braking event is marked as having an uncertain load and is temporarily excluded from subsequent multi-load consistency analysis to ensure the reliability of the analysis samples.

[0100] Simultaneously, the data from the segmented load states are statistically analyzed to ensure that the number of braking behavior samples under each load state meets the analysis requirements, for example, the number of samples under each load state is no less than 50. If the number of samples under a certain load state is insufficient, the data collection time is extended until the number of samples meets the requirements to avoid statistical distortion due to insufficient sample size.

[0101] This step constructs a load state determination model based on drive response characteristics, enabling accurate differentiation of elevator operating load states. This solves the technical problem that existing technologies mostly detect loads under fixed conditions and struggle to reflect performance stability under multiple load conditions. The principle is that changes in elevator operating load cause regular changes in the drive system's current, torque, and other response characteristics. By capturing these patterns through a machine learning model, automatic and accurate load state classification can be achieved.

[0102] In some embodiments, for step S6, the braking performance stability analysis is performed under different load conditions. Please refer to... Figure 7 , Figure 7A schematic diagram of the stability analysis process provided in this application embodiment. Specifically, it includes:

[0103] In S701, the statistical analysis of characteristic data under various load conditions is conducted. For braking behavior samples under light, medium, and heavy load conditions, the distribution of the first characteristic data and response consistency results are statistically analyzed. The statistical analysis of the first characteristic data includes the speed decay continuity characteristic index. Low-speed phase residual motion characteristic indicators Deceleration variation stability characteristic index The distribution; the statistics of response consistency results include the difference between the brake release delay time and the re-brake delay time. The ratio of speed build-up time to complete stop time or difference The distribution of .

[0104] For each type of feature data, calculate the statistical parameters under each load condition, including the mean. Standard deviation Maximum value Minimum value and the proportion of abnormal samples The proportion of abnormal samples This refers to the ratio of the number of samples whose characteristic data exceeds the normal range of historical stable operation to the total number of samples under that load condition. For example, under light load conditions, the statistical speed decay continuity index... mean Standard deviation and the proportion of abnormal samples This comprehensively reflects the distribution characteristics of the feature data under this load condition.

[0105] Optionally, histograms and box plots of the distribution of each feature data under different load conditions can be drawn to visually demonstrate the distribution pattern and dispersion of the feature data, providing visualization support for subsequent comparative analysis.

[0106] In S702, a comparative analysis of the consistency of characteristics across loads is conducted. First, the changing trend of the same characteristic data under different load conditions is analyzed, using the velocity decay continuity index as an example. For example, if as the load increases, The mean shows a continuous upward trend, that is Furthermore, the standard deviation also increases, indicating that as the load increases, the continuity of speed decay gradually deteriorates, and the stability of braking performance decreases.

[0107] Secondly, calculate the degree of difference of the same characteristic data under different load conditions and define a cross-load consistency index. The calculation method is as follows: in, In this embodiment, the number of load states is... , For the first The mean of characteristic data under each load condition For the first The mean of characteristic data under each load condition The number of combinations represents the number of comparisons under different load conditions. The larger the value, the greater the difference in the same feature data under different load conditions, and the worse the consistency across loads.

[0108] The cross-load consistency index of the current braking event Cross-load consistency index corresponding to historical stable operation phase To make a comparison, if If so, the cross-load consistency of the feature data is determined to be abnormal.

[0109] In S703, the determination of load-related stability degradation involves identifying situations where anomalies are significantly concentrated within a specific load range. This is based on the percentage of anomalous samples across multiple characteristic data points under a particular load condition, such as heavy-load operation. All of these are significantly higher than other load conditions, and exceed twice the proportion of abnormal load conditions during historical stable operation phases. For example, the speed attenuation continuity index under heavy load conditions. The proportion of abnormal samples If the proportion of anomalies under heavy load conditions during the historical stable phase is only 10%, and other characteristic data also show a similar situation, then it is determined that the anomalies are significantly concentrated in this load range, and the performance of the brake under this load condition is obviously degraded.

[0110] Identify situations where load changes lead to amplified anomalies. For example, if the anomaly in the characteristic data gradually intensifies as the load changes from light to heavy, such as under light load conditions... If the abnormal samples exceed the upper limit of the normal range by an average of 10%, exceed 25% under medium load conditions, and exceed 50% under heavy load conditions, it is determined that the load change has caused the abnormal amplification, and the brake performance has entered the condition-sensitive degradation stage. That is, the braking performance is significantly more sensitive to load changes and is prone to performance abnormalities under specific load conditions.

[0111] Based on the results of the comprehensive cross-load feature consistency comparison analysis and load-related anomaly identification, if one of the following two situations occurs, it is determined that there is a decrease in load-related stability: First, there is an anomaly in the cross-load consistency of at least two types of core feature data, and there is a significant concentration of anomalies within a load interval; Second, there is an anomaly in the cross-load consistency of at least one type of core feature data, and there is a situation where load changes lead to an amplification of the anomaly.

[0112] This step establishes a cross-load characteristic statistical and consistency analysis system, solving the technical problem that existing technologies struggle to systematically determine changes in braking performance under different load conditions. The principle is that brake performance degradation may only manifest under specific load conditions. By statistically comparing characteristic data under different load conditions, the stability of braking performance as load changes can be comprehensively reflected, and condition-sensitive degradation characteristics can be identified.

[0113] In some embodiments, for step S7, the combined judgment and detection results are output. The brake performance detection conclusion is output by combining the comparison results of the first feature data, the response consistency judgment results, and the load-related stability analysis results. For example, the specific judgment rule is as follows: when at least two of the comparison results of the first feature data, the response consistency judgment results, and the load-related stability analysis results simultaneously indicate an anomaly, a detection conclusion of brake performance anomaly is output; otherwise, a detection conclusion of brake performance being in normal operating condition is output.

[0114] For cases deemed as performance anomalies, the degradation stage is further clarified: if only the comparison result of the first characteristic data indicates anomaly, and the other two results are normal, it is determined to be an early degradation stage; if the comparison result of the first characteristic data and the response consistency judgment result both indicate anomalies, regardless of whether the load-related stability analysis result is normal, it is determined to be a developmental degradation stage; if the load-related stability analysis result and any other result both indicate anomalies, it is determined to be a condition-related degradation stage.

[0115] Therefore, this application achieves accurate and comprehensive testing of elevator brake performance by constructing a detection process that includes early detection, mechanism confirmation, and operational condition verification. Through short-term analysis of the initial braking phase and extraction of three types of primary feature data, transient anomalies that are difficult to detect using traditional methods can be identified, enabling early warning. By utilizing the consistency analysis of the response between brake release and re-braking, occasional disturbances and actual performance degradation can be effectively distinguished, improving the reliability of the judgment. Through multi-load state division and cross-load consistency analysis, the adaptability to complex operating conditions is enhanced, enabling the detection of performance problems under specific loads. This method can provide accurate degradation information before a significant decline in brake performance, clearly identify the degradation stage, provide targeted maintenance suggestions, optimize maintenance timing, reduce the risk of brake failure, and ensure the safe operation of the elevator.

[0116] Please see Figure 8 , Figure 8 This application provides an elevator brake performance testing system as an embodiment. The system embodiment is similar to... Figure 1 Corresponding to the illustrated method embodiments, this system can be specifically applied to various computer devices. The system specifically includes:

[0117] The data acquisition module 801 acquires the running data before and after each braking command is triggered, forming a braking behavior data segment, wherein the running data includes the elevator running speed;

[0118] The suspected anomaly marking module 802, for each braking behavior data segment, determines a short analysis interval from the time the braking command is triggered until the speed first reaches zero, extracts the first feature data representing the dynamic response in the initial stage of braking establishment within the interval, and compares it with historical stable features. If it continues to deviate, the corresponding braking behavior is marked as suspected anomaly.

[0119] The continuous braking segment identification and feature extraction module 803 identifies whether there is a continuous running segment before and after a suspected abnormal event where the brake is released and then braked again. If so, it extracts the second feature data of the brake release process and the third feature data of the re-braking process in the segment.

[0120] The response consistency judgment module 804 compares the second feature data with the third feature data to determine the response consistency between brake release and re-braking. If the consistency is lower than the preset judgment range, the response inconsistency result is recorded.

[0121] The load state division module 805 divides each braking behavior data segment into at least two different load state operation samples based on the drive response characteristics during elevator operation.

[0122] The cross-load consistency analysis module 806 statistically analyzes the distribution of the first feature data and the response consistency results for operating samples under different load states, and analyzes the cross-load consistency of the brake performance. If the abnormal concentration or load change leads to the aggravation of the abnormality under a specific load, it is determined that there is a load-related stability decrease.

[0123] The comprehensive conclusion output module 807 integrates the comparison results of the first feature data, the response consistency judgment results, and the load-related stability analysis results to output the brake performance test conclusion.

[0124] Based on the same inventive concept, this application also provides a computer device, the method corresponding to which can be the method in the foregoing embodiments, and the principle of solving the problem is similar to that method. The computer device provided in this application includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to execute the methods and / or technical solutions of the foregoing embodiments of this application.

[0125] The computer device can be a user device, or a device formed by integrating user devices and network devices through a network, or it can be an application running on the aforementioned devices. The user device includes, but is not limited to, various terminal devices such as computers, mobile phones, tablets, smartwatches, and smart bands. The network device includes, but is not limited to, network hosts, single network servers, multiple network server sets, or cloud computing-based computer sets, and can be used to implement some processing functions when setting an alarm clock. Here, the cloud consists of a large number of hosts or network servers based on cloud computing. Cloud computing is a type of distributed computing, consisting of a virtual computer composed of a group of loosely coupled computer sets.

[0126] Figure 9 The diagram illustrates the structure of an apparatus suitable for implementing the methods and / or technical solutions in the embodiments of this application. The apparatus includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes based on a program stored in a read-only memory (ROM) 902 or a program loaded from a storage portion 908 into a random access memory (RAM) 903. The RAM 903 also stores various programs and data required for system operation. The CPU 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0127] The following components are connected to I / O interface 905: an input section 906 including a keyboard, mouse, touchscreen, microphone, infrared sensor, etc.; an output section 907 including a cathode ray tube (CRT), liquid crystal display (LCD), LED display, OLED display, etc., and speakers, etc.; a storage section 908 including one or more computer-readable media such as hard disk, optical disk, magnetic disk, semiconductor memory, etc.; and a communication section 909 including a network interface card such as a LAN (local area network) card, modem, etc. The communication section 909 performs communication processing via a network such as the Internet.

[0128] In particular, the methods and / or embodiments in this application can be implemented as computer software programs. For example, the embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. When the computer program is executed by a central processing unit (CPU) 901, it performs the functions defined in the methods of this application.

[0129] Another embodiment of this application provides a computer-readable storage medium having computer program instructions stored thereon, which can be executed by a processor to implement the methods and / or technical solutions of any one or more embodiments of this application described above.

[0130] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0131] The flowcharts or block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-specific system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0132] Furthermore, the inclusion of a single word does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in a system statement can also be implemented by a single unit or device through software or hardware. Terms such as "first," "second," etc., are used to indicate names and do not indicate any specific order.

Claims

1. A method for testing the performance of an elevator brake, characterized in that, Includes the following steps: The system acquires operational data before and after each braking command is triggered, forming a braking behavior data segment, wherein the operational data includes the elevator's operating speed; For each braking behavior data segment, a short analysis interval is determined from the time the braking command is triggered until the speed first reaches zero. The first feature data representing the dynamic response in the initial stage of braking establishment within this interval is extracted and compared with historical stable features. If the deviation continues, the corresponding braking behavior is marked as a suspected anomaly. Before and after a suspected abnormal event, identify whether there is a continuous running segment where the brake is released and then braked again. If so, extract the second feature data of the brake release process and the third feature data of the re-braking process in the segment. Compare the second feature data with the third feature data to determine the consistency of the response between brake release and re-brake. If the consistency is lower than the preset judgment range, record the result of inconsistent response. Based on the driving response characteristics during elevator operation, each braking behavior data segment is divided into operating samples under at least two different load states; For operating samples under different load conditions, the distribution of the first feature data and the response consistency results are statistically analyzed to analyze the cross-load consistency of the brake performance. If the abnormality is concentrated under a specific load or the load change causes the abnormality to intensify, it is determined that there is a load-related stability decrease. Based on the comparison results of the first feature data, the response consistency judgment results, and the load-related stability analysis results, the brake performance test conclusion is output.

2. The method for testing the performance of an elevator brake according to claim 1, characterized in that, The first feature data includes at least one of velocity decay continuity feature data, low-speed phase motion residual feature data, and deceleration change stability feature data; the continuous deviation specifically means that the current first feature data exceeds the historical stable feature range in a preset number of consecutive braking events, or the single exceedance exceeds a preset threshold.

3. The method for testing the performance of an elevator brake according to claim 2, characterized in that, The specific method for identifying whether there is a continuous running segment where braking is released and then re-applied is as follows: if, within a preset time range before and after a suspected abnormal braking event, the time interval between two braking commands is less than a preset threshold, and there is a complete braking release process in between, then it is determined to be a continuous running segment.

4. The method for testing the performance of an elevator brake according to claim 3, characterized in that, The second feature data includes at least one of the following: brake release delay time and speed establishment time; the third feature data includes at least one of the following: re-braking delay time and complete stop time.

5. The method for testing the performance of an elevator brake according to claim 4, characterized in that, This also includes establishing a consistency judgment interval based on data from the elevator's historical stable operation phases; Calculate the difference between the brake release delay time and the re-brake delay time, and the ratio or difference between the speed establishment time and the complete stop time; compare the difference or ratio with the corresponding consistency judgment interval, and determine that the response is inconsistent when it exceeds the interval range.

6. The method for testing the performance of an elevator brake according to claim 1, characterized in that, Specifically, dividing each braking behavior data segment into operating samples under at least two different load conditions involves using at least one of the stator current, output torque, or inverter output voltage of the elevator drive motor as input features, and using a preset load condition determination model to divide the braking behavior data segment into operating samples under light load, medium load, or heavy load conditions.

7. The method for testing the performance of an elevator brake according to claim 6, characterized in that, The analysis of the brake's performance consistency under different load conditions specifically includes: For the same type of feature data, calculate the mean difference under different load conditions; Calculate the proportion of abnormal samples in the characteristic data under each load condition; When the mean difference exceeds the preset proportion of the difference corresponding to the historical stable stage, or when the proportion of abnormal samples under a certain load state is significantly higher than that under other load states, it is determined that the brake performance has a load-related stability decline.

8. A performance testing system for elevator brakes, characterized in that, include: The data acquisition module acquires the operating data before and after each braking command is triggered, forming a braking behavior data segment, wherein the operating data includes the elevator running speed; The suspected anomaly marking module determines a short analysis interval for each braking behavior data segment from the time the braking command is triggered until the speed first reaches zero. It extracts the first feature data representing the dynamic response in the initial stage of braking establishment within this interval and compares it with historical stable features. If the deviation continues, the corresponding braking behavior is marked as suspected anomaly. The continuous braking segment identification and feature extraction module identifies whether there is a continuous running segment before and after a suspected abnormal event where the brake is released and then braked again. If so, it extracts the second feature data of the brake release process and the third feature data of the re-braking process in the segment. The response consistency judgment module compares the second feature data with the third feature data to determine the response consistency between brake release and re-braking. If the consistency is lower than the preset judgment range, the response inconsistency result is recorded. The load state segmentation module, based on the drive response characteristics during elevator operation, divides each braking behavior data segment into operating samples under at least two different load states. The cross-load consistency analysis module statistically analyzes the distribution of the first feature data and response consistency results for operating samples under different load states, and analyzes the cross-load consistency of brake performance. If abnormal concentration or load change leads to aggravation of abnormality under a specific load, it is determined that there is a load-related stability decrease. The comprehensive conclusion output module integrates the comparison results of the first feature data, the response consistency judgment results, and the load-related stability analysis results to output the brake performance test conclusion.

9. A computer device, wherein the computer device is characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A computer-readable medium having computer program instructions stored thereon, characterized in that, The computer program instructions can be executed by a processor to implement the method as described in any one of claims 1-7.

Images