Elevator operation state monitoring method and system fusing multiple sensors

Abstract

The application relates to the technical field of elevator operation state monitoring, and discloses an elevator operation state monitoring method and system fusing multiple sensors. The method comprises the following steps: acquiring vibration signals and current signals of an elevator door rail, and generating an initial multi-source signal set; performing time synchronization processing on the initial multi-source signal set to obtain a time synchronization signal sequence, and extracting features of various signals from the time synchronization signal sequence to generate a signal feature segment set; analyzing the interaction mode between signals according to the signal feature segment set, determining an interaction abnormal feature group, fusing the interaction abnormal feature group and historical fault data of the elevator door rail, and generating a corrected door rail operation state description; if an abnormal component in the corrected door rail operation state description exceeds a preset threshold value, performing optimization processing on the abnormal data to obtain an optimized state description, matching an elevator fault mode according to the optimized state description, and generating a fault diagnosis report for the elevator door rail system. The application improves the fault monitoring precision of the elevator door rail.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of elevator operation state monitoring, and in particular to an elevator operation state monitoring method and system fusing multiple sensors. BACKGROUND

[0002] With the acceleration of urbanization and the increase of building height, elevators have become an indispensable vertical transportation tool in modern buildings. The safe operation of elevators is directly related to the safety of passengers, therefore, how to monitor the operation state of elevators in real time and discover potential fault hazards in advance has become an important issue in elevator maintenance and management.

[0003] At present, the fault monitoring method of the elevator mainly relies on a single sensor or periodic inspection by artificial experience. This traditional monitoring method has multiple problems, for example, it is difficult to monitor various abnormalities of the elevator in real time, it is unable to discover potential fault patterns in the system in time, and the accuracy of fault diagnosis is low. Elevator failures often occur suddenly without warning, especially when the door rail system has wear, jamming and other faults, which can easily lead to elevator downtime or more serious safety accidents. In the existing elevator monitoring technology, multi-sensor data fusion and intelligent analysis technology have not been fully applied. Although the traditional vibration monitoring method can provide certain fault indication, it cannot comprehensively evaluate the overall state of the elevator operation, and it is difficult to give accurate diagnosis results when facing complex elevator fault patterns. In order to solve the above problems, in recent years, more and more researches have begun to focus on intelligent diagnosis technology fusing multiple sensors, which realizes comprehensive monitoring of the elevator system by combining vibration, temperature, current and other signals, and improves the accuracy of fault diagnosis by using modern data analysis methods. However, the existing technology still lacks effective algorithms and physical model support, resulting in a large space for improvement in real-time, accuracy and reliability of the elevator operation state monitoring system.

[0004] Therefore, the present application proposes an elevator operation state monitoring method fusing multi-sensor data, combining physical models and dynamic optimization, which can better diagnose potential faults in the elevator system and ensure safe operation of the elevator. SUMMARY

[0005] To solve the above technical problems, the present application provides an elevator operation state monitoring method and system fusing multiple sensors, which is used to improve the fault monitoring accuracy of the elevator door rail.

[0006] In a first aspect, the present application provides an elevator operation state monitoring method fusing multiple sensors, which comprises:

[0007] Step S1: Obtain the vibration signal and current signal of the elevator door rail to generate an initial multi-source signal set;

[0008] Step S2: performing time synchronization processing on the initial multi-source signal set to obtain a time-synchronized signal sequence, extracting features of various signals from the time-synchronized signal sequence, and generating a signal feature segment set;

[0009] Step S3: analyzing interaction modes between signals according to the signal feature segment set, determining an interaction abnormal feature group, fusing the interaction abnormal feature group with historical fault data of the elevator door rail, and generating a corrected door rail operation state description;

[0010] Step S4: if an abnormal component in the corrected door rail operation state description exceeds a preset threshold, performing optimization processing on abnormal data to obtain an optimized state description, matching an elevator fault mode according to the optimized state description, and generating a fault diagnosis report for the elevator door rail system.

[0011] In a second aspect, the present application provides an elevator operation state monitoring system fusing multiple sensors, the system comprising:

[0012] An acquisition module is configured to acquire vibration signals and current signals of an elevator door rail, and generate an initial multi-source signal set;

[0013] A synchronization module is configured to perform time synchronization processing on the initial multi-source signal set to obtain a time-synchronized signal sequence, extract features of various signals from the time-synchronized signal sequence, and generate a signal feature segment set;

[0014] An analysis module is configured to analyze interaction modes between signals according to the signal feature segment set, determine an interaction abnormal feature group, fuse the interaction abnormal feature group with historical fault data of the elevator door rail, and generate a corrected door rail operation state description;

[0015] A diagnosis module is configured to, if an abnormal component in the corrected door rail operation state description exceeds a preset threshold, perform optimization processing on abnormal data to obtain an optimized state description, match an elevator fault mode according to the optimized state description, and generate a fault diagnosis report for the elevator door rail system.

[0016] Compared with the prior art, the present application has at least the following advantages:

[0017] The application significantly improves the accuracy and reliability of the elevator door rail system state monitoring through multi-sensor signal fusion and multi-level intelligent analysis. First, through accurate time synchronization and feature extraction of vibration and current signals, the analysis obstacles of multi-source heterogeneous signals are effectively overcome, laying a high-quality data foundation for subsequent diagnosis; then, by analyzing the interaction mode between signals and fusing historical fault data, an iteratively corrected running state description is generated, greatly improving the stability and historical consistency of state evaluation; when significant abnormalities are detected, a deep optimization based on the physical dynamics model is started, which maps the abnormal phenomenon to specific physical parameter changes, realizing the accurate positioning and quantitative diagnosis of fault sources; finally, combined with real-time wear data and running time prediction, a fault diagnosis report with risk level ranking is generated, providing a direct and reliable action guide for maintenance decisions. The application effectively reduces the false positive and false negative rates, realizes the transition from passive maintenance to predictive maintenance, and fully guarantees the safety and efficiency of elevator operation. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor based on these drawings.

[0019] Figure 1 An embodiment schematic diagram of the elevator running state monitoring method of the present application embodiment fusing multiple sensors;

[0020] Figure 2 A parameterized dynamics model schematic diagram of the elevator door rail system in the present application embodiment;

[0021] Figure 3 An iterative optimization index gain effect diagram in the present application embodiment;

[0022] Figure 4 An embodiment schematic diagram of the elevator running state monitoring system of the present application embodiment fusing multiple sensors. DETAILED DESCRIPTION

[0023] The elevator operation state monitoring method and system fusing multiple sensors are provided in the embodiments of the present application. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not have to be used to describe a particular order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "comprising" or "having" and any variation thereof is intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0024] For ease of understanding, the specific processes of the embodiments of the present application are described below. Please refer to Figure 1 One embodiment of the elevator operation state monitoring method fusing multiple sensors in the embodiments of the present application includes:

[0025] Step S1, obtaining the vibration signal and the current signal of the elevator door rail to generate an initial multi-source signal set.

[0026] Specifically, with the continuous development of elevator operation state monitoring technology, the traditional elevator fault diagnosis method gradually cannot meet the high-precision requirements of modern elevator operation. In order to ensure accurate monitoring of the operation state of the elevator door rail, the sensor array is arranged at the key positions of the elevator door rail, such as the door rail sliding groove, the motor driving part, etc., to capture the vibration signal and the current signal of the elevator door rail in real time. The vibration signal is obtained by an acceleration sensor, and these sensors can detect the small vibration changes in the door rail system. These vibrations are usually caused by changes in the operation state of the elevator door rail, wear or jamming, etc. The current signal is monitored by a current sensor to monitor the driving current change of the motor. The current signal reflects the operation state of the motor load, start, acceleration, etc. If the elevator door rail system fails, the load change of the motor will cause the fluctuation of the current, thereby providing an important clue for fault diagnosis. The arrangement of the sensor array ensures the comprehensiveness of signal acquisition, covering the operation state of each component of the elevator door rail.

[0027] The acquired vibration signals and current signals are preprocessed to remove high-frequency noise and environmental interference, ensuring the effectiveness of the signals. For example, the raw data of the vibration signals may contain high-frequency noise components. During preprocessing, a low-pass filter is used to remove these disturbances. The preprocessed signal data is then normalized to eliminate differences in signal amplitude, making the signals more comparable in subsequent analysis. These preprocessed signal data sets form the initial multi-source signal set, which serves as the basis for subsequent signal analysis and fault diagnosis. The generation of the initial multi-source signal set is the starting point of the entire elevator operation state monitoring system, and it provides necessary data support for subsequent steps such as time synchronization processing, signal feature extraction, and fault pattern recognition.

[0028] Step S2, time synchronization processing is performed on the initial multi-source signal set to obtain a time-synchronized signal sequence. Features of various signals are extracted from the time-synchronized signal sequence to generate a signal feature segment set.

[0029] In step S2, the initial multi-source signal set is time-synchronized to obtain a time-synchronized signal sequence, including: using timestamp alignment technology to process the time sequence segments of the vibration signals and current signals based on the initial multi-source signal set; if the timestamp deviation exceeds a preset threshold, adjusting the sampling frequency to eliminate the deviation through signal synchronization verification; combining the signal mutation interval to perform data interpolation on the time sequence segments of the vibration signals and current signals, and generating continuous time sequence data through interpolation processing; determining the time-synchronized signal sequence based on the interpolated time sequence data; and performing consistency verification on the time-synchronized signal sequence to ensure the alignment accuracy of the vibration signals and current signals on the time axis.

[0030] Specifically, in the operation state monitoring of the elevator system, due to the sampling frequency, time delay and other factors of different sensors, these signals often cannot be synchronized, resulting in deviation in subsequent data analysis and fault diagnosis. In order to ensure that different signals can be effectively analyzed, time synchronization processing must be performed on different signals. Time synchronization processing eliminates the time deviation between signals to ensure that different signals are compared and analyzed at the same time point. The specific execution includes the following sub-steps: aligning the time series of the vibration signal and the current signal according to the timestamp of each data point in the initial multi-source signal set. However, in actual application, due to environmental noise, sensor performance differences and other factors, timestamp deviation may occur. If the deviation of the timestamp is found to exceed the preset threshold, for example, 0.5 seconds, signal synchronization verification is triggered. By calculating the correlation coefficient of the vibration signal and the current signal, the matching degree of the two at the key moment, such as signal peak, can be determined. The correlation coefficient is a statistical quantity used to measure the strength and direction of the linear relationship between two signals. The commonly used correlation coefficient is the Pearson correlation coefficient, which is between -1 and 1. If the correlation coefficient is lower than the preset threshold, for example, 0.8, it means that the synchronization between the signals is poor, and the sampling frequency needs to be adjusted to eliminate this deviation. For example, the sampling frequency of the vibration signal is increased from 100Hz to 120Hz to keep consistent with the current signal, ensuring that their time series are more accurately synchronized.

[0031] After adjusting the sampling frequency, in order to ensure the continuity and integrity of the signal, data interpolation is also needed in the signal mutation interval. For example, in the elevator door rail system, if the vibration signal is missing in some period, it may be due to sensor failure or environmental interference. By using linear interpolation method, estimated values are inserted between missing data points to make the signal smoothly transition within the mutation interval and maintain the continuity of the signal. Through interpolation processing, a continuous time series data is generated, ensuring that the vibration signal and the current signal are perfectly aligned on the time axis. Finally, the signal sequence after interpolation and synchronization processing will enter the consistency verification stage. This stage calculates the correlation coefficient of the verification sequence. If the correlation coefficient between the vibration signal and the current signal is greater than 0.9, it means that the alignment accuracy of the two on the time axis is high, and the signal synchronization meets the requirements of further analysis and feature extraction. Through this accurate synchronization and verification, we ensure the accuracy of subsequent feature extraction, fault pattern recognition and other steps.

[0032] In step S2, the features of various signals are extracted from the time-synchronized signal sequence to generate a signal feature segment set, including: extracting time-domain features of the vibration signal and frequency-domain features of the current signal from the time-synchronized signal sequence, identifying and locating abnormal trigger points based on the time-domain features and the frequency-domain features, segmenting the time-synchronized signal sequence based on the abnormal trigger points to obtain a plurality of signal segments, calculating the correlation coefficient between the vibration signal and the current signal in each signal segment, identifying the abnormal component proportion of each signal segment based on the correlation coefficient, classifying the signal segments according to the abnormal component proportion, generating a signal feature segment set according to the classification result, and standardizing the feature data in the signal feature segment set, analyzing the correlation between different signal segments based on the standardized feature data, adjusting the structure of the signal feature segment set according to the correlation analysis result, and obtaining an optimized signal feature segment set.

[0033] In step S3, the interaction mode between signals is analyzed based on the signal feature segment set to determine an interaction abnormal feature group, and the interaction abnormal feature group and the elevator door rail historical fault data are fused to generate a corrected door rail running state description.

[0034] In step S3, the interaction mode between signals is analyzed based on the signal feature segment set to determine an interaction abnormal feature group, including: analyzing the interaction mode between the vibration signal and the current signal for the signal feature segment set, and quantifying the interaction mode using a deviation distribution interval mapping technique; constructing an interaction feature vector based on the quantization result, and determining the interaction abnormal feature group according to the interaction feature vector, the abnormal component proportion and the deviation range; prioritizing the abnormal components in the interaction abnormal feature group, filtering key abnormal features according to the sorting result, and adjusting the interaction abnormal feature group through the filtered key abnormal features.

[0035] Specifically, in order to improve the fault diagnosis accuracy of the elevator door rail system, the traditional method usually analyzes the vibration signal or the current signal separately, and lacks in-depth analysis of the interaction between the two types of signals. In order to solve this problem, a method of analyzing the interaction mode between signals based on the signal feature segment set to determine the interaction abnormal feature group is proposed. By analyzing the mutual relationship between the vibration signal and the current signal, the potential fault mode can be more accurately identified, thereby improving the accuracy and efficiency of diagnosis.

[0036] Specifically, first, according to the signal feature segment set collected from the elevator door rail system, the interaction mode of the vibration signal and the current signal is analyzed, wherein the interaction mode refers to the corresponding relationship between the time domain features of the vibration signal and the frequency domain features of the current signal, such as the synchronization between the vibration peak value and the current fluctuation. In order to accurately analyze the interaction between these signals, the bias distribution interval mapping technology is used to quantify the interaction mode. Specifically, the bias distribution interval mapping technology is to map the bias value in the interaction mode to a preset distribution interval, for example, the bias value is divided into low, medium and high intervals, each interval corresponds to a different quantization coefficient, and the overall mode is quantified by calculating the distribution density of the bias in each interval. First, the bias value of the vibration signal and the current signal in the interaction mode is calculated, for example, the bias value is obtained by the absolute value of the difference between the two features. The bias value is mapped to the distribution interval, for example, the interval boundary is set to 0 to 0.5 for low bias, 0.5 to 1 for medium bias, and more than 1 for high bias. According to the mapping result, a quantization index is calculated, for example, the quantization index is the weighted average of the bias value in each interval. For example, in the elevator door rail system, when the vibration signal shows high-frequency oscillation and the current signal shows low-frequency fluctuation, the bias distribution interval mapping can quantify that the high bias proportion reaches 60%, which helps to identify the potential risk of card jam. This quantization can improve the accuracy of anomaly detection and reduce false positives. In this case, by bias distribution interval mapping, these changes can be quantified to determine their impact, thereby providing a basis for subsequent anomaly feature recognition. Based on the quantization result, an interaction feature vector is constructed. The interaction feature vector construction technology is used to generate the interaction feature vector, specifically, the interaction feature vector construction technology is to convert the quantized interaction mode into a vector form to obtain, for example, an interaction feature vector, and the vector components include abnormal component proportion, bias range and other dimensions. In order to further analyze these features, the proportion of abnormal components and the bias range are determined according to the results of the interaction feature vector to determine the interaction abnormal feature group. The specific implementation process is as follows.

[0037] Among them, determining the interaction abnormal feature group includes: performing multi-dimensional interaction analysis on the signal feature segment set, constructing an interaction feature matrix through the multi-dimensional interaction analysis result; calculating the abnormal component proportion according to the interaction feature matrix; dividing the abnormal component proportion into intervals by using the bias distribution interval mapping technology; determining the bias range through the interval division result; generating the interaction abnormal feature group according to the bias range and the abnormal component proportion; performing feature clustering on the interaction abnormal feature group; analyzing the distribution law of abnormal features through the clustering result; and adjusting the weight distribution of the interaction abnormal feature group according to the distribution law.

[0038] Specifically, the detailed implementation process of determining the interaction abnormal feature group includes the following steps: first, multi-dimensional interaction analysis is performed on the signal feature segment set, which means not only the simple relationship between the vibration signal and the current signal needs to be considered, but also the interaction of them in multiple dimensions is analyzed. For example, the time domain features of the vibration signal such as peak value, mean value, variance and the frequency domain features of the current signal such as main frequency component, spectral distribution are two different types of features, and through interaction analysis, the complex relationship of the two signals under different operating conditions can be revealed. By constructing these analysis results into an interaction feature matrix, the matrix contains the interaction of the vibration signal and the current signal under different time points and different feature dimensions, for example, a certain element of the matrix may represent the correlation strength between the peak value of the vibration signal and the main frequency component of the current signal at a certain time point, and the correlation strength is usually represented by the Pearson correlation coefficient. This matrix provides a comprehensive data basis for subsequent fault diagnosis. The proportion of abnormal components in each signal segment is calculated using the interaction feature matrix, and the abnormal component refers to the part of the signal that deviates from the normal operating state. Assuming that the vibration signal and the current signal are [1.2, 1.5, 3.0, 1.3, 1.7, 2.1] and [0.8, 1.1, 2.3, 1.0, 1.2, 1.5] respectively, first, the correlation strength between the vibration signal and the current signal is extracted from the interaction feature matrix, assuming that the Pearson correlation coefficient r is 0.4, which indicates that there is a weak linear correlation between the vibration signal and the current signal. A threshold of 0.5 is set, if the correlation coefficient is lower than 0.5, it means that the signal segment may contain abnormalities, and the abnormal points in the abnormal signal segment are identified. Normally, the vibration amplitude should not exceed about 2.0g, and the current should not exceed about 1.5A. The third data point of the vibration signal 3.0g deviates from the normal range, and the third data point of the current signal 2.3A is also higher than the normal value, so it can be considered that these two points belong to abnormal trigger points. The entire signal sequence has 6 sampling points, so the abnormal points account for 1 / 6, and the proportion of abnormal components is 16.7%.

[0039] After obtaining the abnormal component proportion, the deviation distribution interval mapping technology is used to divide the abnormal component proportion into intervals. Specifically, the deviation distribution interval mapping technology maps the abnormal component proportion to a preset interval, so as to quantize the severity of the abnormality. For example, the abnormal component proportion can be divided into several intervals, such as a low deviation interval (0%-10%): indicating that the signal change is not large and the abnormal component proportion is low; a medium deviation interval (10%-30%): indicating that the signal appears certain abnormality, but does not affect the normal operation of the system; and a high deviation interval (30% or more): indicating that the signal abnormality is obvious and may correspond to a more serious fault mode. The abnormal component proportion is 16.7%, which is mapped to the medium deviation interval, indicating that the abnormality degree of the signal belongs to the medium level. Next, based on these deviation intervals and the abnormal component proportion, an interactive abnormal feature group is generated, for example, the abnormal component proportion of a certain signal segment is higher than 30% and is classified into the high deviation interval.

[0040] Subsequently, feature clustering is performed on all generated interactive abnormal feature groups. Through clustering analysis, similar features can be classified into a category, thereby helping to identify common features between different abnormal signal segments and discover the fault mode they may correspond to. For example, if the vibration peak value and current fluctuation of multiple signal segments increase at the same time point, and their abnormal component proportion is high, these segments are likely to indicate a certain fault of the elevator door rail system, such as jamming. Through this clustering analysis, the potential cause of the fault can be summarized, and more basis for fault diagnosis can be provided. By analyzing the distribution law of abnormal features, the distribution trend of fault modes can be identified. For example, during the operation of the elevator door rail, certain abnormal features may frequently appear within a short period of time, which may indicate that the elevator is susceptible to a certain fault mode under certain operating conditions. According to these distribution laws, the weight distribution of the interactive abnormal feature group can be adjusted, and features with greater impact can be given higher weights, and vice versa. For example, when the running time of the elevator door rail system exceeds 500 hours, certain abnormal signals such as current fluctuation abnormality become more frequent, and the weights of these signals may need to be increased. Through this dynamic weight adjustment, the diagnosis capability for complex faults of the elevator door rail system under different running times and different environmental conditions can be improved.

[0041] After determining the interaction abnormal feature group, the abnormal components in the interaction abnormal feature group are sorted, giving priority to those features that have the greatest impact on the elevator door rail fault, for example, if the correlation between the vibration signal and the current signal is high and the proportion of abnormal components is large, it will be ranked in a higher priority. The purpose of this step is to ensure that the most critical abnormal features are given priority, thereby improving the efficiency of fault diagnosis. After sorting, the interaction abnormal feature group is adjusted according to the selected key abnormal features. This adjustment process is to ensure that only those features that can significantly improve the accuracy of fault diagnosis are retained. By prioritizing these abnormal features, the elevator fault diagnosis system can identify door rail problems earlier, thereby taking timely maintenance measures. Subsequently, the elevator door rail historical fault data is obtained and fused with the adjusted interaction abnormal feature group to generate the corrected door rail running state description. The detailed implementation process is described later. Through dynamic updating of the weight distribution and optimization of the interaction feature group, accurate description of the elevator running state and efficient fault diagnosis can be achieved.

[0042] In step S3, the corrected door rail running state description is generated by fusing the interaction abnormal feature group with the elevator door rail historical fault data, calculating the change rate of the current abnormal component proportion relative to the historical fault data, and dynamically updating the weight distribution of each abnormal component based on the change rate. The updated weight distribution is used to prioritize and weight the abnormal components in the interaction abnormal feature group to form a weighted feature vector. The weighted feature vector is input into the preset state description model to generate the current door rail running state description. The current door rail running state description is corrected and iteratively converged to obtain a preliminary corrected door rail running state description. The preliminary corrected door rail running state description is checked for consistency, and the parameters of the weight distribution are adjusted according to the check results. The state description is optimized using the adjusted parameters to generate the final corrected door rail running state description.

[0043] Specifically, the process of generating the corrected door rail operation state description is as follows: First, the interaction abnormal feature group is fused with the historical fault data of the elevator door rail, which contains the past fault records of the elevator door rail system, such as vibration abnormalities, local sticking, etc. By comparing the current signal features with the historical data, the change rate of the current abnormal component proportion relative to the historical fault data is calculated. For example, if the abnormal component proportion of the current vibration signal is 15%, while the proportion in the historical data is usually 10%, the change rate is 50%. Based on this change rate, the weight distribution of each abnormal component is dynamically updated. For example, if the historical data of the elevator system shows that the abnormal component of the vibration signal is highly associated with faults, and the increase of the current abnormal component proportion will increase the weight of the vibration signal, for example, from 0.6 to 0.7, to better reflect the current fault mode. Next, using the updated weight distribution, the abnormal components in the interaction abnormal feature group are prioritized and weighted adjusted, which is to ensure that the system can focus on the most critical abnormal features. For example, if the frequency fluctuation of the current signal changes significantly when there is a fault, while the change of the vibration signal is relatively small, the weight of the current signal may be preferentially enhanced, reflecting its greater impact on the current fault mode.

[0044] Then, the weighted feature vector is input into a pre-set state description model, which outputs a risk level related to the abnormal component proportion. The state description model can be a regression model, a machine learning model, or a statistical model, and the specific choice depends on the complexity of the elevator system and the characteristics of the data. It uses the weighted feature vector as input, which contains the abnormal component information of the current elevator door rail system. Based on these feature vectors, the risk level of the elevator is calculated. The risk level is generated based on the correlation between the abnormal component proportion and the failure mode. For example, if the abnormal component proportion is high, such as more than 30%, the model may rate the elevator as high risk; if the proportion is low, such as below 10%, it is rated as low risk. After generating the preliminary description, the model will perform iterative correction by calculating the difference between the current state and the target state until the difference is below the pre-set threshold, such as 0.01, indicating that the model has converged to the optimal state. This method can accurately reflect the running state of the elevator system, timely detect faults, and ensure the safe operation of the system. After the preliminary correction of the state description, a consistency check is performed to ensure that the current state description is consistent with the historical data. The check step compares the abnormal component proportion with the change range of the historical record to judge the consistency. For example, if the abnormal component proportion in the historical data fluctuates within 5%, and the proportion change in the current description is within ±5%, it is considered to be consistent. If it is not consistent, the weight distribution parameters will be adjusted, such as adjusting the weight of the vibration signal from 0.7 to 0.75 to improve accuracy. Finally, the adjusted state description is optimized to further improve the representation accuracy of the abnormal component proportion. For example, starting from the initial description "abnormal component 10%", it converges to "abnormal component 9.5%" after 15 iterations. Through the optimized description, the elevator system can more accurately reflect the fault state, helping maintenance personnel to take necessary measures quickly. The optimized door rail running state description is saved to the database for subsequent analysis.

[0045] Step S4, if the abnormal component in the corrected door rail running state description exceeds the pre-set threshold, the abnormal data is optimized to obtain an optimized state description. According to the optimized state description, the elevator failure mode is matched to generate a fault diagnosis report for the elevator door rail system.

[0046] The step S4 includes: if the abnormal component in the corrected door rail running state description exceeds the preset threshold, the abnormal data is classified into a high-frequency interference layer and a low-frequency offset layer according to the signal source and the frequency domain characteristics of the abnormal data; the abnormal data within the preset deviation range boundary is optimized according to the different characteristics of the high-frequency interference layer and the low-frequency offset layer, and a preliminary optimized state description is generated according to the optimization result; the correction cycle parameters are adjusted according to the error analysis result of the preliminary optimized state description; and the iterative correction process is started through the adjusted correction cycle parameters and the optimized abnormal data until the residual error converges below the preset threshold, and the final optimized state description is output.

[0047] Specifically, the corrected door rail running state description includes an abnormal component ratio and a risk level. If the abnormal component in the corrected door rail running state description exceeds the preset threshold, for example, 0.15, it means that the running state of the elevator door rail system has deviated greatly, and the elevator may be in a medium to high risk state, which has potential danger of failure, and further optimization processing and fault diagnosis are needed to ensure the safe operation of the elevator. The application classifies the abnormal data through the abnormal data hierarchical processing technology, which specifically includes: according to the source of the abnormal data such as vibration signal or current signal, the abnormal data is classified into a high-frequency interference layer and a low-frequency offset layer. The high-frequency interference layer is usually related to sudden noise or short-term fluctuation of the elevator door rail system, for example, the instantaneous vibration of the elevator door rail during the door rail switching process may cause high-frequency noise. The low-frequency offset layer is related to long-term wear, aging or environmental changes of the elevator door rail system, and usually shows a relatively stable but continuous signal deviation. Through this hierarchical classification, the classified data can be directly used for subsequent processing to form a clear abnormal data grouping. The abnormal data within the preset deviation range boundary is optimized according to the different characteristics of the high-frequency interference layer and the low-frequency offset layer, and a preliminary optimized state description is generated according to the optimization result. The following is the specific implementation process.

[0048] The step S4 includes: if the abnormal component in the corrected door rail running state description exceeds the preset threshold, the abnormal data is classified into a high-frequency interference layer and a low-frequency offset layer according to the signal source and the frequency domain characteristics of the abnormal data; the abnormal data within the preset deviation range boundary is optimized according to the different characteristics of the high-frequency interference layer and the low-frequency offset layer, and a preliminary optimized state description is generated according to the optimization result; the correction cycle parameters are adjusted according to the error analysis result of the preliminary optimized state description; and the iterative correction process is started through the adjusted correction cycle parameters and the optimized abnormal data until the residual error converges below the preset threshold, and the final optimized state description is output.

[0049] Specifically, based on the frequency domain characteristics of the abnormal data, a suitable physical parameter model is selected from a pre-established dynamic model library of the elevator door rail system for matching, each physical parameter model in the model library corresponds to a certain type of failure mode of the elevator door rail system and contains key parameters related thereto. For example, the high-frequency interference layer is usually related to short-time burst noise or instantaneous impact of the elevator door rail system, so the corresponding physical parameter model may focus on the characteristics of the instantaneous impact, such as the vibration mode when the elevator door rail starts or stops; for the low-frequency offset layer, it is usually related to factors such as long-term wear, aging or deformation, at this time the selected physical parameter model focuses on the long-term changes of the elevator door rail system, such as the motor load fluctuation or vibration increase caused by wear. For example Figure 2The physical parameters of the elevator door rail system are shown in the figure, including mass m, stiffness k, damping c and friction coefficient μ, which reflect the inertia, elasticity, energy consumption characteristics and contact surface friction state of the door rail system. Once the appropriate physical parameter model is selected, the abnormal data within the preset deviation range boundary is taken as the target signal, and the key parameters in the physical parameter model, such as stiffness k, friction coefficient μ, mass m and damping c, are adjusted by iterative algorithm to minimize the residual error between the simulation signal and the target signal. For example, in the high-frequency interference layer of the door rail, if there is a mutation in the vibration signal, such as a short-term impact when the door rail is opened and closed, the impact response parameters in the physical parameter model, such as the friction coefficient or the elastic modulus, are adjusted so that the change in the simulation signal matches the mutation characteristics of the target signal. Similarly, in the low-frequency offset layer, if the current signal presents a sustained fluctuation, such as wear caused by long-term operation of the door rail, the long-term change parameters in the model, such as the damping coefficient or the stiffness parameter, are adjusted so that the model can better fit the long-term trend of the target signal. When the residual error of the model adjustment reaches the preset threshold, for example 0.01, indicating that the simulation signal has been highly consistent with the target signal, the parameters of the model are considered to be optimal, and the optimal parameter value will be matched with the corresponding historical fault database to find a similar fault type to the current signal pattern, for example, if the optimal parameter matches the characteristics of the local jam fault in the historical database, the confidence of the fault pattern is extracted, such as 90%, indicating the probability of the occurrence of the fault pattern. Finally, the preliminary optimization state description will include: the optimal physical parameter model and its key parameter values, the fault pattern corresponding to the abnormal data and the confidence of the fault pattern, which are combined together to form a preliminary description of the current running state of the elevator door rail system, providing strong support for subsequent fault diagnosis and risk assessment. By combining the optimized abnormal data with the physical dynamics model of the elevator door rail, the actual fault pattern in the elevator system can be more accurately reflected, the key parameters of the physical parameter model are adjusted using iterative algorithm, and by comparing with the historical fault data, potential fault patterns such as door rail jam or wear can be identified at an early stage, and the confidence of the fault pattern is calculated to provide an assessment of the possibility of the fault occurring, which makes the elevator fault diagnosis more reliable, provides early warning of potential problems, and reduces the risk of sudden failure, improving the efficiency of the elevator system.

[0050] After generating the preliminary optimized state description, further verification of its accuracy is needed to avoid judgment bias caused by model fitting errors, environmental noise, or sensor fluctuations. Therefore, first, error analysis is performed on the preliminary optimized state description. The core of error analysis is to compare the optimal parameter values and the generated simulation signals in the preliminary description with the original time-synchronized signal sequence. The reliability of the optimized description is quantified by calculating the residual error between the two. The residual error can be calculated by the root mean square error. For example, if the simulation signal in a certain period is [1.2, 1.5, 1.8] and the actual synchronization signal is [1.1, 1.6, 1.9], the residual error is about 0.1. When the residual error exceeds the preset threshold, it indicates that the preliminary optimized description still needs to be further corrected. Based on the error analysis results, the correction period parameters are adjusted. The correction period parameters refer to the step size and update frequency of the system during iterative optimization. For example, when the residual error is large, it indicates that the signal fluctuates quickly or changes abnormally. In this case, the correction period is shortened from 10 seconds to 8 seconds to improve the response speed of the model. Conversely, the period is appropriately extended to avoid over-correction. The adjusted correction period parameters can adapt to the door rail running state, making the iterative process more suitable for actual working conditions. After parameter adjustment, the iterative correction process is started using the optimized abnormal data and new correction period parameters. The iterative process updates the key parameters in the physical parameter model multiple times, making the simulation signal gradually approach the actual signal. For example, the first iteration residual error is 0.12, the second iteration residual error is reduced to 0.06, and the third iteration residual error is reduced to 0.03. When the residual error converges below the preset threshold, such as 0.01, the iteration terminates, and the final optimized state description is output. The final optimized state description usually includes: the system physical parameters after residual error convergence, such as friction coefficient 0.45 and damping coefficient 0.12; abnormal component proportion (such as 12%); system risk level (low, medium, high). Next, the system matches the historical fault mode according to the optimized state description. For example, when the friction coefficient significantly increases and the low-frequency offset layer abnormality increases, the similarity with the "door rail local jam" mode in the historical database is 0.88, so this fault mode is judged as the most likely abnormality. Finally, a fault diagnosis report for the elevator door rail system is generated by considering factors such as similarity, abnormal component proportion, and door rail running time. The report includes fault mode category, risk level, potential cause, such as long-term wear causing damping coefficient to rise, recommended maintenance measures, such as lubrication, track adjustment or component replacement, and risk trend prediction to help maintenance personnel develop more effective maintenance plans. Through residual error analysis, correction period adaptive adjustment, and iterative correction, the final optimized state description is closer to the true physical state, significantly reducing the misdiagnosis rate. By matching the optimized physical parameters with historical fault modes, the fault cause can be accurately located, improving the confidence of fault identification. The final generated diagnosis report is clear in structure and accurate in risk assessment, providing a highly reliable decision basis for elevator maintenance and improving door rail operation safety.

[0051] In step S4, the generation of the fault diagnosis report for the elevator door rail system includes: matching the preliminary fault mode according to the optimized state description, combining the local wear degree of the door rail and the historical operation data, analyzing the influence of the door rail operation time on the abnormal component, and generating the fault diagnosis report for the elevator door rail system by combining the preliminary fault mode and the analysis result of the operation time influence; risk level assessment is performed on the fault diagnosis report, and the door rail operation risk level is determined according to the assessment result; the fault mode is classified by the risk level, and the classified fault mode is prioritized to form the final fault diagnosis report.

[0052] Specifically, the process of generating the fault diagnosis report for the elevator door rail system includes multiple steps, and the purpose is to accurately diagnose the fault state of the elevator door rail system through comprehensive analysis of the optimized state description, the local wear degree of the door rail and the historical operation data, and to provide reliable decision basis for maintenance personnel. First, according to the optimized state description, the local wear degree of the door rail and the historical operation data are combined to match the fault mode. The local wear degree can be obtained by methods such as laser scanning measurement, for example, the wear depth obtained by laser scanning is 0.5mm, combined with the historical operation data of the elevator, such as cumulative operation time of 5000 hours, these information form a comprehensive data set, as the basis for subsequent fault mode matching. Next, the state description error correction technique is used to further correct the deviation in the optimized state description. Through error correction techniques such as least squares method, the difference between the optimized state description and the historical fault data is calculated, and iterative adjustment is made until the error is minimized. Assuming that the proportion of abnormal components in the optimized state description is 15%, after correction, it may match the "local jamming fault" mode, and the risk assessment of this mode is medium, which can reduce the misjudgment caused by model deviation and provide more accurate fault mode matching. After matching the fault mode, further analyze the influence of the operation time of the elevator on the abnormal component. For example, use least squares linear regression to analyze the relationship between operation time and abnormal component. If the regression analysis shows that the abnormal component will increase by 2% for every 1000 hours of operation time, then adjust the evaluation of the fault mode according to this regression coefficient, for example, if the operation time is 6000 hours and the abnormal component reaches 15%, then according to the regression model, the abnormal component may rise to 17% within the next 1000 hours. These information will help to make long-term fault prediction and maintenance planning for the elevator door rail system.

[0053] Subsequently, the fault diagnosis report will be evaluated according to the optimized fault mode and the results of regression analysis, for example, if the abnormal component exceeds 10%, it will be rated as medium risk, the risk level of the evaluation can be: low risk (abnormal component less than 10%), medium risk (abnormal component between 10% and 30%), or high risk (abnormal component more than 30%). According to the risk level, the fault mode will be classified, for example, "stuck fault" may be classified as medium risk. The classified fault mode will be prioritized, the priority is determined by the risk level and the frequency of the fault mode, using weighted ranking method, where the priority of the fault mode is higher, for example, high risk mode will be sorted in front, for example, if the frequency of stuck fault in the elevator door rail system is high, and the fault mode has a greater impact on operation, it will be prioritized in the front. The final fault diagnosis report will adjust its content structure according to the sorting result, the high priority fault mode will be located in the front of the report, providing detailed fault description and processing suggestions, such as immediate disablement or regular inspection, the report will help maintenance personnel to take preventive measures as soon as possible to reduce the risk of failure. Finally, all the fault diagnosis reports will be stored in the cloud database for subsequent query and reference.

[0054] By combining the optimized state description, wear degree and historical operation data, the generated fault diagnosis report can provide accurate fault mode, risk assessment and processing suggestions. The application of error correction technology and regression analysis effectively improves the accuracy of fault mode matching, and the priority ranking ensures the priority processing of high risk faults. This method can early warning potential failure, help maintenance personnel to develop reasonable maintenance plan, reduce the failure rate of equipment, prolong the service life of elevator door rail system, so as to improve the safety and reliability of elevator.

[0055] In summary, the elevator running state monitoring method fusing multiple sensors is provided in the application, which realizes accurate perception and intelligent diagnosis of the elevator door rail running state. First, based on the features extracted from the multiple sensor signals, the current door rail running state description is generated through the preset state description model, and the preliminary quantitative evaluation of the system state is completed. Subsequently, the preliminary description is optimized as the final corrected door rail running state description through fusion and correction iteration convergence judgment with historical fault data, which significantly improves the stability of the state evaluation and the consistency with historical experience. If the abnormal component in the corrected description exceeds the preset threshold, a deeper analysis mechanism is triggered, that is, the abnormal data is inversely fitted with the parameterized physical dynamics model to generate a preliminary optimized state description, so as to map the fault phenomenon to specific physical parameter changes and realize preliminary positioning of the fault source. The preliminary description is further subjected to an error analysis based on the residual and an iterative correction process with adaptive correction period, and finally an optimized state description containing accurate physical parameters and high-confidence fault modes is output. Finally, the optimized state description, real-time wear data and running time prediction model are comprehensively used for multi-dimensional risk assessment and priority sorting to form a final fault diagnosis report that can directly guide maintenance decisions. This series of technical steps from raw signal acquisition to fault diagnosis report generation gradually optimize and correct the fault diagnosis of the elevator door rail system from a preliminary and rough description to an accurate and efficient system state evaluation. In order to intuitively verify the continuous improvement effect of the method in diagnosis accuracy and information integrity, as shown in FIG. 8, an iterative optimization index gain effect diagram is shown, which quantitatively shows the performance gain of the five core diagnostic indicators in the process from the "current state description" to the "final optimized description". Figure 3

[0056] The above describes the elevator running state monitoring method fusing multiple sensors in the embodiment of the application, and the elevator running state monitoring system fusing multiple sensors in the embodiment of the application is described below. Please refer to Figure 4 An embodiment of the elevator running state monitoring system fusing multiple sensors in the embodiment of the application includes:

[0057] The acquisition module is configured to acquire the vibration signal and the current signal of the elevator door rail, and generate an initial multi-source signal set.

[0058] The synchronization module is configured to perform time synchronization processing on the initial multi-source signal set to obtain a time synchronization signal sequence, extract features of various signals from the time synchronization signal sequence, and generate a signal feature segment set.

[0059] ​The analysis module is configured to analyze interaction modes between the signals according to the signal feature fragment set, determine an interaction abnormal feature group, fuse the interaction abnormal feature group and the elevator door rail historical fault data, and generate a corrected door rail operation state description.

[0060] The diagnosis module is configured to perform optimization processing on the abnormal data to obtain an optimized state description if the abnormal component in the corrected door rail operation state description exceeds a preset threshold, match an elevator fault mode according to the optimized state description, and generate a fault diagnosis report for the elevator door rail system.

[0061] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the system, the system and the unit described above can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0062] The integrated unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0063] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of monitoring the operating state of an elevator by fusing multiple sensors, characterized by, The method comprises: Step S1: acquiring a vibration signal and a current signal of an elevator door rail, and generating an initial multi-source signal set; Step S2: performing time synchronization processing on the initial multi-source signal set to obtain a time-synchronized signal sequence, extracting features of various signals from the time-synchronized signal sequence, and generating a signal feature segment set; Step S3: analyzing an interaction mode between signals according to the signal feature segment set, determining an interaction abnormal feature group, fusing the interaction abnormal feature group and historical fault data of the elevator door rail, and generating a corrected door rail running state description; Step S4: if an abnormal component in the corrected door rail running state description exceeds a preset threshold, performing optimization processing on abnormal data to obtain an optimized state description, matching an elevator fault mode according to the optimized state description, and generating a fault diagnosis report for the elevator door rail system.

2. The method of claim 1, wherein, In step S2, the time synchronization processing on the initial multi-source signal set to obtain a time-synchronized signal sequence comprises: According to the initial multi-source signal set, the time stamp alignment technology is used to process the time sequence segments of the vibration signal and the current signal; if the time stamp deviation exceeds the preset threshold, the sampling frequency is adjusted to eliminate the deviation through signal synchronization verification; the time sequence segments of the vibration signal and the current signal are subjected to data interpolation combined with signal mutation intervals, and continuous time sequence data is generated through interpolation processing; the time-synchronized signal sequence is determined according to the interpolated time sequence data; the time-synchronized signal sequence is subjected to consistency verification to ensure the alignment accuracy of the vibration signal and the current signal on the time axis.

3. The method of claim 2, wherein, In step S2, the features of various signals are extracted from the time-synchronized signal sequence to generate a signal feature segment set, which comprises: The time domain features of the vibration signal and the frequency domain features of the current signal are extracted from the time-synchronized signal sequence, the abnormal trigger points are identified and located based on the time domain features and the frequency domain features, the time-synchronized signal sequence is segmented based on the abnormal trigger points, and a plurality of signal segments are obtained; the correlation coefficient between the vibration signal and the current signal in each signal segment is calculated, and the abnormal component proportion of each signal segment is identified based on the correlation coefficient; The signal segments are classified according to the abnormal component proportion, the signal feature segment set is generated according to the classification result, the feature data in the signal feature segment set is subjected to standardization processing, the correlation between different signal segments is analyzed based on the standardized feature data; according to the correlation analysis result, the structure of the signal feature segment set is adjusted to obtain an optimized signal feature segment set.

4. The method of claim 1, wherein, In step S3, the interaction mode between signals is analyzed according to the signal feature segment set to determine the interaction abnormal feature group, which comprises: For the signal feature segment set, the interaction mode of the vibration signal and the current signal is analyzed, and the interaction mode is quantized by using a deviation distribution interval mapping technology; an interaction feature vector is constructed based on the quantization result, and the proportion of abnormal components and the deviation range are judged according to the interaction feature vector to determine an interaction abnormal feature group; the abnormal components in the interaction abnormal feature group are prioritized, the key abnormal features are screened according to the sorting result, and the interaction abnormal feature group is adjusted through the screened key abnormal features.

5. The method of claim 4, wherein, The determination of the interaction abnormal feature group comprises: The signal feature segment set is subjected to multi-dimensional interaction analysis, and an interaction feature matrix is constructed through the multi-dimensional interaction analysis result; the proportion of abnormal components is calculated according to the interaction feature matrix; the proportion of abnormal components is divided into intervals by using a deviation distribution interval mapping technology; the deviation range is determined through the interval division result; the interaction abnormal feature group is generated according to the deviation range and the proportion of abnormal components; the interaction abnormal feature group is subjected to feature clustering; the distribution law of abnormal features is analyzed through the clustering result; and the weight distribution of the interaction abnormal feature group is adjusted according to the distribution law.

6. The method of claim 4, wherein, The generation of the corrected door rail running state description in step S3 comprises: The interaction abnormal feature group is fused with the elevator door rail historical fault data, the change rate of the current abnormal component proportion relative to the historical fault data is calculated, and the weight distribution of each abnormal component is dynamically updated based on the change rate; the abnormal components in the interaction abnormal feature group are prioritized and weighted by using the updated weight distribution, and a weighted feature vector is formed; The weighted feature vector is input, a preset state description model is used to generate a current door rail running state description, a correction iterative convergence judgment is performed on the current door rail running state description, and a preliminarily corrected door rail running state description is obtained; a consistency check is performed on the preliminarily corrected door rail running state description, the parameters of the weight distribution are adjusted according to the check result, and the state description is optimized by using the adjusted parameters to generate a finally corrected door rail running state description.

7. The method of claim 1, wherein, The obtaining of the optimized state description in step S4 comprises: If the abnormal components in the corrected door rail running state description exceed a preset threshold, the abnormal data is layered into a high-frequency interference layer and a low-frequency offset layer according to the signal source and the frequency domain characteristics of the abnormal data; According to the different characteristics of the high-frequency interference layer and the low-frequency offset layer, the abnormal data within the preset deviation range boundary is optimized, a preliminary optimized state description is generated according to the optimization result, an error analysis is performed on the preliminary optimized state description, and the correction period parameters are adjusted according to the analysis result; the iterative correction process is started by using the adjusted correction period parameters and the optimized abnormal data, and the process is repeated until the residual error converges below the preset threshold, and the final optimized state description is output.

8. The method of claim 7, wherein, The generation of the preliminary optimized state description according to the optimization result comprises: Based on the frequency domain characteristics of the abnormal data, from the pre-established elevator door rail parameterized dynamic model library, a physical parameter model related to instantaneous impact is matched for the high-frequency interference layer, and a physical parameter model related to long-term wear or deformation is matched for the low-frequency offset layer. Using abnormal data within the preset deviation range boundary as the target signal, the key parameters in the physical parameter model are adjusted in reverse through an iterative algorithm to minimize the residual between the simulation signal output by the model and the target signal. When the residual converges to a preset threshold, the optimal parameter value of the physical parameter model at this time, along with the corresponding fault mode and confidence level in the historical fault database, are used together as the preliminary optimization state description.

9. The method of claim 1, wherein, Step S4 generates a fault diagnosis report for the elevator door rail system, including: Based on the optimized state description, combined with the local wear degree of the door rail and historical operating data, a preliminary fault mode is matched using state description error correction technology. The impact of door rail operating time on abnormal components is analyzed. By integrating the preliminary fault mode and operating time impact analysis results, a fault diagnosis report for the elevator door rail system is generated. The fault diagnosis report is then subjected to a risk level assessment, and the door rail operating risk level is determined based on the assessment results. The fault modes are classified according to the risk level, and the classified fault modes are prioritized to form the final fault diagnosis report.

10. A fusion multi-sensor elevator operation state monitoring system for implementing the fusion multi-sensor elevator operation state monitoring method according to any one of claims 1 to 9, characterized by The system includes: The acquisition module is used to acquire vibration and current signals of the elevator door rail and generate an initial multi-source signal set; The synchronization module is used to perform time synchronization processing on the initial multi-source signal set to obtain a time synchronization signal sequence, extract features of various signals from the time synchronization signal sequence, and generate a set of signal feature segments. The analysis module is used to analyze the interaction patterns between signals based on the set of signal feature segments, determine the interaction anomaly feature group, fuse the interaction anomaly feature group with the elevator door rail historical fault data, and generate a corrected description of the door rail operating status. The diagnostic module is used to optimize the abnormal data if the abnormal components in the corrected door rail operating status description exceed a preset threshold, obtain an optimized status description, match the elevator fault mode according to the optimized status description, and generate a fault diagnosis report for the elevator door rail system.

Images