Fault detection model training method and device, fault detection method and device and storage medium

Abstract

The invention discloses a fault detection model training method and device, a fault detection method and device and a storage medium, and the method comprises the steps: collecting original operation data and a fault state of a motor of a car door when the car door of an elevator executes door opening and closing operation; preprocessing the original operation data according to the opening and closing travel of the car door to obtain target operation data; extracting trend characteristics related to the fault state from the target operation data; performing self-checking on the trend characteristics to filter out the trend characteristics generated when the user interferes with the car door; if self-checking is completed, a fault detection model is trained for the motor of the lift car door according to the tendency characteristics and the fault state, so that the fault detection model is used for calculating the total probability of the fault state of the motor of the lift car door in the next time period. According to the embodiment, the fault prediction quality of tendency characteristics is effectively improved, the fault predictability is improved, the fault detection accuracy can be comprehensively improved, and the guiding significance of elevator maintenance is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of elevators, and in particular to a training of a fault detection model and a fault detection method, device and storage medium thereof. Background Art

[0002] The elevator car door is equipped with a motor for opening and closing operations. The car door motor is one of the parts of the elevator that is more prone to failure.

[0003] At present, sensors are configured in the motor of the car door to collect its operating data, and a Seq2Seq (sequence to sequence) neural network is used to predict the state at the next moment, thereby predicting whether the motor of the car door will fail.

[0004] However, most of the failures of the car door motor are closely related to human factors, and the data collected by the sensor itself has a lot of interference and a low degree of correlation with the failure, resulting in low accuracy in predicting whether the car door motor will fail.

[0005] Moreover, the state of the car door motor at the next moment is an instantaneous state, which has little guiding significance for elevator maintenance. Summary of the invention

[0006] In view of this, the present invention provides a fault detection model training and fault detection method, device and storage medium thereof, so as to improve the accuracy of predicting the state of the motor of the car door over a long period of time, thereby improving the guiding significance for maintenance.

[0007] A first aspect of the present invention provides a method for training a fault detection model, comprising:

[0008] When the elevator car door performs the door opening and closing operation, the original operation data and fault status of the motor of the car door are collected;

[0009] Preprocessing the original operation data according to the opening and closing stroke of the car door to obtain target operation data;

[0010] Extracting trend features related to the fault state from the target operation data;

[0011] Performing self-checking on the trend characteristics according to the fault state to filter out the trend characteristics generated when the user interferes with the car door;

[0012] If the self-check is completed, a fault detection model is trained for the motor of the car door according to the trend characteristics and the fault state, so that the fault detection model is used to calculate the total probability of the motor of the car door being in a fault state in the next time period.

[0013] A second aspect of the present invention provides a fault detection method, comprising:

[0014] Loading the fault detection model trained according to the method of the first aspect;

[0015] When the elevator car door performs the door opening and closing operation, the original operation data and fault status of the motor of the car door are collected;

[0016] Preprocessing the original operation data according to the opening and closing stroke of the car door to obtain target operation data;

[0017] extracting trend features related to the fault state from the target operation data;

[0018] Performing self-checking on the trend characteristics according to the fault state to filter out the trend characteristics generated when the user interferes with the car door;

[0019] If the self-check is completed, the trend characteristics in the current time period are input into the fault detection model to calculate the total probability of the motor of the car door being in a fault state in the next time period.

[0020] A third aspect of the present invention provides a training device for a fault detection model, comprising:

[0021] A data acquisition module, used to collect original operation data and fault status of the motor of the elevator car door when the elevator car door performs the door opening and closing operation;

[0022] A preprocessing module, used for preprocessing the original operation data according to the opening and closing stroke of the car door to obtain target operation data;

[0023] A trend feature extraction module, used to extract trend features related to the fault state from the target operation data;

[0024] A trend feature self-checking module, used for self-checking the trend feature according to the fault state, so as to filter out the trend feature generated when the user interferes with the car door;

[0025] A fault detection model training module is used to train a fault detection model for the car door motor based on the trend characteristics and the fault state if self-checking is completed, so that the fault detection model is used to calculate the total probability of the car door motor being in a fault state within the next time period.

[0026] A fourth aspect of the present invention provides a fault detection device, comprising:

[0027] A fault detection model loading module, used to load the fault detection model trained according to the method described in Example 1;

[0028] A data acquisition module, used to collect original operation data and fault status of the motor of the elevator car door when the elevator car door performs the door opening and closing operation;

[0029] A preprocessing module, used for preprocessing the original operation data according to the opening and closing stroke of the car door to obtain target operation data;

[0030] A trend feature extraction module, used to extract trend features related to the fault state from the target operation data;

[0031] A trend feature self-checking module, used for self-checking the trend feature according to the fault state, so as to filter out the trend feature generated when the user interferes with the car door;

[0032] The total probability calculation module is used to input the trend characteristics in the current time period into the fault detection model to calculate the total probability of the motor of the car door being in a fault state in the next time period if the self-check is completed.

[0033] A fifth aspect of the present invention provides an electronic device, the electronic device comprising:

[0034] at least one processor; and

[0035] a memory communicatively connected to the at least one processor; wherein,

[0036] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the training method of the fault detection model as described in the first aspect above or the fault detection method as described in the second aspect above.

[0037] The sixth aspect of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the training method of the fault detection model as described in the first aspect or the fault detection method as described in the second aspect.

[0038] The seventh aspect of the present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the training method of the fault detection model as described in the first aspect or the fault detection method as described in the second aspect.

[0039] In this embodiment, when the elevator car door performs the door opening and closing operation, the original operation data and fault status of the car door motor are collected; the original operation data is preprocessed according to the opening and closing stroke of the car door to obtain the target operation data; the trend characteristics related to the fault status are extracted from the target operation data; the trend characteristics are self-checked to filter out the trend characteristics generated when the user interferes with the car door; if the self-check is completed, the fault detection model is trained on the car door motor according to the trend characteristics and the fault status, so that the fault detection model is used to calculate the total probability of the car door motor having a fault state in the next time period. This embodiment performs preprocessing according to the characteristics of the car door and eliminates the user's interference with the car door, which can effectively improve the quality of the trend characteristics for fault prediction and improve the predictability of the fault, and improve the generalization of fault detection with the failure rate of a time period, which can comprehensively improve the accuracy of fault detection and improve the guiding significance of elevator maintenance.

[0040] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 It is a flow chart of a method for training a fault detection model provided in the first embodiment of the present invention.

[0043] Figure 2 This is an example diagram of original operation data provided in Example 1 of the present invention.

[0044] Figure 3 This is a characteristic example diagram provided by the first embodiment of the present invention when there is no user interference.

[0045] Figure 4 This is a characteristic example diagram provided by the first embodiment of the present invention when user interference exists.

[0046] Figure 5 This is a flow chart of a fault detection method provided in Embodiment 2 of the present invention.

[0047] Figure 6 It is a structural diagram of a training device for a fault detection model provided in Embodiment 3 of the present invention.

[0048] Figure 7 It is a structural schematic diagram of a fault detection device provided in Embodiment 4 of the present invention.

[0049] Figure 8 It is a structural schematic diagram of an electronic device provided in Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0050] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0051] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can cover sequential implementations other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0052] Embodiment 1

[0053] See also Figure 1 , showing a flowchart of a fault detection model training and fault detection method provided by the first embodiment of the present invention, the method can be performed by the fault detection model training and fault detection device, the fault detection model training and fault detection device can be implemented in the form of hardware and / or software, the fault detection model training and fault detection device can be configured in electronic equipment, especially a cluster server providing services for elevators, the cluster server regularly uses the original operation data and fault status accumulated by the car doors of each elevator to train and update the fault detection model, or, according to the on-site processing performance of the fault detection model, the fault detection model is instantly trained and updated, and the fault detection model is distributed to each elevator for deployment. Figure 1 As shown, the method includes:

[0054] Step 101: When the elevator car door performs an opening and closing operation, the original operation data and fault status of the motor of the car door are collected.

[0055] In different types of buildings, especially high-rise buildings, there are different transportation needs for people, pets, goods, etc. Therefore, different types of elevators can be deployed in the building according to different transportation needs, such as passenger elevators, freight elevators, sightseeing elevators, etc. The method in this embodiment can be applied to various types of elevators.

[0056] This embodiment can be applied to an elevator. An elevator is a comprehensive system. Different types of elevators have different structures.

[0057] In one example, a certain type of elevator is configured with: a controller (also known as an elevator control system), external call devices distributed on each floor, a car (including car doors), a motor for towing the car (also known as a traction machine), a control cabinet, a speed limiter, a door opener, a car frame, a car door, a counterweight guide rail, a car guide rail, a guide rail support, an accompanying cable, a counterweight device, a compensation chain (cable), a floor door, a guide device for the compensation chain (cable), a buffer, and the like.

[0058] Among them, the car door is equipped with a motor, which drives the car door to open and close.

[0059] In some types of elevators, the traction machine, control cabinet, speed limiter, traveling cable, etc. can be omitted.

[0060] These devices can be divided into different sets according to their functions to form various subsystems that support the operation of the elevator. The controller is connected to multiple systems of the elevator through serial ports or serial clock lines (SCL). The controller monitors each system and controls the operation of each subsystem, allowing the car to move in the shaft and reach each floor of the building.

[0061] In one example, the controller includes a door system, a frequency conversion system, a calling system and a traction system, wherein the door system is used to control the door of the elevator, the car is equipped with a car door, and the elevator lobby on each floor is provided with a hall door, and the elevator door includes a car door and a hall door of the elevator lobby on each floor, the type of the car door is the same as the type of the hall door, and they are switched at the same time (open or closed), the frequency conversion system is used to control the frequency converter, the calling system is used to control the logic of the internal call (calling the elevator in the car) and the external call (calling the elevator in the elevator lobby), and the traction system is used to control the movement of the car in the vertical direction (vertically upward or vertically downward) in the shaft.

[0062] The manager or owner of the elevator can choose whether to install an edge computing node on the elevator based on factors such as the load status of the elevator. If you choose not to install an edge computing node, the controller maintains the original control logic and does not affect the normal operation of the elevator. If you choose to install an edge computing node, you can select a suitable computing device as the edge computing node of the elevator according to your needs. The edge computing node is combined with the original controller into a new controller and redefines the control logic of the elevator.

[0063] Generally speaking, edge computing nodes are computing devices with strong computing capabilities, such as computers, servers or embedded devices. In addition, according to different intelligent services, edge computing nodes can be equipped with graphics processing units (GPUs) or embedded neural network processors (NPUs).

[0064] Edge computing nodes refer to a new business platform built at the edge of the network near the elevator, providing storage, computing, network and other resources, and sinking some key business applications to the edge of the access network to reduce the width and delay losses caused by network transmission and multi-level forwarding. The edge computing node is located between the user and the cloud (server), and is closer to the user (data source) than the traditional cloud. It has the characteristics of miniaturization, distribution and closer to the user. Massive data (such as audio data) no longer needs to be uploaded to the cloud for processing, and data processing is realized at the edge of the network, reducing request response time and network bandwidth while ensuring data security and privacy.

[0065] In addition, edge computing nodes can implement algorithm functions and model reasoning, communicate with existing controllers, and provide artificial intelligence (AI) and complex computing capabilities for existing controllers. Edge computing can also communicate with the cloud to implement algorithm functions and model updates, and transfer existing controller function calls and other functions.

[0066] When the elevator car door performs door opening and closing operations (including opening and closing), on the one hand, the original operating data related to the fault is collected from the car door motor at a certain frequency, such as current data, voltage data, speed data, etc.

[0067] On the other hand, the fault status of the car door motor is collected, that is, whether a fault occurs.

[0068] In actual applications, there are many faults in the motor of the car door, such as "acceleration overcurrent", "deceleration overcurrent", "constant speed overcurrent", "acceleration overvoltage", "deceleration overvoltage", "constant speed overvoltage", "undervoltage", "output phase loss", "hardware failure", "motor overload protection", "EEPROM abnormality", "encoder wire break detection protection", "encoder UVW wire break", "angle correction error", "encoder UVW error", "non-level door opening failure", "encoder large pulse abnormality", "door width self-learning error", "pulley slip detection", "door opening and closing limit signals are valid at the same time", "motor speed abnormality", "light curtain output circuit failure", etc.

[0069] Among them, some faults are sudden faults, such as "hardware failure", "encoder UVW disconnection", etc., and some faults are trend faults that can be predicted by data means, such as "acceleration overcurrent", "deceleration overcurrent", etc.

[0070] Then, the fault status collected from the car door motor mainly refers to the trend fault, and the original operation data collected from the car door motor is correlated with the trend fault.

[0071] In this embodiment, if Figure 2 As shown, the starting timestamp of each door opening and closing operation of the elevator car door can be located ( Figure 2 The first dotted line in the figure) and the end timestamp ( Figure 2 The second dotted line in the figure), the original operation data between the start timestamp and the end timestamp of the car door motor is cut out ( Figure 2 The data between the two dashed lines in the figure) and the fault status.

[0072] Step 102: pre-process the original operation data according to the opening and closing stroke of the car door to obtain target operation data.

[0073] In this embodiment, the original operating data can be preprocessed in combination with the characteristics of the car door to obtain target operating data, so that the target operating data better matches the characteristics of the car door, thereby improving the performance of fault detection of the car door motor using the fault detection model.

[0074] In practical applications, at least one of a noise reduction operation, an abnormality elimination operation and an interpolation operation is pre-processed on the original operation data according to the opening and closing stroke of the car door to obtain target operation data.

[0075] On the one hand, since the original operation data contains electrical signals, a noise reduction operation is performed on the original operation data. Then, the noise reduction operation includes:

[0076] The car door is divided into multiple door opening and closing stages, wherein the door opening and closing stages generally include a door opening acceleration section, a door opening uniform speed section, a door opening deceleration section, a door opening hold, a door closing acceleration section, a door closing uniform speed section, a door closing deceleration section, a door closing hold uniform speed section, and so on.

[0077] The operation segment data in each gate opening and closing stage are marked on the original operation data, and bandpass filtering is performed independently on each operation segment data.

[0078] On the other hand, the base and publicity of the original operation data of different elevators in history are different, so the original operation data is adaptively subjected to abnormal elimination operations. Then, the abnormal elimination operations include:

[0079] Query historical operation data; historical operation data is the operation data collected from the car door motor when the car door historically performs door opening and closing operations, which includes normal operation data and operation data when a fault occurs.

[0080] According to the changing trend of historical operation data (such as upward trend, downward trend), the abnormal interval is constructed using the 3σ criterion and other methods. That is, the abnormal interval is constructed for the historical operation data under different changing trends, so that the abnormal interval is a dynamic interval.

[0081] Identify the change trend of the original operation data, add an abnormal interval matching the change trend of the original operation data to the original operation data, and remove the operation parameters outside the abnormal interval from the original operation data.

[0082] On the other hand, after the abnormal operating parameters are removed, the operating parameters are missing at the corresponding positions in the original operating data. In order to maintain the continuity of each operating parameter in the original operating data, an interpolation operation is performed on the original operating data. Then, the interpolation operation includes:

[0083] When an operating parameter is missing at a certain position in the original operating data, a preset operating mechanism model is queried; the operating mechanism model is standard operating data presented by the motor of the elevator car door when the elevator car door performs a door opening and closing operation.

[0084] The operation similarity between the original operation data and the operation mechanism model is calculated using algorithms such as Mean Absolute Error (MAE).

[0085] A certain operation parameter is inserted at a position in the original operation data to increase the operation similarity.

[0086] Of course, the above pre-processing is only used as an example. When implementing this embodiment, other pre-processing can be set according to actual conditions, and this embodiment does not limit this. In addition, in addition to the above pre-processing, those skilled in the art can also use other pre-processing according to actual needs, and this embodiment does not limit this either.

[0087] Step 103: extract trend features related to the fault status from the target operation data.

[0088] In this embodiment, feature engineering is performed on the target operation data, and features that are related to the fault state and show a trend are extracted from the target operation data and recorded as trend features.

[0089] In a specific implementation, a window matching the fault state may be added to the target operation data.

[0090] Generally, the width of the window is fixed. When designing the window, the width of the window is positively correlated with the duration of the fault state (usually the average duration of multiple fault states), and the width of the window is greater than the duration of the fault state. That is, the longer the duration of the fault state, the larger the width of the window. Conversely, the shorter the duration of the fault state, the smaller the width of the window. In addition, the width of the window is slightly greater than the duration of the fault state.

[0091] Each time the window is slid according to the preset step size, a variety of basic features with statistical significance are calculated for various operating parameters in the window to achieve the purpose of feature dimensionality reduction.

[0092] Exemplarily, basic features include mean, variance, standard deviation, peak, peak-to-peak value, root mean square, kurtosis, skewness, spectrum peak, spectrum center frequency, spectrum bandwidth, spectrum entropy, and the like.

[0093] Various basic features of the same operating parameter (such as current data, voltage data, speed data, etc.) are spliced ​​into a feature sequence in chronological order.

[0094] Furthermore, the fault states may be spliced ​​into a fault sequence in chronological order, and the sequence similarity between the feature sequence and the fault sequence may be calculated using a method such as a Pearson correlation coefficient, and the sequence similarity may be compared with a preset similarity threshold.

[0095] If the sequence similarity is greater than or equal to the preset similarity threshold, and the sequence similarity between the feature sequence and the fault sequence is high, the feature sequence is retained.

[0096] If the sequence similarity is less than the preset similarity threshold, and the sequence similarity between the feature sequence and the fault sequence is low, the feature sequence is deleted to reduce the amount of invalid data, which can not only reduce the amount of calculation, but also improve the accuracy of fault detection.

[0097] The car door is divided into multiple door opening and closing stages, and each feature sequence of the time period covering the maintenance period is selected and divided into multiple trend segments according to the door opening and closing stages, that is, the trend segment is the feature sequence located in each door opening and closing stage.

[0098] If the maintenance period is 14 days, then the time period is 17 days.

[0099] By traversing each trend segment, the trend feature can be calculated in each trend segment.

[0100] Exemplarily, the trend characteristics include at least one of the following:

[0101] 1. Time Series Trend: The direction and magnitude of multiple changes in the basic characteristics of different stages of a single door opening and closing within the sample period.

[0102] 2. Growth / Decline Rate: The rate of change of the basic characteristics of different stages of a single door opening and closing within the sample period.

[0103] 3. Volatility: The degree of fluctuation of the basic characteristics of different stages of a single door opening and closing within the sample period, and the degree of fluctuation of the trend line.

[0104] 4. Inflection Point: The point where the trend direction of the basic characteristics of different stages of a single door opening and closing changes within the sample period.

[0105] In this embodiment, a sliding window method is used to extract basic features from the target operation data, and then trend features are extracted from the basic features. The use of this feature fusion technology for the car door motor can effectively help predict the probability of long-term door opening and closing failures.

[0106] Step 104: self-check the trend characteristics according to the fault status to filter out the trend characteristics generated when the user interferes with the car door.

[0107] In this embodiment, there are obvious differences between the trend characteristics when the elevator door fails due to user interference and the trend characteristics when the elevator door fails without user interference.

[0108] For example, Figure 3 As shown in the figure, when the car door is currently being switched, a fault is reported without user interference, and the fault code is E001 (door circuit fault). As shown by the arrow, the trend characteristics of other previous switch operations are on the rise, forming an abnormal interval; Figure 4As shown, when the car door is currently being switched, a fault is reported in the event of user interference (such as blocking the car door from closing), and the fault code is E001 (door circuit fault). As shown by the arrow, the trend characteristics of other previous switch operations remain unchanged.

[0109] Therefore, the trend characteristics can be self-checked according to the fault status, and the trend characteristics generated when the user interferes with the elevator door failure can be filtered out from all trend characteristics, making the trend characteristics more predictable.

[0110] In a specific implementation, if a fault state occurs in the current door opening and closing operation, a specified first number of other door opening and closing operations are searched before the current door opening and closing operation.

[0111] Traverse other door-opening and -closing operations, and if the trend characteristics corresponding to other door-opening and -closing operations change (such as increase, decrease, etc.), accumulate the second quantity for other door-opening and -closing operations.

[0112] When the traversal is completed, the second quantity is compared with a preset quantity threshold. The first quantity and its quantity threshold can be generated by dividing the trend characteristics when there is user interference with the car door and the trend characteristics when there is no user interference with the car door by unsupervised clustering using the trend characteristics corresponding to the historical door opening and closing operations.

[0113] If the second number is greater than or equal to the preset number threshold, it is determined that there is no user interference with the elevator door in the current door opening and closing operation, and the trend feature corresponding to the current door opening and closing operation is retained.

[0114] If the second number is less than a preset number threshold, it is determined that the current door opening and closing operation involves user interference with the elevator door, and the trend feature corresponding to the current door opening and closing operation is filtered out.

[0115] Step 105: If the self-check is completed, a fault detection model is trained for the car door motor according to the trend characteristics and the fault state, so that the fault detection model is used to calculate the total probability of the car door motor having a fault state in the next time period.

[0116] When the self-check is completed, the fault detection model of the car door motor configuration is supervisedly trained with the remaining trend features as samples and the fault status as the label Label, so that the fault detection model of the car door motor configuration has the ability to calculate the total probability of the car door motor fault state in the next time period.

[0117] Among them, the fault detection model can be a machine learning model, such as support vector machine (SVM), decision tree, random forest, etc., and the fault detection model can also be a deep learning model, such as convolutional neural network (CNN), long short-term memory network (LSTM), Transformer (a neural network architecture based on self-attention mechanism), etc.

[0118] For deep learning models, the structure of the fault detection model is not limited to artificially designed neural networks, but can also be a neural network optimized by a model quantization method, a neural network searched for the characteristics of the car door motor by the NAS (Neural Architecture Search) method, and so on. This embodiment does not impose any restrictions on this.

[0119] In one design, the car door can be divided into multiple door opening and closing stages, and each trend feature can be divided into multiple trend segments according to the door opening and closing stages. The trend segments are marked with fault status, that is, the trend segments are marked with 1 (fault exists) or 0 (no fault exists).

[0120] In each time period (such as 17 days), a data set is constructed based on the trend segments under the same opening and closing stage, and the data set is divided into training set, validation set and test set in a ratio of 6:2:2.

[0121] Without distinguishing the fault type, the sub-probability of the fault state is statistically analyzed in each data set, which can improve the generalization of the fault detection model.

[0122] Wherein, the sub-probability of the fault state = the number of times the fault state is 1 (ie, there is a fault) / the total number of effective door opening and closing times.

[0123] A random forest model is trained separately according to each data set and each sub-probability to form a fault detection model for the motor of the car door, that is, the fault detection model includes multiple random forest models, and the number of random forest models is the same as the number of opening and closing stages of the car door.

[0124] Among them, the random forest model has two parameters, namely numTrees (the number of decision trees in the forest) and maxDepth (the maximum depth of a single decision tree). In order to reduce the risk of overfitting, a grid search can be performed to select the optimal settings for the number of trees and the maximum depth.

[0125] In this embodiment, when the elevator car door performs the door opening and closing operation, the original operation data and fault status of the car door motor are collected; the original operation data is preprocessed according to the opening and closing stroke of the car door to obtain the target operation data; the trend characteristics related to the fault status are extracted from the target operation data; the trend characteristics are self-checked to filter out the trend characteristics generated when the user interferes with the car door; if the self-check is completed, the fault detection model is trained on the car door motor according to the trend characteristics and the fault status, so that the fault detection model is used to calculate the total probability of the car door motor having a fault state in the next time period. This embodiment performs preprocessing according to the characteristics of the car door and eliminates the user's interference with the car door, which can effectively improve the quality of the trend characteristics for fault prediction and improve the predictability of the fault, and improve the generalization of fault detection with the failure rate of a time period, which can comprehensively improve the accuracy of fault detection and improve the guiding significance of elevator maintenance.

[0126] Embodiment 2

[0127] See also Figure 5 , shows a flow chart of a fault detection method provided by the second embodiment of the present invention, the method can be executed by a fault detection device, the training of the fault detection model and the fault detection device can be implemented in the form of hardware and / or software, and the fault detection device can be configured in an electronic device, especially an elevator controller. Figure 5 As shown, the method includes:

[0128] Step 501: Load a fault detection model.

[0129] In this embodiment, the fault detection model trained according to the method of Embodiment 1 may be loaded locally and run.

[0130] Step 502: When the elevator car door performs an opening and closing operation, the original operation data and fault status of the motor of the car door are collected.

[0131] Step 503: pre-process the original operation data according to the opening and closing stroke of the car door to obtain target operation data.

[0132] In a specific implementation, at least one pre-processing operation among noise reduction operation, abnormality elimination operation and interpolation operation can be performed on the original operation data according to the opening and closing stroke of the car door to obtain the target operation data.

[0133] The noise reduction operation includes:

[0134] The car door is divided into a plurality of door opening and closing stages; the operation segment data under each door opening and closing stage is marked in the original operation data; and bandpass filtering is performed independently on each operation segment data.

[0135] Exception removal operations include:

[0136] Query historical operation data; historical operation data is the operation data collected from the car door motor when the car door historically performs door opening and closing operations; construct an abnormal interval based on the changing trend of the historical operation data; add an abnormal interval that matches the changing trend of the original operation data to the original operation data, and eliminate the operation parameters outside the abnormal interval in the original operation data.

[0137] Interpolation operations include:

[0138] When an operating parameter is missing at a certain position in the original operating data, a preset operating mechanism model is queried; the operating mechanism model is the standard operating data presented by the elevator car door motor when the elevator car door performs door opening and closing operations; the operating similarity between the original operating data and the operating mechanism model is calculated; and the operating parameters are inserted at the position in the original operating data to increase the operating similarity.

[0139] Step 504: extract trend features related to the fault status from the target operation data.

[0140] In the specific implementation, a window matching the fault state is added to the target operating data; the width of the window is positively correlated with the duration of the fault state, and the width of the window is greater than the duration of the fault state; each time the window is slid, multiple basic features are calculated for various operating parameters in the window; various basic features of the same operating parameter are spliced ​​into a feature sequence; the car door is divided into multiple door opening and closing stages; each feature sequence is divided into multiple trend segments according to the door opening and closing stages; and trend features are calculated in each trend segment.

[0141] Furthermore, the fault states are spliced ​​into a fault sequence in chronological order; the sequence similarity between the feature sequence and the fault sequence is calculated; if the sequence similarity is greater than or equal to a preset similarity threshold, the feature sequence is retained; if the sequence similarity is less than the preset similarity threshold, the feature sequence is deleted.

[0142] Step 505: self-check the trend characteristics to filter out the trend characteristics generated when the user interferes with the elevator door.

[0143] In a specific implementation, if a fault occurs in the current door opening and closing operation, a specified first number of other door opening and closing operations are searched before the current door opening and closing operation; if the trend characteristics corresponding to other door opening and closing operations change, a second number is accumulated for the other door opening and closing operations; if the second number is greater than or equal to a preset number threshold, it is determined that there is no user interference with the car door in the current door opening and closing operation, and the trend characteristics corresponding to the current door opening and closing operation are retained; if the second number is less than the preset number threshold, it is determined that there is user interference with the car door in the current door opening and closing operation, and the trend characteristics corresponding to the current door opening and closing operation are filtered out.

[0144] Step 506: If the self-check is completed, the trend characteristics in the current time period are input into the fault detection model to calculate the total probability of the motor of the car door being in a fault state in the next time period.

[0145] When the self-check is completed, the trend characteristics within the current time period (such as the current 17 days) can be input into the fault detection model to calculate the total probability of the car door motor failing within the next time period (such as the next 17 days).

[0146] When the total probability is greater than or equal to the preset fault threshold, the car door can be included in the maintenance list, so that the maintenance personnel will pay attention to the inspection of the car door when they inspect the elevator next time, thereby reducing the possibility of car door failure in the next time period.

[0147] In a specific implementation, the fault detection model includes multiple random forest models trained for the door opening and closing stages. Then, the car door can be divided into multiple door opening and closing stages, and the trend features in the current time period can be divided into multiple trend segments according to the door opening and closing stages.

[0148] Each trend segment is input into the corresponding random forest model to calculate the sub-probability of the car door motor failing at each door opening and closing stage in the next time period.

[0149] According to the importance of the door opening and closing stages, each sub-probability is integrated into the total probability of the motor of the car door failing in the next time period.

[0150] In general, a weight representing the importance of each door opening and closing stage can be configured. For example, the weights of the door opening uniform speed section, door opening holding section, door closing uniform speed section and door closing holding uniform speed section are relatively low, while the weights of the door opening acceleration section, door opening deceleration section, door closing acceleration section and door closing deceleration section are relatively high. For each door opening and closing stage, the product of the sub-probability and the corresponding weight is summed to obtain the total probability of the car door motor being in a faulty state.

[0151] In this embodiment, a fault detection model is loaded; when the elevator car door performs the door opening and closing operation, the original operation data of the car door motor is collected; the original operation data is preprocessed according to the opening and closing stroke of the car door to obtain the target operation data; the trend characteristics related to the fault state are extracted from the target operation data; the trend characteristics are self-checked to filter out the trend characteristics generated when the user interferes with the car door; if the self-check is completed, the trend characteristics in the current time period are input into the fault detection model to calculate the total probability of the car door motor in the next time period. This embodiment performs preprocessing based on the characteristics of the car door and eliminates the user's interference with the car door, which can effectively improve the quality of the trend characteristics for fault prediction and improve the predictability of the fault. In addition, the generalization of fault detection is improved with the failure rate of a time period, which can comprehensively improve the accuracy of fault detection and improve the guiding significance of elevator maintenance.

[0152] Embodiment 3

[0153] See also Figure 6 , shows a schematic diagram of the structure of a training device for a fault detection model provided by Embodiment 3 of the present invention. Figure 6 As shown, the device comprises:

[0154] The data acquisition module 601 is used to collect original operation data and fault status of the motor of the elevator car door when the elevator car door performs the door opening and closing operation;

[0155] A preprocessing module 602 is used to perform preprocessing on the original operation data according to the opening and closing stroke of the car door to obtain target operation data;

[0156] A trend feature extraction module 603, used to extract trend features related to the fault state from the target operation data;

[0157] A trend characteristic self-checking module 604, used for self-checking the trend characteristic according to the fault state, so as to filter out the trend characteristic generated when the user interferes with the car door;

[0158] The fault detection model training module 605 is used to train the fault detection model for the car door motor according to the trend characteristics and the fault state if the self-check is completed, so that the fault detection model can be used to calculate the total probability of the car door motor failing in the next time period.

[0159] In one embodiment of the present invention, the preprocessing module 602 includes:

[0160] a target operation data survival module, configured to perform at least one pre-processing of a noise reduction operation, an abnormality elimination operation and an interpolation operation on the original operation data according to the opening and closing stroke of the car door, so as to obtain target operation data;

[0161] The noise reduction operation includes:

[0162] Dividing the car door into a plurality of door opening and closing stages;

[0163] Marking the operation segment data in each of the door opening and closing stages in the original operation data;

[0164] independently performing bandpass filtering on each of the running segment data;

[0165] The abnormal elimination operation includes:

[0166] Query historical operation data; the historical operation data is the operation data collected from the motor of the car door when the car door historically performs the door opening and closing operation;

[0167] Constructing an abnormal interval based on the change trend of the historical operation data;

[0168] adding an abnormal interval matching the change trend of the original operating data to the original operating data, and removing operating parameters outside the abnormal interval from the original operating data;

[0169] The interpolation operation includes:

[0170] When an operation parameter is missing at a certain position in the original operation data, a preset operation mechanism model is queried; the operation mechanism model is standard operation data presented by the motor of the elevator car door when the elevator car door performs a door opening and closing operation;

[0171] Calculating the operation similarity between the original operation data and the operation mechanism model;

[0172] An operation parameter is inserted into the position in the original operation data to increase the operation similarity.

[0173] In one embodiment of the present invention, the trend feature extraction module 603 includes:

[0174] A window adding module, used for adding a window matching the fault state to the target operation data; the width of the window is positively correlated with the duration of the fault state, and the width of the window is greater than the duration of the fault state;

[0175] A basic feature extraction module, used for calculating a plurality of basic features for various operating parameters in the window each time the window is slid;

[0176] A feature sequence splicing module, used for splicing various basic features of the same operating parameter into a feature sequence;

[0177] A door opening and closing stage division module, used for dividing the car door into a plurality of door opening and closing stages;

[0178] A trend segment segmentation module, used for segmenting each of the characteristic sequences into a plurality of trend segments according to the gate opening and closing stages;

[0179] The trend feature calculation module is used to calculate the trend feature in each of the trend segments.

[0180] In one embodiment of the present invention, the trend feature extraction module 603 further includes:

[0181] A fault sequence splicing module, used for splicing the fault states into a fault sequence in chronological order;

[0182] A sequence similarity calculation module, used to calculate the sequence similarity between the feature sequence and the fault sequence;

[0183] A feature sequence retaining module, used for retaining the feature sequence if the sequence similarity is greater than or equal to a preset similarity threshold;

[0184] The feature sequence deletion module is used to delete the feature sequence if the sequence similarity is less than a preset similarity threshold.

[0185] In one embodiment of the present invention, the trend feature self-checking module 604 includes:

[0186] A door opening and closing operation search module, configured to search for a specified first number of other door opening and closing operations before the current door opening and closing operation if the fault state occurs in the current door opening and closing operation;

[0187] A quantity accumulation module, configured to accumulate a second quantity for other door opening and closing operations if the trend characteristics corresponding to the other door opening and closing operations change;

[0188] A trend feature retaining module, configured to determine that there is no user interfering with the car door in the current door opening and closing operation if the second number is greater than or equal to a preset number threshold, and retain the trend feature corresponding to the current door opening and closing operation;

[0189] The trend feature filtering module is used to determine that there is user interference with the car door in the current door opening and closing operation if the second number is less than a preset number threshold, and filter out the trend feature corresponding to the current door opening and closing operation.

[0190] In one embodiment of the present invention, the fault detection model training module 605 includes:

[0191] A door opening and closing stage division module, used for dividing the car door into a plurality of door opening and closing stages;

[0192] A trend segment segmentation module, used for segmenting each of the trend features into a plurality of trend segments according to the door opening and closing stages;

[0193] A fault status marking module, used for marking the fault status of the trend segment;

[0194] A data set construction module, used to construct a data set from the trend segments in the same door opening and closing stage in each time period;

[0195] A sub-probability statistics module, used to count the sub-probability of the fault state in each of the data sets;

[0196] The random forest model training module is used to train the random forest model separately according to each of the data sets and each of the sub-probabilities to form a fault detection model for the motor of the car door, so that the fault detection model is used to calculate the total probability of the motor of the car door being in a faulty state within the next time period.

[0197] The training device for the fault detection model provided in the embodiment of the present invention can execute the training method for the fault detection model provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the training method for the fault detection model.

[0198] Embodiment 4

[0199] See also Figure 7 , shows a schematic diagram of the structure of a fault detection device provided by Embodiment 4 of the present invention. Figure 7 As shown, the device comprises:

[0200] A fault detection model loading module 701 is used to load the fault detection model trained according to the method described in Embodiment 1;

[0201] The data acquisition module 702 is used to collect original operation data and fault status of the motor of the elevator car door when the elevator car door performs the door opening and closing operation;

[0202] A preprocessing module 703 is used to perform preprocessing on the original operation data according to the opening and closing stroke of the car door to obtain target operation data;

[0203] A trend feature extraction module 704, used to extract trend features related to the fault state from the target operation data;

[0204] A trend characteristic self-checking module 705, for self-checking the trend characteristic according to the fault state, so as to filter out the trend characteristic generated when the user interferes with the car door;

[0205] The total probability calculation module 706 is used to input the trend characteristics in the current time period into the fault detection model to calculate the total probability of the motor of the car door being in a fault state in the next time period if the self-check is completed.

[0206] In one embodiment of the present invention, the fault detection model includes multiple random forest models, and the total probability calculation module 706 includes:

[0207] A door opening and closing stage division module, used for dividing the car door into a plurality of door opening and closing stages;

[0208] A trend segment segmentation module, used to segment the trend characteristics in the current time period into multiple trend segments according to the door opening and closing stages;

[0209] A trend segment calculation module, used for inputting each of the trend segments into each of the random forest models to calculate the sub-probability of the motor of the car door being in a fault state at each of the door opening and closing stages in the next time period;

[0210] The total probability fusion module is used to fuse the sub-probabilities into a total probability of the motor of the car door being in a faulty state within the next time period according to the importance of the door opening and closing stages.

[0211] In one embodiment of the present invention, the preprocessing module 703 includes:

[0212] a target operation data survival module, configured to perform at least one pre-processing of a noise reduction operation, an abnormality elimination operation and an interpolation operation on the original operation data according to the opening and closing stroke of the car door, so as to obtain target operation data;

[0213] The noise reduction operation includes:

[0214] Dividing the car door into a plurality of door opening and closing stages;

[0215] Marking the operation segment data in each of the door opening and closing stages in the original operation data;

[0216] independently performing bandpass filtering on each of the running segment data;

[0217] The abnormal elimination operation includes:

[0218] Query historical operation data; the historical operation data is the operation data collected from the motor of the car door when the car door historically performs the door opening and closing operation;

[0219] Constructing an abnormal interval based on the change trend of the historical operation data;

[0220] adding an abnormal interval matching the change trend of the original operating data to the original operating data, and removing operating parameters outside the abnormal interval from the original operating data;

[0221] The interpolation operation includes:

[0222] When an operation parameter is missing at a certain position in the original operation data, a preset operation mechanism model is queried; the operation mechanism model is standard operation data presented by the motor of the elevator car door when the elevator car door performs a door opening and closing operation;

[0223] Calculating the operation similarity between the original operation data and the operation mechanism model;

[0224] An operation parameter is inserted into the position in the original operation data to increase the operation similarity.

[0225] In one embodiment of the present invention, the trend feature extraction module 704 includes:

[0226] A window adding module, used for adding a window matching the fault state to the target operation data; the width of the window is positively correlated with the duration of the fault state, and the width of the window is greater than the duration of the fault state;

[0227] A basic feature extraction module, used for calculating a plurality of basic features for various operating parameters in the window each time the window is slid;

[0228] A feature sequence splicing module, used for splicing various basic features of the same operating parameter into a feature sequence;

[0229] A door opening and closing stage division module, used for dividing the car door into a plurality of door opening and closing stages;

[0230] A trend segment segmentation module, used for segmenting each of the characteristic sequences into a plurality of trend segments according to the gate opening and closing stages;

[0231] The trend feature calculation module is used to calculate the trend feature in each of the trend segments.

[0232] In one embodiment of the present invention, the trend feature extraction module 704 further includes:

[0233] A fault sequence splicing module, used for splicing the fault states into a fault sequence in chronological order;

[0234] A sequence similarity calculation module, used to calculate the sequence similarity between the feature sequence and the fault sequence;

[0235] A feature sequence retaining module, used for retaining the feature sequence if the sequence similarity is greater than or equal to a preset similarity threshold;

[0236] The feature sequence deletion module is used to delete the feature sequence if the sequence similarity is less than a preset similarity threshold.

[0237] In one embodiment of the present invention, the trend feature self-checking module 705 includes:

[0238] A door opening and closing operation search module, configured to search for a specified first number of other door opening and closing operations before the current door opening and closing operation if the fault state occurs in the current door opening and closing operation;

[0239] A quantity accumulation module, configured to accumulate a second quantity for other door opening and closing operations if the trend characteristics corresponding to the other door opening and closing operations change;

[0240] A trend feature retaining module, configured to determine that there is no user interfering with the car door in the current door opening and closing operation if the second number is greater than or equal to a preset number threshold, and retain the trend feature corresponding to the current door opening and closing operation;

[0241] The trend feature filtering module is used to determine that there is user interference with the car door in the current door opening and closing operation if the second number is less than a preset number threshold, and filter out the trend feature corresponding to the current door opening and closing operation.

[0242] The fault detection device provided in the embodiment of the present invention can execute the fault detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the fault detection method.

[0243] Embodiment 5

[0244] See also Figure 8 , shows a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0245] like Figure 8As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0246] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0247] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 performs the various methods and processes described above, such as the training of the fault detection model and its fault detection method.

[0248] In some embodiments, the training of the fault detection model and the fault detection method thereof may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the training of the fault detection model and the fault detection method thereof described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the training of the fault detection model and the fault detection method thereof by any other appropriate means (e.g., by means of firmware).

[0249] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0250] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0251] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0252] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0253] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0254] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0255] Embodiment 6

[0256] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the training of the fault detection model and the fault detection method thereof as provided in any embodiment of the present invention are implemented.

[0257] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0258] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0259] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for training a fault detection model, characterized in that: include: When the elevator car door performs the door opening and closing operation, the original operation data and fault status of the motor of the car door are collected; Preprocessing the original operation data according to the opening and closing stroke of the car door to obtain target operation data; Extracting trend features related to the fault state from the target operation data; Performing self-checking on the trend characteristics according to the fault state to filter out the trend characteristics generated when the user interferes with the car door; If the self-check is completed, a fault detection model is trained for the motor of the car door according to the trend characteristics and the fault state, so that the fault detection model is used to calculate the total probability of the motor of the car door being in a fault state in the next time period.

2. The method according to claim 1, characterized in that The preprocessing of the original operation data according to the opening and closing stroke of the car door to obtain target operation data includes: Performing at least one pre-processing of a noise reduction operation, an abnormality elimination operation, and an interpolation operation on the original operation data according to the opening and closing stroke of the car door to obtain target operation data; The noise reduction operation includes: Dividing the car door into a plurality of door opening and closing stages; Marking the operation segment data in each of the door opening and closing stages in the original operation data; independently performing bandpass filtering on each of the running segment data; The abnormal elimination operation includes: Query historical operation data; the historical operation data is the operation data collected from the motor of the car door when the car door historically performs the door opening and closing operation; Constructing an abnormal interval based on the change trend of the historical operation data; adding an abnormal interval matching the change trend of the original operating data to the original operating data, and removing operating parameters outside the abnormal interval from the original operating data; The interpolation operation includes: When an operation parameter is missing at a certain position in the original operation data, a preset operation mechanism model is queried; the operation mechanism model is standard operation data presented by the motor of the elevator car door when the elevator car door performs a door opening and closing operation; Calculating the operation similarity between the original operation data and the operation mechanism model; An operation parameter is inserted into the position in the original operation data to increase the operation similarity.

3. The method according to claim 1, characterized in that The extracting of trend features related to the fault state from the target operation data includes: Adding a window matching the fault state to the target operation data; the width of the window is positively correlated with the duration of the fault state, and the width of the window is greater than the duration of the fault state; When sliding the window each time, calculating a plurality of basic features for various operating parameters within the window; splicing various basic features of the same operating parameter into a feature sequence; Dividing the car door into a plurality of door opening and closing stages; Dividing each of the characteristic sequences into a plurality of trend segments according to the gate opening and closing stages; A trend feature is calculated in each of the trend segments.

4. The method according to claim 3, characterized in that The extracting of trend features related to the fault state from the target operation data further includes: splicing the fault states into a fault sequence in chronological order; Calculating the sequence similarity between the feature sequence and the fault sequence; If the sequence similarity is greater than or equal to a preset similarity threshold, retaining the feature sequence; If the sequence similarity is less than a preset similarity threshold, the feature sequence is deleted.

5. The method according to claim 1, characterized in that The self-checking of the trend feature according to the fault state to filter out the trend feature generated when the user interferes with the car door includes: If the fault state occurs in the current door opening and closing operation, searching for a specified first number of other door opening and closing operations before the current door opening and closing operation; If the trend characteristics corresponding to the other door opening and closing operations change, then a second number is accumulated for the other door opening and closing operations; If the second number is greater than or equal to a preset number threshold, it is determined that there is no user interference with the car door in the current door opening and closing operation, and the trend feature corresponding to the current door opening and closing operation is retained; If the second number is less than a preset number threshold, it is determined that the current door opening and closing operation involves user interference with the car door, and the trend feature corresponding to the current door opening and closing operation is filtered out.

6. The method according to any one of claims 1 to 5, characterized in that The step of training a fault detection model for the motor of the car door according to the trend feature and the fault state so that the fault detection model is used to calculate the total probability of the motor of the car door being in a fault state in the next time period includes: Dividing the car door into a plurality of door opening and closing stages; Dividing each of the trend features into a plurality of trend segments according to the door opening and closing stages; marking the fault status on the trend segment; In each time period, the trend segments in the same gate opening and closing stage are used to construct a data set; Counting the sub-probabilities of the fault states in each of the data sets; A random forest model is trained separately according to each of the data sets and each of the sub-probabilities to form a fault detection model for the motor of the car door, so that the fault detection model is used to calculate the total probability of the motor of the car door being in a faulty state within the next time period.

7. A fault detection method, characterized in that: include: Loading a fault detection model trained according to the method described in any one of claims 1 to 6; When the elevator car door performs the door opening and closing operation, the original operation data and fault status of the motor of the car door are collected; Preprocessing the original operation data according to the opening and closing stroke of the car door to obtain target operation data; extracting trend features related to the fault state from the target operation data; Performing self-checking on the trend characteristics according to the fault state to filter out the trend characteristics generated when the user interferes with the car door; If the self-check is completed, the trend characteristics in the current time period are input into the fault detection model to calculate the total probability of the motor of the car door being in a fault state in the next time period.

8. The method according to claim 7, characterized in that The fault detection model includes a plurality of random forest models, and the trend characteristics in the current time period are input into the fault detection model to calculate the total probability of the motor of the car door being in a fault state in the next time period, including: Dividing the car door into a plurality of door opening and closing stages; Divide the trend characteristics in the current time period into multiple trend segments according to the gate opening and closing stages; Input each of the trend segments into each of the random forest models to calculate the sub-probability of the motor of the car door being in a fault state at each of the door opening and closing stages in the next time period; The sub-probabilities are integrated into a total probability of a fault state of the car door motor in the next time period according to the importance of the door opening and closing stages.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the training method of the fault detection model as described in any one of claims 1-6 or the fault detection method as described in any one of claims 7-8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the training method of the fault detection model according to any one of claims 1 to 6 or the fault detection method according to any one of claims 7 to 8 is implemented.

Images