Elevator brake fault lossless online diagnosis and fatigue prediction method and system

Abstract

The embodiment of the invention relates to the technical field of special equipment maintenance, in particular to an elevator brake fault lossless online diagnosis and fatigue prediction method and system. The method comprises the following steps: acquiring action data and braking times when a single ladder brake acts on line, wherein the action data comprises sound data, vibration data, current data, braking distance and load; when it is judged that the sudden stop state occurs, action data of the sudden stop stage are extracted and obtained immediately and recorded as sudden stop action data; according to comparison between the sudden stop action data and a pre-established fault diagnosis model, a fault diagnosis result is obtained; and when the fault diagnosis result is no fault, comparing the action data with a preset brake fatigue baseline to obtain a fatigue prediction result of the single ladder brake. According to the method, fault diagnosis and fatigue prediction can be carried out, 125% load test is avoided, the safety is higher, the elevator and the brake are not damaged, and online detection is achieved.

Description

Technical Field

[0001] Multiple embodiments of this specification relate to the technical field of special equipment maintenance, and specifically to a method and system for non-destructive online diagnosis and fatigue prediction of elevator brake faults. Background Art

[0002] The brake is a very critical safety component on the elevator. It is responsible for performing various safety functions during the operation of the elevator, such as daily parking brake, protective brake when overspeeding, and emergency brake when the car moves unexpectedly. The common type of brake in the elevator is the friction normally closed brake. The normally closed brake here means that the brake is in the braking state by default when there is no power supply; and when the mechanical system works, it releases the brake. The braking process is achieved by the electromagnetic core controlling the contact or separation between the brake shoe and the brake disc. In order to ensure the working performance of the brake, the so-called "125% load test" is usually carried out. This test requires that the brake is operated to stop the traction machine under the condition that the car is loaded with 125% of the rated load, and check whether the car can be effectively stopped.

[0003] However, for elevators in use, especially old elevators, the implementation of the "125% load test" may cause potential damage to the traction system, wire ropes, and suspension devices. Therefore, the study of non-destructive testing of elevator brakes has become one of the important research topics at present. On the other hand, there is currently a lack of monitoring means between two regular maintenance of elevators, resulting in the inability to grasp the operating status of the elevator in a timely manner. Therefore, it is necessary to study online elevator brake monitoring technology to improve the safety of elevator brakes. Summary of the invention

[0004] Multiple embodiments of this specification describe a method and system for non-destructive online diagnosis and fatigue prediction of elevator brake faults.

[0005] In a first aspect, the embodiments of this specification provide a method for non-destructive online diagnosis and fatigue prediction of elevator brake faults, comprising the steps of: Online collection of action data and braking times of a single-elevator brake, wherein the action data includes sound data, vibration data, current data, braking distance and load; When it is determined that an emergency stop state occurs, the action data of the emergency stop stage is immediately extracted and recorded as the emergency stop action data; Obtain fault diagnosis results by comparing the emergency stop action data with the pre-established fault diagnosis model; When the fault diagnosis result is no fault, the action data is compared with a preset brake fatigue baseline to obtain a fatigue prediction result of the single-ladder brake.

[0006] In a second aspect, the embodiments of this specification provide a system for non-destructive online diagnosis and fatigue prediction of elevator brake faults, including: An online acquisition module collects online the action data and braking times of the single-elevator brake, wherein the action data includes sound data, vibration data, current data, braking distance and load; The judgment module, when judging that an emergency stop state occurs, immediately extracts and obtains the action data of the emergency stop stage, and records it as the emergency stop action data; The fault diagnosis module obtains the fault diagnosis result by comparing the emergency stop action data with the pre-established fault diagnosis model; The fatigue prediction module compares the action data with a preset brake fatigue baseline to obtain a fatigue prediction result of the single-ladder brake when the fault diagnosis result is no fault.

[0007] In a third aspect, an embodiment of this specification provides an electronic device, including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method described in any one of the above aspects.

[0008] In a fourth aspect, an embodiment of the present specification provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in any of the above aspects.

[0009] In a fifth aspect, an embodiment of this specification provides a computer program product, including a computer program, which implements the method described in any of the above aspects when executed by a processor.

[0010] The beneficial effects brought by the technical solutions provided by some embodiments of this specification include at least: In multiple embodiments of the present specification, the provided elevator brake fault non-destructive online diagnosis and fatigue prediction method can perform fault diagnosis and fatigue prediction based on the collected motion data, avoid 125% load test, have higher safety, no damage to the elevator and brake, and realize online detection, which has higher safety. With the help of the established fault diagnosis model, the fault diagnosis result of the brake can be obtained, which helps to get rid of the situation where the judgment of the fault depends on the experience level of the maintenance personnel, and the fault diagnosis has higher accuracy. Through the analysis of the motion data, the up and down can be divided, and the starting stage, braking stage and emergency stop stage can be divided, so that the extracted feature expression is more targeted and the accuracy of fault diagnosis can be improved. With the help of single elevator data and the establishment of a universal fatigue prediction model, the fatigue life of the brake of a single elevator with the same structural type, the same year of use, the number of emergency stops, and the maintenance status can be universally predicted, providing an important reference for the maintenance of the single elevator.

[0011] Other features and advantages of the various embodiments of the present specification will be further disclosed in the following detailed description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of this specification, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0013] Figure 1 This is a schematic diagram of the application of the non-destructive online diagnosis and fatigue prediction method of elevator brake faults provided in this manual.

[0014] Figure 2 This is a schematic diagram of the interactive interface provided for this manual.

[0015] Figure 3 This is a flow chart of the elevator brake fault non-destructive online diagnosis and fatigue prediction method provided in this manual.

[0016] Figure 4 It is a curve diagram of the action data in the downward emergency stop stage.

[0017] Figure 5 It is a curve diagram of the action data in the upward emergency stop stage.

[0018] Figure 6 It is a curve diagram of the action data of the upward emergency stop stage using STO technology.

[0019] Figure 7This is a flow chart of the method for establishing a fault diagnosis model provided in this manual.

[0020] Figure 8 Schematic diagram of the process of establishing a brake fatigue baseline provided in this manual.

[0021] Fig. 9 A schematic flow chart of another method for establishing a brake fatigue baseline provided in this specification.

[0022] Fig.10 Baseline diagram of brake fatigue provided for this specification.

[0023] Fig.11 This is a flow chart of the method for establishing a universal fatigue prediction model provided in this manual.

[0024] Fig.12 This is a flow chart of another fatigue prediction method provided in this specification.

[0025] Fig.13 Schematic diagram of the elevator brake fault non-destructive online diagnosis and fatigue prediction system provided in this manual.

[0026] Fig.14 Schematic diagram of the electronic device provided for this instruction manual. DETAILED DESCRIPTION

[0027] The following is an explanation and description of the technical solutions of the embodiments of this specification in conjunction with the drawings of the embodiments of this specification, but the following embodiments are only preferred embodiments of this specification, not all. Based on the embodiments in the implementation mode, other embodiments obtained by those skilled in the art without creative work are all within the scope of protection of this specification.

[0028] The terms "first", "second", "third", etc. in the description and claims of this specification and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. 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 limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0029] In the following description, terms such as "inside", "outside", "up", "down", "left", "right", etc. that indicate directions or positional relationships are only used to facilitate the description of the embodiments and simplify the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as a limitation of this specification.

[0030] The data involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection of relevant data complies with the relevant laws, regulations and standards of relevant countries and regions.

[0031] Before describing the technical solution in this specification, an introduction is given to the application scenarios and related technologies of the technical solution.

[0032] Special equipment refers to boilers, pressure vessels, elevators, lifting machinery, special motor vehicles, etc. that involve life safety and are more dangerous. These equipment have specific working conditions and technical requirements, and require special management and maintenance. Elevators are special equipment used to quickly transport people between floors of a building. Traction elevators use electric motors to drive the traction ropes, so that the car 12 runs on the guide rails to move between floors. Elevators are in a state of reciprocating motion for a long time. In order to ensure their normal operation and safety, regular manual maintenance is required.

[0033] Elevator maintenance is usually performed by professional technicians. Maintenance personnel enter the elevator shaft, machine room, and car roof to inspect the various parts of the elevator. This includes cleaning the pulleys, guide shoes, and the interior of the car 12; checking and adjusting the door system; testing the electrical control system; calibrating the speed limiter and safety clamp device; and testing functions such as emergency lighting and alarm phones. In addition, the mechanical parts of the elevator need to be lubricated.

[0034] The brake 11 is a key component in the elevator safety system, responsible for quickly braking the car 12 in the event of a power outage or abnormal situation to prevent a fall accident. For the maintenance of the elevator brake 11, it is first necessary to ensure that the brake 11 can respond to the command and act immediately, that is, when the control system sends a stop signal, the brake 11 can stop the elevator quickly and effectively. During the maintenance process, it is necessary to check whether the spring force of the brake 11 is sufficient, and at the same time, it is necessary to check whether the gap between the brake pad and the brake disc is appropriate. A gap that is too small will cause unnecessary wear, while a gap that is too large will result in poor braking effect. The surface of the brake 11 should be kept clean and free of oil. Maintenance personnel will also judge whether there is any abnormality in the brake 11 based on the action and sound of the brake 11.

[0035] There are some disadvantages to manual maintenance. Due to the tight time schedule for maintenance work, there may be a risk of undetected problems. Some faults or hidden dangers may only appear under certain conditions, and it is difficult for conventional maintenance inspections to capture these problems. On the other hand, manual maintenance relies on the experience and technical level of maintenance personnel, and there may be differences between different personnel, which will also affect the consistency of maintenance quality. Furthermore, with the acceleration of urbanization, there are more and more high-rise buildings, and the number of elevators has increased dramatically, which has brought huge challenges to maintenance work. Faced with the huge amount of maintenance tasks, how to ensure that each elevator can be maintained in a timely and effective manner has become an urgent problem to be solved.

[0036] In order to improve the maintenance efficiency and quality of the elevator brake 11, this embodiment provides a method and system for fault diagnosis and fatigue prediction of the elevator brake 11.

[0037] Please refer to the attached Figure 1 When this embodiment is applied, a current sensor 21, a vibration sensor 22 and a sound sensor 23 are installed on the brake 11, and a vibration sensor 22 and a sound sensor 23 are installed on the top of the car 12. After obtaining the motion data, the motion data is uploaded to the server 40 through the handheld terminal 30, and the server 40 gives the fault diagnosis and fatigue prediction results. In the case where the handheld terminal 30 performs edge computing, part or all of the fault diagnosis and fatigue prediction can also be performed on the handheld terminal 30.

[0038] The method provided in this application is applied to Figure 1 The system architecture shown in FIG. 1 includes a server 40 and a handheld terminal 30. An interactive interface 31 is provided on the handheld terminal 30. Figure 2The interactive interface 31 can be run on the handheld terminal 30 in the form of a browser, or in the form of an independent application (APP), etc. The specific display form of the interactive interface 31 is not limited here. The server 40 involved in this application can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms. The handheld terminal 30 can be a smart phone, a tablet computer, a laptop, a PDA, a personal computer, a smart speaker, a smart TV, a smart watch, a car device, a wearable device, etc., but is not limited to this. The handheld terminal 30 and the server 40 can be directly or indirectly connected by wired or wireless communication, which is not limited in this application. The number of servers 40 and handheld terminals 30 is also not limited. The solution provided in the present application may be completed independently by the handheld terminal 30, may be completed independently by the server 40, or may be completed in cooperation between the handheld terminal 30 and the server 40, and the present application does not make any specific limitation on this.

[0039] Since this application involves some professional terms, these professional terms will be introduced below.

[0040] Machine Learning Models Machine learning models refer to methods that use algorithms and statistical models to enable computer systems to learn from data to improve their performance or make predictions without being explicitly programmed. Machine learning is a subfield of artificial intelligence that allows computers to learn from experience and improve their capabilities without being explicitly programmed. Machine learning models can be divided into the following categories: supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning.

[0041] Clustering Algorithms Clustering algorithm is an unsupervised learning method that aims to divide the objects in the data set into several clusters (clusters) so that the objects within the cluster are similar to each other, while the objects between different clusters are quite different. Clustering algorithms are widely used in many fields such as data analysis, pattern recognition, market segmentation, social network analysis, etc. By measuring the similarity or distance between data points, the data set is divided into several groups, and the data points in each group share certain characteristics. The goal of clustering is to make the data points within the cluster as similar as possible, while the differences between clusters are as large as possible. Clustering algorithms include partitioning clustering such as K-means. K-means is one of the most commonly used clustering algorithms. It divides the data into a preset number of clusters through an iterative process. The center point (centroid) of each cluster represents the average attribute of the cluster. K-medoids is similar to K-means, but the centroid must be the actual data point in the cluster. Hierarchical clustering, such as agglomerative hierarchical clustering, merges the nearest clusters from the bottom up to form a tree structure. Divisive hierarchical clustering divides the data set into smaller and smaller clusters from the top down. Density-based clustering, such as DBSCAN, discovers clusters of arbitrary shapes by measuring the density of the neighborhood around a point and can identify noise points. OPTICS extends the idea of ​​DBSCAN and provides a hierarchical density clustering method. Grid-based clustering, such as STING, divides the space into cells and performs statistical analysis at the cell level. CLIQUE combines the advantages of grid division and hierarchical clustering and can efficiently process large-scale data sets. Model-based clustering, such as the EM algorithm, uses a mixed model (such as a Gaussian mixture model) for clustering and estimates the probability distribution by iteratively optimizing parameters.

[0042] Autoencoder Model The autoencoder model is an autoencoder. Autoencoder is an unsupervised learning algorithm that is mainly used for data dimensionality reduction, feature extraction and data reconstruction. It implements this process through two main parts: encoder and decoder. The autoencoder includes encoder, latent space and decoder. Among them, the encoder compresses the input data into a low-dimensional latent space representation. This process is usually implemented through several layers of neural networks, aiming to extract key features or information from the input data. Latent space is a low-dimensional representation of the encoder output, also known as code or bottleneck. The representation in this space is a compressed form of the input data and contains the key information needed to reconstruct the original data. The decoder decodes the low-dimensional latent space representation back to the dimension of the original data. The decoder also consists of several layers of neural networks, and its goal is to reconstruct the original input data as accurately as possible. The autoencoder is trained and used in two stages. In the training stage, the input data x is mapped to the latent space z through the encoder, expressed as z=f(x). Then, the latent space representation z is used to reconstruct the original data x' through the decoder, expressed as x'=g(z)=g(f(x)). The training goal is to minimize the reconstruction error, that is, the difference between x and x'. The commonly used loss function is the mean square error (MSE). The use stage is after the training is completed. The encoder can be used to map new data to a low-dimensional latent space for feature extraction or dimensionality reduction; the decoder can generate data from the latent space representation and be applied to tasks such as generating models.

[0043] This manual first provides a non-destructive online diagnosis and fatigue prediction method for elevator brake faults. Figure 3 , including the steps of: Step S101) collects online the action data and braking times of the single-elevator brake when it is in action, wherein the action data includes sound data, vibration data, current data, braking distance and load.

[0044] To collect sound data, you can use an omnidirectional MEMS audio sensor or a bone conduction sound sensor. The omnidirectional MEMS audio sensor is a miniaturized microphone that can capture sounds from all directions. It has high sensitivity and can effectively pick up low-volume sounds. However, it is easily disturbed by environmental noise, and the airflow caused by the movement of the elevator can also generate noise. The bone conduction sound sensor mainly senses the vibration generated by the part where the sound is generated by contacting the part where the sound is generated, and converts it into an electrical signal for processing. The bone conduction sound sensor can reduce environmental noise interference. However, there may be some distortion, especially in the high-frequency part, so it is possible to miss the fault and generate high-frequency sound. The current data is the current data of the brake electromagnetic coil. To collect current data, you can use a current sensor 21 connected in series with the electromagnetic coil, or use a Hall current sensor 21 to obtain the current detection result without invading the electromagnetic coil circuit.

[0045] The vibration sensor 22 is a six-axis vibration sensor 22. The six-axis vibration sensor 22 can not only detect vibration, but also directly reflect six-axis acceleration. The total vibration synthesized by the six-axis vibration sensor 22 constitutes vibration data, which can be used as six-axis acceleration data when calculated separately according to the six axes.

[0046] This embodiment deploys the relevant sensors and equipment for collecting motion data at relevant positions of elevators and brakes for a long time, which can realize uninterrupted online collection of motion data. And by setting up a concentrator, the collected motion data is centralized, and a communication connection is established with a server or cloud server to report the motion data regularly. The devices on the concentrator or connected to the concentrator can also deploy edge computing devices to realize online real-time diagnosis of faults and fatigue prediction of single elevator brakes. The online collection of motion data and the use of edge computing technology to realize real-time non-destructive fault diagnosis and fatigue prediction are relatively more significant new technical effects of this embodiment. At the same time, this embodiment can diagnose faults and predict fatigue through motion data, without any harmful consequences to elevators and brakes, and has relatively higher safety.

[0047] There are many ways to obtain the braking distance, including: (1) Detecting the vibration of the car 12 through the vibration sensor 22. When there is no vibration or the vibration is very small, it indicates that the elevator is stationary. When the vibration is relatively regular and the amplitude change rate is less than a certain threshold, it indicates that the elevator is basically in a uniform motion state. When the vibration amplitude change rate exceeds a certain threshold, it indicates that the elevator is in the starting stage or braking stage. The starting stage or braking stage can be distinguished according to the vibration situation before the vibration amplitude changes. When it is in the braking stage, when the amplitude detected by the vibration sensor 22 is small, it indicates that the braking is completed. At this time, the braking distance can be obtained according to the position of the elevator car 12 at the start and end times of the braking stage. The position of the elevator car 12 is obtained from the elevator controller. (2) Detecting that the electromagnetic coil of the brake 11 is energized through the current sensor 21 indicates that the braking has started. At this time, the brake 11 will also vibrate due to friction. When the vibration amplitude detected by the vibration sensor 22 on the brake 11 is lower than a certain value, it indicates that the car 12 has been braked and the braking is over. The braking distance can be obtained according to the position of the elevator car 12 at the start and end times of the braking stage. (3) The speed of the car 12 is obtained according to the acceleration accumulation method detected on the vertical axis of the six-axis vibration sensor 22, and the start and end times of the braking phase are determined according to the speed of the car 12. The braking distance is obtained from the position of the car 12 at the start and end times of the braking phase, or the braking distance is obtained according to the integral of the car 12 speed.

[0048] The action data is associated with the marking of the braking action generated by the brake, and the marking includes one or more of the stage marking and the direction marking. The stage marking includes starting, braking and emergency stop, and the direction marking includes up and down. The number of starts is equal to the sum of the number of braking and the number of emergency stops. That is, normal braking of the elevator belongs to the braking stage, and emergency stop belongs to the emergency stop stage.

[0049] It is worth noting that the braking distance when going up is different from the braking distance when going down. The braking distance under different load conditions is also different. The role of annotation is to group the action data. The prediction of failure and fatigue for each group has higher accuracy. When the fatigue prediction results of going up and down are different, the average of the two can be used to obtain the fatigue representation of going up and down separately. For example, as shown in the attached figure, Figure 4 As shown in the figure, it is the jerk, acceleration and speed curves in the downward emergency stop stage. Figure 5As shown, it is the jerk, acceleration and speed curves in the upward emergency stop stage. In addition, some elevators have STO technology. STO (Safe Torque Off) technology is a safety function used in motor drive systems, which is designed to ensure that the torque output of the motor can be quickly and reliably cut off in an emergency or when needed. STO directly controls the safety relay or other form of switching device inside the motor drive through hardware circuits to quickly disconnect the motor power supply. When the STO function is activated, it prevents current from flowing into the motor windings, thereby immediately braking the torque generated by the motor. It includes not only the active torque output, but also any residual torque that may be caused by inertia or other factors. As shown in the attached Figure 6 As shown in the figure, the jerk, acceleration and speed curves of the upward emergency stop phase using the STO technology. Figure 4-6 In the figure, from top to bottom are the jerk curve, acceleration curve and velocity curve. Figure 5 and attached Figure 6 It can be seen that the emergency stop using the STO technology is more stable. However, whether the STO technology is used or not, the brake 11 fault diagnosis and fatigue prediction method disclosed in this embodiment can be applied.

[0050] Step S102) When it is determined that an emergency stop state occurs, the action data of the emergency stop stage is immediately extracted and recorded as the emergency stop action data. The acceleration, current data, and braking distance obtained through the vibration data can all accurately identify the emergency stop stage. When the acceleration is greater than the threshold, the current exceeds the threshold, or the braking distance is less than a certain value, it can be determined that an emergency stop occurs.

[0051] Emergency stop includes both downward emergency stop and upward emergency stop. The upward emergency stop is the top-rushing phenomenon.

[0052] Step S103) Obtain a fault diagnosis result based on the comparison between the emergency stop action data and a pre-established fault diagnosis model.

[0053] Please see the attached Figure 7 ,The method of establishing the fault diagnosis model includes: Step S201) receiving the action data associated with the fault, and grouping the action data according to the annotations.

[0054] Step S202 ) respectively extracts the time-frequency domain features of the sound data, vibration data and current data contained in each group of the action data.

[0055] Step S203) respectively compares the time-frequency domain features of the motion data of each group with the time-frequency domain features of the motion data in a single ladder normal state to obtain distinguishing motion data.

[0056] The method of comparing the time-frequency domain features of the action data with the time-frequency domain features of the action data in a normal state of a single ladder to obtain distinguished action data includes: Calculate the similarity of the time-frequency domain features according to the frequency composition and its amplitude, and calculate the similarity of the action data of the associated fault and the action data of the single elevator in a normal state; When the similarity is lower than a preset threshold, distinguishing action data is obtained according to the action data corresponding to the time-frequency domain features.

[0057] The frequency components and their amplitudes can be expressed in the form of vectors, and calculating the similarity is to calculate the similarity between vectors. The similarity between vectors can be calculated by the inverse of the distance between vectors.

[0058] Step S204) Establishing and using the time-frequency domain features of the distinguishing action data to train an autoencoder model, and obtaining feature expressions of the sound data, vibration data and current data of the distinguishing action data.

[0059] Step S205) After associating the characteristic expression, braking distance and load of each group with the fault, the fault sample data of the group is obtained.

[0060] Step S206) Establish and use the fault sample data of each group to train a machine learning model, and obtain a fault diagnosis model for each group based on the machine learning model.

[0061] On the other hand, according to the comparison between the emergency stop action data and the pre-established fault diagnosis model, the method for obtaining the fault diagnosis result includes: Inputting the time-frequency domain features of the sound data, vibration data and current data contained in the emergency stop action data into the autoencoder model to obtain feature expressions of the sound data, vibration data and current data; The characteristic expressions of the sound data, vibration data and current data are associated with corresponding braking distances and loads, and then input into the fault diagnosis model to obtain a fault diagnosis result.

[0062] Faults are highly correlated with stages, which are divided into the starting stage, braking stage, and emergency stop stage. The action data does not distinguish between stages and does not affect the diagnosis of faults. For example, some faults only have abnormal action data in the starting stage, such as brake 11 jamming, that is, the brake shoe is not fully opened, and the elevator runs with the brake. At this time, abnormal action data will appear in the starting stage, but there will be no abnormal action data in the braking stage or the emergency stop stage. When the stages of the action data are not distinguished, when the fault of brake 11 jamming is identified, it will naturally be inferred that the action data corresponding to the starting stage is matched with the fault diagnosis model. Another exemplary example is that insufficient braking force may be caused by excessive brake shoe clearance, excessive wear, oil stains, etc., which will cause abnormal action data in the braking stage and the emergency stop stage, while the action data in the starting stage is normal. Therefore, the feature expression associated with the fault may be one or more of the starting stage, braking stage, and emergency stop stage.

[0063] When a large amount of action data is obtained during a fault, the action data of the same fault is also different. By extracting the time-frequency domain features of the action data, clustering them, and filtering out the time-frequency domain features with high discreteness. The time-frequency domain features of the clustered action data correspond to a fault type. Take the time-frequency domain features of the cluster center, associate them with a fault type, and you can get a sample data.

[0064] After obtaining the fault sample data, the corresponding fault diagnosis model can be obtained by training the machine learning model with the fault sample data. It is worth noting that the fault sample data of different fault types contain different quantities. Therefore, it is necessary to fill in the quantities not included in the fault sample data, that is, fill them with default values. For example, the brake jam fault only corresponds to the action data of the startup phase, and the action data of the remaining phases are filled with default values.

[0065] When obtaining the fault diagnosis result of the brake 11, it is necessary to extract the feature expression from the collected action data using the self-encoding model generated by the method described above, and input the corresponding feature expression into the fault diagnosis model. It should be noted that in the process, one or more action data in the startup phase, braking phase and emergency stop phase need to be overwritten with default values ​​and input into the fault diagnosis model multiple times. Exemplarily, the action data in the braking phase and the emergency stop phase are first overwritten with default values ​​to check whether the brake 11 has the fault of brake 11 being stuck. Similarly, the action data in the startup phase can also be overwritten with default values ​​to determine whether the brake 11 has the fault of insufficient braking force.

[0066] There are two ways of comparison. One is to take the uplink sound frequency composition and amplitude, the downlink sound frequency composition and amplitude, the uplink vibration frequency composition and amplitude, the downlink vibration frequency composition and amplitude, the uplink current data value, the downlink current data value, the uplink braking distance value, and the downlink braking distance value as a whole vector, and find the point where the brake fatigue baseline 50 is closest to the vector distance of the vector. The number of braking times corresponding to the point is the fatigue prediction result. If the maximum healthy braking times of the single-ladder brake 11 are known, the fatigue life of the current single-ladder brake 11 can be obtained.

[0067] Another way is to find the number of braking times corresponding to the upstream sound frequency composition and amplitude, the downstream sound frequency composition and amplitude, the upstream vibration frequency composition and amplitude, the downstream vibration frequency composition and amplitude, the upstream current data value, the downstream current data value, the upstream braking distance value, and the downstream braking distance value, and calculate the average or weighted average of these braking times as the fatigue prediction result.

[0068] On the other hand, in another embodiment, the uplink sound frequency composition and amplitude, the downlink sound frequency composition and amplitude, the uplink vibration frequency composition and amplitude, the downlink vibration frequency composition and amplitude, the uplink current data value, the downlink current data value, the uplink braking distance value, and the downlink braking distance value are taken as a whole vector, and the vector is multiplied by a weight coefficient vector. After adding the weight, the point at which the brake fatigue baseline 50 is closest to the vector distance of the vector is found. The weight coefficient vector is generated by machine learning, and the machine learning model gives the best weight coefficient vector. Such as BP neural network model, decision tree algorithm, random forest algorithm, support vector machine, deep learning algorithm. Exemplarily, the BP neural network model is used. Construct a BP neural network model, use the feature expression of the action data under different faults as the input feature, and the fault result as the output result. By training the model, the influence weight of each input feature on the output target can be obtained.

[0069] Step S104) When the fault diagnosis result is no fault, the action data is compared with a preset brake fatigue baseline to obtain a fatigue prediction result of the single-ladder brake.

[0070] Please see the attached Figure 8 , methods for presetting brake fatigue baselines include: Step S301) collects the action data and braking times of the brakes of multiple single elevators in normal operation.

[0071] Step S302) intercepts the action data of the starting phase and the braking phase.

[0072] Step S303) Extract the time-frequency domain features of the sound data, vibration data and current data contained in the action data of the starting phase and the braking phase. The time-frequency domain features are extracted by Fourier transform, wavelet transform and other technologies disclosed in the art. The time-frequency domain features include frequency composition and its amplitude. The time-frequency domain features refer to the features that take into account both the time domain and frequency domain characteristics, which are technologies already available in the art. The characteristic expressions of the sound data, vibration data and current data are also frequency composition and amplitude.

[0073] Step S304) A brake fatigue baseline is established based on the time-frequency domain characteristics of the sound data, vibration data and current data, braking distance, load and number of braking times.

[0074] The method of comparing the action data with the preset brake fatigue baseline to obtain the fatigue prediction result of the single ladder brake includes: Extracting the time-frequency domain features of the sound data, vibration data and current data of the motion data, and reading the braking distance and load of the motion data; The fatigue prediction result of the single-ladder brake is obtained based on the comparison of the time-frequency domain characteristics of the sound data, vibration data and current data, the braking distance and load with the brake fatigue baseline.

[0075] In step S304), according to the time-frequency characteristics of the sound data, vibration data and current data, braking distance, load and braking times, please refer to the attached Fig. 9 , methods for establishing a brake fatigue baseline include: Step S401) Dividing the load into a plurality of load intervals according to a preset interval, and grouping the time-frequency domain characteristics and braking distance of the sound data, vibration data and current data according to the load intervals; Step S402) using the number of braking times as a label, associating the time-frequency domain features and braking distance of each group of the sound data, vibration data and current data, and obtaining calibration data; Step S403) establishing a brake fatigue baseline for each group according to the calibration data.

[0076] The brake fatigue baseline is obtained directly from the action data and braking times of a single elevator under normal conditions.

[0077] The action data and braking times of a single elevator under normal conditions can be obtained under laboratory conditions or by collating historical data obtained during daily maintenance. When the load is divided into several load intervals, for example, 0%-30% of the maximum load is used as the low load interval, 30%-60% as the medium load interval, and more than 60% as the high load interval. Or other division methods can be used.

[0078] Referring to the method described above, the starting phase, braking phase and emergency stop phase are distinguished. That is, the vertical acceleration is used for distinction, or the electromagnetic coil current of the brake 11 is combined with the vibration data for distinction. The feature expression includes the feature expression of sound data, vibration data, current data and braking distance, and can also distinguish between up and down. Therefore, the feature expression of the starting phase finally obtained includes low-load feature expression, medium-load feature expression and high-load feature expression. The low-load feature expression, medium-load feature expression and high-load feature expression all include the upward sound feature expression, the downward sound feature expression, the upward vibration feature expression, the downward vibration feature expression, the upward current feature expression, the downward current feature expression, the upward braking distance feature expression and the downward braking distance feature expression. The upward current feature expression and the downward current feature expression are the current values ​​of the upward and downward directions respectively. The upward braking distance feature expression and the downward braking distance feature expression are the braking distances of the upward and downward directions respectively. The feature expression is also a time-frequency domain feature, that is, it includes frequency composition and its amplitude.

[0079] When the sound data, vibration data, and current data are distinguished between up and down, the fault diagnosis and fatigue prediction of the elevator will have more accurate results, but the amount of data processing will increase, which will reduce the efficiency to a certain extent. If the up and down are not distinguished, it is best to use only the up or down motion data for fault diagnosis and fatigue prediction. When the up and down motion data are used without distinction, the accuracy of the fault diagnosis and fatigue prediction results obtained is relatively lower.

[0080] On the other hand, in another embodiment, when an emergency stop occurs, the preset emergency stop equivalent braking number is added to the predicted braking number of the single-elevator brake, and the fatigue prediction result of the single-elevator brake is obtained based on the predicted braking number of the single-elevator brake.

[0081] Among them, the method of presetting the emergency stop equivalent braking times includes: Under laboratory conditions, measure the brake shoe wear caused by N braking times and N emergency stops at a preset load; The equivalent number of emergency stop braking times is obtained based on the ratio of the brake shoe wear caused by N braking times to the brake shoe wear caused by N emergency stops.

[0082] On the other hand, in other embodiments, according to the characteristic expressions of the braking stage and the emergency stop stage, the equivalent number of braking times of the emergency stop is obtained, and the specific method includes: sorting the characteristic expressions of the braking stage and the emergency stop stage according to the time axis; calculating and obtaining the change rate of the characteristic expressions of the braking stages adjacent to each other before and after the emergency stop stage; calculating and obtaining multiple change rates corresponding to multiple emergency stop stages to obtain an average change rate; selecting multiple braking stages to obtain the change rate of the characteristic expressions of the braking stages adjacent to each other before and after the multiple braking stages as a whole; making the number of braking stages whose change rate is closest to the average change rate as the equivalent number of braking times of the emergency stop. The equivalent number of braking times of an emergency stop can also be obtained by calculation.

[0083] Specifically, the following characteristic expressions of the action data are extracted: upward sound frequency composition and amplitude, downward sound frequency composition and amplitude, upward vibration frequency composition and amplitude, downward vibration frequency composition and amplitude, upward current data value, downward current data value, upward braking distance value, downward braking distance value, and compared with the brake fatigue baseline 50.

[0084] Among them, according to the action data of the single-elevator brake and the brake fatigue baseline, the method for obtaining the fatigue prediction result of the single-elevator brake includes: Extracting time-frequency domain features of sound data, vibration data and current data included in the motion data; According to the load of the motion data, a brake fatigue baseline corresponding to the load range is obtained; Compare the time-frequency domain characteristics of the sound data, vibration data, current data and braking distance included in the action data with the brake fatigue baseline to obtain the corresponding braking times; The average of all matching braking times is taken as the fatigue prediction result of the single ladder brake.

[0085] Specifically, according to the reference of the characteristic expression of the startup phase of all labels and loads, and the reference of the braking distance, the brake fatigue baseline 50 of the startup phase is obtained. The average value of the characteristic expression refers to the average value of the frequency composition. For example, one characteristic expression includes frequencies F1, F2 and F3, and the amplitudes are A11, A12 and A13 respectively, and another characteristic expression includes frequencies F1, F3, F4, and the amplitudes are A21, A23, A24 respectively. Then the average values ​​of these two characteristic expressions include frequencies F1, F2, F3, F4, and the amplitudes are (A11+A21) / 2, A12 / 2, (A13+A23) / 2, A24 / 2 respectively. When the number of characteristic expressions involved in calculating the average value is large enough, if the frequency F4 only exists in one characteristic expression, the amplitude of the frequency F4 in the average value of the characteristic expression finally calculated can be almost ignored. Therefore, through the average value of the characteristic expression, those typical frequency components and their amplitudes with reference value can be effectively obtained.

[0086] The characteristic expression includes the characteristic expression of sound data, vibration data, current data and braking distance, and can also distinguish between up and down. Therefore, the brake fatigue baseline 50 finally obtained in the starting stage includes a low load baseline 51, a medium load baseline 52, and a high load baseline 53. The horizontal axes of the low load baseline 51, the medium load baseline 52, and the high load baseline 53 are all the number of braking times, that is, the fatigue degree is expressed by the number of braking times, and the vertical axis is the amplitude. A point on the low load baseline 51, the medium load baseline 52, and the high load baseline 53 represents the corresponding upward sound reference frequency composition and amplitude 511, the downward sound reference frequency composition and amplitude 512, the upward vibration reference frequency composition and amplitude 513, the downward vibration reference frequency composition and amplitude, the upward current data reference value, the downward current data reference value, the upward braking distance reference value, and the downward braking distance reference value under the braking times, as shown in the attached figure. Fig.10 Similarly, the low load baseline 51, the medium load baseline 52, and the high load baseline 53 can be obtained in the braking stage and the emergency stop stage, which together constitute a complete brake fatigue baseline 50.

[0087] On the other hand, in another embodiment, the elevator brake fault non-destructive online diagnosis and fatigue prediction method further includes the steps of: The action data of the two single-ladder brakes are sorted according to the time axis, the action data of the two single-ladder brakes with an interval of M are obtained, and the time-frequency domain features are extracted.

[0088] According to the action data of the two single-elevator brakes and the brake fatigue baseline, the predicted braking times of the two single-elevator brakes are respectively obtained.

[0089] Exemplarily, according to the characteristic expression, the vibration and wear generated by an emergency stop are equivalent to the vibration and wear generated by several normal brakings. It can be obtained by empirical formula, manual setting or simulation, which is a technology disclosed in the art. Specifically, when the empirical formula is used, the equivalent number of braking times of an emergency stop can be calculated based on the amount of brake shoe wear caused by 1000 normal brakings and the amount of brake shoe wear caused by 1000 emergency stops. That is, the equivalent number of braking times of an emergency stop is obtained according to the same amount of brake shoe wear, which can be obtained by laboratory or factory experiments. When manual setting is used, the equivalent number of braking times of an emergency stop can be set to 2 times. When simulation is used, the amount of brake shoe wear is set as the observation amount, and the equivalent number of braking times that is the same as the amount of brake shoe wear caused by an emergency stop is obtained through simulation. On the other hand, according to different load ratios, an equivalent number of braking times can be set for an emergency stop under each load.

[0090] On the other hand, in another embodiment, the difference between the predicted braking times of two single-ladder brakes is calculated as the predicted difference, and the ratio of the predicted difference to M is calculated as the proportionality coefficient. The equivalent braking times are obtained according to the proportionality coefficient.

[0091] In this embodiment, the predicted braking times of the single-elevator brake are directly used as the fatigue prediction result. When the total braking times of the single-elevator brake are known, the fatigue status of the current single-elevator brake can be determined. The total braking times can be obtained from factory data.

[0092] On the other hand, please see the attached Fig.11 , the method further comprises the steps of: Step S501) receiving single elevator data, the single elevator data including the year of use, number of brakes, number of emergency stops, and maintenance status; Step S502) Incorporating the service year, emergency stop times, and maintenance status of the single elevator data into the corresponding action data; Step S503) Associating the braking times of the single-elevator data with the corresponding action data as a label to obtain sample data; Step S504) A universal fatigue prediction model for brakes of the same type is established based on the sample data of brakes of the same type.

[0093] Use the number of braking times as a label. The number of braking times includes normal braking, and emergency stops will be converted into the number of braking times. When a sufficient number of single-elevator data with a sufficient length of time is obtained, the maximum number of braking times of a sufficient number of monomers can be obtained. Find and calculate the average value of all maximum braking times of the general type of brake 11 as the maximum service life of this type of brake 11, that is, the fatigue life. When used for a newly installed single elevator, the fatigue life of the newly installed single elevator can be obtained for reference based on the structure of the brake 11.

[0094] On the other hand, please see the attached Fig.12 , the method further comprises the steps of: Step S601) obtaining the action data of the normally operating single-ladder brake according to a preset period and extracting the time-frequency domain features; Step S602) obtaining a predicted number of braking times of a single-ladder brake according to the action data and the brake fatigue baseline; Step S603) According to the predicted braking times of the single-elevator brake, a fatigue prediction result of the single-elevator brake is obtained.

[0095] On a regular basis, when the elevator has not experienced an emergency stop, the fatigue of the elevator brake is predicted based on the braking data during normal operation, and the fatigue prediction results are uploaded to the server, which provides guidance for the health status and maintenance of the elevator.

[0096] On the other hand, even after obtaining the fault diagnosis results and fatigue prediction results of the single-ladder brake 11, it is still necessary to judge whether the single-ladder brake 11 needs to be repaired or replaced. At present, it still relies on the experience and judgment of maintenance personnel. This specification provides a machine learning model based on machine learning, which associates the action data with labels of whether to deal with it and the specific treatment method, and then establishes and trains a machine learning model, such as a BP neural network model, a decision tree algorithm, a random forest algorithm, a support vector machine, and a deep learning algorithm. After the training is completed, the fault diagnosis results and fatigue prediction results are input into the machine learning model to obtain whether it needs to be dealt with and how to deal with it for reference.

[0097] On the other hand, this manual provides a non-destructive online diagnosis and fatigue prediction system for elevator brake faults. Fig.13 ,include: An online acquisition module 100 collects online the action data and braking times of the single-elevator brake when it is in action, wherein the action data includes sound data, vibration data, current data, braking distance and load; The judgment module 200, when judging that an emergency stop state occurs, immediately extracts and obtains the action data of the emergency stop stage, and records it as the emergency stop action data; The fault diagnosis module 300 obtains the fault diagnosis result by comparing the emergency stop action data with the pre-established fault diagnosis model; The fatigue prediction module 400 compares the action data with a preset brake fatigue baseline to obtain a fatigue prediction result of the single-ladder brake when the fault diagnosis result is no fault.

[0098] See also Fig.14 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification is shown.

[0099] like Fig.14 As shown, the electronic device 1100 may include: at least one processor 1101, at least one network interface 1104, a user interface 1103, a memory 1105 and at least one communication bus 1102. Among them, the communication bus 1102 can be used to realize the connection and communication of the above-mentioned components. Among them, the user interface 1103 may include a button, and the optional user interface may also include a standard wired interface and a wireless interface. Among them, the network interface 1104 may include but is not limited to a Bluetooth module, an NFC module, a Wi-Fi module, etc. Among them, the processor 1101 may include one or more processing cores. The processor 1101 uses various interfaces and lines to connect the various parts of the entire electronic device 1100, and executes various functions of the routing device and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 1105, and calling data stored in the memory 1105. Optionally, the processor 1101 can be implemented in at least one hardware form of DSP, FPGA, and PLA. The processor 1101 can integrate one or a combination of CPU, GPU, modem, etc. Among them, the CPU mainly handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content that needs to be displayed on the display; and the modem is used to handle wireless communications.

[0100] It is understandable that the above-mentioned modem may not be integrated into the processor 1101, but may be implemented by a separate chip.

[0101] Among them, the memory 1105 may include RAM or ROM. Optionally, the memory 1105 includes a non-transitory computer-readable medium. The memory 1105 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1105 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1105 may also be at least one storage device located away from the aforementioned processor 1101. The memory 1105 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application. The processor 1101 may be used to call the application stored in the memory 1105 and execute the methods in the above-mentioned multiple embodiments.

[0102] The embodiments of this specification also provide a computer-readable storage medium, which stores instructions, and when the instructions are executed on a computer or a processor, the computer or the processor executes the multiple steps in the above embodiments. If the components of the above electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in the computer-readable storage medium.

[0103] The embodiments of this specification also provide a computer program product, including a computer program, which implements multiple steps in the above embodiments when executed by a processor.

[0104] In the absence of conflict, the technical features in this embodiment and implementation scheme can be combined arbitrarily.

[0105] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes a plurality of computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of this specification is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes multiple available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state drive (SSD)).

[0106] When implemented by hardware or firmware, the aforementioned method flow is programmed into the hardware circuit to obtain the corresponding hardware circuit structure and realize the corresponding function. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit, and its logic function is determined by the user programming the device. The designer programs by himself to "integrate" a digital system on a PLD, without asking a chip manufacturer to design and make a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when writing program development, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL), and HDL is not just one, but many. Those skilled in the art should also be aware that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit to easily obtain the hardware circuit that implements the logic method flow.

[0107] The embodiments described above are merely preferred embodiments of this specification and are not intended to limit the scope of this specification. Without departing from the design spirit of this specification, various modifications and improvements made to the technical solutions of this specification by ordinary technicians in this field should fall within the scope of protection determined by the claims of this specification.

Claims

1. A non-destructive online diagnosis and fatigue prediction method for elevator brake faults, characterized in that: Includes steps: Online collection of action data and braking times of a single-elevator brake, wherein the action data includes sound data, vibration data, current data, braking distance and load; When it is determined that an emergency stop state occurs, the action data of the emergency stop stage is immediately extracted and recorded as the emergency stop action data; Obtain fault diagnosis results by comparing the emergency stop action data with the pre-established fault diagnosis model; When the fault diagnosis result is no fault, the action data is compared with a preset brake fatigue baseline to obtain a fatigue prediction result of the single-ladder brake.

2. The elevator brake fault non-destructive online diagnosis and fatigue prediction method according to claim 1 is characterized in that: The action data is associated with a label of a braking action generated by the brake, wherein the label includes one or more of a stage label and a direction label, wherein the stage label includes starting, braking and emergency stop, and the direction label includes up and down; The method further comprises the steps of: Receive single elevator data, the single elevator data including year of use, number of brakes, number of emergency stops, and maintenance status; Incorporate the service year, emergency stop times, and maintenance status of the single elevator data into the corresponding action data; Associating the braking times of the single-elevator data with the corresponding action data as a label to obtain sample data; Based on the sample data of the same type of brakes, a universal fatigue prediction model for the corresponding type of brakes is established.

3. The elevator brake fault non-destructive online diagnosis and fatigue prediction method according to claim 2 is characterized in that: Methods for establishing fault diagnosis models include: receiving the action data associated with the fault, and grouping the action data according to the annotations; Respectively extracting time-frequency domain features of sound data, vibration data and current data included in the action data of each group; Respectively comparing the time-frequency domain features of the motion data of each group with the time-frequency domain features of the motion data in a normal state of a single ladder to obtain distinguishing motion data; Establish and use the time-frequency domain features of the distinguishing action data to train an autoencoder model to obtain feature expressions of the sound data, vibration data, and current data of the distinguishing action data; After associating the characteristic expression, braking distance and load of each group with the fault, the fault sample data of the group is obtained; A machine learning model is established and used to train the fault sample data of each group, and a fault diagnosis model of each group is obtained according to the machine learning model.

4. The elevator brake fault non-destructive online diagnosis and fatigue prediction method according to claim 3 is characterized in that: The method of comparing the time-frequency domain features of the motion data with the time-frequency domain features of the motion data in a normal state of a single ladder to obtain distinguished motion data includes: Calculate the similarity of the time-frequency domain features according to the frequency composition and its amplitude, and calculate the similarity of the action data of the associated fault and the action data of the single elevator in a normal state; When the similarity is lower than a preset threshold, distinguishing action data is obtained according to the action data corresponding to the time-frequency domain features.

5. The elevator brake fault non-destructive online diagnosis and fatigue prediction method according to claim 4 is characterized in that: According to the comparison between the emergency stop action data and the pre-established fault diagnosis model, the method for obtaining the fault diagnosis result includes: Inputting the time-frequency domain features of the sound data, vibration data and current data contained in the emergency stop action data into the autoencoder model to obtain feature expressions of the sound data, vibration data and current data; The characteristic expressions of the sound data, vibration data and current data are associated with corresponding braking distances and loads, and then input into the fault diagnosis model to obtain a fault diagnosis result.

6. The elevator brake fault non-destructive online diagnosis and fatigue prediction method according to any one of claims 2 to 5, characterized in that: Methods for presetting a brake fatigue baseline include: Collect the action data and braking times of the brakes of multiple single elevators in normal operation; intercepting the action data of the starting phase and the braking phase; The time-frequency domain features of the sound data, vibration data and current data included in the action data of the starting phase and the braking phase; A brake fatigue baseline is established based on the time-frequency domain characteristics of the sound data, vibration data and current data, braking distance, load and number of braking times.

7. The elevator brake fault non-destructive online diagnosis and fatigue prediction method according to claim 6 is characterized in that: The method of comparing the action data with the preset brake fatigue baseline to obtain the fatigue prediction result of the single ladder brake includes: Extracting the time-frequency domain features of the sound data, vibration data and current data of the motion data, and reading the braking distance and load of the motion data; The fatigue prediction result of the single-ladder brake is obtained based on the comparison of the time-frequency domain characteristics of the sound data, vibration data and current data, the braking distance and load with the brake fatigue baseline.

8. The elevator brake fault non-destructive online diagnosis and fatigue prediction method according to claim 7 is characterized in that: The method for establishing a brake fatigue baseline according to the time-frequency domain characteristics of the sound data, vibration data and current data, braking distance, load and number of braking times includes: Dividing the load into a plurality of load intervals according to a preset interval, and grouping the time-frequency domain characteristics and braking distances of the sound data, vibration data, and current data according to the load intervals; The number of braking times is used as a label, and the time-frequency domain features and braking distance of the sound data, vibration data and current data of each group are associated to obtain calibration data; A brake fatigue baseline for each group is established based on the calibration data.

9. The elevator brake fault non-destructive online diagnosis and fatigue prediction method according to claim 8 is characterized in that: According to the comparison of the time-frequency domain characteristics of the sound data, vibration data and current data, the braking distance and load with the brake fatigue baseline, the method for obtaining the fatigue prediction result of the single-ladder brake includes: Extracting time-frequency domain features of sound data, vibration data and current data included in the motion data; According to the load of the motion data, a brake fatigue baseline corresponding to the load range is obtained; Compare the time-frequency domain characteristics of the sound data, vibration data, current data and braking distance included in the action data with the brake fatigue baseline to obtain the corresponding braking times; The average of all matching braking times is taken as the fatigue prediction result of the single ladder brake.

10. The elevator brake fault non-destructive online diagnosis and fatigue prediction method according to any one of claims 2 to 5, characterized in that: The method further comprises the steps of: Obtain the action data of the normally operating single-ladder brake according to a preset period and extract the time-frequency domain features; Obtaining a predicted number of braking times of a single-ladder brake according to the action data and the brake fatigue baseline; According to the predicted braking times of the single-elevator brake, the fatigue prediction result of the single-elevator brake is obtained.

11. The elevator brake fault non-destructive online diagnosis and fatigue prediction method according to any one of claims 2 to 5, characterized in that: The method further comprises the steps of: Sort the action data of the single-ladder brake according to the time axis, obtain the action data of two single-ladder brakes with an interval of M and extract the time-frequency domain features; According to the action data of the two single-staircase brakes and the brake fatigue baseline, respectively obtain the predicted braking times of the two single-staircase brakes; Calculate the difference between the predicted braking times of the two single ladder brakes as the predicted difference, and calculate the ratio of the predicted difference to M as the proportionality coefficient; The equivalent number of braking times is obtained according to the proportional coefficient.

12. The elevator brake fault non-destructive online diagnosis and fatigue prediction method according to claim 10, characterized in that: When an emergency stop occurs, the preset emergency stop equivalent braking times are added to the predicted braking times of the single-elevator brake, and the fatigue prediction result of the single-elevator brake is obtained according to the predicted braking times of the single-elevator brake; Methods for presetting the emergency stop equivalent braking times include: Under laboratory conditions, measure the brake shoe wear caused by N braking times and N emergency stops at a preset load; The equivalent number of emergency stop braking times is obtained based on the ratio of the brake shoe wear caused by N braking times to the brake shoe wear caused by N emergency stops.

13. Elevator brake fault non-destructive online diagnosis and fatigue prediction system, characterized by: include: An online acquisition module collects online the action data and braking times of the single-elevator brake, wherein the action data includes sound data, vibration data, current data, braking distance and load; The judgment module, when judging that an emergency stop state occurs, immediately extracts and obtains the action data of the emergency stop stage, and records it as the emergency stop action data; The fault diagnosis module obtains the fault diagnosis result by comparing the emergency stop action data with the pre-established fault diagnosis model; The fatigue prediction module compares the action data with a preset brake fatigue baseline to obtain a fatigue prediction result of the single-ladder brake when the fault diagnosis result is no fault.

14. An electronic device, characterized in that: including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method according to any one of claims 1 to 12.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 12 is implemented.

16. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 12 is implemented.

Images