Brake fault monitoring method and device based on artificial intelligence, medium and product

Abstract

The invention discloses a brake fault monitoring method and device based on artificial intelligence, a medium and a product, and relates to the technical field of elevators, the method is applied to a cloud server, and the method comprises the following steps: obtaining to-be-inspected data sent by an elevator brake through a gateway, the to-be-detected data is processed on the basis of a preset brake fault monitoring model, a monitoring result is obtained, the brake fault monitoring model comprises an anomaly detection model and / or a fault classification model, the to-be-detected data corresponding to the elevator brake can be rapidly detected through the brake fault monitoring model, and the detection accuracy is improved. According to the method, whether the brake has a fault or not is recognized in time, and / or the fault type of the brake is accurately recognized, so that the real-time performance, accuracy and predictability of fault monitoring of the elevator brake are improved, and then the safety of an elevator is improved.

Description

Technical Field

[0001] This application relates to the technical field of elevators, and particularly to an artificial intelligence-based brake fault monitoring method, device, medium and product. Background Art

[0002] The elevator brake is a core component to ensure the safe operation of the elevator, and its functional failure may lead to serious accidents such as car slipping and elevator falling. At present, the fault monitoring of elevator brakes mainly relies on regular manual inspections or offline detections of traditional mechanical sensors (such as travel switches and displacement sensors), which have some technical defects. For example, key pressure parameters cannot be monitored in real time, the single data dimension leads to the risk of misjudgment, manual inspections rely on experience and are inefficient, etc.

[0003] Therefore, it is urgent to improve the real-time, accuracy and predictability of elevator brake fault monitoring. Summary of the Invention

[0004] The main purpose of this application is to provide an artificial intelligence-based brake fault monitoring method, device, medium and product, aiming to improve the real-time, accuracy and predictability of elevator brake fault monitoring.

[0005] To achieve the above object, this application provides an artificial intelligence-based brake fault monitoring method, which is applied to a cloud server and includes:

[0006] Obtain the data to be inspected sent by the elevator brake through the gateway, where the data to be inspected is obtained by the elevator brake in response to a change in the braking state of the elevator brake, collecting the pressure information on the inner surface of the brake of the elevator brake, performing a first process on the pressure information to obtain electrical signal data, and transmitting the electrical signal data to the gateway, and performing a second process on the electrical signal data by the gateway;

[0007] Process the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result, where the brake fault monitoring model includes an anomaly detection model and / or a fault classification model.

[0008] In one embodiment, before the step of processing the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result, it further includes:

[0009] Obtain sample training data, where the sample training data includes historical inspection data and fault annotation data;

[0010] Extract time domain features, frequency domain features and sliding window statistical features from the historical inspection data to construct a multi-dimensional feature vector;

[0011] Based on the multi-dimensional feature vector, an unsupervised learning algorithm is used for training to obtain the anomaly detection model, and the anomaly threshold is determined by calculating the error between the input data and the reconstructed output of the model;

[0012] According to the anomaly threshold and in combination with the fault annotation data, a supervised learning algorithm is used for classification training to obtain the fault classification model.

[0013] In one embodiment, the step of processing the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result includes:

[0014] Extract time-domain features, frequency-domain features, and sliding window statistical features from the data to be inspected to construct a feature vector to be inspected;

[0015] Input the feature vector to be inspected into the anomaly detection model to obtain a reconstruction error, compare the reconstruction error with a preset anomaly threshold, and generate a preliminary anomaly determination result;

[0016] If the preliminary anomaly determination result is an anomaly, input the feature vector to be inspected into the fault classification model to output the probability distribution of the fault type;

[0017] According to the probability distribution of the fault type and a preset confidence threshold, generate the monitoring result, where the monitoring result includes a fault type identifier and / or a maintenance strategy.

[0018] In addition, to achieve the above object, the present application also proposes an artificial intelligence-based brake fault monitoring method. The artificial intelligence-based brake fault monitoring method is applied to an elevator brake, and the elevator brake includes a brake shoe. The method includes:

[0019] In response to a change in the braking state of the elevator brake, collect the pressure information on the inner surface of the brake shoe;

[0020] Perform a first processing on the pressure information to obtain electrical signal data, and transmit the electrical signal data to a gateway;

[0021] Perform a second processing on the electrical signal data through the gateway to obtain data to be inspected, and send the data to be inspected to a cloud server through the gateway for the cloud server to process the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result, where the brake fault monitoring model includes an anomaly detection model and / or a fault classification model.

[0022] In one embodiment, a pressure sensor is provided on the inner surface of the brake shoe. The step of collecting the pressure information on the inner surface of the brake shoe includes:

[0023] Perform a grid area division on the inner surface of the brake to determine each grid area;

[0024] Detect the pressure of each grid area through the pressure sensor to obtain the pressure information.

[0025] In one embodiment, the step of performing a first processing on the pressure information to obtain electrical signal data includes:

[0026] Convert the pressure information into an initial electrical signal;

[0027] Filter the noise of the initial electrical signal through a filter, and perform outlier detection and removal on the filtered initial electrical signal to obtain a processed initial electrical signal;

[0028] Perform a normalization conversion on the processed initial electrical signal to obtain the electrical signal data.

[0029] In one embodiment, the step of performing a second processing on the electrical signal data through the gateway to obtain data to be tested includes:

[0030] Judge whether the electrical signal data is less than a preset threshold, and count the number of times the electrical signal data is less than the preset threshold;

[0031] In the case where the number of times the electrical signal data is less than the preset threshold reaches a preset number threshold, use the electrical signal data less than the preset threshold as the data to be tested.

[0032] In addition, to achieve the above object, the present application also proposes an artificial intelligence-based brake fault monitoring device, the device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the artificial intelligence-based brake fault monitoring method as described above.

[0033] In addition, to achieve the above object, the present application also proposes a storage medium, the storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, it implements the steps of the artificial intelligence-based brake fault monitoring method as described above.

[0034] In addition, to achieve the above object, the present application also provides a computer program product, the computer program product includes a computer program, and when the computer program is executed by a processor, it implements the steps of the artificial intelligence-based brake fault monitoring method as described above.

[0035] One or more technical solutions proposed by the present application have at least the following technical effects:

[0036] By obtaining the data to be inspected sent by the elevator brake through the gateway, where the data to be inspected is obtained by the elevator brake in response to a change in the braking state of the elevator brake, collecting the pressure information on the inner surface of the brake of the elevator brake, performing a first process on the pressure information to obtain electrical signal data, and transmitting the electrical signal data to the gateway, and then performing a second process on the electrical signal data by the gateway; processing the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result, where the brake fault monitoring model includes an anomaly detection model and / or a fault classification model. The brake fault monitoring model can be used to quickly detect the data to be inspected corresponding to the elevator brake, timely identify whether there is a fault in the brake, and / or accurately identify the fault type of the brake, thereby improving the real-time performance, accuracy, and predictability of elevator brake fault monitoring, and further contributing to improving the safety of the elevator. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings herein are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0039] Figure 1 It is a schematic flowchart provided for the first embodiment of the method for monitoring brake faults based on artificial intelligence in the present application;

[0040] Figure 2 It is a schematic flowchart provided for the second embodiment of the method for monitoring brake faults based on artificial intelligence in the present application;

[0041] Figure 3 It is a schematic flowchart provided for the third embodiment of the method for monitoring brake faults based on artificial intelligence in the present application;

[0042] Figure 4 It is a schematic diagram of the module structure of the device for monitoring brake faults based on artificial intelligence in the embodiments of the present application;

[0043] Figure 5 It is a schematic diagram of the device structure of the hardware operating environment involved in the method for monitoring brake faults based on artificial intelligence in the embodiments of the present application.

[0044] The implementation, functional features, and advantages of the present application will be further described in conjunction with the embodiments with reference to the drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of this application and are not used to limit this application.

[0046] To better understand the technical solutions of this application, the following will be described in detail in combination with the accompanying drawings of the specification and specific implementation manners.

[0047] The main solution of the embodiment of this application is: by obtaining the data to be inspected sent by the elevator brake through the gateway, wherein the data to be inspected is collected by the elevator brake in response to a change in the braking state of the elevator brake, the pressure information on the inner surface of the brake shoe of the elevator brake is collected, the pressure information is subjected to a first process to obtain electrical signal data, and the electrical signal data is transmitted to the gateway, and the electrical signal data is obtained by the gateway through a second process; based on a preset brake failure monitoring model, the data to be inspected is processed to obtain a monitoring result, wherein the brake failure monitoring model includes an anomaly detection model and / or a fault classification model, and the data to be inspected corresponding to the elevator brake can be quickly detected through the brake failure monitoring model, and it can be timely identified whether there is a failure in the brake, and / or the fault type of the brake can be accurately identified, so as to improve the real-time performance, accuracy and predictability of elevator brake failure monitoring, and further help to improve the safety of the elevator.

[0048] In this embodiment, for the convenience of description, the following will be described with the brake failure monitoring device based on artificial intelligence as the execution subject.

[0049] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of implementing the above functions, a brake failure monitoring device based on artificial intelligence, etc. The following will take the brake failure monitoring device based on artificial intelligence as an example to illustrate this embodiment and the following embodiments.

[0050] Based on this, the embodiment of this application provides a brake failure monitoring method based on artificial intelligence, referring to Figure 1 , Figure 1 is a schematic flowchart of the first embodiment of the brake failure monitoring method based on artificial intelligence of this application.

[0051] In this embodiment, the brake failure monitoring method based on artificial intelligence includes steps S10 to S20:

[0052] Step S10, obtain the data to be inspected sent by the elevator brake through the gateway. Among them, the data to be inspected is obtained by the elevator brake in response to a change in the braking state of the elevator brake, collecting the pressure information on the inner surface of the brake of the elevator brake, performing a first process on the pressure information to obtain electrical signal data, and transmitting the electrical signal data to the gateway, and performing a second process on the electrical signal data through the gateway;

[0053] It should be noted that this embodiment is applied to a cloud server, and a brake fault monitoring model deployed on the cloud server is used to monitor the elevator brake for faults. Among them, the elevator brake is mainly used to fix the position of the car when the elevator stops running or to quickly decelerate and stop the movement of the car in an emergency. It is usually directly connected to the elevator drive motor and can quickly respond when an instruction is issued by the elevator control system to ensure the safe operation of the elevator. The working principle of the elevator brake is based on friction, and sufficient braking force is applied to prevent the elevator car from moving.

[0054] Exemplarily, the elevator brake at least includes a brake shoe. The brake shoe is the core execution component of the elevator brake. Its main function is to tightly hold the brake wheel or brake disc after receiving the braking signal, so as to generate sufficient friction to stop the elevator.

[0055] Exemplarily, since the original pressure signal is vulnerable to external factors such as environmental noise interference, sensor nonlinear error, and mechanical vibration, the directly output original data may have problems such as noise pollution, abnormal fluctuations, or nonlinear distortion. Therefore, converting the original pressure information into structured and highly reliable electrical signal data lays a reliable foundation for subsequent model detection.

[0056] Exemplarily, at the moment of physical contact of the brake, a high-precision sensor is used to capture the dynamic change of the pressure, and edge computing capabilities are combined to achieve lightweight preprocessing of the data. Then, the data to be inspected obtained from the preprocessing is transmitted to the cloud server for the brake fault monitoring model in the cloud server to detect the data to be inspected.

[0057] Step S20, process the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result. Among them, the brake fault monitoring model includes an anomaly detection model and / or a fault classification model.

[0058] Furthermore, after the cloud server obtains the data to be inspected sent by the elevator brake through the gateway, it can process the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result.

[0059] Exemplarily, the brake fault monitoring model in the embodiments of the present application includes a hybrid architecture of an anomaly detection model and a fault classification model. Among them, the anomaly detection model is used to identify the degree of data deviation from the normal mode (such as the VAE reconstruction error); the fault classification model is used to further classify the abnormal data (such as brake pad wear, coil aging).

[0060] Exemplarily, the steps of processing the to-be-tested data based on a preset brake fault monitoring model to obtain a monitoring result include:

[0061] Extract time-domain features, frequency-domain features, and sliding window statistical features from the to-be-tested data to construct a to-be-tested feature vector;

[0062] Input the to-be-tested feature vector into the anomaly detection model to obtain a reconstruction error, compare the reconstruction error with a preset anomaly threshold, and generate a preliminary anomaly determination result;

[0063] If the preliminary anomaly determination result is abnormal, input the to-be-tested feature vector into the fault classification model to output a fault type probability distribution;

[0064] Generate the monitoring result according to the fault type probability distribution and a preset confidence threshold, where the monitoring result includes a fault type identifier and / or a maintenance strategy.

[0065] Exemplarily, by extracting time-domain features (such as mean, kurtosis), frequency-domain features (such as the energy ratio of 10 - 50 Hz) from the brake pressure signal, and calculating the variance of the pressure drop rate within the sliding window, a multi-dimensional feature vector is constructed.

[0066] Exemplarily, the anomaly detection model is a model based on unsupervised learning (such as VAE), which learns the normal data distribution. The reconstruction error can reflect the difference degree after the input data is reconstructed by the model, and quantifies the degree of data deviation from the normal mode. The preset anomaly threshold is a critical value for determining anomalies, which can be dynamically adjusted to adapt to equipment aging or environmental changes. The preliminary anomaly determination result includes a binary label, that is, normal or abnormal, which is used to determine whether to trigger the subsequent classification process.

[0067] Exemplarily, in the case where the preliminary anomaly determination result is abnormal, input the time-frequency features and the unsupervised anomaly score into the fault classification model together to output a fault type probability distribution, which includes the prediction probabilities of each fault category (such as 80% for brake pad wear, 15% for coil short circuit), reflecting the model confidence to guide targeted maintenance.

[0068] Exemplarily, a preset confidence threshold is used to determine the lowest probability (e.g., 80%) for a fault to be valid. If it is lower than this value, it is regarded as uncertain. The fault type identifier includes a specific fault category code (e.g., F001 represents brake pad wear). A recommended repair strategy based on the fault type and historical repair records (such as "replace the brake pads immediately") is provided, so as to provide clear repair guidance, shorten the fault handling time, and at the same time, the confidence threshold can be used to avoid over-repair caused by low-probability misjudgments.

[0069] Exemplarily, in the embodiments of the present application, the brake fault monitoring model can also be dynamically optimized in combination with reinforcement learning. The model parameters are adjusted according to the feedback of historical repair effects, so as to realize real-time and accurate diagnosis of elevator brake faults and operable repair guidance, improve safety and operation and maintenance efficiency, and reduce the accident risk and downtime loss caused by brake failure.

[0070] This embodiment provides an artificial intelligence-based brake fault monitoring method. By obtaining the data to be inspected sent by the elevator brake through the gateway, wherein the data to be inspected is obtained by the elevator brake in response to a change in the braking state of the elevator brake, collecting the pressure information on the inner surface of the brake of the elevator brake, performing a first processing on the pressure information to obtain electrical signal data, and transmitting the electrical signal data to the gateway, and performing a second processing on the electrical signal data by the gateway; processing the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result, wherein the brake fault monitoring model includes an anomaly detection model and / or a fault classification model, and the data to be inspected corresponding to the elevator brake can be quickly detected through the brake fault monitoring model, and it can be timely identified whether there is a fault in the brake, and / or the fault type of the brake can be accurately identified, so as to improve the real-time performance, accuracy and predictability of elevator brake fault monitoring, and further contribute to improving the safety of the elevator.

[0071] Based on the first embodiment of the present application, the second embodiment of the present application is proposed. In the second embodiment of the present application, the same or similar content as that in the above-mentioned embodiment 1 can be referred to the above introduction and will not be repeated hereinafter. On this basis, please refer to Figure 2 Before step S20, the artificial intelligence-based brake fault monitoring method further includes steps S01 to S04:

[0072] S01: Obtain sample training data, wherein the sample training data includes historical inspection data and fault annotation data;

[0073] Exemplarily, the sample training data serves as the basis for model training and contains the correlation information between historical operating states and known faults. The historical inspection data is the sensor data (such as pressure, current, vibration) of the normal operation and fault states of the elevator brake, which is used to learn the feature distributions of the normal mode and the abnormal mode. The fault annotation data is the fault types and occurrence times marked manually or by the system, providing target labels for supervised learning. The mechanical and electrical parameters of the brake are collected in real time through sensors, and the fault annotations are generated in combination with the maintenance records. In addition, oversampling or data augmentation (adding noise perturbations) is performed on a small number of fault samples (such as coil short circuits) to solve the problem of class imbalance. During the process of collecting sample training data, it is necessary to cover the data under various working conditions (such as full load, no load, emergency stop) to ensure the generalization ability of the model.

[0074] S02: Extract time-domain features, frequency-domain features, and sliding window statistical features from the historical inspection data to construct a multi-dimensional feature vector;

[0075] Exemplarily, the time-domain features can directly reflect the statistical characteristics of the signal changing with time (such as mean, variance), capturing the transient anomalies in the braking process. The frequency-domain features are used to identify periodic faults through spectrum analysis (such as specific frequency vibrations caused by uneven wear of the brake pads). The sliding window statistical features are based on the rolling calculation of the time window (such as the average pressure of the past 5 brakings), which are used to capture the trend of degradation.

[0076] S03: Based on the multi-dimensional feature vector, use an unsupervised learning algorithm for training to obtain the anomaly detection model, and determine the anomaly threshold by calculating the error between the input data and the reconstructed output of the model;

[0077] Exemplarily, through an unsupervised learning algorithm, it is possible to learn the normal mode boundary from the data distribution without relying on fault labels, and train an anomaly detection model to distinguish the normal state and the abnormal state of the data. The reconstruction error refers to the degree of difference between the input data after being reconstructed by the model, which is used to reflect the degree of deviation of the data from the normal mode. The anomaly threshold is the critical value for determining anomalies, and if the value is exceeded, the data can be determined to be abnormal.

[0078] S04: According to the anomaly threshold, combined with the fault annotation data, use a supervised learning algorithm for classification training to obtain the fault classification model.

[0079] Exemplarily, through a supervised learning algorithm, a mapping relationship between features and fault types is established using the annotation data to obtain a fault classification model, which is used to output specific fault types (such as brake pad wear, coil overheating) and confidence levels. Only the data determined to be abnormal by the unsupervised model is input into the classification model to reduce the waste of computing resources. By jointly training fault classification and severity prediction (such as wear percentage), the information utilization rate of the model is improved.

[0080] In this embodiment, through the above solution, specifically, by obtaining sample training data, where the sample training data includes historical inspection data and fault annotation data; extracting time-domain features, frequency-domain features, and sliding window statistical features from the historical inspection data to construct a multi-dimensional feature vector; based on the multi-dimensional feature vector, using an unsupervised learning algorithm for training to obtain the anomaly detection model, and determining the anomaly threshold by calculating the error between the input data and the model reconstruction output; according to the anomaly threshold, combined with the fault annotation data, using a supervised learning algorithm for classification training to obtain the fault classification model. Through the collaborative training of unsupervised and supervised models, end-to-end automated diagnosis from anomaly detection to fault classification is realized, significantly improving the accuracy and timeliness of elevator brake fault monitoring and avoiding safety accidents caused by missed inspections.

[0081] Based on any of the foregoing embodiments of the present application, the third embodiment of the present application is proposed. In the third embodiment of the present application, the same or similar content as any of the above embodiments can be referred to the above introduction and will not be repeated hereinafter. On this basis, please refer to Figure 3 , Figure 3 which is a schematic flow diagram of the third embodiment of the brake fault monitoring method based on artificial intelligence of the present application.

[0082] In this embodiment, the brake fault monitoring method based on artificial intelligence includes steps A10 to A30:

[0083] Step A10, in response to a change in the braking state of the elevator brake, collect the pressure information on the inner surface of the brake shoe.

[0084] It should be noted that this embodiment is applied to an elevator brake. The elevator brake is mainly used to fix the position of the car when the elevator stops running or to quickly decelerate and stop the movement of the car in an emergency. It is usually directly connected to the elevator drive motor and can quickly respond when an instruction is issued by the elevator control system to ensure the safe operation of the elevator. The working principle of the elevator brake is based on friction, and sufficient braking force is applied to prevent the elevator car from moving.

[0085] The elevator brake includes at least a brake shoe. The brake shoe is the core execution component of the elevator brake, and its main function is to tightly hold the brake wheel or brake disc after receiving the braking signal, thereby generating sufficient friction to stop the elevator.

[0086] In a feasible embodiment, step A10 may include steps A11 to A12:

[0087] Step A11, divide the inner surface of the brake shoe into grid regions to determine each grid region;

[0088] It should be noted that in this embodiment, a pressure sensor is provided on the inner surface of the brake for collecting the pressure information acting on the inner surface of the brake.

[0089] Specifically, according to the actual size of the inner surface of the brake, the contact surface is divided into multiple rectangular or square grid regions of equal size. For example, if the inner surface of the brake is rectangular, it can be divided into N×M grids (such as a 10×10 grid, a total of 100 regions) along the length and width directions.

[0090] Then, a unique identifier (such as a number or coordinate) is assigned to each grid region and corresponds one-to-one with the pre-installed pressure sensor. For example, the grid region corresponds to the pressure sensor.

[0091] By dividing the contact surface of the brake into multiple discrete sub-regions, the pressure distribution characteristics of each region can be accurately monitored, so as to locate local anomalies. For example, accurately identify which region of the inner surface of the brake is more severely worn, and achieve precise fault detection.

[0092] Step A12, the pressure sensors are used to detect the pressure of each grid region to obtain the pressure information.

[0093] Specifically, a pressure sensor is installed at the center of each grid region to directly collect the contact pressure of this region. Among them, a flexible pressure sensing array can also be laid in the grid region to realize continuous monitoring of the pressure distribution in the region.

[0094] The sampling rate is set according to the frequency of the elevator braking state change (such as 100Hz) to ensure that transient pressure fluctuations are captured. When the pressure sensor detects that the pressure fluctuation in this grid region reaches the preset sampling rate, the pressure information is collected.

[0095] Through the above steps, through grid pressure detection, local abnormal pressure information that cannot be recognized by traditional integral sensors can be captured.

[0096] Step A20, perform a first processing on the pressure information to obtain electrical signal data, and transmit the electrical signal data to the gateway;

[0097] It should be noted that since the original pressure signal is easily affected by external factors such as environmental noise interference, sensor nonlinear error, and mechanical vibration, the directly output original data may have problems such as noise pollution, abnormal fluctuations, or nonlinear distortion. Therefore, converting the original pressure information into structured and highly reliable electrical signal data lays a reliable foundation for subsequent cloud consistency verification, fault mode identification, and predictive maintenance.

[0098] In a feasible embodiment, step A20 may include steps A21 to A23:

[0099] Step A21, converting the pressure information into an initial electrical signal;

[0100] Specifically, when pressure acts on the piezoresistive sensor, it causes the strain gauge to change, breaking the balance of the bridge and outputting a voltage signal proportional to the pressure.

[0101]

[0102] Among them, V exc is the excitation voltage, is the resistance change rate.

[0103] Alternatively, when pressure acts on a capacitive sensor, the pressure causes the spacing or area of the capacitor plates to change, thereby converting the capacitance change into an initial electrical signal through a capacitance-to-voltage conversion circuit (such as a charge amplifier or a dedicated ASIC chip).

[0104] Step A22, filtering the initial electrical signal for noise through a filter, and performing an outlier inspection and removal on the filtered initial electrical signal to obtain a processed initial electrical signal;

[0105] Specifically, by combining the Kalman filter strategy, the pressure is dynamically detected (such as the sudden change in pressure when the elevator starts and stops). And a prediction model based on the pressure change rate is constructed using historical data. For example, if the pressure change trend over time during the elevator braking process is known, the following prediction equation can be established:

[0106] P k|k-1 =F k P k-1 +B k u k

[0107] Among them, P k|k-1 is the pressure value predicted at the current moment based on the state at the previous moment, F k is the state transfer matrix, B k is the control input model, u k is the control variable.

[0108] The noise covariance matrix and the observation noise covariance matrix in the Kalman filter determine the trust level of the filter. During the elevator braking process, due to the drastic pressure changes, the noise covariance matrix and the observation noise covariance matrix can be dynamically adjusted by real-time monitoring of the pressure change rate to optimize the filtering effect. For example, when the pressure change rate is detected to increase, the noise covariance matrix is appropriately increased to allow more process noise to enter the model, thereby better tracking the rapidly changing pressure.

[0109] After completing the Kalman filtering, check whether the initial electrical signal after the filtering process meets the preset normal operating range. If it does not meet the preset normal operating range, the initial electrical signal is considered an outlier and is then removed. Usually, this range can be determined based on the characteristics of the sensor (such as range, accuracy) and historical data analysis.

[0110] Step A23, perform a normalization transformation on the processed initial electrical signal to obtain the electrical signal data.

[0111] Convert the processed initial electrical signal into an industrial standard signal form to obtain compliant electrical signal data.

[0112] After obtaining the final electrical signal data, transmit it to the gateway for the gateway to further process the electrical signal data.

[0113] Through the above steps, not only are the noise and outliers in the original electrical signal effectively eliminated, but also the data quality and consistency in the subsequent processing stage are ensured, greatly improving the reliability and accuracy of fault detection.

[0114] Step A30, perform a second processing on the electrical signal data through the gateway to obtain the data to be inspected, and send the data to be inspected to the cloud server through the gateway for the cloud server to process the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result, where the brake fault monitoring model includes an anomaly detection model and / or a fault classification model.

[0115] It should be noted that in order to effectively focus on the most critical fault information in the electrical signal data, therefore, performing Step A30 can ensure that only the data that truly reflects the health status of the elevator brake will be uploaded to the cloud for the final consistency check.

[0116] In a feasible embodiment, Step A30 may include Steps A31 - A32:

[0117] Step A31, determine whether the electrical signal data is less than a preset threshold, and count the number of times the electrical signal data is less than the preset threshold;

[0118] Specifically, for each piece of electrical signal data from the pressure sensor, first compare it with a preset threshold through the gateway. If the piece of electrical signal data is less than the preset threshold, record a count. This process continues until a certain time window (such as within one minute) or a specific number of data samples are processed.

[0119] This step aims to screen out data points that may indicate potential problems. For example, when the pressure of the brake is lower than the first preset threshold, it may mean that there is wear or other faults in the brake.

[0120] Step A32, in the case where the number of times the electrical signal data is less than the preset threshold reaches the preset number threshold, the electrical signal data less than the preset threshold is used as the data to be tested.

[0121] Specifically, once it is detected that the number of times the electrical signal data is less than the preset threshold reaches the preset number threshold (for example, 5 consecutive times), these data are marked as "data to be tested". Subsequently, these data will be packaged and sent to the cloud server through the gateway. After the cloud server obtains the data to be tested sent by the elevator brake through the gateway, it can process the data to be tested based on the preset brake fault monitoring model to obtain the monitoring result.

[0122] Through the above steps, selecting the data that shows potential problems for transmission reduces unnecessary network traffic and cloud processing load. And by setting reasonable thresholds and number limits, the problem areas that really need attention can be identified more accurately, improving the overall system response speed and accuracy.

[0123] Through the method of the above embodiment, in response to a change in the braking state of the elevator brake, the pressure information on the inner surface of the brake is collected; then, the pressure information is subjected to a first process to obtain electrical signal data, and the electrical signal data is transmitted to the gateway; finally, the gateway performs a second process on the electrical signal data to obtain the data to be tested, and sends the data to be tested to the cloud server through the gateway for the cloud server to process the data to be tested based on the preset brake fault monitoring model to obtain the monitoring result. This method integrates high-sensitivity sensor technology, intelligent signal processing algorithms and cloud big data analysis platforms to monitor elevator faults, which can improve the real-time performance and accuracy of detecting elevator faults, and greatly enhance the ability of fault prediction and maintenance.

[0124] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the brake fault monitoring method based on artificial intelligence of this application. Based on this technical concept, more forms of simple transformations are within the protection scope of this application.

[0125] This application also provides a brake fault monitoring device based on artificial intelligence. Please refer to Figure 4 , the brake fault monitoring device based on artificial intelligence includes an elevator brake and a cloud server;

[0126] The elevator brake includes:

[0127] The acquisition module 10 is configured to acquire the pressure information on the inner surface of the brake when the braking state of the elevator brake changes;

[0128] The first processing module 20 is configured to perform first processing on the pressure information to obtain electrical signal data, and transmit the electrical signal data to the gateway;

[0129] The second processing module 30 is configured to perform second processing on the electrical signal data through the gateway to obtain data to be inspected, and send the data to be inspected to the cloud server through the gateway for the cloud server to process the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result;

[0130] The cloud server includes:

[0131] The acquisition module 40 is configured to acquire the data to be inspected sent by the elevator brake through the gateway, where the data to be inspected is obtained by the elevator brake in response to a change in the braking state of the elevator brake, acquiring the pressure information on the inner surface of the brake of the elevator brake, performing first processing on the pressure information to obtain electrical signal data, and transmitting the electrical signal data to the gateway, and performing second processing on the electrical signal data through the gateway;

[0132] The monitoring module 50 is configured to process the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result, where the brake fault monitoring model includes an anomaly detection model and / or a fault classification model.

[0133] The brake fault monitoring device based on artificial intelligence provided by the present application adopts the brake fault monitoring method based on artificial intelligence in the above embodiments, and can solve the technical problem of brake fault monitoring. Compared with the prior art, the beneficial effects of the brake fault monitoring device based on artificial intelligence provided by the present application are the same as those of the brake fault monitoring method based on artificial intelligence provided in the above embodiments, and other technical features in the brake fault monitoring device based on artificial intelligence are the same as the features disclosed in the above embodiment method, and will not be elaborated here.

[0134] The present application provides a brake fault monitoring device based on artificial intelligence. The brake fault monitoring device based on artificial intelligence includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the brake fault monitoring method based on artificial intelligence in the first embodiment above.

[0135] Next, refer to Figure 5, which shows a schematic structural diagram of a brake failure monitoring device based on artificial intelligence suitable for implementing the embodiments of the present application. The brake failure monitoring device based on artificial intelligence in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The shown brake failure monitoring device based on artificial intelligence is merely an example and should not impose any limitations on the functions and usage scopes of the embodiments of the present application.

[0136] As Figure 5 shown, the brake failure monitoring device based on artificial intelligence may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory 1002 or the program loaded from the storage device 1003 into the random access memory 1004. In the random access memory 1004, various programs and data required for the operation of the brake failure monitoring device based on artificial intelligence are also stored. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are connected to each other through a bus 1005. The input / output interface 1006 is also connected to the bus. Generally, the following systems may be connected to the input / output interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the brake failure monitoring device based on artificial intelligence to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a brake failure monitoring device based on artificial intelligence having various systems, it should be understood that it is not required to implement or have all the shown systems. Instead, more or fewer systems may be implemented or had.

[0137] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by a processing device 1001, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are executed.

[0138] The brake failure monitoring device based on artificial intelligence provided by the present application adopts the method for monitoring brake failure based on artificial intelligence in the above embodiments, and can solve the technical problems of brake failure monitoring. Compared with the prior art, the beneficial effects of the brake failure monitoring device based on artificial intelligence provided by the present application are the same as those of the method for monitoring brake failure based on artificial intelligence provided in the above embodiments, and other technical features in the brake failure monitoring device based on artificial intelligence are the same as the features disclosed in the method of the previous embodiment, and will not be elaborated herein.

[0139] It should be understood that the various parts disclosed in the present application can be implemented by hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0140] As described above, the above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all of them should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0141] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the method for monitoring brake failure based on artificial intelligence in the above embodiments.

[0142] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0143] The above computer-readable storage medium can be included in the artificial intelligence-based brake failure monitoring device; or it can exist separately without being assembled into the artificial intelligence-based brake failure monitoring device.

[0144] The above computer-readable storage medium carries one or more programs. When the one or more programs are executed by the artificial intelligence-based brake failure monitoring device, the artificial intelligence-based brake failure monitoring device is enabled to: obtain the data to be inspected sent by the elevator brake through the gateway, where the data to be inspected is collected by the elevator brake in response to a change in the braking state of the elevator brake, and the pressure information on the inner surface of the brake shoe of the elevator brake is collected, and the pressure information is subjected to a first process to obtain electrical signal data, and the electrical signal data is transmitted to the gateway, and the electrical signal data is obtained by the gateway through a second process; process the data to be inspected based on a preset brake failure monitoring model to obtain a monitoring result, where the brake failure monitoring model includes an anomaly detection model and / or a fault classification model, and the data to be inspected corresponding to the elevator brake can be quickly detected through the brake failure monitoring model, and it can be timely identified whether the brake has a fault, and / or the fault type of the brake can be accurately identified, thereby improving the real-time performance, accuracy, and predictability of elevator brake failure monitoring, and further contributing to improving the safety of the elevator.

[0145] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent 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: Local Area Network) or a wide area network (WAN: Wide Area Network), or it can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0146] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutively represented blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0147] The modules involved in the embodiments described in this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0148] The readable storage medium provided in this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned artificial intelligence-based brake failure monitoring method, and can solve the technical problems of brake failure monitoring. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the artificial intelligence-based brake failure monitoring method provided in the above embodiments, and will not be elaborated here.

[0149] The present application also provides a computer program product, including a computer program which, when executed by a processor, implements the steps of the above-mentioned artificial intelligence-based brake fault monitoring method.

[0150] The computer program product provided by the present application can solve the technical problem of brake fault monitoring. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the artificial intelligence-based brake fault monitoring method provided in the above embodiments, and will not be elaborated here.

[0151] The above are only some embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. An artificial intelligence-based brake fault monitoring method, characterized in that, The method is applied to a cloud server and includes: Obtaining the data to be inspected sent by an elevator brake through a gateway, where the data to be inspected is obtained by the elevator brake in response to a change in the braking state of the elevator brake, collecting pressure information on the inner surface of the brake shoe of the elevator brake, performing a first processing on the pressure information to obtain electrical signal data, and transmitting the electrical signal data to the gateway, and the gateway performs a second processing on the electrical signal data to obtain it; Processing the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result, where the brake fault monitoring model includes an anomaly detection model and / or a fault classification model.

2. The method for monitoring brake faults based on artificial intelligence according to claim 1, wherein Before the step of processing the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result, it further includes: Obtaining sample training data, where the sample training data includes historical inspection data and fault annotation data; Extracting time-domain features, frequency-domain features, and sliding window statistical features from the historical inspection data to construct a multi-dimensional feature vector; Based on the multi-dimensional feature vector, using an unsupervised learning algorithm for training to obtain the anomaly detection model, and determining an anomaly threshold by calculating the error between the input data and the reconstructed output of the model; According to the anomaly threshold, combined with the fault annotation data, using a supervised learning algorithm for classification training to obtain the fault classification model.

3. The method for monitoring brake faults based on artificial intelligence according to claim 2, characterized in that, The step of processing the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result includes: Extracting time-domain features, frequency-domain features, and sliding window statistical features from the data to be inspected to construct a feature vector to be inspected; Inputting the feature vector to be inspected into the anomaly detection model to obtain a reconstruction error, comparing the reconstruction error with a preset anomaly threshold, and generating a preliminary anomaly determination result; If the preliminary anomaly determination result is an anomaly, inputting the feature vector to be inspected into the fault classification model to output a probability distribution of fault types; According to the probability distribution of fault types and a preset confidence threshold, generating the monitoring result, where the monitoring result includes a fault type identifier and / or a maintenance strategy.

4. An artificial intelligence-based brake fault monitoring method, characterized in that, The method for monitoring elevator brake faults based on artificial intelligence is applied to an elevator brake, and the elevator brake includes a brake shoe. The method includes: In response to a change in the braking state of the elevator brake, collecting pressure information on the inner surface of the brake shoe; Performing a first processing on the pressure information to obtain electrical signal data, and transmitting the electrical signal data to the gateway; Performing a second processing on the electrical signal data through the gateway to obtain the data to be inspected, and sending the data to be inspected to the cloud server through the gateway for the cloud server to process the data to be inspected based on a preset brake fault monitoring model to obtain a monitoring result, where the brake fault monitoring model includes an anomaly detection model and / or a fault classification model.

5. The method for monitoring brake faults based on artificial intelligence according to claim 4, wherein A pressure sensor is arranged on the inner surface of the brake shoe. The step of collecting pressure information on the inner surface of the brake shoe includes: Dividing the inner surface of the brake shoe into grid regions to determine each grid region; Pressure detection is performed on each grid area through the pressure sensor to obtain the pressure information.

6. The method for monitoring brake faults based on artificial intelligence according to claim 5, wherein the step of performing a first process on the pressure information to obtain electrical signal data includes: Converting the pressure information into an initial electrical signal; Filtering noise from the initial electrical signal through a filter, and performing outlier inspection and removal on the filtered initial electrical signal to obtain a processed initial electrical signal; Performing a normalization conversion on the processed initial electrical signal to obtain the electrical signal data.

7. The method for monitoring brake faults based on artificial intelligence according to claim 6, characterized in that, The step of performing a second process on the electrical signal data through the gateway to obtain data to be inspected includes: Judging whether the electrical signal data is less than a preset threshold, and counting the number of times the electrical signal data is less than the preset threshold; When the number of times the electrical signal data is less than the preset threshold reaches a preset number threshold, the electrical signal data less than the preset threshold is used as the data to be inspected.

8. An artificial intelligence-based brake fault monitoring device, characterized in that, The device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the method for monitoring brake faults based on artificial intelligence according to any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the method for monitoring brake faults based on artificial intelligence according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that, The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method for monitoring brake faults based on artificial intelligence according to any one of claims 1 to 6 are implemented.

Images