Fault monitoring method and device based on artificial intelligence, equipment, medium and product

Abstract

The invention discloses a fault monitoring method, device and equipment based on artificial intelligence, a medium and a product, and relates to the technical field of elevators, the method comprises the steps that multi-dimensional sensor data are obtained, and the multi-dimensional sensor data comprise acceleration sensor data and vibration sensor data; performing preset processing on the multi-dimensional sensor data to obtain to-be-analyzed data; and the to-be-analyzed data is sent to a cloud server, so that the cloud server analyzes the to-be-analyzed data based on a preset multi-modal fusion analysis model to obtain a monitoring result, graded feedback is conducted according to the monitoring result, and the elevator can be monitored in real time through the multi-dimensional sensor data. According to the method, whether the elevator operation has faults or not is recognized in time, and / or the fault type of the elevator is accurately recognized, so that the real-time performance, the accuracy and the predictability of elevator operation fault monitoring are improved, and then the safety of the elevator is improved.

Description

Technical Field

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

[0002] As a complex system involving mechanical transmission (traction machine / guide rail), electrical control (frequency converter / PLC), and software algorithms, an elevator has multiple potential fault points. Traditional visual inspections can only cover 32% of mechanical wear problems, and most faults often occur earlier than visible damage. Currently, there is a lack of a perfect monitoring technology that can identify abnormalities in the elevator in real time and accurately, which is not conducive to improving the safety of the elevator.

[0003] Therefore, it is necessary to propose a solution to improve the real-time performance, accuracy, and predictability of elevator operation fault monitoring, thereby improving the safety of the elevator. Summary of the Invention

[0004] The main purpose of this application is to provide a fault monitoring method, device, equipment, medium and product based on artificial intelligence, aiming to improve the real-time performance, accuracy, and predictability of elevator operation fault monitoring, thereby improving the safety of the elevator.

[0005] To achieve the above object, this application provides a fault monitoring method based on artificial intelligence. The method is applied to an elevator and includes:

[0006] Obtain multi-dimensional sensor data, where the multi-dimensional sensor data includes acceleration sensor data and vibration sensor data;

[0007] Perform a preset process on the multi-dimensional sensor data to obtain data to be analyzed;

[0008] Send the data to be analyzed to a cloud server for the cloud server to analyze the data to be analyzed based on a preset multi-modal fusion analysis model to obtain a monitoring result, and perform hierarchical feedback according to the monitoring result.

[0009] In one embodiment, the step of obtaining multi-dimensional sensor data includes:

[0010] Collect the acceleration sensor data through an acceleration sensor array located at the car door guide rail of the elevator;

[0011] Collect the vibration sensor data through a vibration sensor array located at the top of the car door of the elevator;

[0012] Wherein, the acceleration sensor data includes a door machine movement acceleration signal in the X-axis direction, a guide rail vibration acceleration signal in the Y-axis direction, and a car displacement acceleration signal in the Z-axis direction.

[0013] In one embodiment, the step of performing preset processing on the multi-dimensional sensor data to obtain the data to be analyzed includes:

[0014] Performing at least one of signal conversion, noise filtering, and feature extraction on the multi-dimensional sensor data to obtain initial processed data;

[0015] Screening the initial processed data according to preset rules to obtain the data to be analyzed.

[0016] In addition, to achieve the above object, the present application also proposes an artificial intelligence-based fault monitoring method, which is applied to a cloud server and includes:

[0017] Receiving the data to be analyzed sent by the elevator, where the data to be analyzed is obtained by the elevator acquiring multi-dimensional sensor data and performing preset processing on the multi-dimensional sensor data, and the multi-dimensional sensor data includes acceleration sensor data and vibration sensor data;

[0018] Analyzing the data to be analyzed based on a preset multi-modal fusion analysis model to obtain a monitoring result;

[0019] Performing hierarchical feedback according to the monitoring result.

[0020] In one embodiment, the step of analyzing the data to be analyzed based on a preset multi-modal fusion analysis model to obtain a monitoring result includes:

[0021] Performing spatio-temporal feature extraction and temporal sequence analysis on the data to be analyzed through the multi-modal fusion analysis model to obtain a feature vector;

[0022] Performing similarity matching between the feature vector and a pre-stored fault feature map to obtain matching degree data;

[0023] Comparing the matching degree data with a preset matching degree threshold to obtain the monitoring result corresponding to the matching degree data.

[0024] In one embodiment, the monitoring result includes a fault type and / or a fault probability, and the step of performing hierarchical feedback according to the monitoring result includes:

[0025] Triggering a first-level warning when the fault probability is in the first interval, generating a monitoring log according to the monitoring result and storing it;

[0026] Triggering a second-level alarm when the fault probability is in the second interval, generating a monitoring report according to the monitoring result, and pushing the monitoring report to the maintenance system;

[0027] When the failure probability is in the third interval, a three - level emergency stop is triggered, and an emergency stop control instruction is sent to the elevator according to the monitoring result, so that the elevator executes an emergency stop according to the emergency stop control instruction.

[0028] In addition, to achieve the above object, the present application also proposes an artificial - intelligence - based fault monitoring device, which is applied to an elevator and includes:

[0029] An acquisition module, configured to acquire multi - dimensional sensor data, where the multi - dimensional sensor data includes acceleration sensor data and vibration sensor data;

[0030] A processing module, configured to perform preset processing on the multi - dimensional sensor data to obtain data to be analyzed;

[0031] A sending module, configured to send the data to be analyzed to a cloud server, so that the cloud server analyzes the data to be analyzed based on a preset multi - modal fusion analysis model to obtain a monitoring result, and performs hierarchical feedback according to the monitoring result.

[0032] In addition, to achieve the above object, the present application also proposes an artificial - intelligence - based fault monitoring device, which 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 fault monitoring method as described above.

[0033] In addition, to achieve the above object, the present application also proposes a storage medium, which 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 fault monitoring method as described above.

[0034] In addition, to achieve the above object, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the artificial - intelligence - based 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 acquiring multi-dimensional sensor data, where the multi-dimensional sensor data includes acceleration sensor data and vibration sensor data; performing preset processing on the multi-dimensional sensor data to obtain data to be analyzed; sending the data to be analyzed to a cloud server for the cloud server to analyze the data to be analyzed based on a preset multi-modal fusion analysis model to obtain a monitoring result, and performing hierarchical feedback according to the monitoring result, the elevator can be monitored in real time through the multi-dimensional sensor data, the presence of faults in the elevator operation can be identified in a timely manner, and / or the types of elevator faults can be accurately identified, thereby improving the real-time performance, accuracy and predictability of elevator operation fault monitoring, and further contributing to improving the safety of the elevator. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0038] To more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the following will briefly introduce the accompanying drawings required for 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 Embodiment 1 of the fault monitoring method based on artificial intelligence of the present application;

[0040] Figure 2 It is a schematic flowchart provided for Embodiment 2 of the fault monitoring method based on artificial intelligence of the present application;

[0041] Figure 3 It is a schematic module structure diagram of the fault monitoring device based on artificial intelligence according to an embodiment of the present application;

[0042] Figure 4 It is a schematic device structure diagram of the hardware operating environment involved in the fault monitoring method based on artificial intelligence according to an embodiment of the present application.

[0043] The implementation, functional features and advantages of the present application will be further described in conjunction with the embodiments with reference to the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0045] To better understand the technical solutions of the present application, the following will be described in detail in conjunction with the accompanying drawings of the specification and the specific embodiments.

[0046] The main solution of the embodiment of the present application is as follows:

[0047] In this embodiment, for the convenience of description, the following takes the fault monitoring device based on artificial intelligence as the execution subject for elaboration.

[0048] 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 fault monitoring device based on artificial intelligence, etc. The following takes the fault monitoring device based on artificial intelligence as an example to illustrate this embodiment and the following embodiments.

[0049] Based on this, the embodiment of the present application provides a fault monitoring method based on artificial intelligence. Refer to Figure 1 , Figure 1 which is the flowchart of the first embodiment of the fault monitoring method based on artificial intelligence of the present application.

[0050] In this embodiment, the fault monitoring method based on artificial intelligence includes steps S10 to S30:

[0051] Step S10, obtain multi-dimensional sensor data, where the multi-dimensional sensor data includes acceleration sensor data and vibration sensor data;

[0052] Specifically, the fault monitoring method based on artificial intelligence in the embodiment of the present application is applied to an elevator. Sensors are installed at various positions of the elevator, and multi-dimensional sensor data can be collected in real time through the sensor array.

[0053] Exemplarily, the step of obtaining multi-dimensional sensor data includes:

[0054] Collect the acceleration sensor data through the acceleration sensor array located at the car door guide rail of the elevator;

[0055] Collect the vibration sensor data through the vibration sensor array located at the top of the car door of the elevator;

[0056] Among them, the acceleration sensor data includes the door machine movement acceleration signal in the X-axis direction, the guide rail vibration acceleration signal in the Y-axis direction, and the car displacement acceleration signal in the Z-axis direction.

[0057] Exemplarily, an acceleration sensor array is installed at the car door guide rail of the elevator, and the acceleration sensor data can be collected through the acceleration sensor array. The X / Y / Z three-axis linear acceleration values are collected through MEMS or piezoelectric sensors, which can reflect the elevator movement state and impact characteristics.

[0058] Exemplarily, a vibration sensor array is installed at the top of the car door of the elevator, and vibration sensor data can be collected through the vibration sensor array. An ICP-type sensor is used to obtain vibration signals in the frequency band of 20 - 5000 Hz, which can characterize the dynamic characteristics of mechanical components.

[0059] Exemplarily, a number of (e.g., 8) nodes (with a spacing of 200 mm) can also be equidistantly arranged on both sides of the car door guide rail of the elevator for detecting the sliding resistance of the door leaf (normal range 8 - 15 N), positioning the jamming position (through the analysis of pressure mutation points), detecting the clamping force of foreign objects (sensitivity 0.5 N), etc.

[0060] Exemplarily, through each sensor array (sampling rate 1 kHz ± 10%), a holographic perception of the multi-dimensional motion state of the elevator is realized, and a multi-source data pool including mechanical vibration, motion trajectory, and environmental parameters is constructed to provide a complete input for state analysis.

[0061] Step S20, perform preset processing on the multi-dimensional sensor data to obtain data to be analyzed;

[0062] Furthermore, after obtaining the multi-dimensional sensor data, the multi-dimensional sensor data can be subjected to preset processing to obtain data to be analyzed.

[0063] Exemplarily, the step of performing preset processing on the multi-dimensional sensor data to obtain data to be analyzed includes:

[0064] Perform at least one of signal conversion, noise filtering, and feature extraction on the multi-dimensional sensor data to obtain initial processed data;

[0065] Screen the initial processed data according to preset rules to obtain the data to be analyzed.

[0066] Exemplarily, the multi-dimensional sensor data collected by each sensor array usually needs to be converted into a standardized data format, which can solve the compatibility problem of sensor heterogeneous data. During the noise filtering process, time-frequency domain joint processing is used to suppress environmental interference (such as building vibration noise, electromagnetic interference) and increase the proportion of effective signals. Time-domain / frequency-domain features (such as kurtosis, FFT peak value) that can characterize the device state are extracted from high-dimensional data to achieve data dimensionality reduction. The original multi-dimensional sensor data is converted into a standard input format suitable for machine learning models while retaining as much effective information as possible.

[0067] Exemplarily, the preset rules in the embodiments of the present application are a set of decision logics including at least one of threshold conditions (such as acceleration > 3g), statistical conditions (such as continuous overrun 5 times), and correlation conditions (multi-sensor data consistency). The threshold conditions are updated through a dynamic threshold algorithm, and a sensor topology correlation matrix (for example, correlation coefficient > 0.8) is constructed through null correlation analysis. Thereby, most of the invalid data can be filtered out, the data overhead caused by continuous reporting of normal data can be reduced, and at the same time, it is ensured to avoid missed reports of key events.

[0068] Step S30: Send the data to be analyzed to the cloud server for the cloud server to analyze the data to be analyzed based on a preset multi-modal fusion analysis model, obtain a monitoring result, and perform hierarchical feedback according to the monitoring result.

[0069] Furthermore, after performing preset processing on the multi-dimensional sensor data to obtain the data to be analyzed, the data to be analyzed can be sent to the cloud server for the cloud server to analyze the data to be analyzed based on a preset multi-modal fusion analysis model, obtain a monitoring result, and perform hierarchical feedback according to the monitoring result.

[0070] Exemplarily, the elevator sends the data to be analyzed to the cloud server through a gateway.

[0071] Exemplarily, the multi-modal fusion analysis model is a hybrid neural network architecture integrating vibration spectrum (processed by CNN), motion trajectory (processed by LSTM), and topological association (processed by GNN) for feature-level information fusion. Spatiotemporal feature extraction includes capturing the spatial distribution and temporal evolution law of sensor data through a 3D convolution kernel (size 5×5×3). Temporal analysis includes using a bidirectional LSTM unit (hidden layer dimension 128) to model the dependence relationship of feature vectors on the time axis. The feature vector includes a 128-dimensional floating-point array after dimensionality reduction (normalized to the interval [-1,1]) and is used to represent the core features of the elevator operation state. For example, when processing car door vibration data, the model extracts the vibration propagation phase difference at different positions of the door panel through 3D-CNN, combines Bi-LSTM to analyze the integral trajectory of the X-axis acceleration, and outputs a 128-dimensional vector containing 32 spatial features + 96 temporal features.

[0072] Exemplarily, the pre-stored fault feature map in the embodiments of the present application includes a feature vector database of more than 2,000 historical fault cases (including 9 standard fault modes), and clustering centers are established according to fault types. Similarity matching includes quantifying the feature correlation degree through cosine similarity (threshold > 0.85) or dynamic time warping distance (DTW < 1.2). The matching degree data is a structured similarity quantification result (numerical range 0-1), and the three most likely candidate fault types are marked, associating real-time features with historical experience knowledge to achieve rapid fault mode identification. For example, when the cosine similarity between the real-time feature vector and the center of the "guide rail wear" category (ID: FLT-203) in the map reaches 0.91 and the DTW distance is 0.78, the matching degree data {fault type: FLT-203, confidence: 0.89, ranking: 1} is generated.

[0073] Exemplarily, the preset matching degree threshold is a dynamically adjustable judgment boundary (benchmark value 0.85 ± 0.1), which can be intelligently adjusted in combination with the elevator operating state (speed / load). By implementing a three-level logical judgment (threshold interval division) and combining a voting mechanism (3 / 5 majority decision), the reliability of the result can be improved. The monitoring result includes a structured diagnostic conclusion, such as including fault type, confidence, risk level, recommended measures, etc. For example, when the matching degree data is 0.87 (the compensation threshold corresponding to a speed of 2 m / s is 0.85 × 1.1 = 0.935), it enters the pending observation state because the threshold requirement is not met; after the matching degree > 0.93 for three consecutive times, a secondary alarm is triggered, and the diagnostic conclusion of "early wear of the door wheel bearing" (confidence 88%) is pushed.

[0074] Exemplarily, in the embodiments of the present application, the fault probability is denoted as P. When the fault probability P ∈ [30%, 70%), that is, the fault probability is in the first interval, representing a potential risk state, at this time, a first-level early warning is triggered, and continuous observation is required but no immediate intervention is needed. A monitoring log is generated according to the monitoring result and stored. The monitoring log includes a structured record file (including timestamp, sensor snapshot, feature vector), which is used for retrospective analysis after the event. A dual mechanism of local encrypted storage (retention period 72h ± 10%) and cloud cold storage (retention period 3 years) can be adopted.

[0075] Exemplarily, when the fault probability P ∈ [70%, 90%), that is, the fault probability is in the second interval, representing an impending preventable fault, at this time, a secondary alarm is triggered, a monitoring report is generated according to the monitoring result, and the monitoring report is pushed to the maintenance system. The monitoring report can include a structured document of fault type, positioning coordinates (±0.5 m), and maintenance suggestions (in PDF / JSON format). The maintenance system is a SaaS platform for integrated work order management, personnel scheduling, and spare parts inventory, and can perform maintenance on the elevator according to the monitoring report.

[0076] Exemplarily, when the failure probability P≥90%, that is, the failure probability is in the third interval, which represents an immediate dangerous state. At this time, a three-level emergency stop is triggered, and an emergency stop control instruction is sent to the elevator according to the monitoring result, so that the elevator executes an emergency stop according to the emergency stop control instruction. The emergency stop control instruction needs to conform to the CANopen protocol instruction of the EN 81-20 standard, and the elevator control system starts the safety brake within 300 ms according to the emergency stop control instruction.

[0077] In this embodiment, through the above solution, specifically by obtaining multi-dimensional sensor data, where the multi-dimensional sensor data includes acceleration sensor data and vibration sensor data; performing preset processing on the multi-dimensional sensor data to obtain data to be analyzed; sending the data to be analyzed to the cloud server for the cloud server to analyze the data to be analyzed based on a preset multi-modal fusion analysis model to obtain a monitoring result, and performing hierarchical feedback according to the monitoring result. The elevator can be monitored in real time through multi-dimensional sensor data, and it can be timely identified whether there is a fault in the elevator operation, and / or the fault type of the elevator can be accurately identified, thereby improving the real-time performance, accuracy and predictability of the elevator operation fault monitoring, and further contributing to improving the safety of the elevator.

[0078] 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 first embodiment can be referred to the above introduction and will not be repeated hereinafter. On this basis, please refer to Figure 2 , the fault monitoring method based on artificial intelligence further includes steps A10 to A30:

[0079] A10: Receive the data to be analyzed sent by the elevator, where the data to be analyzed is obtained by the elevator by obtaining multi-dimensional sensor data and performing preset processing on the multi-dimensional sensor data, and the multi-dimensional sensor data includes acceleration sensor data and vibration sensor data;

[0080] Specifically, the fault monitoring method based on artificial intelligence in the embodiment of the present application is applied to the cloud server, and the cloud server can interact with the elevator for data. Sensor arrays are installed at various positions of the elevator, and multi-dimensional sensor data can be collected in real time through the sensor arrays.

[0081] Exemplarily, an acceleration sensor array is installed at the car door guide rail of the elevator, and acceleration sensor data can be collected through the acceleration sensor array. The X / Y / Z three-axis linear acceleration values are collected through MEMS or piezoelectric sensors, which can reflect the elevator motion state and impact characteristics.

[0082] Exemplarily, a vibration sensor array is installed at the top of the car door of the elevator, and vibration sensor data can be collected through the vibration sensor array. An ICP-type sensor is used to obtain vibration signals in the frequency band of 20 - 5000 Hz, which can characterize the dynamic characteristics of mechanical components.

[0083] Exemplarily, through each sensor array (sampling rate 1 kHz ± 10%), holographic perception of the multi-dimensional motion state of the elevator is realized, and a multi-source data pool including mechanical vibration, motion trajectory, and environmental parameters is constructed to provide complete input for state analysis.

[0084] Exemplarily, the multi-dimensional sensor data collected by each sensor array usually needs to be converted into a standardized data format, thereby solving the compatibility problem of heterogeneous sensor data. During the noise filtering process, time-frequency domain joint processing is used to suppress environmental interference (such as building vibration noise, electromagnetic interference), and the proportion of effective signals is increased. Time-domain / frequency-domain features (such as kurtosis, FFT peak value) that can characterize the device state are extracted from the high-dimensional data to achieve data dimensionality reduction. The original multi-dimensional sensor data is converted into a standard input format suitable for machine learning models while retaining as much effective information as possible.

[0085] Exemplarily, the preset rules in the embodiments of the present application are a set of decision logics including at least one of threshold conditions (such as acceleration > 3g), statistical conditions (such as continuous overrun 5 times), and correlation conditions (multi-sensor data consistency). The threshold conditions are updated through a dynamic threshold algorithm, and a sensor topology correlation matrix (for example, correlation coefficient > 0.8) is constructed through null correlation analysis. Most of the invalid data can be filtered out in this way, reducing the data overhead caused by continuous reporting of normal data, and at the same time ensuring that key events are not missed.

[0086] Exemplarily, the cloud server receives the data to be analyzed sent by the elevator through the gateway, and then analyzes the data to be analyzed to obtain a monitoring result.

[0087] A20: Analyze the data to be analyzed based on a preset multi-modal fusion analysis model to obtain a monitoring result;

[0088] Furthermore, after receiving the data to be analyzed, the cloud server can analyze the data to be analyzed based on a preset multi-modal fusion analysis model to obtain a monitoring result.

[0089] Exemplarily, the step of analyzing the data to be analyzed based on a preset multi-modal fusion analysis model to obtain a monitoring result includes:

[0090] Extract spatio-temporal features and perform temporal sequence analysis on the data to be analyzed through the multi-modal fusion analysis model to obtain a feature vector;

[0091] Perform similarity matching between the feature vector and a pre-stored fault feature map to obtain matching degree data;

[0092] Compare the matching degree data with a preset matching degree threshold to obtain the monitoring result corresponding to the matching degree data.

[0093] Exemplarily, the multi-modal fusion analysis model is a hybrid neural network architecture that integrates vibration spectrum (processed by CNN), motion trajectory (processed by LSTM), and topological association (processed by GNN) for feature-level information fusion. Spatiotemporal feature extraction includes capturing the spatial distribution and temporal evolution law of sensor data through a 3D convolutional kernel (with a size of 5×5×3). Temporal analysis includes using a bidirectional LSTM unit (with a hidden layer dimension of 128) to model the dependence relationship of the feature vector on the time axis. The feature vector includes a 128-dimensional floating-point array after dimensionality reduction (normalized to the interval [-1,1]), which is used to represent the core features of the elevator operation state. For example, when processing the vibration data of the car door, the model extracts the vibration propagation phase difference at different positions of the door panel through 3D-CNN, combines the Bi-LSTM to analyze the integral trajectory of the X-axis acceleration, and outputs a 128-dimensional vector containing 32 spatial features + 96 temporal features.

[0094] Exemplarily, the pre-stored fault feature map in the embodiments of the present application includes a feature vector database of more than 2000 historical fault cases (including 9 standard fault modes), and clustering centers are established according to fault types. Similarity matching includes quantifying the feature correlation degree through cosine similarity (threshold > 0.85) or dynamic time warping distance (DTW < 1.2). The matching degree data is a structured similarity quantification result (numerical range 0-1), which labels the three most likely candidate fault types, associates real-time features with historical experience knowledge, and realizes fast fault mode identification. For example, when the cosine similarity between the real-time feature vector and the center of the "guide rail wear" category (ID: FLT-203) in the map reaches 0.91 and the DTW distance is 0.78, matching degree data {fault type: FLT-203, confidence: 0.89, ranking: 1} is generated.

[0095] Exemplarily, the preset matching degree threshold is a dynamically adjusted judgment boundary (benchmark value 0.85 ± 0.1), which can be intelligently adjusted in combination with the elevator operation state (speed / load). By implementing a three-level logical judgment (threshold interval division) and combining a voting mechanism (3 / 5 majority decision), the reliability of the result can be improved. The monitoring result includes a structured diagnosis conclusion, such as including fault type, confidence, risk level, recommended measures, etc. For example, when the matching degree data is 0.87 (the compensation threshold corresponding to a speed of 2m / s is 0.85×1.1 = 0.935), it enters the pending observation state because the threshold requirement is not met; after the matching degree > 0.93 for 3 consecutive times, a secondary alarm is triggered, and a diagnosis conclusion of "early wear of the door wheel bearing" (confidence 88%) is pushed.

[0096] A30: Perform hierarchical feedback based on the monitoring results.

[0097] Furthermore, the cloud server analyzes the data to be analyzed based on a preset multimodal fusion analysis model. After obtaining the monitoring results, hierarchical feedback can be performed according to the monitoring results.

[0098] Exemplarily, the monitoring results include the fault type and / or the fault probability. The step of performing hierarchical feedback according to the monitoring results includes:

[0099] Trigger a first-level warning when the fault probability is in the first interval, generate a monitoring log according to the monitoring results, and store it;

[0100] Trigger a second-level alarm when the fault probability is in the second interval, generate a monitoring report according to the monitoring results, and push the monitoring report to the maintenance system;

[0101] Trigger a third-level emergency stop when the fault probability is in the third interval, send an emergency stop control instruction to the elevator according to the monitoring results, so that the elevator executes an emergency stop according to the emergency stop control instruction.

[0102] Exemplarily, in the embodiments of the present application, the fault probability is denoted as P. When the fault probability P ∈ [30%, 70%), that is, the fault probability is in the first interval, indicating a potential risk state. At this time, a first-level warning is triggered, and continuous observation is required but no immediate intervention is needed. A monitoring log is generated according to the monitoring results and stored. The monitoring log includes a structured record file (including a timestamp, a sensor snapshot, and a feature vector) for retrospective analysis afterwards. A dual mechanism of local encrypted storage (retention period 72h ± 10%) and cloud cold storage (retention period 3 years) can be adopted.

[0103] Exemplarily, when the fault probability P ∈ [70%, 90%), that is, the fault probability is in the second interval, indicating an impending preventable fault. At this time, a second-level alarm is triggered, a monitoring report is generated according to the monitoring results, and the monitoring report is pushed to the maintenance system. The monitoring report can include a structured document of the fault type, the positioning coordinates (±0.5m), and the maintenance suggestions (in PDF / JSON format). The maintenance system is a SaaS platform for integrated work order management, personnel scheduling, and spare parts inventory, and can perform maintenance on the elevator according to the monitoring report.

[0104] Exemplarily, when the failure probability P≥90%, that is, the failure probability is in the third interval, which represents an immediate dangerous state, a three-level emergency stop is triggered at this time. According to the monitoring results, an emergency stop control instruction is sent to the elevator so that the elevator executes an emergency stop according to the emergency stop control instruction. The emergency stop control instruction needs to conform to the CANopen protocol instruction of the EN 81-20 standard. The elevator control system starts the safety brake within 300 ms according to the emergency stop control instruction.

[0105] It should be noted that in other embodiments, the division of the first interval, the second interval, and the third interval can be determined according to the actual situation, and the embodiments of the present application do not specifically limit this.

[0106] Through the hierarchical feedback mechanism, through precise interval division, reliable instruction transmission, and intelligent disposal strategies, the elevator safety accident rate can be effectively reduced, and at the same time, the labor cost of maintenance can be reduced, achieving a double breakthrough in safety and economy.

[0107] In this embodiment, through the above solution, specifically, the cloud server receives the data to be analyzed sent by the elevator. Among them, the data to be analyzed is obtained by the elevator acquiring multi-dimensional sensor data and performing preset processing on the multi-dimensional sensor data. The multi-dimensional sensor data includes acceleration sensor data and vibration sensor data; based on a preset multi-modal fusion analysis model, the data to be analyzed is analyzed to obtain a monitoring result; according to the monitoring result, hierarchical feedback is performed. The elevator can be monitored in real time through the multi-modal fusion analysis model, and whether there is a fault in the elevator operation can be identified in time, and / or the fault type of the elevator can be accurately identified, so as to improve the real-time performance, accuracy, and predictability of the elevator operation fault monitoring, and further contribute to improving the safety of the elevator.

[0108] It should be noted that the above examples are only for understanding the present application and do not constitute a limitation on the fault monitoring method based on artificial intelligence of the present application. Based on this technical concept, more forms of simple transformations are within the protection scope of the present application.

[0109] The present application also provides a fault monitoring device based on artificial intelligence. Please refer to Figure 3 , the device is applied to an elevator and includes:

[0110] An acquisition module 10, configured to acquire multi-dimensional sensor data, where the multi-dimensional sensor data includes acceleration sensor data and vibration sensor data;

[0111] A processing module 20, configured to perform preset processing on the multi-dimensional sensor data to obtain data to be analyzed;

[0112] A sending module 30, configured to send the data to be analyzed to a cloud server, so that the cloud server analyzes the data to be analyzed based on a preset multimodal fusion analysis model to obtain a monitoring result, and performs hierarchical feedback according to the monitoring result.

[0113] The fault monitoring device based on artificial intelligence provided by the present application adopts the fault monitoring method based on artificial intelligence in the above embodiment, and can solve the technical problem of elevator operation fault monitoring. Compared with the prior art, the beneficial effects of the fault monitoring device based on artificial intelligence provided by the present application are the same as those of the fault monitoring method based on artificial intelligence provided by the above embodiment, and other technical features in the fault monitoring device based on artificial intelligence are the same as the features disclosed in the above embodiment method, and will not be described in detail here.

[0114] The present application provides a fault monitoring device based on artificial intelligence. The 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 fault monitoring method based on artificial intelligence in Embodiment 1 above.

[0115] The following refers to Figure 4 , which shows a schematic structural diagram of a fault monitoring device based on artificial intelligence suitable for implementing the embodiments of the present application. The fault 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), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The fault monitoring device based on artificial intelligence shown is only an example, and should not impose any limitation on the functions and usage scope of the embodiments of the present application.

[0116] As Figure 4As shown, the artificial intelligence-based fault monitoring device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which may 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 artificial intelligence-based fault monitoring device 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. An 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 touch pad, 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: Liquid Crystal Display), 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 may allow the artificial intelligence-based fault monitoring device to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows an artificial intelligence-based fault monitoring device having various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or had alternatively.

[0117] Particularly, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device, or installed from the storage device 1003, or installed from the read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are executed.

[0118] The artificial intelligence-based fault monitoring device provided by the present application adopts the artificial intelligence-based fault monitoring method in the above-mentioned embodiment and can solve the technical problem of elevator operation fault monitoring. Compared with the prior art, the beneficial effects of the artificial intelligence-based fault monitoring device provided by the present application are the same as those of the artificial intelligence-based fault monitoring method provided by the above-mentioned embodiment, and other technical features in the artificial intelligence-based fault monitoring device are the same as those disclosed in the method of the previous embodiment, which will not be elaborated here.

[0119] It should be understood that each part disclosed in this 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.

[0120] As described above, the above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0121] This 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 artificial intelligence-based fault monitoring method in the above embodiments.

[0122] 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 by any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0123] The above computer-readable storage medium can be included in the artificial intelligence-based fault monitoring device; it can also exist separately and not be assembled into the artificial intelligence-based fault monitoring device.

[0124] The above computer-readable storage medium carries one or more programs, which, when executed by an artificial intelligence-based fault monitoring device, cause the artificial intelligence-based fault monitoring device to: obtain multi-dimensional sensor data, where the multi-dimensional sensor data includes acceleration sensor data and vibration sensor data; perform preset processing on the multi-dimensional sensor data to obtain data to be analyzed; send the data to be analyzed to a cloud server for the cloud server to analyze the data to be analyzed based on a preset multi-modal fusion analysis model to obtain a monitoring result, and perform hierarchical feedback according to the monitoring result. The elevator can be monitored in real time through multi-dimensional sensor data, and whether there is a fault in the elevator operation can be identified in a timely manner, and / or the fault type of the elevator can be accurately identified, so as to improve the real-time performance, accuracy and predictability of elevator operation fault monitoring, and further contribute to improving the safety of the elevator.

[0125] Computer program code for performing the operations of the present application may be written in one or more programming languages or combinations thereof. The 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 may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone 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 may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., by using an Internet service provider to connect through the Internet).

[0126] 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 the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing a 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 consecutive blocks shown 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 that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0127] The modules described in the embodiments of the present 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.

[0128] The readable storage medium provided by the present application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned artificial intelligence-based fault monitoring method, and can solve the technical problem of elevator operation fault monitoring. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as those of the artificial intelligence-based fault monitoring method provided by the above embodiments, and will not be elaborated here.

[0129] The present application also provides a computer program product, including a computer program, and the steps of the artificial intelligence-based fault monitoring method as described above are implemented when the computer program is executed by a processor.

[0130] The computer program product provided by the present application can solve the technical problem of elevator operation 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 fault monitoring method provided by the above embodiments, and will not be elaborated here.

[0131] The above are only some embodiments of the present application, and do not limit the patent scope of the present application accordingly. All equivalent structural transformations made under the technical concept of the present application by using the content of the specification and drawings of the present application, or directly / indirectly applied in other related technical fields, are included in the patent protection scope of the present application.

Claims

1. A fault monitoring method based on artificial intelligence, characterized in that, The method is applied to an elevator and includes: Obtaining multi-dimensional sensor data, where the multi-dimensional sensor data includes acceleration sensor data and vibration sensor data; Performing preset processing on the multi-dimensional sensor data to obtain data to be analyzed; Sending the data to be analyzed to a cloud server for the cloud server to analyze the data to be analyzed based on a preset multi-modal fusion analysis model to obtain a monitoring result and perform hierarchical feedback according to the monitoring result.

2. The fault monitoring method based on artificial intelligence according to claim 1, wherein The step of obtaining multi-dimensional sensor data includes: Collecting the acceleration sensor data through an acceleration sensor array located at the car door guide rail of the elevator; Collecting the vibration sensor data through a vibration sensor array located at the top of the car door of the elevator; Wherein, the acceleration sensor data includes a door machine movement acceleration signal in the X-axis direction, a guide rail vibration acceleration signal in the Y-axis direction, and a car displacement acceleration signal in the Z-axis direction.

3. The fault monitoring method based on artificial intelligence according to claim 1, wherein The step of performing preset processing on the multi-dimensional sensor data to obtain data to be analyzed includes: Performing at least one of signal conversion, noise filtering, and feature extraction on the multi-dimensional sensor data to obtain initial processed data; Screening the initial processed data according to a preset rule to obtain the data to be analyzed.

4. A fault monitoring method based on artificial intelligence, characterized in that, The method is applied to a cloud server and includes: Receiving data to be analyzed sent by an elevator, where the data to be analyzed is obtained by the elevator by obtaining multi-dimensional sensor data and performing preset processing on the multi-dimensional sensor data, and the multi-dimensional sensor data includes acceleration sensor data and vibration sensor data; Analyzing the data to be analyzed based on a preset multi-modal fusion analysis model to obtain a monitoring result; Performing hierarchical feedback according to the monitoring result.

5. The fault monitoring method based on artificial intelligence according to claim 4, wherein The step of analyzing the data to be analyzed based on a preset multi-modal fusion analysis model to obtain a monitoring result includes: Performing spatio-temporal feature extraction and time series analysis on the data to be analyzed through the multi-modal fusion analysis model to obtain a feature vector; Performing similarity matching between the feature vector and a pre-stored fault feature map to obtain matching degree data; Comparing the matching degree data with a preset matching degree threshold to obtain a monitoring result corresponding to the matching degree data.

6. The fault monitoring method based on artificial intelligence according to claim 4, characterized in that, The monitoring result includes a fault type and / or a fault probability, and the step of performing hierarchical feedback according to the monitoring result includes: Triggering a first-level warning when the fault probability is in a first interval, generating a monitoring log according to the monitoring result and storing it; Triggering a second-level alarm when the fault probability is in a second interval, generating a monitoring report according to the monitoring result, and pushing the monitoring report to a maintenance system; Triggering a third-level emergency stop when the fault probability is in a third interval, sending an emergency stop control instruction to the elevator according to the monitoring result so that the elevator executes an emergency stop according to the emergency stop control instruction.

7. A fault monitoring device based on artificial intelligence, characterized in that, The device is applied to an elevator and includes: An obtaining module for obtaining multi-dimensional sensor data, where the multi-dimensional sensor data includes acceleration sensor data and vibration sensor data; A processing module for performing preset processing on the multi-dimensional sensor data to obtain data to be analyzed; A sending module for sending the data to be analyzed to a cloud server for the cloud server to analyze the data to be analyzed based on a preset multi-modal fusion analysis model to obtain a monitoring result and perform hierarchical feedback according to the monitoring result.

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

Images