CN118255227A

CN118255227A - Elevator state early warning system based on sensor data acquisition and AI algorithm

Info

Publication number: CN118255227A
Application number: CN202410517390.3A
Authority: CN
Inventors: 陈爽; 孙长安; 国玉刚; 朱瑞祺; 李旭东; 韩昭瑞
Original assignee: Shandong Inspur Ultra HD Video Industry Co Ltd
Current assignee: Shandong Inspur Ultra HD Video Industry Co Ltd
Priority date: 2024-04-28
Filing date: 2024-04-28
Publication date: 2024-06-28

Abstract

The invention provides an elevator state early warning system based on sensor data acquisition and an AI algorithm, which relates to the technical field of elevator safety. The system monitors the tension, the abrasion degree and the running smoothness of the elevator rope in real time through various sensors. The sensor data is transmitted to the central processing unit in real time through the microcontroller and the analog-to-digital converter. The data processing module cleans, denoises and normalizes the data by using an advanced algorithm to provide accurate data for AI analysis. The AI algorithm module analyzes the data using machine learning and deep learning techniques, predicts faults, and alerts in advance. And the decision module is used for triggering early warning when an abnormality is found according to comparison of the analysis result and a preset safety threshold value. The feedback and early warning module provides real-time safety state update through a visual interface and an audible and visual alarm system operator and passengers, and ensures safe operation of the elevator.

Description

Elevator state early warning system based on sensor data acquisition and AI algorithm

Technical Field

The invention relates to the technical field of elevator safety, in particular to an elevator state early warning system based on sensor data acquisition and an AI algorithm.

Background

With the increasing number of urban high-rise buildings, elevators are becoming an important vertical vehicle, and their safety is receiving increasing attention. Elevator ropes are key load bearing members of an elevator, and the quality of the state of the elevator ropes directly affects the safe running of the elevator. Meanwhile, the smoothness of elevator operation is also an important index for measuring the performance and safety of the elevator. The traditional elevator safety detection and early warning system still has the following defects:

1. Real-time performance: conventional systems rely on manual periodic inspection or monitoring at fixed time intervals, limiting the frequency and timeliness of data collection. In the event of a fault or abnormality, the problem cannot be detected immediately because the system is not monitored in real time. This delay results in an inability to respond immediately to potential security threats in the data acquisition, increasing the risk of an incident.

2. Accuracy: traditional systems rely on simple threshold decisions or limited parameter analysis, lack complex data processing capabilities and in-depth analysis, resulting in false positives or false negatives. Without advanced AI algorithm support, the accuracy and reliability of data analysis are low, and the actual safety condition of the elevator is difficult to accurately judge, so that the effect of the whole safety management system is affected.

3. Intelligent: the traditional electric system requires more manual intervention in operation, is periodically checked and maintained manually, and has low intelligent degree. The labor cost is increased, and omission or mistakes of the safety check are caused by human factors. In addition, automatic data analysis and decision support functions are often lacking, and the continuously changing operating conditions or real-time updating of security policies cannot be automatically adapted.

4. Preventive: traditional systems favor post-processing rather than pre-prevention. In many cases, safety issues are identified only when an accident has occurred or is about to occur, and such a response method is not effective in preventing the occurrence of the accident.

Disclosure of Invention

An elevator state early warning system based on sensor data acquisition and AI algorithm comprises the following specific steps:

step S1: the sensor module comprises a plurality of sensors and can detect state data of the elevator rope, including rope tension, wear degree, broken wire number and the like; the elevator running smoothness data comprise acceleration, deceleration, vibration frequency and the like of an elevator;

Step S2: the data acquisition module is responsible for transmitting and storing the data acquired by the sensor module in real time.

Step S3: the data processing module utilizes a preprocessing algorithm to carry out cleaning, denoising and normalization operations on the acquired data.

Step S4: the AI algorithm module comprises a machine learning algorithm and a deep learning algorithm, and is used for carrying out feature extraction, classification and regression analysis on the processed data and mining hidden information and rules in the data.

Step S5: the decision module judges the safety state of the elevator according to the output result of the AI algorithm module and by combining a preset safety threshold value and a rule, and if the elevator has potential safety hazard, the feedback and early warning module is triggered.

Step S6: the feedback and early warning module is responsible for displaying and reminding the judgment result of the decision module in a visual interface, audible and visual alarm and other modes.

Further, in step S1, the sensor module includes a tension sensor, a wear detection sensor, and a broken wire detection sensor, which are used for detecting parameters such as tension, wear degree, and broken wire number of the elevator rope; meanwhile, the acceleration sensor, the deceleration sensor and the vibration frequency sensor evaluate the smoothness of the elevator operation.

Further, in step S2, the data acquisition module is responsible for transmitting and storing data from the sensor module in real time, which module ensures the integrity and accuracy of the data by means of the data acquisition device.

Further, in step S3, the data processing module uses an advanced preprocessing algorithm to perform cleaning, denoising and normalization processing on the collected data, and this step ensures that the processed data meets the requirements of AI algorithm analysis in quality, thereby improving the analysis accuracy and efficiency of the whole system.

Further, in step S4, the AI algorithm module integrates a machine learning algorithm and a deep learning algorithm, and performs feature extraction, classification and regression analysis on the data output from the data processing module.

Further, in step S5, the decision module determines the safety state of the elevator according to the analysis result of the AI algorithm module and by combining with a preset safety threshold and rule, and when a potential safety hazard is detected, the feedback and early warning module is automatically triggered to realize response.

Further, in step S6, the feedback and early warning module is responsible for displaying and reminding the result of the decision module to related personnel through the visual interface and the audible and visual alarm system, and the module supports data interfacing with the upper management system.

Compared with the prior art, the invention has the following advantages:

1. Real-time performance: the system ensures the timeliness of information by acquiring the detection state data of the elevator rope and the elevator running smoothness data in real time. The real-time nature allows the system to immediately detect any anomalies or deviations from normal operation, allowing immediate action to be taken, reducing potential threats to passenger safety.

2. Accuracy: the system can provide high-accuracy safety state judgment by utilizing an AI algorithm to process and analyze the acquired data. The AI algorithm can identify complex patterns and trends, reducing errors and limitations of human judgment. The fault diagnosis precision is improved, and the prevention measures and maintenance activities are ensured to be based on reliable data analysis, so that the overall safety management effect is improved.

3. Intelligent: the intelligent management of the system means that all steps from data acquisition to processing, decision making and feedback pre-warning can be automatically performed. The automation reduces the requirement of manual operation and reduces the risk of causing safety problems due to human errors. The intelligent system can continuously monitor and learn, continuously optimize the performance and response strategy of the system along with the time, and provide more accurate safety guarantee.

4. Preventive: the preventive function of the system can timely discover potential safety hazards before the elevator breaks down through a real-time monitoring and early warning mechanism. Early diagnosis and intervention can significantly reduce the possibility of accidents and avoid personnel injury or significant property loss caused by elevator faults. By preventing, rather than merely responding, the system improves the safety of the elevator, while also extending the service life and operating efficiency of the elevator installation.

Drawings

Fig. 1 is a schematic structural diagram of an elevator safety status judgment and early warning system according to the present invention;

FIG. 2 is a schematic diagram of a sensor module implementation strategy according to the present invention;

FIG. 3 is a flow chart of the data acquisition module, the data processing module, the AI algorithm module and the decision module of the present invention.

Detailed Description

The subject matter described herein will now be discussed with reference to example embodiments. It should be appreciated that these embodiments are discussed only to enable a person skilled in the art to better understand and thereby practice the subject matter described herein, and are not limiting of the scope, applicability, or examples set forth in the claims. Changes may be made in the function and arrangement of elements discussed without departing from the scope of the disclosure as set forth in the specification. Various examples may omit, replace, or add various procedures or components as desired. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. In addition, features described with respect to some examples may be combined in other examples as well.

As used herein, the term "comprising" and variations thereof mean open-ended terms, meaning "including, but not limited to. The term "based on" means "based at least in part on". The terms "one embodiment" and "an embodiment" mean "at least one embodiment. The term "another embodiment" means "at least one other embodiment". The terms "first," "second," and the like, may refer to different or the same object. Other definitions, whether explicit or implicit, may be included below. Unless the context clearly indicates otherwise, the definition of a term is consistent throughout this specification.

Examples

In step S1, the sensor module implements elevator safety monitoring by integrating a plurality of high-precision sensors. Tension sensors are used to monitor the tension level of the elevator rope and wear sensors and wire break detection sensors are used to evaluate the wear level and the number of wire breaks of the elevator rope. In addition, in order to evaluate the running smoothness of the elevator, an acceleration sensor, a deceleration sensor, and a vibration frequency sensor are installed. The sensors collect data in real time and provide necessary safety information in time by accurately measuring the physical state of the elevator rope and the dynamic performance of elevator operation. The sensor is installed at the elevator car and rope tie point, and real-time supervision and pass through wireless network with data transmission to central processing system, this system real-time analysis data ensures the safe and high-efficient operation of elevator.

In step S2, the data acquisition module realizes real-time transmission and storage of sensor data by adopting efficient data acquisition equipment and communication technology. The data acquisition module comprises a microcontroller and an analog-to-digital converter, these devices being connected to each sensor, responsible for collecting the analog signals output by the sensors and converting them into digital format. These digital data are then transmitted to the central processing unit via a stable communication interface. In addition, to ensure the integrity and security of the data, the collected data may be encrypted in real time and uploaded to a cloud storage or local server. All elevator sensor data is centrally processed and stored in a security server at the site, allowing a system administrator to remotely monitor the operating conditions of the elevator, while the data supports real-time analysis and historical performance assessment to optimize elevator maintenance and operation.

In step S3, the data processing module cleans, denoises and normalizes the acquired data by using advanced preprocessing algorithms to optimize data quality and prepare for subsequent AI analysis. The abnormal value and noise in the data are automatically identified and removed by utilizing a software algorithm, and the method relates to a statistical analysis method, a Kalman filter and a moving average filter. The normalization processing is to adjust the data scale to make the data of different sources have uniform proportion and range, thereby enhancing the processing efficiency and accuracy of the algorithm. The data processing module periodically receives a large amount of data collected from the elevator sensors and then automatically performs a data cleansing and normalization process to ensure that the data delivered to the AI module is accurate and consistent.

In step S4, the method is implemented by integrating a plurality of machine learning and deep learning algorithms, which can perform complex analysis on the preprocessed data, including feature extraction, classification and regression analysis. This module uses a support vector machine to classify whether the elevator is operating properly and uses a deep neural network to predict future wear of elevator components. The AI algorithm module is configured to periodically receive the cleaned and normalized data from the data processing module and then automatically detect possible abnormal patterns and trends using a deep learning algorithm. By continuously learning elevator operation data, the system can discover potential faults and pre-warn before the problem becomes a serious fault, thereby performing maintenance in advance.

In step S5, the decision module integrates the analysis result of the AI algorithm module with a preset safety threshold and rule to realize the safety state judgment of the elevator. The system uses the data output received from the AI algorithm module to compare the wear level or abnormal running index of the elevator rope with a preset safety threshold. If the data show that any parameter exceeds the safety threshold, the vibration frequency of the elevator is abnormally increased, and the decision module can automatically trigger the early warning system. The decision-making module is responsible for monitoring the running state of the elevator in real time, and immediately activating an audible and visual alarm and notifying a maintenance team to check when potential risks such as abnormal acceleration or deceleration are detected.

In step S6, the feedback and early warning module displays and reminds maintenance personnel and user of the safety state of the elevator by implementing a comprehensive warning system including a visual interface and an audible and visual warning device. The module is configured to receive the safety alert information from the decision module and then provide immediate feedback to the operator and passengers via the LED display screen and the alert system on the elevator control panel. The elevator system comprises an integrated display screen for displaying in real time the operating status and safety warning of the elevator. Upon detection of a security problem, such as a door failure or overload, the system automatically triggers an audible and visual warning, ensuring that passengers and technicians respond quickly.

The specific module implementation conditions of the invention are as follows:

a) Realization of the sensor module: and a high-precision and high-stability sensor such as a tension sensor, a Hall sensor, an acceleration sensor and the like is selected for real-time acquisition of detection state data of the elevator rope and elevator running smoothness data. Meanwhile, the layout and the installation mode of the sensor are considered so as to ensure the accuracy and the reliability of the acquired data.

B) The realization of the data acquisition module: and the data acquired by the sensor module is transmitted and stored in real time by adopting high-speed and high-stability data acquisition equipment. Meanwhile, compression and encryption technology of data are considered to ensure the security and integrity of the data.

C) Implementation of the data processing module: and the collected data is subjected to operations such as cleaning, denoising, normalization and the like by adopting various preprocessing algorithms, so that the subsequent AI algorithm processing and analysis are facilitated.

D) Realization of AI algorithm module: and selecting a proper machine learning algorithm and a proper deep learning algorithm according to actual requirements for data processing and analysis.

E) Implementation of the decision module: and carrying out decision judgment according to the output result of the AI algorithm module and a preset safety threshold value and rules. For example, safety indexes such as a tension threshold value, an abrasion threshold value and the like can be set, and an early warning mechanism is triggered when the actual detection value exceeds the threshold value; and simultaneously, a decision rule base is formulated by combining historical data and expert experience so as to improve the accuracy and reliability of decision.

F) And the feedback and early warning module is realized: and displaying the decision result to related personnel by adopting a visual interface, an audible and visual alarm and other modes, and providing corresponding operation suggestions and guidance. Meanwhile, the elevator safety state remote monitoring and management system is in butt joint and data sharing with an upper management system, so that the elevator safety state remote monitoring and management is realized.

The specific steps of the invention are as follows:

1. step one:

the key parts of the elevator rope and the elevator car are provided with layout sensors for monitoring the state of the elevator rope and the smoothness data of elevator operation in real time, and the main sensors comprise: when the elevator traction steel wire rope passes through the permanent magnet probe, a Hall sensor is selected to collect a change signal of a leakage magnetic field, and whether the elevator is damaged internally or not is judged, such as fatigue, rust, abrasion, wire breakage and the like; a photoelectric encoder is selected to determine the running position of the steel wire rope, and the specific conditions and corresponding positions of the equivalent broken wire number and equivalent abrasion loss of the steel wire rope are obtained in a data acquisition module; a tension sensor is selected to measure the tension of the elevator rope; and an acceleration sensor, a vibration sensor and a noise sensor are selected to monitor the running stability and the sound level of the elevator so as to judge whether the elevator parts are worn or damaged.

2. Step two:

The hardware layer of the data acquisition module adopts a microcontroller, an analog-to-digital converter, a storage device and an interface circuit to realize the tasks of analog-to-digital conversion, transmission, storage and quick access of the sensor output signals; the software layer develops drivers, data transmission protocols, data storage management and communication interfaces, etc. for each sensor. Through the cooperative work of the software and the hardware, the elevator state data is accurately and reliably collected in real time, and support is provided for subsequent data processing and decision making.

3. Step three:

The data processing module is mainly used for realizing the processing of data transmitted by the data acquisition module based on the field programmable gate array, and comprises the following main processing steps: adopting a filtering algorithm to reduce random errors and noise interference in the data; converting the data into the same dimension range by using a normalization algorithm, and eliminating dimension influence among different features; then, main component analysis and linear discriminant analysis are adopted to reduce the data dimension and retain main information; and finally, extracting signal characteristics based on Hilbert-Huang transformation, and constructing characteristic vectors, so that the subsequent AI algorithm module is convenient to process and analyze.

4. Step four:

And inputting different sensor source data processed by the data processing module into respective deep belief networks, extracting deep features, and then evaluating, predicting and classifying and identifying the elevator running state by using a deep learning algorithm and a support vector machine classifier. The AI algorithm module is integrated into an FPGA hardware accelerator of the elevator control system as an independent unit and is combined with a central processing unit of the control system to execute the prediction and classification recognition of the elevator state.

5. Step five:

The decision rule base and the safety threshold index are formulated by combining historical data and expert experience, and mainly comprise: the tension threshold value, the abrasion threshold value, the elevator running smoothness and the sound level of the elevator rope are preset. And carrying out decision judgment according to the output result of the AI algorithm module and a preset safety threshold and rule, and feeding back the decision result to the early warning module in real time through an interface circuit.

6. Step six:

Judging whether the elevator has potential safety hazard or not according to the output result of the AI algorithm module, and starting an early warning mechanism to feed back and early warn when necessary. The early warning information can send out an alarm in the elevator through an audible and visual alarm device or a visual interface, and can be sent to a manager or a maintenance person through a remote communication module.

It will be appreciated by those skilled in the art that various changes and modifications can be made to the embodiments disclosed above without departing from the spirit of the invention. Accordingly, the scope of the invention should be limited only by the attached claims.

It should be noted that not all the steps and units in the above-mentioned processes are necessary, and some steps or units may be omitted according to actual needs. The order of execution of the steps is not fixed and may be determined as desired. The apparatus structures described in the above embodiments may be physical structures or logical structures, that is, some units may be implemented by the same physical entity, or some units may be implemented by multiple physical entities, or may be implemented jointly by some components in multiple independent devices.

The detailed description set forth above describes exemplary embodiments, but does not represent all embodiments that may be implemented or fall within the scope of the claims. The term "exemplary" used throughout this specification means "serving as an example, instance, or illustration," and does not mean "preferred" or "advantageous over other embodiments. The detailed description includes specific details for the purpose of providing an understanding of the described technology. However, the techniques may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form in order to avoid obscuring the concepts of the described embodiments.

The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An elevator state early warning system based on sensor data acquisition and AI algorithm is characterized in that: the system comprises a sensor module, a data acquisition module, a data processing module, an AI algorithm module, a decision module and a feedback and early warning module;

step S2: the data acquisition module is responsible for transmitting and storing the data acquired by the sensor module in real time;

Step S3: the data processing module performs cleaning, denoising and normalization operations on the acquired data by utilizing a preprocessing algorithm;

Step S4: the AI algorithm module comprises a machine learning algorithm and a deep learning algorithm, and is used for carrying out feature extraction, classification and regression analysis on the processed data and mining hidden information and rules in the data;

Step S5: the decision module judges the safety state of the elevator according to the output result of the AI algorithm module and by combining a preset safety threshold value and a rule, and if the elevator has potential safety hazard, the feedback and early warning module is triggered;

2. The elevator status warning system based on sensor data acquisition and AI algorithm of claim 1, wherein: in step S1, the sensor module includes a tension sensor, a wear detection sensor, and a broken wire detection sensor, which are used for detecting parameters such as tension, wear degree, and broken wire number of the elevator rope; meanwhile, the acceleration sensor, the deceleration sensor and the vibration frequency sensor evaluate the smoothness of the elevator operation.

3. The elevator status warning system based on sensor data acquisition and AI algorithm of claim 1, wherein: in step S2, the data acquisition module is responsible for transmitting and storing data from the sensor module in real time.

4. The elevator status warning system based on sensor data acquisition and AI algorithm of claim 1, wherein: in step S3, the data processing module uses an advanced preprocessing algorithm to perform cleaning, denoising and normalization processing on the acquired data, and this step ensures that the processed data meets the requirements of AI algorithm analysis in quality.

5. The elevator status warning system based on sensor data acquisition and AI algorithm of claim 1, wherein: in step S4, the AI algorithm module integrates machine learning and deep learning algorithms, and performs feature extraction, classification and regression analysis on the data output from the data processing module.

6. The elevator status warning system based on sensor data acquisition and AI algorithm of claim 1, wherein: in step S5, the decision module determines the safety state of the elevator according to the analysis result of the AI algorithm module and in combination with a preset safety threshold and rule, and when a potential safety hazard is detected, the feedback and early warning module is automatically triggered.

7. The elevator status warning system based on sensor data acquisition and AI algorithm of claim 1, wherein: in step S6, the feedback and early warning module is responsible for displaying and reminding the result of the decision module to related personnel through the visual interface and the audible and visual alarm system, and the module supports data docking with the upper management system.