Monitoring system suitable for installing sensor on motor

By installing wireless vibration and sound sensors on the motor and combining them with the deep learning algorithm of the centralized control cloud platform system, automated AI fault diagnosis and prediction of multi-functional crane motors have been achieved, solving the problem of frequent equipment failures caused by motor aging and improving production safety and efficiency.

CN118900000APending Publication Date: 2024-11-05山东宏拓实业有限公司 +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411067918.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-11-05

AI Technical Summary

Technical Problem

As the service life of existing multi-functional overhead cranes increases, the motors age faster, and the lack of effective automated measurement and prediction devices leads to frequent equipment failures, affecting production safety and efficiency.

Method used

Wireless vibration and sound sensors are installed on the motor, and combined with a centralized control cloud platform system, deep learning algorithms are used to analyze the motor's vibration, sound, and temperature data to achieve automated AI fault diagnosis and prediction.

Benefits of technology

It enables accurate diagnosis of motor status and fault prediction, reduces the labor intensity of on-site measurement personnel, lowers production risks, and improves the automation level and safety of equipment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118900000A_ABST
    Figure CN118900000A_ABST
Patent Text Reader

Abstract

The invention provides a monitoring system suitable for installing a sensor on a motor, and relates to the technical field of motor monitoring, the monitoring system comprises a hardware unit and a centralized control cloud platform system, the hardware unit comprises a wireless vibration sensor, a sound sensor and a wireless communication module, the wireless vibration sensor and the sound sensor are both arranged on the motor, and the wireless communication module is connected with the wireless vibration sensor. The signal output end of the wireless vibration sensor is wirelessly connected with the centralized control cloud platform system; a wireless vibration sensor and a sound sensor are installed on a motor, vibration data and sound decibel data of the motor are collected, a control terminal synchronously connected to the motor collects motor temperature data, on the basis, a deep learning algorithm and a standard data large model are adopted for comparison verification, vibration types, sound types and temperature rise of the motor are analyzed, three-step verification is carried out, and the accuracy of the motor temperature rise is improved. The current state and the fault of the motor are inferred more accurately, automatic fault diagnosis is realized, the labor intensity of field measurement personnel is reduced, and the production risk is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of motor monitoring, and in particular to a monitoring system suitable for adding sensors to motors. Background Art

[0002] A multifunctional overhead crane is a heavy mechanical equipment that can perform multiple functions. It is usually composed of a body, a boom and a control system. It can bear a large load weight and is widely used in manufacturing, construction and metallurgical industries. Multifunctional overhead cranes are mainly used for tasks such as lifting, transportation and storage, such as lifting overweight objects (such as steel bars, concrete, etc.), transporting items from one place to another (such as machine components, ship parts, etc.), and storing important items in factories and commercial places (such as cars, steel plates, etc.). Its advantages are high safety, high efficiency and great flexibility. It can achieve remote control through an electric control system, avoiding the risk of workers operating from a height. At the same time, it can quickly move and transport items to improve work efficiency. With the increase of the service life of the multifunctional overhead crane, the aging degree of the motor is accelerated, especially the high-power motors in the main parts such as the air compressor, hydraulic station, and aluminum hook. Once damaged, it will not only cause huge economic losses to the company, but also seriously affect the normal production. At present, there is no practical automated measurement and prediction device, and it can only be measured manually by on-site personnel, which cannot play an effective monitoring role. The equipment has a low degree of automation and does not utilize safe production. Therefore, the present invention proposes a monitoring system suitable for adding sensors to motors to solve the problems existing in the prior art. Summary of the invention

[0003] In response to the above problems, the present invention proposes a monitoring system suitable for motors equipped with sensors. The monitoring system suitable for motors equipped with sensors performs three-step verification to infer the current status and faults of the motor more accurately, realizes automated AI fault diagnosis, reduces the labor intensity of on-site measurement personnel, and reduces production risks caused by abnormal equipment failures.

[0004] To achieve the purpose of the present invention, the present invention is implemented through the following technical solutions: a monitoring system suitable for adding sensors to motors, comprising a hardware unit and a centralized control cloud platform system, wherein the hardware unit comprises a wireless vibration sensor, a sound sensor and a wireless communication module, wherein the wireless vibration sensor and the sound sensor are both arranged on the motor, and the signal output end of the wireless vibration sensor is wirelessly connected to the centralized control cloud platform system, and the acquisition end of the wireless communication module is connected to the control terminal of the sound sensor and the motor, and is used to transmit the collected sound data and motor temperature data to the centralized control cloud platform system; The centralized control cloud platform system includes a data storage module, an AI diagnosis module and a mobile phone APP smart connection module. The data storage module is used to store data transmitted by wireless vibration sensors and wireless communication modules. The AI ​​diagnosis module has a built-in standard data model for analyzing the vibration category data of wireless vibration sensors, the sound type data of sound sensors and the temperature rise data of motors, and using deep learning algorithms for comparison and verification to infer the current state and faults of the motor, and perform fault prediction based on the current rotation state and historical data of the motor. The mobile phone APP smart connection module is used to connect to the mobile phone APP of the manager's mobile terminal to provide real-time access function.

[0005] Further improvements are: the wireless vibration sensor adopts an energy collection module to convert the vibration energy of the motor into electrical energy for self-powering. The wireless vibration sensor has a built-in accelerometer and communication chip for real-time collection of the vibration frequency, displacement, speed, and acceleration data of the motor, and transmits it wirelessly to the centralized control cloud platform system.

[0006] Further improvements are: the wireless vibration sensor and sound sensor both adopt a modular design, and the wireless vibration sensor and sound sensor are both installed on the motor through quick-release adhesive parts, and the wireless communication module adopts low-power wide area network LPWAN technology, including LoRa and NB-IoT.

[0007] A further improvement is that the data storage module includes a collection unit, a storage unit and a retrieval channel, the collection unit is used to wirelessly connect to the wireless vibration sensor and the signal output end of the wireless communication module to collect the transmitted data, the storage unit is used to store the transmitted data and add a time stamp, and the retrieval channel is a human-computer interaction channel, which provides keyword retrieval and time stamp retrieval functions for stored data.

[0008] Further improvements are: the AI ​​diagnosis module includes a standard data large model, a deep learning comparison module and a fault prediction module; the standard data large model includes a vibration data module, a sound data model and a temperature sensing data model; the vibration data model includes all relevant vibration frequency, displacement, speed, and acceleration standard data under motor imbalance, misalignment, rotor eccentricity, friction, shaft bending, mechanical looseness, gear failure, and abnormal vibration; the sound data model includes all relevant sound types and frequency decibel standard data under motor imbalance, misalignment, rotor eccentricity, friction, shaft bending, mechanical looseness, gear failure, and abnormal vibration; and the temperature sensing data model is used to store temperature rise data of the motor under various abnormal conditions.

[0009] Further improvements are as follows: the deep learning comparison module has a built-in AI deep learning algorithm, which is used to extract the data collected by the current wireless vibration sensor, sound sensor and the motor temperature data collected by the wireless communication module from the data storage module and input them into the standard data large model for one-by-one comparison and demonstration. First, the data of relevant vibration frequency, displacement, velocity and acceleration are compared and judged, and then the relevant sound type and frequency decibel standard data are compared and judged for secondary verification. Finally, the motor temperature rise data is analyzed to diagnose whether the equipment has imbalance, misalignment, rotor eccentricity, friction, shaft bending, mechanical looseness, gear failure, motor vibration, and abnormal temperature rise. When no of the above faults are found in the three comparisons, the motor is judged to be normal.

[0010] Further improvements are: the fault prediction module is connected to the data storage module, statistics are collected currently and historical data, the data collected by the wireless vibration sensor, sound sensor and motor temperature data are listed as a line graph, the data change trend and the change in equal time intervals are evaluated, so as to predict the type of faults that may occur in the motor in the future and the time of occurrence.

[0011] Further improvements are: the fault prediction module is connected to the after-sales service desk of the official website engineer of the motor equipment through the Internet, and is used to output the line graph as a change report to the after-sales service desk for manual inspection by engineers. When abnormal change trends appear in the parameters, the after-sales service desk connects to the mobile phone APP intelligent connection module to notify the management personnel.

[0012] A further improvement is that the mobile phone APP smart connection module includes an identity authentication module and a data synchronization module. The identity authentication module uses fingerprints and 3D faces to identify the identity of the manager. After the verification is passed, the manager is granted login and data management permissions.

[0013] A further improvement is that the data synchronization module is used to link data with the mobile phone APP of the manager's mobile terminal, synchronize the motor equipment operating status and fault warning information to the mobile phone APP for real-time display, and at the same time connect to the motor's control terminal to provide the manager with the function of emergency control of the motor.

[0014] The beneficial effects of the present invention are: 1. The present invention installs wireless vibration sensors and sound sensors on the motor to collect the vibration frequency, displacement, speed, acceleration data and sound decibel data of the motor, and synchronously accesses the control terminal of the motor to collect the motor temperature data. Based on this, a deep learning algorithm is used to compare and verify with a large standard data model to analyze the vibration category, sound type and temperature rise of the motor. Through these three-step verification, the current state and fault of the motor are inferred more accurately, realizing automated AI fault diagnosis, reducing the labor intensity of on-site measurement personnel, and reducing production risks caused by abnormal equipment failures.

[0015] 2. The present invention summarizes the real-time and historical data collected by wireless vibration sensors, sound sensors, and motor temperature data into a line graph, evaluates the data change trend and the change in equal time intervals, thereby predicting the type and time of possible motor failures in the future, predicting equipment failures in advance, and reducing the loss of high-power motors.

[0016] 3. The present invention establishes a unique centralized control cloud platform system, which can be directly accessed by the mobile phone APP of the manager's mobile terminal, so as to facilitate and quickly obtain information for investigation and processing, and has diversified functions. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a composition diagram of the present invention. DETAILED DESCRIPTION

[0018] In order to deepen the understanding of the present invention, the present invention will be further described in detail below in conjunction with examples. The examples are only used to explain the present invention and do not constitute a limitation on the protection scope of the present invention.

[0019] Embodiment 1 according to Figure 1 As shown, this embodiment proposes a monitoring system suitable for adding sensors to motors, including a hardware unit and a centralized control cloud platform system, wherein the hardware unit includes a wireless vibration sensor, a sound sensor and a wireless communication module, wherein the wireless vibration sensor and the sound sensor are both arranged on the motor, and the signal output end of the wireless vibration sensor is wirelessly connected to the centralized control cloud platform system, and the acquisition end of the wireless communication module is connected to the sound sensor and the control terminal of the motor, and is used to transmit the collected sound data and motor temperature data to the centralized control cloud platform system; The centralized control cloud platform system includes a data storage module, an AI diagnosis module and a mobile phone APP intelligent connection module. The data storage module is used to store data transmitted by wireless vibration sensors and wireless communication modules. The AI ​​diagnosis module has a built-in standard data large model for analyzing the vibration category data of wireless vibration sensors, the sound type data of sound sensors and the temperature rise data of motors, and using deep learning algorithms for comparison and verification, so as to infer the current state and fault of the motor, and predict faults according to the current state and historical data of the motor. The mobile phone APP intelligent connection module is used to connect to the mobile phone APP of the manager's mobile terminal to provide real-time access functions. Collect the displacement, speed, acceleration data, sound data, and temperature rise data of the motor, diagnose motor imbalance, misalignment, rotor eccentricity, friction, shaft bending, mechanical looseness, gear failure, abnormal vibration, abnormal temperature rise and other problems, facilitate real-time monitoring of the motor operation, find abnormalities and deal with them in time, protect the motor from damage, make the equipment operate normally, improve equipment automation, use intelligent monitoring methods, predict motor abnormalities and motor normal operation data collection in advance, improve essential safety, be able to send and receive data normally, evaluate the motor health status normally, and respond to early warnings in time.

[0020] The wireless vibration sensor uses an energy collection module to convert the vibration energy of the motor into electrical energy for self-powering. The wireless vibration sensor has a built-in accelerometer and communication chip for real-time collection of the vibration frequency, displacement, speed, and acceleration data of the motor, and transmits it to the centralized control cloud platform system wirelessly. The wireless vibration sensor and sound sensor are both modularly designed, and the wireless vibration sensor and sound sensor are both installed on the motor through quick-release adhesives. The wireless communication module uses low-power wide area network LPWAN technology, including LoRa and NB-IoT. It realizes self-powered maintenance-free, high-frequency data collection, AI diagnostic data, precise fault location, fault prediction, quick disassembly and installation, the self-powered module works normally, and the average power of the energy storage module is maintained above 80%.

[0021] The data storage module includes a collection unit, a storage unit and a retrieval channel. The collection unit is used to wirelessly connect to the wireless vibration sensor and the signal output end of the wireless communication module to collect the transmitted data. The storage unit is used to store the transmitted data and add a time stamp. The retrieval channel is a human-computer interaction channel and provides keyword retrieval and time stamp retrieval functions for stored data.

[0022] The AI ​​diagnosis module includes a large standard data model, a deep learning comparison module and a fault prediction module. The large standard data model includes a vibration data module, a sound data model and a temperature sensing data model. The vibration data model includes all relevant vibration frequency, displacement, speed and acceleration standard data under motor imbalance, misalignment, rotor eccentricity, friction, shaft bending, mechanical looseness, gear failure and abnormal vibration. The sound data model includes all relevant sound types and frequency decibel standard data under motor imbalance, misalignment, rotor eccentricity, friction, shaft bending, mechanical looseness, gear failure and abnormal vibration. The temperature sensing data model is used to store the temperature rise data of the motor under various abnormal conditions. As a total database for comparison and verification.

[0023] The deep learning comparison module has a built-in AI deep learning algorithm, which is used to extract the data collected by the current wireless vibration sensor, sound sensor and the motor temperature data collected by the wireless communication module from the data storage module and input them into the standard data large model for one-by-one comparison and demonstration. First, the data of relevant vibration frequency, displacement, speed and acceleration are compared and judged, and then the relevant sound type and frequency decibel standard data are compared and judged for secondary verification. Finally, the motor temperature rise data is analyzed to diagnose whether the equipment has imbalance, misalignment, rotor eccentricity, friction, shaft bending, mechanical looseness, gear failure, motor vibration, and abnormal temperature rise. When there are no above-mentioned faults in the three comparisons, it is judged that the motor state is normal. First, data is collected from wireless vibration sensors, sound sensors and wireless communication modules in real time or regularly. These data include vibration data of vibration frequency, displacement, speed and acceleration, sound data of sound type and frequency decibel, and temperature data of the motor. The collected data is preprocessed, including denoising, standardization, normalization, etc., to ensure data quality and make it suitable for the input requirements of the deep learning model. Select a deep learning architecture, Convolutional Neural Network (CNN) for processing images or time series data (such as vibration signals), Recurrent Neural Network (RNN) or its variants (such as LSTM, GRU) for processing sequence data (such as sound signals), and Multilayer Perceptron (MLP) for processing multi-dimensional features. Design the model structure, including input layer, hidden layer, and output layer. The output layer can output the classification or prediction value of the equipment health status. Use a large amount of labeled data (i.e., standard data big model) to train the deep learning model. This data includes data in normal state and various fault states. During the training process, the model learns to extract features from the input data and automatically learns the complex relationship between these features and the equipment health status. Use the validation set to evaluate the model to check its performance on unknown data. Adjust the model structure, hyperparameters, or data preprocessing steps based on the evaluation results to optimize the model performance. Deploy the trained deep learning model to the actual production environment to receive data from sensors. The model processes the input data and compares it with the data in the standard data big model, including vibration data, sound data, and temperature data. Based on the comparison results, the model outputs the diagnostic results of the equipment health status, including whether there are faults such as imbalance, misalignment, rotor eccentricity, etc.

[0024] The fault prediction module is connected to the data storage module, counts the currently collected data and historical data, lists the data collected by the wireless vibration sensor, sound sensor and motor temperature data as a line graph, evaluates the data change trend and the change in equal time intervals, so as to predict the type and occurrence time of possible faults of the motor in the future. The real-time and historical data collected by wireless vibration sensors, sound sensors, and motor temperature data are summarized into a line graph, and the data change trend and the change amount at equal time intervals are evaluated to predict the possible fault types and occurrence time of the motor in the future, predict the equipment failure in advance, and reduce the loss of high-power motors; Use statistical software (Excel, Python's Matplotlib or Seaborn, R language, etc.) to draw the trend of key parameters such as vibration frequency, displacement, speed, acceleration, sound decibels, and motor temperature over time into a line graph, set the time axis to ensure that the time axis is clear, and show the details of the data change over time. Group the data of different parameters of different sensors and compare the change trends, identify the long-term trends (such as rising, falling, or stable) and short-term fluctuations in the data, calculate the average change amount or rate of change of the data in each time interval (such as daily, hourly) to quantify the speed of data change, and use time series analysis models (ARIMA, LSTM, etc.) to predict the data in the future, including the possible fault types and occurrence time. By comparing with the actual data, evaluate the accuracy and reliability of the prediction results, and optimize them.

[0025] The fault prediction module is connected to the after-sales service desk of the official website of the motor equipment through the Internet, and is used to output the line graph as a change report to the after-sales service desk for manual inspection by engineers. After the parameters show an abnormal change trend, the after-sales service desk accesses the mobile phone APP intelligent connection module to notify the management personnel. Provide a direct manual after-sales channel to improve the safety protection of the motor.

[0026] Embodiment 2 according to Figure 1 As shown, this embodiment proposes a monitoring system suitable for adding sensors to motors, including a hardware unit and a centralized control cloud platform system, wherein the hardware unit includes a wireless vibration sensor, a sound sensor and a wireless communication module, wherein the wireless vibration sensor and the sound sensor are both arranged on the motor, and the signal output end of the wireless vibration sensor is wirelessly connected to the centralized control cloud platform system, and the acquisition end of the wireless communication module is connected to the sound sensor and the control terminal of the motor, and is used to transmit the collected sound data and motor temperature data to the centralized control cloud platform system; The centralized control cloud platform system includes a data storage module, an AI diagnosis module and a mobile phone APP intelligent connection module. The data storage module is used to store data transmitted by wireless vibration sensors and wireless communication modules. The AI ​​diagnosis module has a built-in standard data large model for analyzing the vibration category data of wireless vibration sensors, the sound type data of sound sensors and the temperature rise data of motors, and using deep learning algorithms for comparison and verification, so as to infer the current state and fault of the motor, and predict faults according to the current state and historical data of the motor. The mobile phone APP intelligent connection module is used to connect to the mobile phone APP of the manager's mobile terminal to provide real-time access functions. Collect the displacement, speed, acceleration data, sound data, and temperature rise data of the motor, diagnose motor imbalance, misalignment, rotor eccentricity, friction, shaft bending, mechanical looseness, gear failure, abnormal vibration, abnormal temperature rise and other problems, facilitate real-time monitoring of the motor operation, find abnormalities and deal with them in time, protect the motor from damage, make the equipment operate normally, improve equipment automation, use intelligent monitoring methods, predict motor abnormalities and motor normal operation data collection in advance, improve essential safety, be able to send and receive data normally, evaluate the motor health status normally, and respond to early warnings in time.

[0027] The wireless vibration sensor uses an energy collection module to convert the vibration energy of the motor into electrical energy for self-powering. The wireless vibration sensor has a built-in accelerometer and communication chip for real-time collection of the vibration frequency, displacement, speed, and acceleration data of the motor, and transmits it to the centralized control cloud platform system wirelessly. The wireless vibration sensor and sound sensor are both modularly designed, and the wireless vibration sensor and sound sensor are both installed on the motor through quick-release adhesives. The wireless communication module uses low-power wide area network LPWAN technology, including LoRa and NB-IoT. It realizes self-powered maintenance-free, high-frequency data collection, AI diagnostic data, precise fault location, fault prediction, quick disassembly and installation, the self-powered module works normally, and the average power of the energy storage module is maintained above 80%.

[0028] The mobile phone APP intelligent connection module includes an identity authentication module and a data synchronization module. The identity authentication module uses fingerprints and 3D faces to identify the identity of managers. After the verification is passed, the manager is granted the right to log in and manage data. Improve security and avoid data leakage. When the manager uses it for the first time, he enters his fingerprint and 3D face information through the system. During the entry process, additional identity authentication steps (password, ID card verification, etc.) are performed to ensure that the identity of the person entering the information is accurate. After the verification is correct, the fingerprint template and 3D face data are encrypted and stored in the database, and associated with the manager's account information. When the manager needs to log in to the system or perform sensitive operations, the system will trigger the identity authentication process. After the double verification is passed, the system will grant the manager the corresponding login and data management permissions based on the identity authentication results and the preset permission policy. After the manager successfully logs in, he can perform data management, system configuration and other operations according to the granted permissions.

[0029] The data synchronization module is used to link data with the mobile phone APP of the manager's mobile terminal, synchronize the motor equipment operation status and fault warning information to the mobile phone APP for real-time display, and connect the motor control terminal at the same time to provide the manager with the function of emergency motor control. The present invention establishes a unique centralized control cloud platform system, which can be directly accessed by the mobile phone APP of the manager's mobile terminal, conveniently and quickly obtain information for investigation and processing, and has diversified functions.

[0030] The monitoring system suitable for adding sensors to motors installs wireless vibration sensors and sound sensors on the motors, collects the vibration frequency, displacement, speed, acceleration data and sound decibel data of the motors, and synchronously accesses the control terminal of the motors to collect the motor temperature data. Based on this, a deep learning algorithm is used to compare and verify with the standard data large model, analyze the vibration category, sound type and temperature rise of the motor, and thus three-step verification is used to infer the current state and fault of the motor, which is more accurate, realizes automated AI fault diagnosis, reduces the labor intensity of on-site measurement personnel, and reduces the production risks caused by abnormal equipment failures. At the same time, the present invention summarizes the data collected by real-time and historical wireless vibration sensors, sound sensors, and motor temperature data into a line graph, evaluates the change trend of the data and the change in equal time intervals, so as to predict the possible fault types and occurrence times of the motors in the future, predict the faults of the equipment in advance, and reduce the loss of high-power motors. In addition, the present invention sets up a unique centralized control cloud platform system, which can be directly accessed by the mobile phone APP of the manager's mobile terminal, so as to facilitate and quickly obtain information for investigation and processing, and has diversified functions.

[0031] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A monitoring system suitable for adding sensors to motors, comprising a hardware unit and a centralized control cloud platform system, characterized in that: The hardware unit includes a wireless vibration sensor, a sound sensor and a wireless communication module. The wireless vibration sensor and the sound sensor are both arranged on the motor, and the signal output end of the wireless vibration sensor is wirelessly connected to the centralized control cloud platform system. The acquisition end of the wireless communication module is connected to the control terminal of the sound sensor and the motor, and is used to transmit the collected sound data and motor temperature data to the centralized control cloud platform system; The centralized control cloud platform system includes a data storage module, an AI diagnosis module and a mobile phone APP smart connection module. The data storage module is used to store data transmitted by wireless vibration sensors and wireless communication modules. The AI ​​diagnosis module has a built-in standard data model for analyzing the vibration category data of wireless vibration sensors, the sound type data of sound sensors and the temperature rise data of motors, and using deep learning algorithms for comparison and verification to infer the current state and faults of the motor, and perform fault prediction based on the current rotation state and historical data of the motor. The mobile phone APP smart connection module is used to connect to the mobile phone APP of the manager's mobile terminal to provide real-time access function.

2. A monitoring system suitable for adding sensors to motors according to claim 1, characterized in that: The wireless vibration sensor adopts an energy collection module to convert the vibration energy of the motor into electrical energy for self-powering. The wireless vibration sensor has a built-in accelerometer and a communication chip for real-time collection of the vibration frequency, displacement, speed, and acceleration data of the motor, and transmits them wirelessly to the centralized control cloud platform system.

3. A monitoring system suitable for adding sensors to motors according to claim 2, characterized in that: The wireless vibration sensor and the sound sensor both adopt a modular design, and are installed on the motor through quick-release adhesives. The wireless communication module adopts low-power wide area network LPWAN technology, including LoRa and NB-IoT.

4. A monitoring system suitable for adding sensors to motors according to claim 1, characterized in that: The data storage module includes a collection unit, a storage unit and a retrieval channel. The collection unit is used to wirelessly connect to the wireless vibration sensor and the signal output end of the wireless communication module to collect the transmitted data. The storage unit is used to store the transmitted data and add a time stamp. The retrieval channel is a human-computer interaction channel and provides keyword retrieval and time stamp retrieval functions for stored data.

5. A monitoring system suitable for adding sensors to motors according to claim 4, characterized in that: The AI ​​diagnosis module includes a large standard data model, a deep learning comparison module and a fault prediction module. The large standard data model includes a vibration data module, a sound data model and a temperature sensing data model. The vibration data model includes all relevant vibration frequency, displacement, speed, and acceleration standard data under motor imbalance, misalignment, rotor eccentricity, friction, shaft bending, mechanical looseness, gear failure, and abnormal vibration. The sound data model includes all relevant sound types and frequency decibel standard data under motor imbalance, misalignment, rotor eccentricity, friction, shaft bending, mechanical looseness, gear failure, and abnormal vibration. The temperature sensing data model is used to store the temperature rise data of the motor under various abnormal conditions.

6. A monitoring system suitable for adding sensors to motors according to claim 5, characterized in that: The deep learning comparison module has a built-in AI deep learning algorithm, which is used to extract the data collected by the current wireless vibration sensor, sound sensor and the motor temperature data collected by the wireless communication module from the data storage module and input them into the standard data large model for one-by-one comparison and demonstration. First, the data of relevant vibration frequency, displacement, velocity, and acceleration are compared and judged, and then the relevant sound type and frequency decibel standard data are compared and judged for secondary verification. Finally, the motor temperature rise data is analyzed to diagnose whether the equipment has imbalance, misalignment, rotor eccentricity, friction, shaft bending, mechanical looseness, gear failure, motor vibration, and abnormal temperature rise. When no of the above faults are found in the three comparisons, the motor is judged to be in normal condition.

7. A monitoring system suitable for adding sensors to motors according to claim 6, characterized in that: The fault prediction module is connected to the data storage module, counts the currently collected data and historical data, lists the data collected by the wireless vibration sensor, sound sensor and motor temperature data as a line graph, evaluates the data change trend and the change in equal time intervals, so as to predict the type and occurrence time of possible faults of the motor in the future.

8. A monitoring system suitable for adding sensors to motors according to claim 7, characterized in that: The fault prediction module is connected to the after-sales service desk of the engineer of the official website of the motor equipment through the Internet, and is used to output the line graph as a change report to the after-sales service desk for manual inspection by engineers. When an abnormal change trend appears in the parameters, the after-sales service desk connects to the mobile phone APP intelligent connection module to notify the management personnel.

9. The monitoring system for adding sensors to motors according to claim 1, characterized in that: The mobile phone APP smart connection module includes an identity authentication module and a data synchronization module. The identity authentication module uses fingerprints and 3D faces to identify the identity of the manager. After the verification is passed, the manager is granted the authority to log in and manage data.

10. A monitoring system suitable for adding sensors to motors according to claim 9, characterized in that: The data synchronization module is used to link data with the mobile phone APP of the manager's mobile terminal, synchronize the motor equipment operation status and fault warning information to the mobile phone APP for real-time display, and at the same time connect to the motor's control terminal to provide the manager with the function of emergency control of the motor.

Citation Information

Cited By

  • Energy efficiency and economy evaluation method for self-energized iron core grounding state monitoring data

    CN120851712A