CN118228122A - An intelligent industrial Internet of Things terminal detection system - Google Patents

Abstract

The invention relates to the technical field of Internet of things, and discloses an intelligent industrial Internet of things terminal detection system, which comprises: the data acquisition and transmission module is used for acquiring the operation data of the equipment in real time and storing the data in a reliable database; the data processing and analyzing module is used for cleaning, processing and converting a large amount of collected data and removing abnormal values and noise; the intelligent detection module is used for detecting the abnormality of the terminal equipment in real time; a predictive maintenance module for predicting possible faults or damages of equipment, performing maintenance and maintenance in advance, comprising: the system comprises a data processing unit, a fault diagnosis algorithm unit, an early warning and alarming unit and a maintenance plan optimizing unit; and the man-machine cooperation module is used for finding potential fault rules and trends by combining a visual identification technology and robot operation, realizing the advanced prediction of faults and being beneficial to enterprises to take preventive maintenance measures.

Description

An intelligent industrial Internet of Things terminal detection system

Technical Field

The present invention relates to the technical field of Internet of Things, and in particular to an intelligent industrial Internet of Things terminal detection system.

Background technique

The concept of industrial Internet of Things terminal detection originated in the field of industrial automation. With the continuous development of sensor technology, Internet of Things technology, big data analysis and other technologies, industrial Internet of Things terminal detection has developed rapidly and played an increasingly important role in industrial production, especially in the vibration monitoring of large high-speed fans. It provides a more intelligent and efficient management method for fan vibration monitoring, and timely detects abnormal vibration and failure risks, so as to take corresponding repair and maintenance measures to improve the reliability and safety of fans.

After searching, the Chinese patent number CN111526072A discloses an intelligent industrial Internet of Things terminal detection system, which simplifies the protocol development process. The detection terminal automatically matches the data packet and exchanges data with the monitored equipment, reduces the difficulty of project implementation, and can free up R&D resources from repetitive work, thereby reducing the difficulty and cost of project implementation.

Traditional systems usually use rule-based or experience-based fault diagnosis methods, lack the ability to comprehensively solve complex problems, have weak data processing and analysis capabilities, and can often only perform simple data collection and storage. They lack predictive detection and corresponding measures. Therefore, an intelligent industrial Internet of Things terminal detection system is proposed.

Summary of the invention

The present invention proposes an intelligent industrial Internet of Things terminal detection system to solve the problems of lack of comprehensive solution capability for complex problems, weak data processing and analysis capabilities, lack of predictive detection, and lack of corresponding measures.

In order to achieve the above object, the present invention adopts the following technical solutions:

Data collection and transmission module, used to collect equipment operation data in real time and store the data in a reliable database;

Data processing and analysis module, used to clean, process and transform the large amount of collected data to remove outliers and noise;

Intelligent detection module, used to detect abnormalities of terminal devices in real time;

Predictive maintenance module, used to predict possible equipment failures or damages and perform maintenance and upkeep in advance, including: data processing unit, fault diagnosis algorithm unit, early warning and alarm unit, and maintenance plan optimization unit;

A human-robot collaboration module for combining visual recognition technology and robotic manipulation;

Adaptive learning module, used to continuously optimize the coordination between the system and the terminal according to the actual working environment and needs;

Remote monitoring and control module, used to remotely access the system through the Internet, monitor the operating status of the equipment in real time, and perform remote control and adjustment when necessary;

Augmented reality module for remote equipment inspection, maintenance and training.

The above technical solution further includes:

The data acquisition and transmission module is responsible for real-time monitoring of various parameters of the equipment, and collects and organizes the data, and transmits it to the data processing and analysis module for analysis and processing, and obtains equipment status information in a timely manner through the efficient data acquisition and transmission module.

The data processing and analysis module receives and processes a large amount of equipment data from the data acquisition and transmission module, so as to enable the data processing and analysis module to operate efficiently, quickly and accurately identify equipment status changes and potential failures, and provide strong support for real-time decision-making and equipment maintenance. The intelligent detection module obtains terminal detection data and machine algorithms and deep learning algorithms to achieve real-time monitoring and analysis of equipment status, perform data processing and fault diagnosis, and predict possible equipment failures.

The fault diagnosis algorithm unit analyzes the equipment data through machine learning and deep learning algorithms, identifies the existing faults and provides accurate diagnosis results. When industrial machines need to be diagnosed, the fault diagnosis algorithm unit uses machine learning and deep learning algorithms, support vector machines and deep neural networks to analyze the equipment sensor data to identify potential fault conditions, and uses support vector machines as the model of the fault diagnosis algorithm to find the decision boundary that can best distinguish different categories of data points. Among them, w is the feature weight vector, b is the bias term, ξ _i is the slack variable, C is the penalty coefficient, and n is the number of samples. By collecting device sensor data as training samples, a better decision boundary is learned using the support vector machine algorithm.

The human-machine collaboration module directly presents the data processing and analysis results to the operator through a visual interface, provides intelligent decision-making support for fault prediction and maintenance suggestions, receives feedback from personnel, continuously optimizes the algorithm model, and achieves continuous improvement and optimization;

The adaptive learning module autonomously learns, optimizes algorithms and improves performance according to the environment and tasks. A robot performs a specific task, inspects equipment in a factory workshop and records data. The adaptive learning module is used to adjust path planning according to real-time environmental information and historical data to achieve more efficient task execution. The robot's path is adjusted to minimize inspection time or energy consumption θ = θ-α·▽J(θ) where θ is a parameter of path planning, J(θ) is a loss function, α is a learning rate, and ▽J(θ) is the gradient of the loss function with respect to the parameter. The learning rate and update frequency are dynamically adjusted through the adaptive learning module according to the robot's performance during the inspection process and environmental changes.

The remote monitoring and control module realizes remote monitoring and control of the equipment by transmitting equipment data and status information to the remote platform in real time, monitors the equipment operation status, receives alarm information and performs remote control operations through network connection.

The augmented reality module provides an intuitive perception experience and operation interface by combining virtual information and real scenes, and uses AR technology to project equipment status data and fault information into the user's field of view in real time, providing training simulation and remote support functions, so that users can perform practical operations and skill training through virtual reality scenes.

The present invention has the following beneficial effects:

1. In the present invention, by analyzing and learning historical data, potential failure patterns and trends are discovered, and failures are predicted in advance, which is beneficial for enterprises to take preventive maintenance measures and avoid losses and downtime caused by sudden equipment failures.

2. In the present invention, parameters and rules are dynamically adjusted according to actual conditions to adapt to different environments and data characteristics, and quickly adapt to new environments and devices without retraining the model, thereby reducing the time and cost of system configuration and adjustment.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is an overall system block diagram of an intelligent industrial Internet of Things terminal detection system proposed by the present invention;

FIG2 is a partial system block diagram of an intelligent industrial Internet of Things terminal detection system proposed by the present invention.

Detailed ways

Embodiment 1

The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

As shown in Fig. 1-2, an intelligent industrial Internet of Things terminal detection system proposed by the present invention includes: a data acquisition and transmission module, which is used to collect the operation data of the equipment in real time and store the data in a reliable database; a data processing and analysis module, which is used to clean, process and convert the large amount of collected data to remove abnormal values and noise; an intelligent detection module, which is used to detect abnormalities of terminal equipment in real time; a predictive maintenance module, which is used to predict possible failures or damages of the equipment and perform maintenance and care in advance, including: a data processing unit, a fault diagnosis algorithm unit, an early warning and alarm unit and a maintenance plan optimization unit;

Human-machine collaboration module, used to combine visual recognition technology and robot operation; adaptive learning module, used to continuously optimize the coordination between the system and the terminal according to the actual working environment and needs; remote monitoring and control module, used to remotely access the system through the Internet, monitor the equipment operation status in real time, and remotely control and adjust when necessary; augmented reality module, used to realize remote equipment inspection, maintenance and training;

The data acquisition and transmission module is responsible for real-time monitoring of various parameters of the equipment, collecting and collating the data, and transmitting it to the data processing and analysis module for analysis and processing. Through the efficient data acquisition and transmission module, the equipment status information is obtained in a timely manner, providing sufficient data support for subsequent machine learning and deep learning algorithms;

The data processing and analysis module receives and processes a large amount of equipment data from the data acquisition and transmission module, making the data processing and analysis module operate efficiently, quickly and accurately identifying equipment status changes and potential failures, and providing strong support for real-time decision-making and equipment maintenance. The intelligent detection module obtains terminal detection data and machine algorithms and deep learning algorithms to achieve real-time monitoring and analysis of equipment status, perform data processing and fault diagnosis, and predict possible equipment failures;

The fault diagnosis algorithm unit uses machine learning and deep learning algorithms to analyze equipment data, identify existing faults and provide accurate diagnostic results. When industrial machines need to be diagnosed, the fault diagnosis algorithm unit uses machine learning and deep learning algorithms, support vector machines and deep neural networks, to analyze equipment sensor data to identify potential fault conditions. Support vector machines are used as the model of the fault diagnosis algorithm to find the decision boundary that can best distinguish different categories of data points. Among them, w is the feature weight vector, b is the bias term, ξ _i is the slack variable, C is the penalty coefficient, and n is the number of samples. By collecting device sensor data as training samples, a better decision boundary is learned using the support vector machine algorithm.

The data acquisition and transmission module is used to automatically collect data obtained by sensors and transmit it to the data processing unit through wired or wireless means to ensure the timeliness and accuracy of the data. The data is then transmitted to the data processing and analysis module, which processes and analyzes the received data, extracts key information and generates reports to help users understand the operating status and trends of the equipment;

The intelligent detection module obtains data from the data processing and analysis module to judge the abnormalities of the terminal equipment used for real-time detection. The predictive maintenance module is used to predict possible failures or damages of the equipment and perform maintenance and care in advance. Based on the learned patterns and decision boundaries, it can quickly and accurately determine whether the equipment has a fault and give the corresponding diagnostic results. Through such a fault diagnosis algorithm unit, the intelligent industrial Internet of Things terminal detection system can detect equipment problems in a timely manner, reduce production interruption time, and improve equipment reliability and efficiency.

Embodiment 2

As shown in FIG1-2 , in an embodiment of the present invention, the human-machine collaboration module intuitively presents the data processing and analysis results to the operator through a visual interface, provides intelligent decision support for fault prediction and maintenance suggestions, and receives feedback from the operator to continuously optimize the algorithm model and achieve continuous improvement and optimization;

Adaptive learning module, autonomously learns, optimizes algorithms and improves performance according to the environment and tasks. A robot performs a specific task, inspects equipment in a factory workshop and records data. Using the adaptive learning module, the path planning is adjusted according to real-time environmental information and historical data to achieve more efficient task execution. The robot's path is adjusted to minimize the inspection time or energy consumption θ = θ-α·▽J(θ) where θ is the path planning parameter, J(θ) is the loss function, α is the learning rate, and ▽J(θ) is the gradient of the loss function with respect to the parameter. The learning rate and update frequency are dynamically adjusted through the adaptive learning module according to the robot's performance during the inspection process and environmental changes;

Remote monitoring and control module, which can realize remote monitoring and control of equipment by transmitting equipment data and status information to the remote platform in real time, monitor equipment operation status, receive alarm information and perform remote control operations through network connection;

The augmented reality module, with its ability to perfectly integrate virtual information with the real world, brings users unprecedented intuitive experience and convenient operation. Through AR technology, the status and fault data of the equipment can be presented in real time in the user's field of vision, greatly improving the accessibility and processing efficiency of information. In addition, it also supports simulation training and remote assistance functions, allowing users to practice and improve skills in a virtual environment close to reality, effectively promoting learning efficiency and operation accuracy.

The human-machine collaboration module obtains data from the data processing and analysis module to combine visual recognition technology and robot operation, and transmits the data to the adaptive learning module. It dynamically adjusts parameters and rules according to actual conditions to adapt to different environments and data characteristics, and can quickly adapt to new environments and equipment without manual intervention or retraining models. It can quickly adapt to new equipment and data characteristics, reducing the time and cost of system configuration and adjustment. The remote monitoring and control module obtains data from the data processing and analysis module and the corresponding data from the intelligent detection module, remotely accesses the system through the Internet, monitors the equipment operation status in real time, and performs remote control and adjustment when necessary. Through the augmented reality module, AR technology realizes remote equipment inspection, maintenance and training, and improves the work efficiency and safety of operators.

Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims (8)

1. An intelligent industrial Internet of Things terminal detection system, characterized by comprising: Data collection and transmission module, used to collect equipment operation data in real time and store the data in a reliable database; Data processing and analysis module, used to clean, process and transform the large amount of collected data to remove outliers and noise; Intelligent detection module, used to detect abnormalities of terminal devices in real time; Predictive maintenance module, used to predict possible equipment failures or damages and perform maintenance and upkeep in advance, including: data processing unit, fault diagnosis algorithm unit, early warning and alarm unit, and maintenance plan optimization unit; A human-robot collaboration module for combining visual recognition technology and robotic manipulation; Adaptive learning module, used to continuously optimize the coordination between the system and the terminal according to the actual working environment and needs; Remote monitoring and control module, used to access the system remotely via the Internet, monitor the equipment operation status in real time, and perform remote control and adjustment when necessary; Augmented reality module for remote equipment inspection, maintenance and training. 2. According to claim 1, an intelligent industrial Internet of Things terminal detection system is characterized in that the data acquisition and transmission module is responsible for real-time monitoring of various parameters of the equipment, and collecting and collating the data, transmitting it to the data processing and analysis module for analysis and processing, and obtaining the equipment status information in time through the efficient data acquisition and transmission module. 3. According to claim 1, an intelligent industrial Internet of Things terminal detection system is characterized in that the data processing and analysis module, by receiving and processing a large amount of equipment data from the data acquisition and transmission module, enables the data processing and analysis module to operate efficiently, quickly and accurately identify equipment status changes and potential failures, and provide strong support for real-time decision-making and equipment maintenance. The intelligent detection module, by acquiring terminal detection data and machine algorithms and deep learning algorithms, realizes real-time monitoring and analysis of equipment status, performs data processing and fault diagnosis, and predicts possible equipment failures. 4. According to claim 1, a smart industrial Internet of Things terminal detection system is characterized in that the fault diagnosis algorithm unit analyzes equipment data through machine learning and deep learning algorithms to identify existing faults and provide accurate diagnosis results. When industrial machines need to be diagnosed, the fault diagnosis algorithm unit uses machine learning and deep learning algorithms, support vector machines and deep neural networks to analyze equipment sensor data to identify potential fault conditions, and uses support vector machines as the model of the fault diagnosis algorithm to find the decision boundary that can best distinguish different categories of data points. Among them, w is the feature weight vector, b is the bias term, ξ _i is the slack variable, C is the penalty coefficient, and n is the number of samples. By collecting device sensor data as training samples, a better decision boundary is learned using the support vector machine algorithm. 5. According to claim 1, an intelligent industrial Internet of Things terminal detection system is characterized in that the human-machine collaboration module intuitively presents the data processing and analysis results to the operator through a visual interface, provides fault prediction, maintenance suggestion intelligent decision support, and receives feedback information from personnel, continuously optimizes the algorithm model, and achieves continuous improvement and optimization. 6. According to claim 1, a smart industrial Internet of Things terminal detection system is characterized in that the adaptive learning module autonomously learns, optimizes algorithms and improves performance according to the environment and tasks. A robot performs a specific task, inspects equipment in a factory workshop and records data. The adaptive learning module is used to adjust the path planning according to real-time environmental information and historical data to achieve more efficient task execution, and adjust the robot's path to minimize inspection time or energy consumption. Among them, θ is the parameter of path planning, J(θ) is the loss function, α is the learning rate, /> It is the gradient of the loss function with respect to the parameters. The learning rate and update frequency are dynamically adjusted through the adaptive learning module according to the robot’s performance during the inspection process and the changes in the environment. 7. An intelligent industrial Internet of Things terminal detection system according to claim 1 is characterized in that the remote monitoring and control module realizes remote monitoring and control of the equipment by transmitting equipment data and status information to the remote platform in real time, monitors the equipment operation status, receives alarm information and performs remote control operations through network connection. 8. According to claim 1, an intelligent industrial Internet of Things terminal detection system is characterized in that the augmented reality module provides an intuitive perception experience and operation interface by combining virtual information and real scenes, and uses AR technology to project equipment status data and fault information into the user's field of view in real time, providing training simulation and remote support functions, so that users can perform practical operations and skills training through virtual reality scenes.