Intelligent equipment data interaction system based on industrial internet

Abstract

The invention, which relates to the technical field of the industrial internet, discloses an intelligent equipment data interaction system based on the industrial internet, comprising an industrial internet platform. The industrial internet platform is in communication connection with a data acquisition and preprocessing module, an edge calculation module, a data transmission module, an anomaly analysis module, an intelligent decision module, a feedback control module and a man-machine interaction module, and all the modules are in electric signal connection. According to the intelligent equipment data interaction system based on the industrial internet, the production efficiency is remarkably improved by monitoring and optimizing the production process in real time, data are collected through a sensor and an equipment state monitor, and abnormal states in the production process are quickly recognized and responded through preprocessing and analysis of an edge calculation module; and the intelligent decision-making module generates an optimization control scheme according to an analysis result and feeds back the implementation scheme of the control module, so that the risks of equipment failure and production interruption are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial Internet, and specifically to an intelligent device data interaction system based on industrial Internet. Background Art

[0002] The Industrial Internet is an emerging business model and application pattern formed by the deep integration of new-generation information technology and industrial economy. It is the key foundation for realizing the digital transformation of the industry. With the rapid development of technologies such as the Internet of Things, cloud computing, and big data, the Industrial Internet has become an important force in promoting enterprise transformation and upgrading and improving production efficiency. In industrial production, the application of intelligent devices is becoming more and more extensive. In order to achieve more efficient production, real-time data interaction is required between these devices to adjust production parameters and optimize production processes in a timely manner.

[0003] In the existing technology, since the industrial Internet platform involves a large amount of data transmission and processing, the interference of network delay will cause the system to respond and interact in a timely manner, which will make it difficult to respond in time when industrial equipment has abnormalities. Therefore, how to weaken the interference of network delay and improve the system's response speed and interaction efficiency to abnormal conditions is the problem we need to solve. To this end, a smart device data interaction system based on the industrial Internet is proposed. Summary of the invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent device data interaction system based on the industrial Internet, including an industrial Internet platform, wherein the industrial Internet platform is communicatively connected with a data acquisition and preprocessing module, an edge computing module, a data transmission module, an abnormality analysis module, an intelligent decision-making module, a feedback control module and a human-computer interaction module, wherein the modules are connected by electrical signals;

[0005] The data acquisition and preprocessing module is used to collect data from various industrial equipment and sensors, including real-time information on temperature, humidity, pressure, and equipment status, and preprocess the collected data. Through ubiquitous sensing technology, it can realize real-time and efficient data acquisition of multi-source equipment and heterogeneous systems, providing a basis for subsequent data processing and analysis;

[0006] The edge computing module is used to perform preliminary analysis and processing of data on the industrial equipment side, using edge computing capabilities to reduce the amount of data transmitted to the cloud. By processing data on edge devices, the demand for data transmission is reduced, thereby reducing network latency and improving real-time response capabilities.

[0007] The data transmission module optimizes the data sharing transmission path through protocol conversion technology and information model technology, transmits data from the industrial equipment end to the cloud of the industrial Internet platform, reduces network delay, and improves the efficiency and reliability of data interaction;

[0008] The abnormal analysis module uses big data analysis technology to perform intelligent analysis on the pre-processed data, identify the abnormal state of industrial equipment, and enable the system to quickly respond and adjust to the abnormal state of industrial equipment, thereby improving the degree of automation and system response speed;

[0009] The intelligent decision-making module optimizes and controls the abnormal state of the production process according to the analysis results of the abnormal analysis module, and generates real-time decision instructions to improve production efficiency and quality;

[0010] The feedback control module performs feedback control on the industrial equipment according to the decision instructions generated by the intelligent decision module, ensuring that the system can execute the required operations immediately, enhancing the responsiveness of the system, ensuring that the equipment can adjust its status in time, and reducing the reaction time of the system;

[0011] The human-computer interaction module includes an industrial large screen, mobile applications, and a Web interface, which are used to display and interact with various data of industrial equipment, allowing users to monitor and control the status of industrial equipment in real time, and provide users with intuitive and convenient data display and operation methods.

[0012] Preferably, in the data acquisition and preprocessing module, the process of data acquisition and preprocessing includes:

[0013] Deploy various sensors and data acquisition devices in industrial environments, including temperature sensors, humidity sensors, pressure sensors, and equipment status monitors;

[0014] According to the monitoring characteristics and requirements of industrial equipment, set the sampling frequency, monitor the status of industrial equipment and environment in real time, and obtain real-time information data on temperature, humidity, pressure, and equipment status;

[0015] Convert the collected raw data into a unified format for subsequent processing, and clean the collected data;

[0016] The preprocessed data is encoded and encrypted, and the preprocessed and encoded data is transmitted to the edge computing module for further analysis.

[0017] Preferably, in the edge computing module, the process of using edge computing capabilities to reduce the amount of data transmitted to the cloud includes:

[0018] The edge computing module receives the preprocessed data and compresses it using the Huffman coding compression algorithm to reduce the amount of data transmission. Based on the characteristics of Huffman coding, the character frequency in the coding process is further used to filter key data.

[0019] Encode the filtered and compressed data to facilitate subsequent data storage and transmission, and use a strong encryption algorithm to encrypt the data to ensure the security of the data during transmission and storage, and effectively prevent the data from being accessed or tampered with by unauthorized personnel;

[0020] Before transmitting the data to the cloud, the edge computing module is used to integrate the filtered, compressed and encrypted data, merge multiple data packets into one data packet, and transmit it to the data transmission module.

[0021] Preferably, in the data transmission module, the process of optimizing the data sharing transmission path includes:

[0022] The data transmission module receives the industrial equipment data packets integrated from the edge computing module, identifies its communication protocol, and determines the target protocol according to the communication protocol requirements of the target cloud platform. It uses the built-in protocol conversion engine to convert the received data packets from the original protocol to the target protocol, including decoding the original data packets, extracting valid data, and re-encoding them into the target protocol format.

[0023] The data transmission module builds the corresponding information model according to the data structure and attributes of the industrial equipment, and formats and converts the received data according to the information model, including data type conversion, field rearrangement, unit conversion, etc., to ensure data consistency and readability;

[0024] The data transmission module selects the optimal data transmission path and performs load balancing according to the network conditions and data transmission requirements, including distributing data to multiple transmission channels and adjusting the transmission rate to avoid network congestion and data loss. It also uses efficient data transmission protocols (such as MQTT, CoAP, etc.) to transmit protocol-converted and formatted data packets to the cloud, and uses the cloud to further analyze and process the uploaded data.

[0025] Preferably, in the abnormality analysis module, the process of identifying abnormal status of industrial equipment includes:

[0026] Collect historical data and known abnormal case data, and further clean and normalize them to ensure data quality and provide an accurate data basis for analysis;

[0027] By comparing the data features of normal and abnormal states, the abnormal features reflecting the abnormal state of industrial equipment are extracted, and the data is divided into different categories according to the severity of the abnormal state to obtain an abnormal feature set, so as to more clearly identify abnormal data points. The abnormal features include deviation of equipment performance parameters, vibration analysis abnormalities, abnormal changes in temperature and pressure, sound changes, production quality degradation, equipment life and wear, and energy consumption abnormalities. The deviation of equipment performance parameters means that the operating parameters of the equipment (such as temperature, pressure, vibration, current, speed, etc.) deviate from the normal working range. The vibration analysis abnormality means that the abnormal vibration mode of the equipment is identified by analyzing the spectrum of the vibration signal, such as bearing failure, imbalance, misalignment, etc.

[0028] The abnormal feature set is divided into a training set and a test set. The training set data is combined with the decision tree model to build an anomaly detection model to monitor the status of industrial equipment. The trained anomaly detection model is evaluated using the test set data to adjust the parameters of the anomaly detection model and improve the performance of the model.

[0029] Combining the analysis results of the anomaly detection model with the associated data of the anomaly feature set, the anomaly detection coefficient is obtained to identify the abnormal state of the industrial equipment, and different warning levels are divided according to the severity of the abnormal state, namely low warning level, medium warning level and high warning level;

[0030] Match the corresponding warning threshold to each warning level. Once an abnormal state is detected, a warning signal of the corresponding warning level will be issued to notify relevant personnel to handle it.

[0031] Preferably, the calculation expression of the abnormality detection coefficient is:

[0032] ;

[0033] ;

[0034] in, is the anomaly detection coefficient, is the state value deviation function, is the currently observed state value of the industrial equipment, is the benchmark value of the state value in the historical data, is the standard deviation of the state value in the historical data, which is used to measure the degree of dispersion of the data. is the maximum value of the normal state in the historical data, is the minimum value of abnormal state in historical data, The function ensures that the value of the anomaly detection coefficient is between 0 and 1. The value range is between 0 and 1. Close to When the index part As it approaches 1, the entire denominator increases, resulting in Close to 0, indicating normal status. Significant deviation When the index part decreases rapidly, the entire denominator decreases, resulting in Increases and tends to 1, indicating an abnormal state. Using the exponential function enlarge With the mean The deviation between Deviation When , the exponential function grows rapidly, so that the coefficient Increase, express Further adjustment relative to the range of normal and abnormal states The value of the minimum function Ensure coefficient will not exceed 1, even if Significant deviation , Nor will it exceed the set warning threshold.

[0035] Preferably, the value of the anomaly detection coefficient and the warning threshold preset by the warning level are obtained to match the three warning levels, which are:

[0036] Low alert level: ;

[0037] Medium warning level: ;

[0038] High alert level: ;

[0039] in, is the anomaly detection coefficient, is the lower threshold corresponding to the medium warning level and the upper threshold corresponding to the low warning level, is the lower threshold corresponding to the high warning level and the upper threshold corresponding to the medium warning level, , .

[0040] Preferably, in the intelligent decision-making module, the process of generating the real-time decision instruction includes:

[0041] Receive the analysis results of the abnormal analysis module, including the abnormal detection coefficient of the equipment status and performance indicators, and analyze and determine the abnormal status and severity of the production process;

[0042] After identifying and evaluating the abnormal state, the intelligent decision-making module selects a response strategy based on the preset optimization control strategy library. The response strategy includes adjusting production parameters, replacing faulty equipment, optimizing production processes, and formulating an optimization control plan based on the actual situation and the suggestions in the strategy library.

[0043] Determine the optimal control plan, and the intelligent decision-making module generates corresponding real-time decision instructions. The real-time decision instructions include sending signals to production equipment to adjust parameters and sending notifications to operators to repair or replace equipment. By issuing instructions in real time, the intelligent decision-making module can quickly respond to abnormal conditions in the production process to avoid further deterioration of the problem.

[0044] Preferably, in the feedback control module, the process of performing feedback control on the industrial equipment includes:

[0045] The feedback control module receives the decision instructions from the intelligent decision module for adjusting equipment parameters, replacing faulty equipment, and optimizing production processes, and parses the decision instructions to clarify the specific requirements of the decision instructions, including the parameter values ​​that need to be adjusted, the type of operation that needs to be performed, and the priority of the operation;

[0046] According to the parsed instruction content, the corresponding control signal is generated, and the control signal is sent to the control system of the industrial equipment through the communication interface, ensuring the fast and accurate transmission of the signal, thereby ensuring that the industrial equipment can respond to the instruction immediately;

[0047] After receiving the control signal, the control system of the industrial equipment interprets the signal and drives the target industrial equipment to perform corresponding operations, including adjusting the speed of the motor, changing the temperature setting of the heater, and starting or stopping the conveyor belt;

[0048] While executing the operation, the actual working status of the target industrial equipment and the status information of the changes in the operating parameters are collected in real time through sensors to ensure that the target industrial equipment performs the corresponding operation according to the control signal and verify whether the effect of the operation of the target industrial equipment meets the expectations. If the actual status is consistent with the expected target, the operation is considered successful; if there is a difference, the control strategy needs to be adjusted or the decision instruction needs to be regenerated;

[0049] Record a log of all feedback control operations, including the instructions sent, device responses, operation time and results, to facilitate subsequent audit and analysis.

[0050] Preferably, in the human-computer interaction module, the process of displaying and interacting with various data of industrial equipment includes:

[0051] Integrate various data generated by industrial equipment, including industrial equipment operating status, parameter settings, fault alarms, and performance indicators;

[0052] Aggregate the integrated data and display the relevant data through industrial large screens, mobile applications, and web interfaces. It also provides historical data query functions, allowing users to view the historical performance and operation records of industrial equipment.

[0053] When the status of industrial equipment is abnormal, alarms and notifications are sent to users through interface prompts, sounds, emails and text messages, allowing users to send decision-making instructions through the interface to adjust equipment parameters and perform specific operations;

[0054] Record all user operation logs, including operation time, operation type and operation results, to facilitate auditing and troubleshooting.

[0055] The present invention provides a smart device data interaction system based on the industrial Internet. It has the following beneficial effects:

[0056] 1. This intelligent device data interaction system based on the industrial Internet can accurately grasp the operating status and production efficiency of the equipment by real-time collection, processing and analysis of industrial equipment data, and predict the maintenance needs of the equipment in advance, thereby avoiding equipment downtime due to failures. It also monitors and analyzes the quality data in the production process in real time, promptly discovers quality problems and traces the causes, thereby improving product quality and production efficiency.

[0057] 2. This intelligent device data interaction system based on the Industrial Internet significantly improves production efficiency by real-time monitoring and optimizing production processes. It collects data through sensors and equipment status monitors, and quickly identifies and responds to abnormal conditions in the production process after preprocessing and analysis by the edge computing module. The intelligent decision-making module generates an optimized control plan based on the analysis results, and implements the plan through the feedback control module, thereby reducing the risk of equipment failure and production interruption. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a module structure diagram of an intelligent device data interaction system based on the industrial Internet of the present invention;

[0059] Figure 2 A flow chart of the present invention using edge computing capabilities to reduce the amount of data transmitted to the cloud;

[0060] Figure 3 This is a flow chart of the present invention for identifying abnormal status of industrial equipment. DETAILED DESCRIPTION

[0061] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0062] The first embodiment, as Figure 1 , Figure 2 As shown, the present invention provides a technical solution: an intelligent device data interaction system based on the industrial Internet, including an industrial Internet platform, the industrial Internet platform is communicatively connected with a data acquisition and preprocessing module, an edge computing module, a data transmission module, an abnormality analysis module, an intelligent decision-making module, a feedback control module and a human-computer interaction module, wherein the modules are connected by electrical signals;

[0063] The data acquisition and preprocessing module is used to collect data from various industrial equipment and sensors, including real-time information on temperature, humidity, pressure, and equipment status, and preprocess the collected data. Through ubiquitous sensing technology, real-time and efficient data acquisition of multi-source equipment and heterogeneous systems is achieved, providing a basis for subsequent data processing and analysis. Various sensors and data acquisition devices are deployed in industrial environments, including temperature sensors, humidity sensors, pressure sensors, and equipment status monitors. Temperature sensors are used to monitor the temperature in industrial environments to ensure that equipment operates at appropriate temperatures. Humidity sensors monitor ambient humidity to prevent damage to equipment and products caused by excessively high or low humidity. Pressure sensors are used to monitor fluid pressure, gas pressure, etc. to ensure that the pressure is within a safe range. Equipment status monitors monitor the vibration, speed, temperature, etc. of the equipment. Parameters, timely discover equipment failures, set sampling frequencies according to the monitoring characteristics and needs of industrial equipment, monitor the status of industrial equipment and the environment in real time, and obtain real-time information data on temperature, humidity, pressure, and equipment status, convert the collected raw data into a unified format for subsequent processing, and clean the collected data to remove duplicate data, invalid data, and noise data, fill in missing data, and use mean filling, median filling, interpolation and other methods to further process the data to improve data quality, encode the preprocessed data, and encrypt it to ensure the security of the data during the collection and preprocessing process, including data encryption and access control to prevent data leakage or unauthorized access, and transmit the preprocessed and encoded data to the edge computing module for further analysis;

[0064] The edge computing module is used to perform preliminary analysis and processing of data on the industrial equipment side, and use edge computing capabilities to reduce the amount of data transmitted to the cloud. By processing data on the edge device, the demand for data transmission is reduced, thereby reducing network latency and improving real-time response capabilities. The edge computing module receives pre-processed data and compresses it using the Huffman coding compression algorithm to reduce the amount of data transmission. Based on the characteristics of Huffman coding, the character frequency in the encoding process is further used to filter key data. High-frequency characters often contain more information value. By filtering, only key data containing important information is transmitted to the cloud, which can further reduce the demand for data transmission while ensuring the validity and value of the data. The filtered and compressed data is encoded for subsequent data storage and transmission, and a strong encryption algorithm is used to encrypt the data to ensure the security of the data during transmission and storage, effectively preventing the data from being accessed or tampered with by unauthorized personnel. Before transmitting the data to the cloud, the edge computing module is used to integrate the filtered, compressed and encrypted data, merge multiple data packets into one data packet, and transmit it to the data transmission module;

[0065] The data transmission module optimizes the data sharing transmission path through protocol conversion technology and information model technology, transmits data from the industrial equipment end to the cloud of the industrial Internet platform, reduces network delays, and improves the efficiency and reliability of data interaction. The data transmission module receives the industrial equipment data packets integrated from the edge computing module, identifies its communication protocol, and determines the target protocol according to the communication protocol requirements of the target cloud platform. It uses the built-in protocol conversion engine to convert the received data packets from the original protocol to the target protocol, including decoding the original data packets, extracting valid data, and re-encoding them into the target protocol format. The data transmission module builds the corresponding information model according to the data structure and attributes of the industrial equipment, formats and converts the received data according to the information model, including data type conversion, field rearrangement, unit conversion, etc., to ensure data consistency and readability. The data transmission module selects the optimal data transmission path according to the network status and data transmission requirements, and performs load balancing processing, including distributing data to multiple transmission channels, adjusting the transmission rate, etc., to avoid network congestion and data loss, and uses efficient data transmission protocols (such as MQTT, CoAP, etc.) to transmit the protocol-converted and formatted data packets to the cloud, and uses the cloud to further analyze and process the uploaded data;

[0066] The abnormal analysis module uses big data analysis technology to perform intelligent analysis on pre-processed data and identify abnormal conditions of industrial equipment, so that the system can quickly respond and adjust to abnormal conditions of industrial equipment, thereby improving the degree of automation and system response speed;

[0067] The intelligent decision-making module optimizes and controls the abnormal state of the production process based on the analysis results of the abnormal analysis module, and generates real-time decision-making instructions to improve production efficiency and quality;

[0068] The feedback control module performs feedback control on the industrial equipment according to the decision instructions generated by the intelligent decision module, ensuring that the system can execute the required operations immediately, enhancing the system's responsiveness, ensuring that the equipment can adjust its status in time, and reducing the system's reaction time;

[0069] The human-computer interaction module, including industrial large screens, mobile applications, and Web interfaces, is used to display and interact with various data of industrial equipment, allowing users to monitor the status of industrial equipment in real time and control it, providing users with intuitive and convenient data display and operation methods. By real-time collection, processing, and analysis of industrial equipment data, it can accurately grasp the operating status and production efficiency of the equipment, predict the maintenance needs of the equipment in advance, thereby avoiding equipment downtime due to failures, and monitor and analyze the quality data in the production process in real time, promptly discover quality problems and trace the causes, thereby improving product quality and production efficiency.

[0070] The second embodiment is based on the first embodiment. Figure 3 As shown, in the abnormal analysis module, the process of identifying abnormal status of industrial equipment includes:

[0071] Collect historical data and known abnormal case data, and further clean and normalize them to ensure data quality and provide an accurate data basis for analysis. By comparing the data features of normal and abnormal states, extract the abnormal features that reflect the abnormal state of industrial equipment, and divide the data into different categories according to the severity of the abnormal state to obtain an abnormal feature set, so as to more clearly identify abnormal data points. The abnormal features include deviation of equipment performance parameters, vibration analysis abnormalities, abnormal changes in temperature and pressure, sound changes, production quality degradation, equipment life and wear, and energy consumption abnormalities. The deviation of equipment performance parameters means that the operating parameters of the equipment (such as temperature, pressure, vibration, current, speed, etc.) deviate from the normal working range. The vibration analysis abnormality is to analyze the spectrum of the vibration signal. Identify abnormal vibration patterns of equipment, such as bearing failure, imbalance, misalignment, etc., divide the abnormal feature set into training set and test set, use the training set data combined with the decision tree model to build an anomaly detection model, monitor the status of industrial equipment, and use the test set data to evaluate the trained anomaly detection model in order to adjust the parameters of the anomaly detection model and improve the performance of the model. Combine the analysis results of the anomaly detection model and the associated data of the abnormal feature set to obtain the anomaly detection coefficient, identify the abnormal state of industrial equipment, and divide different warning levels according to the severity of the abnormal state, namely low warning level, medium warning level and high warning level, match the corresponding warning threshold for each warning level, and once an abnormal state is detected, issue a warning signal of the corresponding warning level to notify relevant personnel to handle it;

[0072] Furthermore, the calculation expression of the anomaly detection coefficient is:

[0073] ;

[0074] ;

[0075] in, is the anomaly detection coefficient, is the state value deviation function, is the currently observed state value of the industrial equipment, is the benchmark value of the state value in the historical data, is the standard deviation of the state value in the historical data, which is used to measure the degree of dispersion of the data. is the maximum value of the normal state in the historical data, is the minimum value of abnormal state in historical data, The function ensures that the value of the anomaly detection coefficient is between 0 and 1. The value range is between 0 and 1. Close to When the index part As it approaches 1, the entire denominator increases, resulting in Close to 0, indicating normal status. Significant deviation When the index part decreases rapidly, the entire denominator decreases, resulting in Increases and tends to 1, indicating an abnormal state. Using the exponential function enlarge With the mean The deviation between Deviation When , the exponential function grows rapidly, so that the coefficient Increase, express Further adjustment relative to the range of normal and abnormal states The value of the minimum function Ensure coefficient will not exceed 1, even if Significant deviation , Nor will it exceed the set warning threshold;

[0076] Furthermore, the value of the anomaly detection coefficient and the preset warning threshold of the warning level are obtained to match the three warning levels, which are:

[0077] Low alert level: ;

[0078] Medium warning level: ;

[0079] High alert level: ;

[0080] in, is the anomaly detection coefficient, is the lower threshold corresponding to the medium warning level and the upper threshold corresponding to the low warning level, is the lower threshold corresponding to the high warning level and the upper threshold corresponding to the medium warning level, , ;

[0081] In the intelligent decision-making module, the process of generating real-time decision instructions includes:

[0082] Receive the analysis results of the abnormal analysis module, including the abnormal detection coefficients of the equipment status and performance indicators, analyze and determine the abnormal status and severity of the production process, and after identifying and evaluating the abnormal status, the intelligent decision-making module selects a response strategy based on the preset optimization control strategy library. The response strategy includes adjusting production parameters, replacing faulty equipment, and optimizing production processes. According to the actual situation and the suggestions in the strategy library, an optimization control plan is formulated. After the optimization control plan is determined, the intelligent decision-making module generates corresponding real-time decision instructions. The real-time decision instructions include sending a signal to adjust the parameters to the production equipment and sending a notification to the operator to repair or replace the equipment. By issuing instructions in real time, the intelligent decision-making module can quickly respond to the abnormal status of the production process to avoid further deterioration of the problem;

[0083] In the feedback control module, the process of feedback control of industrial equipment includes:

[0084] The feedback control module receives the decision instructions for adjusting equipment parameters, replacing faulty equipment, and optimizing production processes from the intelligent decision module, and parses the decision instructions to clarify the specific requirements of the decision instructions, including the parameter values ​​that need to be adjusted, the types of operations that need to be performed, and the priority of the operations. According to the parsed instruction content, the corresponding control signal is generated, and the control signal is sent to the control system of the industrial equipment through the communication interface to ensure the fast and accurate transmission of the signal, thereby ensuring that the industrial equipment can respond to the instruction immediately. After receiving the control signal, the control system of the industrial equipment parses the signal and drives the target industrial equipment to perform the corresponding operation, including adjusting the speed of the motor, changing the temperature setting of the heater, and starting or stopping the conveyor belt. While performing the operation, the actual working state of the target industrial equipment and the change of the operating parameters are collected in real time through the sensor to ensure that the target industrial equipment performs the corresponding operation according to the control signal, and verify whether the effect of the target industrial equipment operation meets the expectations. If the actual state is consistent with the expected target, the operation is considered successful; if there is a difference, the control strategy needs to be adjusted or the decision instruction needs to be regenerated, and the log of all feedback control operations, including the instructions sent, the equipment response, the operation time and the results, is recorded for subsequent audit and analysis;

[0085] In the human-computer interaction module, the process of displaying and interacting with various data of industrial equipment includes:

[0086] It integrates various data generated by industrial equipment, including the operating status, parameter settings, fault alarms, and performance indicators of industrial equipment, aggregates the integrated data, and displays relevant data through industrial large screens, mobile applications, and Web interfaces. It also provides historical data query functions, allowing users to view the historical performance and operation records of industrial equipment. When the status of industrial equipment is abnormal, it will send alarms and notifications to users through interface prompts, sounds, emails, and text messages, allowing users to send decision-making instructions through the interface to adjust equipment parameters and perform specific operations. It records all user operation logs, including operation time, operation type, and operation results, for easy auditing and troubleshooting. It significantly improves production efficiency by real-time monitoring and optimization of production processes. It collects data through sensors and equipment status monitors, and quickly identifies and responds to abnormal conditions in the production process after preprocessing and analysis by the edge computing module. The intelligent decision-making module generates an optimized control plan based on the analysis results, and implements the plan through the feedback control module, thereby reducing the risk of equipment failure and production interruption.

[0087] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. An intelligent device data interaction system based on the industrial Internet, including an industrial Internet platform, characterized in that: The industrial Internet platform is connected in communication with a data acquisition and preprocessing module, an edge computing module, a data transmission module, an abnormality analysis module, an intelligent decision-making module, a feedback control module, and a human-computer interaction module, wherein electrical signals are connected between the modules; The data acquisition and preprocessing module is used to collect data from various industrial equipment and sensors, including real-time information on temperature, humidity, pressure, and equipment status, and preprocess the collected data; The edge computing module is used to perform preliminary analysis and processing of data on the industrial equipment side, using edge computing capabilities to reduce the amount of data transmitted to the cloud; The data transmission module optimizes the data sharing transmission path through protocol conversion technology and information model technology, and transmits data from the industrial equipment end to the cloud of the industrial Internet platform; The abnormality analysis module uses big data analysis technology to intelligently analyze the pre-processed data and identify abnormal conditions of industrial equipment; The intelligent decision-making module optimizes and controls the abnormal state of the production process according to the analysis results of the abnormal analysis module, and generates real-time decision instructions; The feedback control module performs feedback control on the industrial equipment according to the decision instructions generated by the intelligent decision module; The human-computer interaction module includes an industrial large screen, mobile applications, and a Web interface, which are used to display and interact with various data of industrial equipment.

2. According to the industrial Internet-based intelligent device data interaction system according to claim 1, it is characterized by: In the data collection and preprocessing module, the process of data collection and preprocessing includes: Deploy various sensors and data acquisition devices in industrial environments, including temperature sensors, humidity sensors, pressure sensors, and equipment status monitors; According to the monitoring characteristics and requirements of industrial equipment, set the sampling frequency, monitor the status of industrial equipment and environment in real time, and obtain real-time information data on temperature, humidity, pressure, and equipment status; Convert the collected raw data into a unified format and clean the collected data; The preprocessed data is encoded and encrypted, and the preprocessed and encoded data is transmitted to the edge computing module for further analysis.

3. According to the industrial Internet-based intelligent device data interaction system according to claim 2, it is characterized by: In the edge computing module, the process of using edge computing capabilities to reduce the amount of data transmitted to the cloud includes: The edge computing module receives the preprocessed data and compresses it using the Huffman coding compression algorithm to reduce the amount of data transmission. Based on the characteristics of Huffman coding, the character frequency in the coding process is further used to filter key data. Encode the filtered and compressed data and encrypt the data using a strong encryption algorithm; Before transmitting the data to the cloud, the edge computing module is used to integrate the filtered, compressed and encrypted data, merge multiple data packets into one data packet, and transmit it to the data transmission module.

4. According to claim 3, a smart device data interaction system based on industrial Internet is characterized in that: In the data transmission module, the process of optimizing the data sharing transmission path includes: The data transmission module receives the industrial equipment data packets integrated from the edge computing module, identifies its communication protocol, and determines the target protocol according to the communication protocol requirements of the target cloud platform. It uses the built-in protocol conversion engine to convert the received data packets from the original protocol to the target protocol. The data transmission module builds the corresponding information model according to the data structure and attributes of the industrial equipment, and formats and converts the received data according to the information model; The data transmission module selects the optimal data transmission path and performs load balancing according to the network status and data transmission requirements, and uses the data transmission protocol to transmit the protocol-converted and formatted data packets to the cloud, and uses the cloud to further analyze and process the uploaded data.

5. According to the industrial Internet-based intelligent device data interaction system according to claim 4, it is characterized in that: In the abnormality analysis module, the process of identifying abnormal status of industrial equipment includes: Collect historical data and known abnormal case data, and further clean and normalize them; By comparing the data features of normal state and abnormal state, the abnormal features reflecting the abnormal state of industrial equipment are extracted, and the data are divided into different categories according to the severity of the abnormal state to obtain the abnormal feature set; The abnormal feature set is divided into a training set and a test set. The training set data is combined with the decision tree model to build an anomaly detection model to monitor the status of industrial equipment, and the test set data is used to evaluate the trained anomaly detection model. Combining the analysis results of the anomaly detection model with the associated data of the anomaly feature set, the anomaly detection coefficient is obtained to identify the abnormal state of industrial equipment, and different warning levels are divided according to the severity of the abnormal state, namely low warning level, medium warning level and high warning level; Match the corresponding warning threshold to each warning level. Once an abnormal state is detected, a warning signal of the corresponding warning level will be issued to notify relevant personnel to handle it.

6. According to the industrial Internet-based intelligent device data interaction system of claim 5, it is characterized by: The calculation expression of the abnormality detection coefficient is: ； ； in, is the anomaly detection coefficient, is the state value deviation function, is the currently observed state value of the industrial equipment, is the benchmark value of the state value in the historical data, is the standard deviation of the state value in the historical data, which is used to measure the degree of dispersion of the data. is the maximum value of the normal state in the historical data, is the minimum value of abnormal state in historical data, The value range is between 0 and 1.

7. The data interaction system of intelligent devices based on industrial Internet according to claim 6 is characterized in that: Get the value of the anomaly detection coefficient and the preset warning threshold of the warning level to match the three warning levels, which are: Low alert level: ; Medium warning level: ; High alert level: ; in, is the anomaly detection coefficient, is the lower threshold corresponding to the medium warning level and the upper threshold corresponding to the low warning level, is the lower threshold corresponding to the high warning level and the upper threshold corresponding to the medium warning level, , .

8. The data interaction system of intelligent devices based on industrial Internet according to claim 7 is characterized in that: In the intelligent decision-making module, the process of generating real-time decision instructions includes: Receive the analysis results of the abnormal analysis module, including the abnormal detection coefficient of the equipment status and performance indicators, and analyze and determine the abnormal status and severity of the production process; After identifying and evaluating the abnormal state, the intelligent decision-making module selects a response strategy based on the preset optimization control strategy library. The response strategy includes adjusting production parameters, replacing faulty equipment, optimizing production processes, and formulating an optimization control plan based on the actual situation and the suggestions in the strategy library. Determine the optimal control plan, and the intelligent decision-making module generates corresponding real-time decision instructions, which include sending signals to adjust parameters to production equipment and sending notifications to operators to repair or replace equipment.

9. The data interaction system of intelligent devices based on industrial Internet according to claim 8 is characterized in that: In the feedback control module, the process of performing feedback control on industrial equipment includes: The feedback control module receives the decision instructions for adjusting equipment parameters, replacing faulty equipment, and optimizing production processes from the intelligent decision module, and analyzes the decision instructions; Generate corresponding control signals according to the parsed instruction content, and send the control signals to the control system of the industrial equipment through the communication interface; After receiving the control signal, the control system of the industrial equipment analyzes the signal and drives the target industrial equipment to perform corresponding operations; While performing the operation, the sensor collects the actual working status of the target industrial equipment and the status information of the changes in the operating parameters in real time to ensure that the target industrial equipment performs the corresponding operation according to the control signal and verify whether the effect of the target industrial equipment operation meets the expectations; Record a log of all feedback control operations, including the commands sent, device responses, operation times and results.

10. The data interaction system of intelligent devices based on industrial Internet according to claim 9 is characterized in that: In the human-computer interaction module, the process of displaying and interacting with various data of industrial equipment includes: Integrate various data generated by industrial equipment, including industrial equipment operating status, parameter settings, fault alarms, and performance indicators; Aggregate the integrated data and display the relevant data through industrial large screens, mobile applications, and web interfaces. It also provides historical data query functions, allowing users to view the historical performance and operation records of industrial equipment. When the status of industrial equipment is abnormal, alarms and notifications are sent to users through interface prompts, sounds, emails and text messages, allowing users to send decision-making instructions through the interface to adjust equipment parameters and perform specific operations; Record all user operation logs, including operation time, operation type and operation results.

Images