Data monitoring method based on RCP equipment and upper computer software data transmission

Abstract

The invention discloses a data monitoring method based on RCP equipment and upper computer software data transmission. Efficient data transmission and monitoring of the RCP equipment and an upper computer are achieved through an RCP protocol, efficient low-delay communication is achieved based on a UDP, routing information is added through a packaging layer, dynamic routing decisions are supported, and network adaptability is improved. Session table management ensures data integrity and reliability, and supports session recovery and data retransmission; the method has the remarkable advantages in the aspects of data processing efficiency, monitoring comprehensiveness, prediction intelligence, alarm accuracy and user experience.

Description

Technical Field

[0001] The invention relates to the technical field of Internet of Things, and in particular to a data monitoring method based on data transmission between RCP equipment and host computer software. Background Art

[0002] Traditional industrial control systems face challenges such as low data transmission efficiency, single monitoring methods, and high maintenance costs.

[0003] The equipment and host computer software have significant defects in the field of data transmission and data monitoring. The core problem lies in insufficient protocol support and poor network optimization capabilities, which lead to unstable data transmission. In data processing, insufficient computing power and intelligent algorithm support affect the preprocessing effect and reduce the efficiency of subsequent analysis. The unreasonable data storage architecture or poor query performance affects the efficiency of data retrieval. At the same time, the lack of advanced algorithm support makes it impossible to rely on AI technology to automatically detect abnormal data, and the alarm notification mechanism is not flexible or timely enough, which affects the efficiency of abnormal processing.

[0004] The existing patent CN202111331235.5 discloses a monitoring data processing method and device for an industrial control terminal, which relates to the field of industrial control technology and aims to solve the problem of poor monitoring data processing efficiency of existing industrial control terminals. It includes: obtaining equipment information, control function information and process flow information matching the industrial control terminals of at least two industrial control terminals, and establishing a terminal control network based on the equipment information, control function information and process flow information; sending each terminal node in the terminal control network to the industrial control terminal, collecting the monitoring data generated by the industrial control terminal, and predicting and processing the monitoring data collected by the industrial control terminal based on the prediction model to obtain at least one monitoring prediction result; determining the monitoring state matching at least one monitoring prediction result according to the network level and network attributes of the terminal control network; if the number of abnormal monitoring states of the industrial control terminals in the terminal control network is greater than the preset monitoring threshold, a monitoring alarm information is sent.

[0005] However, the above patent has the following disadvantages:

[0006] 1. Insufficient accuracy and applicability of the prediction model: The prediction model in this solution is of a single type, while different industrial scenarios may require different prediction models. The accuracy and applicability of the model directly affect the accuracy of the monitoring prediction results.

[0007] 2. The abnormal state judgment criteria lack clarity: Different monitoring data and industrial scenarios may require different abnormal judgment logic and threshold settings. The lack of clarity may lead to false alarms or missed alarms.

[0008] 3. Complexity of network hierarchy and attributes: This solution determines the monitoring status according to the network hierarchy and network attributes of the terminal control network, which may involve complex network structure and attribute analysis, which requires the system to have strong data processing and logical judgment capabilities. If the system is improperly designed or the processing power is insufficient, it may lead to inefficient or erroneous monitoring status judgment.

[0009] 4. Real-time and delay issues: In industrial control environments, real-time is very important. If there are delays in the acquisition, transmission, processing and status judgment of monitoring data, key abnormal events may be missed or control decisions may be delayed. This solution ignores how to optimize the real-time performance of these links.

[0010] 5. Insufficient system scalability and flexibility: With the continuous expansion and upgrading of industrial control systems, the number of industrial control terminals and monitoring data may increase significantly. The system needs to have good scalability and flexibility to cope with possible changes in the future. The article does not discuss the system's scalability design and flexibility implementation in detail.

[0011] 6. Poor user-friendliness: The solution lacks an intuitive and easy-to-use user interface so that operators can quickly master the system's usage and monitoring status. For operators, the interface friendliness and ease of use of the monitoring system are also very important. Summary of the invention

[0012] The purpose of the present invention is to provide a data monitoring method based on data transmission between RCP equipment and host computer software. The present invention has the advantages of high transmission reliability, low delay, strong network adaptability and simplified communication between devices.

[0013] The technical solution of the present invention is a data monitoring method based on data transmission between RCP equipment and host computer software, including the following process:

[0014] S1. The collection gateway collects IoT data of the RCP device cluster based on the RCP protocol;

[0015] S2, uploading the data to the data receiving and processing unit through the data transmission network;

[0016] S3, after the data receiving and processing unit performs preliminary data processing, the processed data is sent to the time series database for storage;

[0017] S4, obtain historical data from the time series database, use the deep learning algorithm to build a prediction model and perform training prediction, store the prediction results and send them to the host computer monitoring platform;

[0018] S5. The host computer monitoring platform displays data and prediction results in real time and executes alarm measures according to the alarm threshold.

[0019] In the aforementioned data monitoring method based on data transmission between RCP device and host computer software, the RCP protocol described in S1 is a private communication protocol with routing function implemented based on UDP protocol, and its specific contents are as follows:

[0020] S1.1, adding routing information: based on the UDP protocol, adding an encapsulation layer to add additional routing information to the UDP message; the routing information at least includes the next hop address, path selection strategy and hop limit to ensure that the data packet can be transmitted along the predetermined path;

[0021] S1.2, Data packet encapsulation: encapsulate user data, UDP header and routing information into a complete data packet;

[0022] S1.3, Session establishment: When IoT devices start communicating, the RCP protocol creates a session table entry on their respective endpoints; the session table entry records at least basic information including the session identifier, source address, destination address, port number, and the current state of the session;

[0023] S1.4, state information recording: As data packets are sent and received, session entries are continuously updated; the session entries record key information including at least the sequence number of the data packets sent in each session, the confirmation information of the received data packets, and the retransmission request;

[0024] S1.5, routing decision: Based on the routing information in the encapsulation layer, the network device makes corresponding routing decisions and sends the data packet to the corresponding next-hop address; if a failure or congestion occurs in the path, the RCP protocol will dynamically adjust according to the preset routing selection strategy;

[0025] S1.6, Multi-path transmission: The RCP protocol supports multi-path transmission, which improves the reliability and efficiency of transmission; the data packet can be sent simultaneously through multiple paths, which increases the probability of successful transmission and reduces latency;

[0026] S1.7, timeout detection: if the data packet does not receive confirmation information within the predetermined time, it is considered that the data packet may have been lost; the RCP protocol triggers the timeout detection mechanism and prepares for retransmission;

[0027] S1.8, data retransmission: According to the records in the session table, the RCP protocol will select the lost data packets for retransmission; the data packets to be retransmitted will be processed by the encapsulation layer again and the corresponding routing information will be added; the data retransmission process will continue until the data packet is successfully delivered or the retransmission limit is reached.

[0028] In the aforementioned data monitoring method based on data transmission between RCP equipment and host computer software, the prediction model described in S4 has the following specific contents:

[0029] The forecasting model adopts the ARIMA model to accurately forecast data values ​​by identifying at least data trends, seasonality and random fluctuation characteristics, thereby optimizing resource scheduling and demand forecasting;

[0030] By comparing the actual observed values ​​with the predicted values ​​of the ARIMA model, abnormal conditions in the data can be identified to diagnose equipment failures and conduct safety monitoring.

[0031] The prediction model can optimize the performance of the Internet of Things system.

[0032] In the aforementioned data monitoring method based on data transmission between RCP equipment and host computer software, when the prediction model is applied to the energy management system, the energy allocation strategy can be adjusted according to the energy consumption prediction results to improve energy utilization efficiency. The specific steps are as follows:

[0033] S6.1. Collect the original RCP equipment point data in real time and transfer it to the database, including at least key parameters such as operating status, temperature, pressure, and flow;

[0034] S6.2. Perform pre-processing procedures on the collected point data, clean the data according to the equipment category and data type; classify and organize the data according to the equipment category and data type; and construct a time series data set so that each data set can accurately reflect the operating status and change trend of a specific device within a given time period;

[0035] S6.3. Perform a stationarity test on time series data;

[0036] S6.4. Analyze the residuals of the ARIMA model to test the fitting effect and prediction ability of the ARIMA model; after confirming the effectiveness of the ARIMA model, use the model to predict the future operating status of the RCP equipment and evaluate the risk level of the equipment based on the prediction results;

[0037] S6.5. After the equipment risk is predicted, the risk value of each equipment point is calculated through the risk value calculation model to provide strong support for subsequent monitoring and early warning;

[0038] S6.6. Set alarm thresholds based on the risk level of the equipment and actual operating requirements; formulate different levels of alarms and corresponding response measures based on the specific attributes and importance of the equipment to achieve more accurate and efficient monitoring and risk warning;

[0039] S6.7. Regularly monitor the forecasting performance of the ARIMA model, including at least key indicators such as accuracy and recall, so as to identify and resolve potential problems in a timely manner.

[0040] In the aforementioned data monitoring method based on data transmission between RCP equipment and host computer software, the alarm threshold described in S5, the user can set the corresponding alarm threshold for the monitoring point of the Internet of Things, the specific contents of which are as follows:

[0041] For Boolean data, set an alert when the state changes;

[0042] For analog data, the alarm thresholds of high alarm, high high alarm, low alarm and low low alarm can be set at the same time, and the corresponding alarm levels can be configured. The alarm levels include at least warning, minor, general, major and severe alarms;

[0043] Different alarm modes can be selected for different alarm levels;

[0044] Customize alarm SMS templates based on data tags to ensure the accuracy of alarm information.

[0045] In the aforementioned data monitoring method based on data transmission between RCP device and host computer software, the user interaction interface described in S5 has a data display module, a data query module, a result prediction module, a status monitoring module and an alarm module.

[0046] In the aforementioned data monitoring method based on data transmission between RCP equipment and host computer software, the data display module includes a data panel that can display real-time data and reflect data change trends with dynamic icons;

[0047] The data query module includes a time selector, which allows users to select a specific time period, query and display historical data within the time period; it includes a historical data chart, which displays historical data in the form of a chart, so that users can deeply analyze data trends and modify selected data;

[0048] The result prediction module includes a prediction chart to display the prediction results, including the data trend prediction for a period of time in the future; it includes a prediction error to display the prediction error range to help users evaluate the reliability of the prediction results;

[0049] The status monitoring module includes a device map to display the device distribution and status; a device list to list the basic information of all monitored devices; and device details to display the detailed monitoring information of the device.

[0050] The alarm module includes an alarm panel that displays currently unprocessed alarm information; an alarm threshold setting that allows users to set the alarm threshold; and a notification setting that supports multiple notification methods to ensure that alarm information can be received in a timely manner.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] By building a private protocol RCP, low-latency communication based on UDP is achieved; the protocol introduces an encapsulation layer and routing mechanism, which not only simplifies the data transmission process, but also significantly improves the data transmission efficiency, which is particularly suitable for industrial control fields with extremely high real-time requirements; the protocol supports dynamic routing decisions and can automatically adjust the transmission path according to changes in the network environment, enhancing the adaptability and stability of the network; the protocol design is simple and easy to integrate into existing industrial control systems, reducing the cost of system upgrades and modifications;

[0053] Although the existing technology can improve data processing efficiency, it focuses more on the data processing level. The present application starts from the communication level and provides a more efficient communication foundation for the entire industrial control system, thereby indirectly promoting the improvement of data processing efficiency and enhancing the overall performance and reliability of the system.

[0054] By adopting more efficient algorithms and data processing technologies, the processing efficiency of monitoring data has been significantly improved, which not only solves the efficiency problem in existing technologies, but also achieves a qualitative leap in real-time performance and accuracy.

[0055] The sources and analysis dimensions of monitoring data have been expanded to include not only equipment information, control function information, and process flow information, but also data from more dimensions such as environmental parameters and equipment life prediction, making the monitoring results more comprehensive and accurate.

[0056] The application of prediction models is more advanced and intelligent. Advanced algorithms such as deep learning and machine learning are used to achieve in-depth mining and intelligent prediction of monitoring data, which can detect potential problems in advance and avoid failures.

[0057] The monitoring status judgment and alarm mechanism are more flexible and intelligent, and can dynamically adjust the judgment criteria according to the network level and network attributes, reduce false alarms and missed alarms, and improve the accuracy and timeliness of alarms;

[0058] Focusing on user experience and system integration, it provides a more user-friendly interface and rich interfaces to facilitate users to carry out monitoring management and system integration, and improves the ease of use and scalability of the system;

[0059] In summary, the present invention demonstrates significant advantages in data processing efficiency, monitoring comprehensiveness, predictive intelligence, alarm accuracy and user experience. DETAILED DESCRIPTION

[0060] The present invention will be further described below in conjunction with the embodiments, but they are not intended to limit the present invention.

[0061] Embodiment: A data monitoring method based on data transmission between an RCP device and a host computer software includes the following process:

[0062] S1. The collection gateway collects IoT data of the RCP device cluster based on the RCP protocol;

[0063] S2, upload data to the data receiving and processing unit through the data transmission network; support wireless communication protocols or wired networks such as Wi-Fi, LoRa, NB-IoT, MQTT, etc.;

[0064] S3. After the data receiving and processing unit performs preliminary data processing, the processed data is sent to the time series database for storage; data processing includes data cleaning, format conversion, etc.

[0065] S4, obtain historical data from the time series database, use deep learning algorithms to build a prediction model, receive new data in real time, use the trained model to make predictions, and store and send the prediction results to the host computer monitoring platform;

[0066] S5. The host computer monitoring platform supports desktop and mobile terminals, provides a user interactive interface, and is responsible for displaying real-time data, historical data, and AI prediction results. The monitoring platform is equipped with tools such as real-time data charts and prediction curves to help users gain insight into data trends. Users can set alarm thresholds. Once real-time data or prediction results exceed the set threshold, the system will trigger an alarm notification and promptly inform the user through various means such as email, text messages, and WeChat public account messages.

[0067] RCP protocol refers to Routable Communication Protocol.

[0068] The RCP protocol described in S1 is a private communication protocol with routing function implemented based on the UDP protocol. Its specific contents are as follows:

[0069] S1.1, adding routing information: based on the UDP protocol, adding an encapsulation layer to add additional routing information to the UDP message; the routing information at least includes the next hop address, path selection strategy and hop limit to ensure that the data packet can be transmitted along the predetermined path;

[0070] S1.2, Data packet encapsulation: Encapsulate user data, UDP header and routing information into a complete data packet; when the data packet is transmitted in the network, the router or other network device can make forwarding decisions based on the routing information in the encapsulation layer;

[0071] S1.3, Session establishment: When IoT devices start communicating, the RCP protocol creates a session table entry on their respective endpoints; the session table entry records at least basic information including the session identifier, source address, destination address, port number, and the current state of the session, such as active, paused, terminated, etc.;

[0072] S1.4, state information recording: As data packets are sent and received, session entries are continuously updated; the session entries record key information including at least the sequence number of the data packets sent in each session, the confirmation information of the received data packets, and the retransmission request;

[0073] S1.5, routing decision: Based on the routing information in the encapsulation layer, the network device makes corresponding routing decisions and sends the data packet to the corresponding next-hop address; if a failure or congestion occurs in the path, the RCP protocol will dynamically adjust according to the preset routing selection strategy;

[0074] S1.6, Multi-path transmission: The RCP protocol supports multi-path transmission, which improves the reliability and efficiency of transmission; the data packet can be sent simultaneously through multiple paths, which increases the probability of successful transmission and reduces latency;

[0075] S1.7, timeout detection: if the data packet does not receive confirmation information within the predetermined time, it is considered that the data packet may have been lost; the RCP protocol triggers the timeout detection mechanism and prepares for retransmission;

[0076] S1.8, data retransmission: According to the records in the session table, the RCP protocol will select the lost data packets for retransmission; the data packets to be retransmitted will be processed by the encapsulation layer again and the corresponding routing information will be added; the data retransmission process will continue until the data packet is successfully delivered or the retransmission limit is reached.

[0077] The prediction model described in S4 is as follows:

[0078] The forecasting model adopts the ARIMA model to accurately forecast data values ​​by identifying at least data trends, seasonality and random fluctuation characteristics, thereby optimizing resource scheduling and demand forecasting;

[0079] By comparing the actual observed values ​​with the predicted values ​​of the ARIMA model, abnormal conditions in the data can be identified to diagnose equipment failures and conduct safety monitoring.

[0080] The prediction model can optimize the performance of the Internet of Things system.

[0081] When the prediction model is applied to the energy management system, the energy allocation strategy can be adjusted according to the energy consumption prediction results to improve energy utilization efficiency. The specific steps are as follows:

[0082] S6.1. Collect the original RCP equipment point data in real time and transfer it to the database, including at least key parameters such as operating status, temperature, pressure, and flow rate; data collection is carried out in real time to ensure the timeliness and accuracy of the information;

[0083] S6.2. Perform preprocessing procedures on the collected point data, clean the data according to the equipment category and data type to eliminate interference factors such as abnormal values ​​and missing values; classify and organize the data according to equipment category (such as pumps, valves, sensors, etc.) and data type (such as temperature, pressure, vibration, etc.); and construct a time series data set so that each data set can accurately reflect the operating status and change trend of a specific device within a given time period;

[0084] S6.3. To ensure the accuracy of ARIMA model prediction, the time series data is tested for stationarity. This involves careful observation of the trend, seasonality and random characteristics of the data set. For data sets that show non-stationarity in the test results, technical means such as differentiation will be used to adjust them until the stationarity standard is met. After the data is processed, correlation analysis will be carried out to accurately determine the lag order (p), difference order (d) and moving average order (q) of the model. By comparing the model performance under different parameter combinations, the most suitable ARIMA model structure and its parameters are scientifically selected.

[0085] S6.4. Analyze the residuals of the ARIMA model to test the fitting effect and prediction ability of the ARIMA model; evaluate whether the model fully captures the dynamic characteristics of the data by examining the distribution of the residuals, autocorrelation and other properties; after confirming the effectiveness of the ARIMA model, use the model to predict the future operating status of the RCP equipment, and evaluate the risk level of the equipment based on the prediction results;

[0086] S6.5. After the equipment risk is predicted, the risk value of each equipment point is calculated through the risk value calculation model to provide strong support for subsequent monitoring and early warning; the prediction results are combined with the actual operating status of the equipment, historical fault data, industry standards and other factors to build a reasonable risk value calculation model;

[0087] S6.6. Set alarm thresholds based on the risk level of the equipment and actual operating requirements; formulate different levels of alarms and corresponding response measures based on the specific attributes and importance of the equipment to achieve more accurate and efficient monitoring and risk warning;

[0088] S6.7. Regularly monitor the forecasting performance of the ARIMA model, including at least key indicators such as accuracy and recall, so as to identify and resolve potential problems in a timely manner.

[0089] In the aforementioned data monitoring method based on data transmission between RCP equipment and host computer software, the alarm threshold described in S5, the user can set the corresponding alarm threshold for the monitoring point of the Internet of Things, the specific contents of which are as follows:

[0090] For Boolean data, set an alert when the state changes;

[0091] For analog data, the alarm thresholds of high alarm, high high alarm, low alarm and low low alarm can be set at the same time, and the corresponding alarm levels can be configured. The alarm levels include at least warning, minor, general, major and severe alarms;

[0092] Different alarm modes can be selected for different alarm levels;

[0093] Customize alarm SMS templates based on data tags to ensure the accuracy of alarm information.

[0094] The user interaction interface described in S5 comprises a data display module, a data query module, a result prediction module, a status monitoring module and an alarm module.

[0095] The data display module includes a data panel that can display real-time data and reflect data change trends with dynamic icons;

[0096] The data query module includes a time selector, which allows users to select a specific time period, query and display historical data within the time period; it includes a historical data chart, which displays historical data in the form of a chart, so that users can deeply analyze data trends and modify selected data;

[0097] The result prediction module includes a prediction chart to display the prediction results, including the data trend prediction for a period of time in the future; it includes a prediction error to display the prediction error range to help users evaluate the reliability of the prediction results;

[0098] The status monitoring module includes a device map to display the device distribution and status; a device list to list the basic information of all monitored devices; and device details to display the detailed monitoring information of the device.

[0099] The alarm module includes an alarm panel that displays currently unprocessed alarm information; an alarm threshold setting that allows users to set the alarm threshold; and a notification setting that supports multiple notification methods to ensure that alarm information can be received in a timely manner.

[0100] The alarm thresholds include high alarm, high high alarm, low alarm, and low low alarm, and their specific contents are as follows:

[0101] High alarm: refers to the alarm state triggered when the monitored parameter value exceeds the preset high threshold; for example, in the temperature monitoring system, if the set temperature high threshold is 30℃, when the actual temperature exceeds 30℃, the system will issue a high alarm to prompt relevant personnel to pay attention or take corresponding measures;

[0102] High-high alarm: It is a further extension of high alarm. It is usually used to set an emergency alarm threshold higher than the high threshold. When the monitored parameter value not only exceeds the high threshold but also reaches a higher emergency threshold, the system will trigger a high-high alarm. High-high alarm is usually used to deal with more serious abnormal situations, which require faster response and higher level of attention.

[0103] Low alarm: Corresponding to high alarm, it refers to the alarm state triggered when the monitored parameter value is lower than the preset low threshold; for example, in the liquid level monitoring system, if the set liquid level low threshold is 50%, when the actual liquid level is lower than 50%, the system will issue a low alarm to remind relevant personnel to pay attention to the problems that may be caused by too low liquid level;

[0104] Low-low report: It is a further extension of the low report and is used to set an emergency alarm threshold lower than the low threshold. When the monitored parameter value is not only lower than the low threshold but also reaches a lower emergency threshold, the system will trigger a low-low report. Low-low report is also used to deal with more serious abnormal situations, which require more timely intervention and a higher level of attention.

[0105] This method has the following characteristics:

[0106] 1. Efficient private protocol: By implementing a customized communication protocol RCP based on the User Datagram Protocol (UDP), it has routing functions; through session table management and data retransmission, it improves the unreliability of UDP; the encapsulation layer and routing mechanism optimize the data transmission path, reduce network jumps and delays, and improve real-time performance; support multi-path transmission and dynamic routing selection, adapt to network changes, avoid congestion and failures, and enhance transmission stability and efficiency; the protocol simplifies communication between IoT devices, reducing complexity and cost; with the development of the Internet of Things, the efficiency and reliability of the protocol make it suitable for large-scale deployment.

[0107] 2. Diversified communication protocol support: Support for multiple wireless communication protocols (such as Wi-Fi, LoRa, NB-IoT, MQTT) and wired networks to ensure that data can be transmitted to the data receiving and processing unit stably and quickly; this key point improves the compatibility and flexibility of the system, enabling it to adapt to different industrial environments and equipment requirements.

[0108] 3. Deep learning prediction model: Use deep learning algorithms to build a prediction model, analyze historical data, and receive new data in real time for prediction; this key point uses advanced artificial intelligence technology to improve the accuracy and real-time nature of the prediction, providing a scientific basis for decision-making.

[0109] 4. Multi-platform monitoring interface: Provides a host computer monitoring platform for desktop and mobile terminals to display real-time data, historical data and AI prediction results; this key point enhances the user's data insight ability, allowing users to monitor and manage anytime and anywhere.

[0110] 5. Real-time alarm and notification: Supports setting alarm thresholds and triggering alarm notifications to ensure timely response to abnormal situations; this key point improves the system's emergency response capabilities and ensures the safety of industrial production and operation and maintenance

[0111] Furthermore, edge computing can be used to process data to reduce the burden of data transmission; or cloud computing services can be used to replace self-built data receiving and processing units to improve scalability and flexibility; at the same time, the prediction model can try to integrate other algorithms such as time series analysis to enrich the prediction dimension; the monitoring platform can consider integrating video monitoring to achieve more intuitive on-site monitoring. These alternatives can optimize the system at different levels to achieve the same monitoring purpose.

[0112] Application Analysis

[0113] The present invention is compared with the prior art under the same conditions and it is found that the present invention performs better in the following aspects:

[0114] 1. Low-latency communication: In a typical industrial control network environment of the prior art, using the unoptimized UDP protocol for data transmission, the average delay is about 10 milliseconds;

[0115] After the present invention adopts the RCP protocol, through actual testing, the average delay is reduced to less than 3 milliseconds, and the minimum can be less than 1 millisecond, which significantly reduces the communication delay;

[0116] On an automated production line, critical control signals, such as emergency stop commands, are transmitted via the RCP protocol, ensuring that they reach all relevant equipment in a very short time (<1 millisecond), effectively avoiding production accidents caused by delays.

[0117] 2. Improved data transmission efficiency: Under the same network conditions, it takes about 30 seconds to transmit 1GB of monitoring data using traditional protocols;

[0118] After the present invention adopts the RCP protocol, it only takes about 20 seconds to transmit the same amount of monitoring data, and the efficiency is improved by about 33%;

[0119] In the scenario where large data centers monitor a large number of industrial equipment in real time, the high efficiency of the RCP protocol makes data updates more timely, providing strong support for quick decision-making.

[0120] 3. Improved comprehensiveness and accuracy of monitoring data: In the existing technology, the data source of the monitoring system only contains basic information such as equipment status and control instructions;

[0121] The present invention is extended to include multi-dimensional information such as environmental parameters (such as temperature and humidity), equipment life prediction, and detailed process flow data, and the number of monitoring data items has increased by more than 50%;

[0122] In practical applications, the present invention successfully warned of a possible equipment failure due to abnormal temperature by integrating environmental parameters and equipment life prediction data, thus avoiding production suspension losses.

[0123] 4. Intelligent prediction and warning accuracy: The existing technology is based on simple statistics or rules, and the accuracy rate is about 70%;

[0124] The present invention uses deep learning and machine learning algorithms to increase the prediction accuracy to more than 90%, especially significantly improving the ability to detect potential faults in advance;

[0125] By dynamically adjusting the judgment criteria and reducing the false alarm and missed alarm mechanism, the alarm accuracy of the present invention is increased from 85% to more than 95%, and the alarm response time is shortened to seconds;

[0126] In actual applications, the present invention has predicted an impending material blockage problem on a production line several hours in advance and automatically triggered an emergency plan, effectively avoiding production interruptions.

[0127] 5. User experience and system integration: Compared with existing technologies, users of the RCP system generally report that the system has a user-friendly interface, is easy to operate, and is easy to use;

[0128] The system integration process of the present invention is simple and fast, and the average integration time is shortened by more than 30% compared with the existing technical solutions; it can quickly realize seamless data connection and automated optimization of processes, significantly improving the overall operational efficiency.

[0129] In summary, it can be clearly seen that the present invention has significant advantages in low-latency communication, data transmission efficiency, monitoring comprehensiveness, intelligent prediction and alarm accuracy, and user experience.

Claims

1. A data monitoring method based on data transmission between RCP equipment and host computer software, characterized in that: The process includes: S1. The collection gateway collects IoT data of the RCP device cluster based on the RCP protocol; S2, uploading the data to the data receiving and processing unit through the data transmission network; S3, after the data receiving and processing unit performs preliminary data processing, the processed data is sent to the time series database for storage; S4, obtain historical data from the time series database, use the deep learning algorithm to build a prediction model and perform training prediction, store the prediction results and send them to the host computer monitoring platform; S5. The host computer monitoring platform displays data and prediction results in real time and executes alarm measures according to the alarm threshold.

2. A data monitoring method based on RCP equipment and host computer software data transmission according to claim 1, characterized in that: The RCP protocol described in S1 is a private communication protocol with routing function implemented based on the UDP protocol. Its specific contents are as follows: S1.1, adding routing information: based on the UDP protocol, adding an encapsulation layer to add additional routing information to the UDP message; the routing information at least includes the next hop address, path selection strategy and hop limit to ensure that the data packet can be transmitted along the predetermined path; S1.2, Data packet encapsulation: encapsulate user data, UDP header and routing information into a complete data packet; S1.3, Session establishment: When IoT devices start communicating, the RCP protocol creates a session table entry on their respective endpoints; the session table entry records at least basic information including the session identifier, source address, destination address, port number, and the current state of the session; S1.4, state information recording: As data packets are sent and received, session entries are continuously updated; the session entries record key information including at least the sequence number of the data packets sent in each session, the confirmation information of the received data packets, and the retransmission request; S1.5, routing decision: Based on the routing information in the encapsulation layer, the network device makes corresponding routing decisions and sends the data packet to the corresponding next-hop address; if a failure or congestion occurs in the path, the RCP protocol will dynamically adjust according to the preset routing selection strategy; S1.6, Multi-path transmission: The RCP protocol supports multi-path transmission, which improves the reliability and efficiency of transmission; the data packet can be sent simultaneously through multiple paths, which increases the probability of successful transmission and reduces latency; S1.7, timeout detection: if the data packet does not receive confirmation information within the predetermined time, it is considered that the data packet may have been lost; the RCP protocol triggers the timeout detection mechanism and prepares for retransmission; S1.8, data retransmission: According to the records in the session table, the RCP protocol will select the lost data packets for retransmission; the data packets to be retransmitted will be processed by the encapsulation layer again and the corresponding routing information will be added; the data retransmission process will continue until the data packet is successfully delivered or the retransmission limit is reached.

3. A data monitoring method based on data transmission between RCP equipment and host computer software according to claim 1, characterized in that: The prediction model described in S4 is as follows: The forecasting model adopts the ARIMA model to accurately forecast data values ​​by identifying at least data trends, seasonality and random fluctuation characteristics, thereby optimizing resource scheduling and demand forecasting; By comparing the actual observed values ​​with the predicted values ​​of the ARIMA model, abnormal conditions in the data can be identified to diagnose equipment failures and conduct safety monitoring. The prediction model can optimize the performance of the Internet of Things system.

4. A data monitoring method based on RCP equipment and host computer software data transmission according to claim 3, characterized in that: When the prediction model is applied to the energy management system, the energy allocation strategy can be adjusted according to the energy consumption prediction results to improve energy utilization efficiency. The specific steps are as follows: S6.

1. Collect the original RCP equipment point data in real time and transfer it to the database, including at least key parameters such as operating status, temperature, pressure, and flow; S6.

2. Perform pre-processing procedures on the collected point data, clean the data according to the equipment category and data type; classify and organize the data according to the equipment category and data type; and construct a time series data set so that each data set can accurately reflect the operating status and change trend of a specific device within a given time period; S6.

3. Perform a stationarity test on time series data; S6.

4. Analyze the residuals of the ARIMA model to test the fitting effect and prediction ability of the ARIMA model; after confirming the effectiveness of the ARIMA model, use the model to predict the future operating status of the RCP equipment and evaluate the risk level of the equipment based on the prediction results; S6.

5. After the equipment risk is predicted, the risk value of each equipment point is calculated through the risk value calculation model to provide strong support for subsequent monitoring and early warning; S6.

6. Set alarm thresholds based on the risk level of the equipment and actual operating requirements; formulate different levels of alarms and corresponding response measures based on the specific attributes and importance of the equipment to achieve more accurate and efficient monitoring and risk warning; S6.

7. Regularly monitor the forecasting performance of the ARIMA model, including at least key indicators such as accuracy and recall, so as to identify and resolve potential problems in a timely manner.

5. A data monitoring method based on RCP equipment and host computer software data transmission according to claim 1, characterized in that: The alarm threshold described in S5, the user can set the corresponding alarm threshold for the monitoring point of the Internet of Things, the specific contents are as follows: For Boolean data, set an alert when the state changes; For analog data, the alarm thresholds of high alarm, high high alarm, low alarm and low low alarm can be set at the same time, and the corresponding alarm levels can be configured. The alarm levels include at least warning, minor, general, major and severe alarms; Different alarm modes can be selected for different alarm levels; Customize alarm SMS templates based on data tags to ensure the accuracy of alarm information.

6. A data monitoring method based on data transmission between RCP equipment and host computer software according to claim 1, characterized in that: The user interaction interface described in S5 comprises a data display module, a data query module, a result prediction module, a status monitoring module and an alarm module.

7. A data monitoring method based on data transmission between RCP equipment and host computer software according to claim 6, characterized in that: The data display module includes a data panel that can display real-time data and reflect data change trends with dynamic icons; The data query module includes a time selector, which allows users to select a specific time period, query and display historical data within the time period; it includes a historical data chart, which displays historical data in the form of a chart, so that users can deeply analyze data trends and modify selected data; The result prediction module includes a prediction chart to display the prediction results, including the data trend prediction for a period of time in the future; it includes a prediction error to display the prediction error range to help users evaluate the reliability of the prediction results; The status monitoring module includes a device map to display the device distribution and status; a device list to list the basic information of all monitored devices; and device details to display the detailed monitoring information of the device. The alarm module includes an alarm panel that displays currently unprocessed alarm information; an alarm threshold setting that allows users to set the alarm threshold; and a notification setting that supports multiple notification methods to ensure that alarm information can be received in a timely manner.