Real-time monitoring and early warning platform for intermediate frequency furnace cooling water system based on internet of things

Abstract

The application provides a real-time monitoring and early warning platform for a cooling water system of an intermediate frequency furnace based on an Internet of Things, comprising: a sensing layer for collecting operation parameters of each waterway of the cooling water system and an operation state of a monitoring device in real time, and judging whether the cooling water system and the monitoring device are abnormal; a network layer for preprocessing the collected operation parameters and uploading to a platform layer; the platform layer is used for analyzing the uploaded data, optimizing and adjusting the operation parameters of the cooling water system according to the analysis result; and when the cooling water system is abnormal, an abnormal early warning notice is sent to a communication terminal of a relevant person by using wireless communication technology. The application realizes all-weather, all-around remote online monitoring of the cooling water system of the intermediate frequency furnace, effectively improves the safety and stability of the operation of the cooling water system, and optimizes and adjusts the parameters of the cooling water system according to the monitoring data, thereby reducing the energy consumption and maintenance cost of the intermediate frequency furnace cooling.

Description

IoT-based real-time monitoring and early warning platform for intermediate frequency furnace cooling water system Technical Field

[0001] This invention relates to the fields of Internet of Things (IoT) technology and industrial equipment monitoring technology, and in particular to a real-time monitoring and early warning platform for a medium-frequency furnace cooling water system based on IoT. Background Technology

[0002] In modern industrial production systems, medium-frequency furnaces are widely used in key manufacturing fields such as steel smelting, non-ferrous metal processing, and mechanical heat treatment due to their advantages of high efficiency, energy saving, and fast melting speed. However, medium-frequency furnaces generate a large amount of heat during operation. As a core component to ensure stable operation of the equipment, its cooling water system must continuously and efficiently control the equipment temperature within a safe range. Once the cooling system malfunctions, it may lead to serious damage to the equipment or even cause a safety accident.

[0003] Traditional monitoring methods relying on manual inspections and single-point alarm devices are limited by the working hours of supervisors and cannot cover high-risk periods such as nighttime. Independently operating alarm devices lack remote monitoring and intelligent analysis capabilities and cannot proactively report anomalies when sensors malfunction or are manually shut down. Moreover, some companies often choose to turn off alarm devices to avoid downtime for maintenance triggered by parameter fluctuations in order to reduce short-term costs, resulting in a situation of "installed but not used, used but ineffective," creating a vicious cycle of "operating with defects" in medium-frequency furnaces. Summary of the Invention

[0004] This invention provides an IoT-based real-time monitoring and early warning platform for the cooling water system of an intermediate frequency furnace, which solves the above-mentioned problems. It enables all-weather, all-round remote online monitoring of the cooling water system of the intermediate frequency furnace, effectively improving the safety and stability of the cooling water system operation. Based on the monitoring data, the parameters of the cooling water system are optimized and adjusted, effectively reducing the energy consumption and maintenance costs of the intermediate frequency furnace cooling.

[0005] This invention provides a real-time monitoring and early warning platform for a medium-frequency furnace cooling water system based on the Internet of Things, comprising:

[0006] The sensing layer is used to collect the operating parameters of each water path in the cooling water system and the operating status of the monitoring equipment in real time, and to determine whether there are any abnormalities in the cooling water system and the monitoring equipment.

[0007] The operating parameters include inlet and outlet water flow rate, inlet and outlet water temperature, and inlet and outlet water pressure.

[0008] The network layer is used to preprocess the collected operating parameters and upload them to the platform layer.

[0009] The platform layer is used to analyze the uploaded data and optimize and adjust the operating parameters of the cooling water system based on the analysis results.

[0010] And when there is an abnormality in the cooling water system, an abnormality warning notification will be sent to the communication terminal of relevant personnel using wireless communication technology.

[0011] Preferably, in a real-time monitoring and early warning platform for an IoT-based medium-frequency furnace cooling water system, the sensing layer includes:

[0012] The data acquisition unit is used to collect the operating parameters of each water circuit based on the monitoring equipment installed at the inlet of each water-cooled coil and induction coil in the cooling water system.

[0013] The anomaly warning unit is used to determine whether there are any anomalies in various operating parameters of the chilled water system based on the alarm standards corresponding to various operating parameters.

[0014] If an anomaly exists, an anomaly tag is added to the abnormal operating parameter, and a corresponding parameter anomaly warning signal is generated.

[0015] The equipment status monitoring unit is used to collect the operating status of each monitoring device in real time. When the monitoring device is operating abnormally, it obtains the type and location information of the abnormal monitoring device, generates an abnormal monitoring device warning signal, and immediately uploads it to the platform layer through the network layer.

[0016] Preferably, in a real-time monitoring and early warning platform for an IoT-based intermediate frequency furnace cooling water system, the network layer includes:

[0017] The data caching unit is used to cache the operating parameters collected by the perception layer;

[0018] The tag recognition unit is used to identify the data tags of the operating parameters and determine the warning status of various operating parameters;

[0019] The data preprocessing unit is used to filter, convert formats, and convert protocols of the operating parameters collected by the perception layer.

[0020] The data transmission unit is used to utilize Internet of Things (IoT) communication technology to set the transmission frequency of various operating parameters based on the early warning status of various operating parameters, and upload the processed operating parameters to the platform layer according to the set transmission frequency.

[0021] Simultaneously, the operating status of each monitoring device is uploaded to the platform layer at a preset frequency.

[0022] Preferably, in a real-time monitoring and early warning platform for an IoT-based intermediate frequency furnace cooling water system, the data caching unit further includes:

[0023] The transmission processing subunit is used to compare the uploaded operating parameters, merge the same operating parameters of multiple waterways at the same monitoring time, and generate data to be uploaded.

[0024] The system compares the various operating parameters of the latest data to be uploaded with the data to be uploaded at the previous monitoring time point. If there is any identical data, the identical data in the data to be uploaded at the previous time point is counted, and the non-identical data is cached normally, and the time point is updated.

[0025] Preferably, in a real-time monitoring and early warning platform for an IoT-based medium-frequency furnace cooling water system, the platform layer includes:

[0026] The anomaly detection unit is used to identify the data tags of the uploaded data. When any abnormal operating parameter is detected, it immediately generates an early warning signal and sends the anomaly warning notification to the communication terminal of relevant personnel using wireless communication technology.

[0027] Simultaneously, the location of the waterway and the type of the parameter corresponding to the abnormal operating parameters are obtained, and an abnormal location warning notification is generated and sent to the communication terminal of relevant technical personnel;

[0028] The abnormal cause synchronous prediction unit is used to determine the abnormal cause of the cooling water circuit based on the abnormal operating parameters and their correlation, combined with the cooling water system abnormal cause comparison table, when determining the type of abnormal operating parameters, and to send the abnormal cause and abnormal location early warning notification to the communication terminal of relevant technical personnel.

[0029] Preferably, in a real-time monitoring and early warning platform for an IoT-based medium-frequency furnace cooling water system, the platform layer further includes:

[0030] The equipment early warning unit is used to infer the abnormality type of the monitoring equipment based on the correlation of the operating parameters of each abnormal monitoring equipment in the cooling water system after receiving the abnormality early warning signal of the monitoring equipment, and to determine whether the abnormality of the monitoring equipment is caused by human shutdown.

[0031] If so, a warning signal will be generated and sent based on the abnormal early warning signal of the monitoring equipment, and wireless communication technology will be used to send it to the communication terminal of relevant personnel to remind them to manually shut down the monitoring equipment.

[0032] Otherwise, based on the abnormal warning signal of the monitoring equipment, a suspected equipment damage warning signal will be generated and sent to the communication terminal of relevant personnel using wireless communication technology, reminding them to manually shut down the monitoring equipment.

[0033] Preferably, in a real-time monitoring and early warning platform for an IoT-based medium-frequency furnace cooling water system, the platform layer includes:

[0034] The first optimization and adjustment unit is used to update the corresponding parameter fluctuation diagrams of the corresponding waterways based on the uploaded data.

[0035] Based on the cause of the anomaly, determine whether the current operating parameter anomaly is a controllable anomaly.

[0036] If so, based on the updated parameter fluctuation diagram, obtain the abnormal amplitude and corresponding abnormal direction of each operating parameter corresponding to the abnormal waterway, and generate the corresponding parameter anomaly vector.

[0037] Acquire historical control data and corresponding historical operating parameters of each waterway-related control device. Based on the time axis, generate control vectors and operating vectors from the historical control data and second historical operating parameters corresponding to each time point to obtain paired vectors.

[0038] Each pairing vector corresponding to a waterway is input into a preset feature extraction model for feature extraction to obtain the associated features of the pairing vectors.

[0039] Based on the correlation features between the parameter anomaly vector and the paired vector corresponding to the anomaly waterway, the control vector is inferred to obtain the target control vector;

[0040] Based on the target control vector, the target control parameters of each relevant controller corresponding to the abnormal waterway are determined, and the corresponding regulation signals are generated and sent to each relevant controller of the abnormal waterway according to the target control parameters, so as to complete the autonomous optimization of the operating parameters of the abnormal waterway.

[0041] Preferably, in a real-time monitoring and early warning platform for an IoT-based medium-frequency furnace cooling water system, the platform layer further includes:

[0042] The second optimization and adjustment unit is used to determine the fluctuation range of various operating parameters of each water circuit within a preset time period based on the updated parameter fluctuation diagram when all water circuits of the cooling water system are normal.

[0043] When the fluctuation amplitude of all water channels is within the preset range, the average parameter value of each water channel within the preset time period is obtained, and the average parameter value is compared with its corresponding alarm standard value.

[0044] Based on the comparison results, the evaluation coefficients of each average parameter value are determined. When the evaluation coefficients are within a preset range, the current waterway is determined to be in the best state.

[0045] Otherwise, obtain the average parameter values ​​corresponding to the same type of operating parameters for each waterway and compare them to obtain the parameter differences between adjacent waterways;

[0046] Based on the current operating parameters and preset percentages of each waterway, the maximum target difference is obtained;

[0047] When the parameter difference is greater than the maximum target difference corresponding to the target operating parameter type of the corresponding waterway, a potential risk warning signal is generated and sent to the communication terminal of relevant personnel.

[0048] Preferably, in a real-time monitoring and early warning platform for an IoT-based intermediate frequency furnace cooling water system, the second optimization and adjustment unit is further used for:

[0049] When the parameter difference is less than or equal to the maximum target difference corresponding to the target operating parameter type of the corresponding water circuit, the temperature evaluation coefficient of each water circuit is obtained respectively, and the water circuit with the temperature evaluation coefficient greater than the preset value is regarded as the water circuit to be controlled.

[0050] Based on the difference level corresponding to the temperature evaluation coefficient, the control parameters of the relevant control devices of the water circuit to be regulated are negatively adjusted according to the preset downward adjustment step size, and the operating parameters of the water circuit to be regulated are re-checked when the preset time is reached.

[0051] Preferably, in a real-time monitoring and early warning platform for an IoT-based medium-frequency furnace cooling water system, the platform layer further includes:

[0052] The periodic control unit is used to acquire and analyze the historical working data of the intermediate frequency furnace to obtain the operating cycle distribution characteristics of the intermediate frequency furnace and determine the operating cycle of the intermediate frequency furnace.

[0053] Based on the job cycle, historical job data is periodically divided to obtain multiple job cycle datasets;

[0054] By comparing and analyzing the data sets of multiple work cycles after division, the range of control quantity changes of the control devices of the medium frequency furnace in multiple working intervals and corresponding water circuits within the work cycle is determined.

[0055] Based on the distribution characteristics of the work cycle, the nodes of work volume change within the minimum cycle are determined. According to the range of control quantity change and its corresponding work volume interval, the preset control data corresponding to each work volume change node is determined.

[0056] When a change in the operation of the intermediate frequency furnace is detected, the actual workload is compared with the target workload range of the corresponding workload change node. If the actual workload is within the target workload range, then based on the preset control data, corresponding control commands are generated and sent to the relevant control devices of the corresponding water circuit to adjust their control parameters.

[0057] Compared with the prior art, the present invention has at least the following beneficial effects:

[0058] This invention uses a sensing layer to collect real-time data on operating parameters such as inlet and outlet flow rates, temperature, and pressure of each water path in the cooling water system, as well as the operating status of monitoring equipment. This allows for a comprehensive and thorough understanding of the entire cooling water system's operation. The collected data is then uploaded to the platform layer via the network layer. Supervisory personnel can view detailed operating data for all intermediate frequency furnace cooling water systems in real time through the platform, achieving 24 / 7 uninterrupted monitoring. This significantly improves the timeliness and comprehensiveness of monitoring, effectively preventing potential malfunctions caused by monitoring blind spots. The sensing layer not only has data acquisition capabilities but also performs real-time analysis of the collected data based on preset rules and algorithms to determine if there are any anomalies in the cooling water system and monitoring equipment. This intelligent judgment of cooling water anomalies overcomes the limitations of traditional manual inspections that rely on experience. When the platform layer detects an anomaly in the cooling water system, it immediately sends an anomaly warning notification to relevant personnel via wireless communication technology, including SMS, telephone, and app push notifications. Compared to the delayed notification process of traditional manual inspections that detect faults, this invention can trigger an early warning immediately upon the occurrence of an anomaly, enabling relevant personnel to take swift action. This effectively avoids serious consequences such as equipment damage and safety accidents caused by untimely fault handling, maximizing the safety of the intermediate frequency furnace equipment and personnel, and reducing equipment maintenance costs. Simultaneously, the platform layer can analyze uploaded data and optimize the operating parameters of the cooling water system based on the analysis results. This ensures the cooling water system is always in optimal operating condition, effectively preventing energy waste caused by unreasonable parameter settings. It is estimated that this can improve the energy efficiency of the cooling water system by 15%-20%, significantly reducing enterprise production costs.

[0059] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in this application.

[0060] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0061] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0062] Figure 1 is a structural diagram of a real-time monitoring and early warning platform for a medium-frequency furnace cooling water system based on the Internet of Things;

[0063] Figure 2 is a structural diagram of the sensing layer;

[0064] Figure 3 shows the structure of the network layers. Detailed Implementation

[0065] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0066] Example 1:

[0067] This invention provides a real-time monitoring and early warning platform for a medium-frequency furnace cooling water system based on the Internet of Things, as shown in Figure 1, comprising:

[0068] The sensing layer is used to collect the operating parameters of each water path in the cooling water system and the operating status of the monitoring equipment in real time, and to determine whether there are any abnormalities in the cooling water system and the monitoring equipment.

[0069] The operating parameters include inlet and outlet water flow rate, inlet and outlet water temperature, and inlet and outlet water pressure.

[0070] The network layer is used to preprocess the collected operating parameters and upload them to the platform layer.

[0071] The platform layer is used to analyze the uploaded data and optimize and adjust the operating parameters of the cooling water system based on the analysis results.

[0072] And when there is an abnormality in the cooling water system, an abnormality warning notification will be sent to the communication terminal of relevant personnel using wireless communication technology.

[0073] The beneficial effects of the above technical solution are as follows: This invention collects real-time data on the inlet and outlet flow rates, temperatures, pressures, and other operating parameters of each water path in the cooling water system, as well as the operating status of monitoring equipment, through the sensing layer. This allows for a comprehensive and thorough understanding of the entire cooling water system's operation. The collected data is then uploaded to the platform layer via the network layer. Supervisory personnel can view detailed operating data of all intermediate frequency furnace cooling water systems in real time through the platform, achieving 24 / 7 uninterrupted monitoring. This significantly improves the timeliness and comprehensiveness of monitoring, effectively avoiding potential faults caused by monitoring blind spots. The sensing layer not only has data acquisition capabilities but also performs real-time analysis of the collected data based on preset rules and algorithms to determine if there are any abnormalities in the cooling water system and monitoring equipment. This enables intelligent judgment of cooling water anomalies, overcoming the limitations of traditional manual inspections that rely on experience. When the platform layer detects an anomaly in the cooling water system, it immediately sends an anomaly warning notification to relevant personnel's communication terminals using wireless communication technology. Notification methods include SMS, telephone, and APP push notifications. Compared to the delayed notification process of traditional manual inspections that detect faults, this invention can trigger an early warning immediately upon the occurrence of an anomaly, enabling relevant personnel to take swift action. This effectively avoids serious consequences such as equipment damage and safety accidents caused by untimely fault handling, maximizing the safety of the intermediate frequency furnace equipment and personnel, and reducing equipment maintenance costs. Simultaneously, the platform layer can analyze uploaded data and optimize the operating parameters of the cooling water system based on the analysis results. This ensures the cooling water system is always in optimal operating condition, effectively preventing energy waste caused by unreasonable parameter settings. It is estimated that this can improve the energy efficiency of the cooling water system by 15%-20%, significantly reducing enterprise production costs.

[0074] Example 2:

[0075] Based on Example 1, the sensing layer, as shown in Figure 2, includes:

[0076] The data acquisition unit is used to collect the operating parameters of each water circuit based on the monitoring equipment installed at the inlet of each water-cooled coil and induction coil in the cooling water system.

[0077] The anomaly warning unit is used to determine whether there are any anomalies in various operating parameters of the chilled water system based on the alarm standards corresponding to various operating parameters.

[0078] If an anomaly exists, an anomaly tag is added to the abnormal operating parameter, and a corresponding parameter anomaly warning signal is generated.

[0079] The equipment status monitoring unit is used to collect the operating status of each monitoring device in real time. When the monitoring device is operating abnormally, it obtains the type and location information of the abnormal monitoring device and generates an abnormal monitoring device warning signal.

[0080] In this embodiment, the monitoring equipment includes, but is not limited to, flow monitoring equipment, temperature monitoring equipment, and pressure monitoring equipment.

[0081] The beneficial effects of the above technical solution are as follows: By deploying monitoring equipment at the inlet of each water-cooling coil and induction coil in the cooling water system, the present invention achieves refined collection of the operating parameters of each water circuit. It can obtain parameters such as inlet and outlet water flow, temperature, and pressure of the entire water circuit, forming a complete cooling water system operation data map. For complex multi-water cooling networks, it can accurately capture sudden changes in the flow of a certain branch, avoiding overall system failures caused by the failure to detect local water circuit anomalies, and effectively improving the integrity and accuracy of the collected data. Furthermore, the anomaly early warning unit, based on preset alarm standards (water flow reaching the set lower limit alarm, inlet / outlet flow difference reaching the set upper limit alarm, water temperature reaching the set high temperature alarm, pressure below the set lower limit alarm, etc.), performs real-time intelligent judgment on operating parameters. This changes the inefficient traditional method of manually comparing data to judge anomalies. When an anomaly occurs in operating parameters, it can not only quickly add an anomaly tag but also immediately generate a parameter anomaly early warning signal, shortening the early warning response time to the second level. For example, when the inlet temperature is sensed to exceed the safety threshold, the system can trigger an alarm within 1-2 seconds. Compared to the several hours of delay that may occur with manual inspections, this greatly improves the anomaly response speed, buys valuable time for fault handling, and effectively reduces the probability of accidents. The equipment status monitoring unit monitors the operating status of each monitoring device in real time, effectively solving the problems of difficulty in timely detection of equipment failures in traditional monitoring and the inability to monitor in a timely manner when monitoring devices are manually shut down. Once an anomaly occurs in a monitoring device, this unit can quickly obtain the type and location information of the abnormal device and generate an anomaly early warning signal, avoiding data errors and monitoring blind spots caused by monitoring device failure, thus ensuring the reliability and effectiveness of the entire monitoring system.

[0082] Example 3:

[0083] Based on Example 1, the network layer, as shown in Figure 3, includes:

[0084] The data caching unit is used to cache the operating parameters collected by the perception layer;

[0085] The tag recognition unit is used to identify the data tags of the operating parameters and determine the warning status of various operating parameters;

[0086] The data preprocessing unit is used to filter, convert formats, and convert protocols of the operating parameters collected by the perception layer.

[0087] The data transmission unit is used to utilize Internet of Things (IoT) communication technology to set the transmission frequency of various operating parameters based on the early warning status of various operating parameters, and upload the processed operating parameters to the platform layer according to the set transmission frequency.

[0088] Simultaneously, the operating status of each monitoring device is uploaded to the platform layer at a preset frequency.

[0089] The beneficial effects of the above technical solution are as follows: This invention temporarily stores the operating parameters collected by the perception layer through a data caching unit, effectively solving the problem of data loss or transmission interruption caused by network fluctuations and bandwidth limitations during data transmission. When a brief network failure occurs, the cached data can continue to be uploaded after the network is restored, ensuring data integrity and continuity, and providing a reliable data foundation for accurate analysis at the platform layer. Then, the tag recognition unit can identify the data tags of the operating parameters in real time, quickly determining the warning status of various operating parameters. Compared to traditional systems where the platform layer needs to receive data before analyzing and judging the warning status, the network layer completes the warning status identification before data transmission, significantly shortening the response time for abnormal warnings. Once an abnormal parameter tag is detected, the data transmission unit uses a lower transmission frequency for parameters in a normal state to reduce network bandwidth usage; while for parameters with abnormal warning states, it immediately increases the transmission frequency of that parameter (for example, when the values ​​of operating parameters such as temperature, flow difference, and water pressure are within a reasonable range, it uploads once every 10 seconds; in abnormal situations, it immediately sets it to once per second), enabling the platform layer to obtain abnormal data faster, issue warnings in a timely manner, gain valuable time for fault handling, and significantly reduce the risk of accidents. Furthermore, the monitoring equipment's operating status is uploaded periodically at a preset frequency, ensuring the platform layer is promptly informed of the equipment's operational status. This allows for differentiated settings for different data transmissions, effectively reducing network load and improving the overall monitoring system's operational efficiency while ensuring data timeliness. It is particularly suitable for complex network environments with multiple devices and large data volumes in industrial parks, significantly improving network bandwidth utilization. The data preprocessing unit filters, converts, and performs protocol conversions on the collected operating parameters, effectively resolving compatibility issues caused by inconsistencies in data formats and communication protocols between different monitoring devices. Whether it's Modbus protocol data from older equipment or MQTT protocol data from newer smart sensors, the data preprocessing unit uniformly converts it into a standard format recognizable by the platform layer, ensuring accurate data transmission and processing. Moreover, the data filtering function removes noisy and invalid data, improving data quality and making the platform layer's analysis results more reliable, thus effectively avoiding misjudgments and misoperations caused by data errors.

[0090] Example 4:

[0091] Based on embodiment 3, the data caching unit further includes:

[0092] The transmission processing subunit is used to compare the uploaded operating parameters, merge the same operating parameters of multiple waterways at the same monitoring time, and generate data to be uploaded.

[0093] The system compares the various operating parameters of the latest data to be uploaded with the data to be uploaded at the previous monitoring time point. If there is any identical data, the identical data in the data to be uploaded at the previous time point is counted, and the non-identical data is cached normally, and the time point is updated.

[0094] The beneficial effects of the above technical solution are as follows: This invention merges parameters, significantly reducing data redundancy. For example, in a multi-water-path parallel cooling system, if the inlet water temperature of multiple water paths is 25°C at the same time, the system only needs to store one temperature data record, instead of storing each water path separately. This reduces the amount of uploaded data by 40%-60%, effectively reducing network bandwidth usage, improving data transmission efficiency, and significantly improving the platform layer's response speed to real-time data. Merging parameters further optimizes storage space by comparing the latest data to be uploaded with the data from the previous time point and counting identical data instead of storing it repeatedly. During stable operation of the cooling water system, a large number of parameters remain relatively stable, which can greatly reduce storage costs. For example, if a parameter remains unchanged for 10 consecutive monitoring cycles, the system only stores the initial value and count 10, instead of 10 identical records. It also facilitates rapid anomaly location; when the counting of a parameter is suddenly interrupted or changes abnormally, the system can immediately identify it as a potential anomaly. For example, if the pressure value of a certain waterway remains stable for 50 consecutive cycles (counting 50 cycles), and then changes in the 51st cycle, the system can quickly mark this time point as the start of the anomaly. Combined with the parameter fluctuation graph, this allows maintenance personnel to quickly pinpoint the time of the anomaly, reducing troubleshooting time from hours to minutes. Simultaneously, different data is cached normally and the time points are updated, ensuring the system's complete record of parameter changes. The optimized processing of uploaded data by the data caching unit significantly reduces the burden on subsequent data processing modules, lowering the risk of system crashes due to data overload. By reducing redundant data and optimizing the storage structure, the platform layer can process and analyze core data more efficiently, improving the stability and reliability of the entire monitoring and early warning platform.

[0095] Example 5:

[0096] Based on Example 1, the platform layer includes:

[0097] The anomaly detection unit is used to identify the data tags of the uploaded data. When any abnormal operating parameter is detected, it immediately generates an early warning signal and sends the anomaly warning notification to the communication terminal of relevant personnel using wireless communication technology.

[0098] Simultaneously, the location of the waterway and the type of the parameter corresponding to the abnormal operating parameters are obtained, and an abnormal location warning notification is generated and sent to the communication terminal of relevant technical personnel;

[0099] The abnormal cause synchronous prediction unit is used to determine the abnormal cause of the cooling water circuit based on the abnormal operating parameters and their correlation, combined with the cooling water system abnormal cause comparison table, when determining the type of abnormal operating parameters, and to send the abnormal cause and abnormal location early warning notification to the communication terminal of relevant technical personnel.

[0100] In this embodiment, the cooling water system abnormality cause comparison table integrates a large number of historical failure cases and expert experience knowledge, covering a variety of potential causes such as pipe blockage, sensor failure, and water pump abnormality. It will be automatically updated periodically according to a preset time interval.

[0101] The beneficial effects of the above technical solution are as follows: This invention monitors the uploaded data tags in real time through an anomaly identification unit. Once any abnormal operating parameter is detected, an early warning signal can be generated within milliseconds, and an anomaly warning notification can be sent to relevant personnel via wireless communication technologies (such as 5G, telephone, SMS, APP push, etc.). Compared with traditional manual inspection or lagging monitoring systems, this mechanism shortens the anomaly response time from hours or even days to within seconds. For example, when the cooling water temperature suddenly rises above the safety threshold, the anomaly identification unit immediately triggers an early warning, notifying equipment management personnel in a timely manner to avoid equipment damage caused by high temperature. At the same time, the system can also synchronously obtain the water circuit location and parameter type corresponding to the abnormal parameter, generate an anomaly location warning notification and send it to technicians, clearly indicating the specific location of the fault (such as "abnormal inlet water temperature of water circuit B of No. 3 medium frequency furnace"), greatly reducing the fault investigation time, enabling maintenance personnel to quickly arrive at the site, and effectively improving the fault handling efficiency of the cooling water system. After identifying the type of abnormal parameters, the system uses a synchronous anomaly cause prediction unit to perform intelligent analysis based on the correlation between abnormal operating parameters (such as the linkage between temperature and flow rate, and the correspondence between pressure and flow rate) and a cooling water system anomaly cause comparison table. Through multi-parameter cross-validation and logical reasoning, the system can quickly and accurately locate the cause of the anomaly and simultaneously send the anomaly cause and location warning notification to technical personnel. For example, when a sudden drop in flow rate and an increase in temperature are detected in a certain water circuit, the system can quickly determine that the decrease in cooling efficiency is due to pipe blockage, rather than a simple water pump failure. This avoids the blindness and experience limitations of traditional manual troubleshooting, effectively improves the accuracy of cooling water system fault diagnosis, reduces intermediate frequency furnace downtime, and thus reduces production losses caused by faults.

[0102] Example 6:

[0103] Based on Example 5, the platform layer also includes:

[0104] The equipment early warning unit is used to infer the abnormality type of the monitoring equipment based on the correlation of the operating parameters of each abnormal monitoring equipment in the cooling water system after receiving the abnormality early warning signal of the monitoring equipment, and to determine whether the abnormality of the monitoring equipment is caused by human shutdown.

[0105] If so, a warning signal will be generated and sent based on the abnormal early warning signal of the monitoring equipment, and wireless communication technology will be used to send it to the communication terminal of relevant personnel to remind them to manually shut down the monitoring equipment.

[0106] Otherwise, based on the abnormal warning signal of the monitoring equipment, a suspected equipment damage warning signal will be generated and sent to the communication terminal of relevant personnel using wireless communication technology, reminding them to manually shut down the monitoring equipment.

[0107] The beneficial effects of the above technical solution are as follows: This invention, through an equipment early warning unit, infers the type of anomaly based on the correlation between the corresponding operating parameters of the abnormal monitoring equipment. This allows for rapid and accurate differentiation between human-caused damage and internal monitoring equipment malfunctions within the cooling water circuit. For example, when a flow monitoring device issues an abnormal signal, the equipment early warning unit analyzes whether the temperature and pressure parameters of the same water circuit are synchronously abnormal. If both are abnormal, it can quickly deduce that the monitoring shutdown may be caused by human intervention. When the anomaly is determined to be due to human intervention, a warning signal is promptly generated and sent to relevant personnel, reminding them to turn on the equipment, effectively preventing malicious shutdown of the monitoring equipment that could have caused the cooling water system monitoring anomaly. If the equipment is suspected of being damaged, a suspected equipment damage warning signal is immediately sent, enabling maintenance personnel to quickly reach the site with the necessary tools and spare parts for repairs, reducing the downtime of the induction furnace and significantly improving the operating efficiency and production continuity of the induction furnace cooling water system.

[0108] Example 7:

[0109] Based on Example 1, the platform layer includes:

[0110] The first optimization and adjustment unit is used to update the corresponding parameter fluctuation diagrams of the corresponding waterways based on the uploaded data.

[0111] Based on the cause of the anomaly, determine whether the current operating parameter anomaly is a controllable anomaly.

[0112] If so, based on the updated parameter fluctuation diagram, obtain the abnormal amplitude and corresponding abnormal direction of each operating parameter corresponding to the abnormal waterway, and generate the corresponding parameter anomaly vector.

[0113] Acquire historical control data and corresponding historical operating parameters of each waterway-related control device. Based on the time axis, generate control vectors and operating vectors from the historical control data and second historical operating parameters corresponding to each time point to obtain paired vectors.

[0114] Each pairing vector corresponding to a waterway is input into a preset feature extraction model for feature extraction to obtain the associated features of the pairing vectors.

[0115] Based on the correlation features between the parameter anomaly vector and the paired vector corresponding to the anomaly waterway, the control vector is inferred to obtain the target control vector;

[0116] Based on the target control vector, the target control parameters of each relevant controller corresponding to the abnormal waterway are determined, and the corresponding regulation signals are generated and sent to each relevant controller of the abnormal waterway according to the target control parameters, so as to complete the autonomous optimization of the operating parameters of the abnormal waterway.

[0117] The beneficial effects of the above technical solution are as follows: This invention updates the parameter fluctuation diagram of the corresponding water circuit in real time based on uploaded data, which can capture subtle trends in parameter changes. The data update frequency can reach the second level, ensuring that the platform layer always performs analysis and decision-making based on the latest data, thus effectively improving the system's perception accuracy of the operating status. Furthermore, by judging whether the abnormal operating parameters are controllable anomalies, intelligent hierarchical handling of faults is achieved: for controllable anomalies (such as pump speed deviation, valve opening mismatch, etc.), the system automatically triggers optimization processes; for uncontrollable anomalies (such as equipment hardware damage), it quickly locates the problem and issues maintenance warnings, resulting in a 92% autonomous resolution rate for controllable anomalies. This effectively reduces the frequency of manual intervention in cooling water system regulation and significantly improves the operation and maintenance efficiency of the medium-frequency furnace cooling system. By utilizing the correlation features of parameter anomaly vectors and paired vectors to predict control vectors, the limitations of traditional single-parameter regulation are overcome. By integrating historical control data with real-time operating parameters, the system can uncover hidden correlations between parameters. For example, it is found that when the temperature rises by 2°C and the flow rate decreases by 10%, the optimal control strategy is to increase the pump speed by 15% and increase the valve opening by 20%. Based on the feature extraction model of deep learning, the accuracy of the control strategy is effectively improved, achieving precise control.

[0118] Example 8:

[0119] Based on Example 7, the platform layer also includes:

[0120] The second optimization and adjustment unit is used to determine the fluctuation range of various operating parameters of each water circuit within a preset time period based on the updated parameter fluctuation diagram when all water circuits of the cooling water system are normal.

[0121] When the fluctuation amplitude of all water channels is within the preset range, the average parameter value of each water channel within the preset time period is obtained, and the average parameter value is compared with its corresponding alarm standard value.

[0122] Based on the comparison results, the evaluation coefficients of each average parameter value are determined. When the evaluation coefficients are within a preset range, the current waterway is determined to be in the best state.

[0123] Otherwise, obtain the average parameter values ​​corresponding to the same type of operating parameters for each waterway and compare them to obtain the parameter differences between adjacent waterways;

[0124] Based on the current operating parameters and preset percentages of each waterway, the maximum target difference is obtained;

[0125] When the parameter difference is greater than the maximum target difference corresponding to the target operating parameter type of the corresponding waterway, a potential risk warning signal is generated and sent to the communication terminal of relevant personnel;

[0126] When the parameter difference is less than or equal to the maximum target difference corresponding to the target operating parameter type of the corresponding water circuit, the temperature evaluation coefficient of each water circuit is obtained respectively, and the water circuit with the temperature evaluation coefficient greater than the preset value is regarded as the water circuit to be controlled.

[0127] Based on the difference level corresponding to the temperature evaluation coefficient, the control parameters of the relevant control devices of the water circuit to be regulated are negatively adjusted according to the preset downward adjustment step size, and the operating parameters of the water circuit to be regulated are re-checked when the preset time is reached.

[0128] In this embodiment, the evaluation coefficient refers to the degree of difference between the average parameter value and its corresponding alarm standard value. It is the ratio between the absolute value of the difference between the average parameter value and its corresponding alarm standard value and the alarm standard value. It includes the evaluation coefficients of various types of operating parameters such as temperature, water pressure, and flow rate.

[0129] In this embodiment, parameter difference refers to the numerical difference obtained by comparing the average parameter values ​​of the same type of operating parameters between adjacent water circuits after obtaining the average parameter values ​​of each water circuit. This difference is used to determine the balance of the same type of operating parameters between different water circuits and helps to identify potential risks. For example, if the difference between the average pressure parameter values ​​of two adjacent water circuits is large, it may indicate that one of the water circuits has problems such as partial blockage, valve malfunction, or decreased pump performance.

[0130] In this embodiment, the temperature evaluation coefficient refers to the evaluation coefficient obtained by comparing the average parameter value of the temperature parameter of each water circuit with the corresponding alarm standard value when the parameter difference of the same type of operating parameter of adjacent water circuits is less than or equal to the maximum target difference corresponding to the target operating parameter type of the corresponding water circuit.

[0131] The beneficial effects of the above technical solution are as follows: When all water circuits in the cooling water system are operating normally, this invention monitors the fluctuation amplitude of the operating parameters of each water circuit over a long period of time and in multiple dimensions based on the updated parameter fluctuation diagram. Compared with traditional monitoring methods that only focus on the instantaneous values ​​of parameters, this invention can capture the subtle changing trends of parameters within a preset time period. For example, it can identify a slow upward trend of cooling water temperature of 0.3℃ / h over 8 hours, or a gradual decrease in flow rate of 1.2% per hour over 12 hours. This effectively improves the system's perception accuracy of operating status, providing a strong basis for early detection of potential operating anomalies in the cooling water system and for preventive maintenance. By comparing the average parameter values ​​of each water circuit with alarm standard values ​​and determining the evaluation coefficient, the system achieves a quantitative and precise assessment of the water circuit's operating status. This allows for an objective and accurate determination of whether the water circuit is in optimal operating condition. When the evaluation coefficient corresponding to the average flow parameter value of a certain water circuit does not fall within the preset range, the system can immediately determine that there is room for optimization in the operating status of that water circuit. By comparing the average parameter values ​​of the same type of operating parameters of adjacent water circuits, calculating the parameter differences, and comparing them with the maximum target difference, potential risks can be identified in advance. When the parameter difference exceeds the threshold, the system quickly generates a potential risk warning signal and sends it to relevant personnel, achieving early warning of potential faults. In actual production, if the pressure parameter difference between two adjacent water circuits is too large, it may indicate that one of the water circuits has problems such as partial blockage, valve abnormality, or decreased pump performance. The system's early warning allows maintenance personnel to intervene in a timely manner, effectively reducing the risk of intermediate frequency furnace shutdown caused by potential faults and ensuring the continuous production of the intermediate frequency furnace. For water circuits with temperature assessment coefficients exceeding preset values, the system performs negative adjustments based on the difference level and rechecks after a preset time. This achieves precise and intelligent optimization of operating parameters, enabling targeted adjustments to each water circuit within the cooling water system and effectively reducing resource waste and equipment wear caused by indiscriminate adjustments. For example, when the temperature assessment coefficient of a certain water circuit reaches a high level, the system reduces the pump speed or increases the valve opening of that water circuit according to a preset downward adjustment step, reducing energy consumption while ensuring cooling effect. This invention achieves refined control of multiple water circuits, continuously optimizing based on parameter changes and assessment results during normal system operation. This improves the energy efficiency of the entire cooling water system, significantly reducing electricity consumption costs and saving enterprises substantial operating expenses.

[0132] Example 9:

[0133] Based on Example 7, the platform layer also includes:

[0134] The periodic control unit is used to acquire and analyze the historical working data of the intermediate frequency furnace to obtain the operating cycle distribution characteristics of the intermediate frequency furnace and determine the operating cycle of the intermediate frequency furnace.

[0135] Based on the job cycle, historical job data is periodically divided to obtain multiple job cycle datasets;

[0136] By comparing and analyzing the data sets of multiple work cycles after division, the range of control quantity changes of the control devices of the medium frequency furnace in multiple working intervals and corresponding water circuits within the work cycle is determined.

[0137] Based on the distribution characteristics of the work cycle, the nodes of work volume change within the minimum cycle are determined. According to the range of control quantity change and its corresponding work volume interval, the preset control data corresponding to each work volume change node is determined.

[0138] When a change in the operation of the intermediate frequency furnace is detected, the actual workload is compared with the target workload range of the corresponding workload change node. If the actual workload is within the target workload range, then based on the preset control data, corresponding control commands are generated and sent to the relevant control devices of the corresponding water circuit to adjust their control parameters.

[0139] In this embodiment, the data sets of multiple divided work cycles are compared and analyzed to determine the control quantity variation range of the medium-frequency furnace in multiple working intervals within the work cycle and the corresponding control devices of each water circuit. The specific method includes:

[0140] Align data from multiple job cycles;

[0141] Based on the alignment results, the historical changes in the workload of the medium-frequency furnace during the operating cycle and the corresponding changes in the operating parameters of the cooling water system were obtained.

[0142] The workload whose historical operating parameters change within a preset range is used as the similar workload.

[0143] Based on similar workloads, multiple workload intervals are established, a workload interval sequence is generated, and the historical operating parameters within the same workload interval are arranged in order of increasing workload to obtain a parameter change sequence.

[0144] Based on the parameter change sequence, the average change of different types of operating parameters within the corresponding workload range is determined respectively;

[0145] After filtering and selecting multiple sets of historical operating parameters corresponding to the minimum historical workload, a weighted average is performed on each type of operating parameter to obtain a reference operating parameter group.

[0146] Based on the parameter group, workload interval sequence, and the average change of different types of operating parameters in each workload interval of the workload interval sequence, calculate and determine the range of operating parameter changes corresponding to each workload interval.

[0147] For each range of workload, the upper and lower limits of the operating parameter variation range are used to generate corresponding operating parameter vectors. Combined with the pairing vector association features of the corresponding waterway, the control quantity variation range of each relevant controller corresponding to each range of operating parameter variation is determined.

[0148] In this embodiment, obtaining multiple sets of historical operating parameters corresponding to the minimum historical workload for filtering and screening means removing historical operating parameters with large offsets within the workload range.

[0149] In this embodiment, the work cycle refers to the shortest time period for the medium-frequency furnace to complete a complete and repetitive work process. In actual operation, the work process of the medium-frequency furnace often exhibits periodic characteristics, such as the repeated cycles of melting, holding, and cooling.

[0150] In this embodiment, the pairing vector association feature refers to the correspondence between the operating parameters of each waterway and the control parameters of its corresponding controller.

[0151] The beneficial effects of the above technical solution are as follows: By analyzing historical operating data of intermediate frequency furnaces, this invention can accurately obtain the distribution characteristics of the operating cycle and determine the operating cycle, which is beneficial for clearly understanding the time patterns of different operating stages of intermediate frequency furnaces, such as melting and holding. For example, in foundry enterprises, it can accurately identify that the intermediate frequency furnace completes a melting-holding cycle every 3 hours, improving the system's accuracy in grasping the equipment's operating rhythm from the previous rough estimation to near precision, laying a solid data foundation for the subsequent precise control of the cooling water system. Furthermore, based on the operating cycle, historical data is periodically divided and aligned, forming an ordered set of scattered data, facilitating the system's in-depth exploration of the intrinsic relationship between changes in intermediate frequency furnace operating volume and changes in cooling water system operating parameters. Taking a steel plant as an example, this operation revealed that for every 10-ton increase in the melting volume of the intermediate frequency furnace, the cooling water temperature rises by 3°C and the flow rate needs to increase by 8%, improving the efficiency of parameter change pattern exploration by 70%, providing a reliable basis for the scientific control of the cooling water system. Subsequently, by establishing a sequence of operating volume intervals and calculating the average change in operating parameters within each interval, the system generates a dynamic range of operating parameter changes, replacing the traditional fixed threshold control mode. When workload changes, such as when the induction furnace enters a high-load melting stage, the system can automatically and precisely adjust the cooling water flow rate to the appropriate range based on the parameter changes within the corresponding workload range. This avoids insufficient cooling or energy waste due to improper parameter settings, greatly improving the accuracy of cooling water system parameter adjustment. Based on the characteristics of the work cycle distribution, the system identifies workload change nodes and presets control data, giving it predictive capabilities. For example, before the induction furnace enters a high-energy-consuming melting stage, the system adjusts the pump speed and valve opening in advance based on preset control data, synchronizing the cooling water system's response with the furnace's melting task. This effectively reduces the risk of overheating and damage to the induction furnace due to untimely cooling water system response, significantly improving energy efficiency. Furthermore, the system can adjust cooling water system parameters as needed within different workload ranges, greatly enhancing the intelligence of cooling water system control while avoiding energy waste from prolonged high-speed operation of pumps and other components.

[0152] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A real-time monitoring and early warning platform for a medium-frequency furnace cooling water system based on the Internet of Things, characterized in that, include: The sensing layer is used to collect real-time operating parameters of each water path in the cooling water system and the operating status of monitoring equipment, and to determine whether there are any abnormalities in the cooling water system and monitoring equipment. Operating parameters include inlet and outlet water flow rates, inlet and outlet water temperatures, and inlet and outlet water pressures. The network layer is used to preprocess the collected operating parameters and upload them to the platform layer. The platform layer is used to analyze the uploaded data, optimize and adjust the operating parameters of the cooling water system based on the analysis results, and send anomaly warning notifications to relevant personnel's communication terminals using wireless communication technology when anomalies are detected in the cooling water system. The platform layer includes: a first optimization and adjustment unit, used to update the corresponding parameter fluctuation diagrams for each water path based on the uploaded data; and based on the cause of the anomaly, ... Determine whether the current abnormal operating parameters are controllable; if so, based on the updated parameter fluctuation diagram, obtain the abnormal amplitude and corresponding abnormal direction of each operating parameter corresponding to the abnormal waterway, and generate the corresponding parameter abnormal vector; obtain the historical control data and corresponding historical operating parameters of each waterway-related controller, and based on the time axis, generate control vectors and operating vectors from the historical control data and second historical operating parameters corresponding to each time point to obtain paired vectors; input the paired vectors corresponding to each waterway into a preset feature extraction model for feature extraction to obtain paired vector association features; predict the control vector based on the parameter abnormal vectors and the paired vector association features corresponding to the abnormal waterways to obtain the target control vector; Based on the target control vector, the target control parameters of each relevant controller corresponding to the abnormal water path are determined. Based on the target control parameters, corresponding control signals are generated and sent to each relevant controller in the abnormal water path, completing the autonomous optimization of the abnormal water path's operating parameters. The platform layer also includes a second optimization and adjustment unit, used to determine the fluctuation amplitude of various operating parameters of each water path within a preset time period based on the updated parameter fluctuation diagram when all water paths in the cooling water system are normal. When the fluctuation amplitude of all water paths is within a preset range, the average parameter value of each water path within the preset time period is obtained, and the average parameter value is compared with its corresponding alarm standard value. Based on the comparison result, the evaluation of each average parameter value is determined. The evaluation coefficient is determined to be in optimal condition when it is within a preset range; otherwise, the average parameter values ​​corresponding to the same type of operating parameters of each waterway are compared to obtain the parameter differences between adjacent waterways; the maximum target difference is obtained based on the current operating parameters of each waterway and a preset percentage; when the parameter difference is greater than the maximum target difference corresponding to the target operating parameter type of the corresponding waterway, a potential risk warning signal is generated and sent to the communication terminal of relevant personnel; wherein, the second optimization adjustment unit is further used to: when the parameter difference is less than or equal to the maximum target difference corresponding to the target operating parameter type of the corresponding waterway, obtain the temperature evaluation coefficient of each waterway respectively, and designate the waterway with the temperature evaluation coefficient greater than the preset value as the waterway to be controlled;Based on the difference level corresponding to the temperature assessment coefficient, the control parameters of the relevant controllers of the water circuit to be regulated are negatively adjusted according to a preset downward adjustment step size. After a preset time has elapsed, the operating parameters of the water circuit to be regulated are rechecked.

2. The real-time monitoring and early warning platform for a medium-frequency furnace cooling water system based on the Internet of Things as described in claim 1, characterized in that, The perception layer includes: a data acquisition unit, used to collect the operating parameters of each water circuit based on the monitoring equipment installed at the inlet of each water-cooled coil and induction coil in the cooling water system; an anomaly early warning unit, used to determine whether there are any anomalies in the various operating parameters of the cooling water system based on the alarm standards corresponding to various operating parameters; if so, an anomaly tag is added to the abnormal operating parameter, and a corresponding parameter anomaly early warning signal is generated; and an equipment status monitoring unit, used to collect the operating status of each monitoring device in real time, and when the monitoring device is operating abnormally, to obtain the type and location information of the abnormal monitoring device, generate a monitoring device anomaly early warning signal, and immediately upload it to the platform layer through the network layer.

3. The real-time monitoring and early warning platform for a medium-frequency furnace cooling water system based on the Internet of Things as described in claim 1, characterized in that, The network layer includes: a data caching unit for caching operating parameters collected by the sensing layer; a tag identification unit for identifying data tags of operating parameters and determining the warning status of various operating parameters; a data preprocessing unit for filtering, format conversion, and protocol conversion of operating parameters collected by the sensing layer; and a data transmission unit for using IoT communication technology to set the transmission frequency of various operating parameters based on their warning status, and uploading the processed operating parameters to the platform layer according to the set transmission frequency; and simultaneously uploading the operating status of each monitoring device to the platform layer at a preset frequency.

4. The real-time monitoring and early warning platform for a medium-frequency furnace cooling water system based on the Internet of Things as described in claim 3, characterized in that, The data caching unit also includes a transmission processing subunit, which is used to compare the uploaded operating parameters, merge the same operating parameters of multiple waterways at the same monitoring time, generate data to be uploaded, and compare the operating parameters of the latest data to be uploaded with the data to be uploaded at the previous monitoring time point. If there is the same data, the same data in the data to be uploaded at the previous time point is counted, the different data is cached normally, and the time point is updated.

5. A real-time monitoring and early warning platform for a medium-frequency furnace cooling water system based on the Internet of Things, as described in claim 1, is characterized in that... The platform layer includes: an anomaly identification unit, used to identify data tags of uploaded data, and immediately generate an early warning signal when any abnormal operating parameter is detected. It then uses wireless communication technology to send an anomaly warning notification to the communication terminals of relevant personnel; simultaneously, it acquires the water circuit location and parameter type corresponding to the abnormal operating parameter, generates an anomaly location warning notification, and sends it to the communication terminals of relevant technical personnel; and an anomaly cause synchronous inference unit, used to determine the cause of the cooling water circuit anomaly based on the abnormal operating parameter and its correlation, combined with the cooling water system anomaly cause lookup table, and sends the anomaly cause and anomaly location warning notification to the communication terminals of relevant technical personnel.

6. The real-time monitoring and early warning platform for a medium-frequency furnace cooling water system based on the Internet of Things as described in claim 5, characterized in that, The platform layer also includes: an equipment early warning unit, which, upon receiving an abnormality early warning signal from the monitoring equipment, infers the abnormality type of the monitoring equipment based on the correlation of the operating parameters corresponding to each abnormality monitoring device in the cooling water system, and determines whether the abnormality of the monitoring equipment is caused by human-induced shutdown; if so, it generates and sends a warning signal based on the monitoring equipment abnormality early warning signal, and sends it to the communication terminal of relevant personnel using wireless communication technology, reminding relevant personnel to turn on the human-induced shutdown monitoring equipment; otherwise, it generates a suspected equipment damage early warning signal based on the monitoring equipment abnormality early warning signal, and sends it to the communication terminal of relevant personnel using wireless communication technology, reminding relevant personnel to turn on the human-induced shutdown monitoring equipment.

7. The real-time monitoring and early warning platform for a medium-frequency furnace cooling water system based on the Internet of Things as described in claim 1, characterized in that, The platform layer also includes: a periodic control unit, used to acquire and analyze historical operating data of the intermediate frequency furnace to obtain the operating cycle distribution characteristics of the intermediate frequency furnace and determine the operating cycle of the intermediate frequency furnace; based on the operating cycle, periodically divide the historical operating data to obtain multiple operating cycle datasets; compare and analyze the multiple operating cycle datasets after division to determine the multiple working intervals of the intermediate frequency furnace within the operating cycle and the control quantity change range of the relevant controllers of each corresponding water circuit; based on the operating cycle distribution characteristics, determine the operating quantity change nodes within the minimum cycle, and determine the preset control data corresponding to each operating quantity change node according to the control quantity change range and its corresponding operating quantity interval; when a change in the operation of the intermediate frequency furnace is detected, compare the actual operating quantity with the target operating quantity interval of the corresponding operating quantity change node; if the actual operating quantity is within the target operating quantity interval, then based on the preset control data, generate corresponding control commands and send them to the relevant controllers of the corresponding water circuit to adjust their control parameters.

Images