Intelligent temperature control method and system for equipment in industrial harsh environment

Abstract

The application provides an intelligent temperature control method and system for equipment in an industrial harsh environment, and relates to the field of industrial equipment temperature control. The application obtains the electric power input of the equipment, the inlet and outlet water temperatures of the cooling water, the total instantaneous flow of the cooling water and the temperature of the equipment, and calculates the heat generated by the equipment and the heat consumed by the cooling water based on these parameters. When the heat generated by the equipment is greater than the heat consumed by the cooling water and the temperature of the equipment exceeds the preset range, the application can intelligently determine the heat transfer resistance value of the cooling water circuit. The resistance value can accurately represent the degree of blockage caused by scale accumulation inside the cooling water circuit. The application can dynamically adjust the cooling water flow instruction and accurately control the cooling water pump and the regulating valve. The application overcomes the rough strategy of starting cooling at a single fixed upper limit temperature in the prior art, significantly improves the operation stability and energy efficiency of the equipment under complex and variable working conditions, prolongs the service life of the equipment, and reduces the maintenance cost.

Description

Technical Field

[0001] This application relates to the field of industrial equipment temperature control technology, and more specifically, to an intelligent temperature control method and system for equipment in harsh industrial environments. Background Technology

[0002] In industrial production, automated equipment that operates continuously and for extended periods at high temperatures, such as high-frequency induction furnaces, often faces problems with slow response and excessive energy consumption in their temperature control systems. Existing control methods typically employ a fixed upper temperature limit for cooling, but this singular strategy is ill-suited to the complex and ever-changing conditions during production. This leads to equipment shutdowns due to overheating when workload increases, impacting production efficiency and increasing energy consumption.

[0003] Taking a high-frequency induction heating furnace as an example, its cooling system uses circulating deionized water to remove the heat generated by the induction coil and furnace body. However, even with rigorous treatment, trace amounts of dissolved minerals and suspended particulate matter in the cooling water inevitably enter the cooling channels. Under continuous thermal circulation and localized high temperatures, these impurities gradually form scale and deposits on the inner walls of the channels. This scale layer acts like an insulating blanket, significantly increasing the resistance to heat transfer between the heat source and the cooling water, leading to a decrease in the heat exchange efficiency of the cooling system.

[0004] The accumulation of internal scale gradually renders the original predictive heat calculation methods ineffective. Although the control system can accurately estimate heat generation and issue sufficient cooling water flow commands, the actual coil temperature remains consistently higher than expected, or requires a cooling flow rate far exceeding the prediction to maintain the target temperature. On-site maintenance personnel are forced to intervene manually, increasing the base cooling water flow rate or adjusting the temperature setpoint to compensate for insufficient cooling. This manual adjustment is often delayed and inefficient, resulting in unnecessary energy waste. Summary of the Invention

[0005] This application discloses an intelligent temperature control method and system for equipment in harsh industrial environments, aiming to solve the problems of slow response, high energy consumption, difficulty in adapting to complex and changing working conditions, and the inability of existing technologies to effectively quantify the impact of internal scaling of cooling water circuits on heat exchange efficiency in automated equipment temperature control systems in industrial production.

[0006] The technical solution of this application is as follows: In a first aspect, this application discloses an intelligent temperature control method for equipment in harsh industrial environments, the method comprising: Acquire the equipment's electrical power input, cooling water inlet temperature, cooling water outlet temperature, total instantaneous cooling water flow rate, and equipment temperature; Calculate the heat generated by the equipment based on the electrical power input; The heat consumed by the cooling water is calculated based on the cooling water inlet temperature, cooling water outlet temperature, and total instantaneous flow rate of the cooling water. When the heat generated by the equipment exceeds the heat consumed by the cooling water and the equipment temperature exceeds the preset range, the heat transfer resistance value of the cooling water circuit is determined; whereby the heat transfer resistance value characterizes the degree of blockage caused by scale accumulation inside the cooling water circuit. Based on the heat generated by the equipment and the resistance to heat transfer, adjust the cooling water flow command and control the cooling water pump and regulating valves.

[0007] Secondly, this application also discloses an intelligent temperature control system for equipment in harsh industrial environments, the system comprising: The parameter acquisition module is used to acquire the electrical power input, cooling water inlet temperature, cooling water outlet temperature, total instantaneous flow rate of cooling water, and equipment temperature of the equipment. The first heat calculation module is used to calculate the heat generated by the device based on the electrical power input; The second heat calculation module is used to calculate the heat consumed by the cooling water based on the cooling water inlet temperature, cooling water outlet temperature, and total instantaneous flow rate of the cooling water. The obstacle value determination module is used to determine the heat transfer obstacle value of the cooling water circuit when the heat generated by the equipment is greater than the heat consumed by the cooling water and the equipment temperature exceeds the preset range; wherein, the heat transfer obstacle value represents the degree of blockage caused by scale accumulation inside the cooling water circuit. The flow control module is used to adjust the cooling water flow command and control the cooling water pump and regulating valves based on the heat generated by the equipment and the heat transfer resistance value. Beneficial effects

[0008] This application discloses an intelligent temperature control method for equipment in harsh industrial environments. It acquires key operating parameters in real time, such as the equipment's electrical power input, cooling water inlet and outlet temperatures, total instantaneous cooling water flow rate, and equipment temperature. Based on these parameters, it calculates the heat generated by the equipment and the heat consumed by the cooling water. When the heat generated by the equipment exceeds the heat consumed by the cooling water and the equipment temperature exceeds a preset range, this application can intelligently determine the heat transfer resistance value of the cooling water path. This resistance value accurately characterizes the degree of blockage caused by scale accumulation inside the cooling water path. Based on this, the system can dynamically adjust the cooling water flow command according to the heat generated by the equipment and the real-time determined heat transfer resistance value, and precisely control the cooling water pump and regulating valves. This intelligent adjustment mechanism based on actual heat transfer resistance overcomes the crude strategy of starting cooling with a single fixed temperature upper limit, avoids equipment overheating shutdown caused by decreased heat exchange efficiency due to scale accumulation, accurately matches cooling needs, avoids unnecessary energy waste, significantly improves the operational stability and energy efficiency of the equipment under complex and variable operating conditions, extends the equipment's service life, and reduces maintenance costs. Attached Figure Description

[0009] Figure 1 This is a schematic diagram of an intelligent temperature control method for equipment in harsh industrial environments, as provided in this application.

[0010] Figure 2 This is a schematic diagram of an intelligent temperature control system for equipment in harsh industrial environments, provided in this application. Detailed Implementation

[0011] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. The components of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0012] Reference Figure 1 The diagram illustrates an embodiment of an intelligent temperature control method for equipment in harsh industrial environments according to the present invention, which may specifically include the following steps: S101, acquire the electrical power input of the equipment, the inlet temperature of the cooling water, the outlet temperature of the cooling water, the total instantaneous flow rate of the cooling water, and the equipment temperature; S102, calculate the heat generated by the device based on the electrical power input; S103, calculate the heat consumed by the cooling water based on the cooling water inlet temperature, cooling water outlet temperature, and total instantaneous flow rate of the cooling water; S104, when the heat generated by the equipment is greater than the heat consumed by the cooling water and the equipment temperature exceeds the preset range, determine the heat transfer resistance value of the cooling water circuit; wherein, the heat transfer resistance value characterizes the degree of blockage caused by scale accumulation inside the cooling water circuit. S105 adjusts the cooling water flow command and controls the cooling water pump and regulating valves based on the heat generated by the equipment and the heat transfer resistance value.

[0013] This application acquires multi-dimensional operating parameters in real time and introduces the concept of heat transfer resistance value, which can dynamically assess the degree of blockage inside the cooling water circuit, thereby achieving precise adjustment of cooling water flow. It effectively solves the limitations of traditional control methods in harsh industrial environments, such as slow response, high energy consumption, and inability to adapt to internal scaling problems, and significantly improves the stability and energy efficiency of equipment operation.

[0014] The method proposed in this application aims to achieve intelligent temperature control of equipment in harsh industrial environments. Here, "equipment" can refer to any automated equipment requiring precise temperature control in industrial production, such as high-frequency induction furnaces, large motors, and reaction vessels. These devices generate a large amount of heat during operation, which needs to be dissipated through a cooling system to ensure normal operation and extend their service life. "Electrical power input" refers to the electrical energy consumed by the equipment during operation, which is the main source of heat generation. "Cooling water inlet temperature" and "cooling water outlet temperature" refer to the temperatures of the cooling water entering and leaving the equipment's cooling channels, respectively; these temperature data are key parameters for calculating the heat carried away by the cooling water. "Total instantaneous flow rate of cooling water" refers to the total amount of water flowing through the cooling water path per unit time, which directly affects cooling efficiency. "Equipment temperature" refers to the real-time temperature of the equipment body or its key components, and is an important basis for judging whether the equipment is overheating.

[0015] "Heat transfer resistance value" is a core concept introduced in this application. It characterizes the impact of the degree of blockage caused by factors such as scale accumulation inside the cooling water circuit on heat transfer efficiency. Scale accumulation forms a heat insulation layer, hindering the effective transfer of heat generated by the equipment to the cooling water, thereby reducing cooling efficiency. This resistance value quantifies this impact, providing a basis for subsequent cooling water flow rate adjustments. "Cooling water flow command" is an operational command issued by the control system to the cooling water pump and regulating valves, used to adjust the actual flow rate of the cooling water to achieve the desired cooling effect. The "cooling water pump" is the power device that drives the cooling water circulation, while the "regulating valve" is used to precisely control the distribution and flow rate of cooling water in different cooling channels.

[0016] In practical implementation, the first step is to obtain the equipment's operating parameters. The equipment's electrical power input can be measured in real time using a power sensor installed on the equipment's power supply line. The cooling water inlet and outlet temperatures can be obtained by deploying temperature sensors at the inlet and outlet of the cooling water circuit, respectively. The total instantaneous flow rate of the cooling water can be measured using a flow meter installed on the main cooling water pipeline. The equipment temperature can be obtained by installing temperature sensors on the surface of the equipment body or its key heat-generating components. These sensors can be thermocouples, resistance temperature detectors (RTDs), or infrared temperature sensors, etc., with the specific selection depending on the equipment's operating environment and measurement accuracy requirements. For example, for a high-frequency induction heating furnace, multiple temperature sensors can be arranged near the induction coil and on the furnace surface to obtain more comprehensive equipment temperature information.

[0017] After obtaining the above parameters, it is necessary to calculate the heat generated by the equipment and the heat consumed by the cooling water. The heat generated by the equipment can be calculated based on the electrical power input. For example, a mathematical model based on equipment efficiency and electrical power input can be established, or the relationship curve between electrical power input and equipment heat generation can be obtained through experimental calibration. The heat consumed by the cooling water can be calculated based on the cooling water inlet temperature, cooling water outlet temperature, total instantaneous flow rate of cooling water, and specific heat capacity of cooling water. Specifically, the heat consumed by the cooling water is equal to the total instantaneous flow rate of cooling water multiplied by the specific heat capacity of cooling water, and then multiplied by the difference between the cooling water outlet temperature and the cooling water inlet temperature.

[0018] When the heat generated by the equipment exceeds the heat consumed by the cooling water, and the equipment temperature exceeds the preset range, it indicates a potential decrease in the efficiency of the cooling system. In this case, it is necessary to determine the heat transfer resistance value of the cooling water circuit. The heat transfer resistance value can be calculated by establishing a heat transfer model based on parameters such as the heat generated by the equipment, the heat consumed by the cooling water, and the temperature difference between the equipment and the cooling water. For example, the heat transfer resistance value can be inverted and calculated as an unknown parameter in the model based on Newton's law of cooling or more complex heat transfer equations. This resistance value can intuitively reflect the degree of blockage inside the cooling water circuit, such as the accumulation of scale.

[0019] Finally, based on the heat generated by the equipment and the heat transfer resistance value, the cooling water flow command is adjusted to control the cooling water pump and regulating valves. When the heat transfer resistance value is high, even if the heat generated by the equipment does not increase significantly, a larger cooling water flow rate may be required to maintain the equipment temperature within the normal range. In this case, the control system will dynamically increase the cooling water flow command based on the calculated heat transfer resistance value, and increase the actual cooling water flow rate by controlling the speed of the cooling water pump or the opening of the regulating valves. Conversely, when the heat transfer resistance value is low, the cooling water flow rate can be appropriately reduced to achieve energy saving. This dynamic adjustment mechanism ensures that the equipment maintains its optimal operating temperature under different operating conditions and varying degrees of cooling water circuit blockage, avoiding overheating or overcooling.

[0020] The intelligent temperature control method for equipment in harsh industrial environments proposed in this application effectively solves many problems existing in the prior art by introducing the concept of heat transfer resistance value and combining multi-parameter real-time monitoring and dynamic adjustment strategies. Traditional methods often rely on fixed temperature thresholds or simple thermal balance models, which are difficult to cope with the problem of reduced heat transfer efficiency caused by scale accumulation inside the cooling water circuit. When scale accumulates, even if the system issues a "sufficient" cooling water flow command, the equipment temperature may still be higher than expected, leading to overheating shutdown or requiring manual intervention.

[0021] The core innovation of this application lies in its ability to "sensor" and quantify heat transfer obstacles within the cooling water circuit in real time, specifically the impact of scale accumulation on cooling efficiency. By acquiring key parameters such as the equipment's electrical power input, cooling water inlet temperature, cooling water outlet temperature, total instantaneous cooling water flow rate, and equipment temperature, the system can accurately calculate the heat generated by the equipment and the heat consumed by the cooling water. When the heat generated by the equipment exceeds the heat consumed by the cooling water and the equipment temperature exceeds a preset range, the system can intelligently determine the heat transfer obstacle value of the cooling water circuit. This obstacle value directly characterizes the degree of blockage caused by scale accumulation within the cooling water circuit, providing a quantitative basis for subsequent control decisions.

[0022] Compared to existing technologies, the advantages of this application lie in its adaptability and forward-looking nature. Existing systems are ineffective in assessing the actual heat transfer resistance of cooling channels, only able to make reactive adjustments after equipment temperatures abnormally rise. This application, however, can assess the health of the cooling water circuit in real time and dynamically adjust cooling water flow commands based on the heat transfer resistance value. For example, when an increase in heat transfer resistance is detected, the system proactively increases the cooling water flow to compensate for the decrease in heat transfer efficiency caused by scale buildup, thus taking preventative measures before the equipment temperature reaches a dangerous threshold. This control strategy based on real-time resistance feedback not only effectively prevents equipment overheating and shutdown, improving production efficiency, but also optimizes cooling water usage and reduces energy consumption. By precisely controlling the cooling water pump and regulating valves, the system ensures that the cooling water flow matches the actual heat dissipation demand, avoiding energy waste caused by overcooling in traditional methods, and achieving truly intelligent, efficient, and energy-saving temperature control.

[0023] Specifically, determining the heat transfer resistance value of the cooling water circuit can include the following steps: When the heat generated by the device is greater than the heat consumed by the cooling water and the device temperature exceeds the preset range, the first device temperature change is obtained based on the cooling water inlet temperature and the device temperature. The temperature change of the second equipment is obtained based on the temperature change of the equipment corresponding to the instantaneous flow rate change and the temperature change of the first equipment. The heat transfer resistance value of the cooling water circuit is determined by the temperature change of the second device.

[0024] The first equipment temperature change refers to an initial or baseline temperature change obtained by monitoring the difference or dynamic response relationship between the cooling water inlet temperature and the equipment temperature under specific operating conditions where the heat generated by the equipment exceeds the heat consumed by the cooling water and the equipment temperature exceeds a preset range. This change reflects the immediate response of the equipment temperature to the cooling water inlet temperature under the initial judgment that there may be an anomaly in the cooling system. Further, the equipment temperature change corresponding to an instantaneous flow rate change refers to the change in equipment temperature that occurs when the total instantaneous flow rate of the cooling water is actively or passively adjusted. This is usually obtained by introducing a controlled flow disturbance and observing the dynamic response of the equipment temperature. The second equipment temperature change is obtained by correcting or normalizing the equipment temperature change corresponding to an instantaneous flow rate change, based on the first equipment temperature change. Its purpose is to eliminate or reduce the influence of other factors on equipment temperature changes, thereby more accurately reflecting the changes in heat transfer efficiency within the cooling water circuit.

[0025] This application's solution, by dynamically monitoring the equipment temperature response to changes in cooling water inlet temperature and instantaneous flow rate, enables a more precise assessment of the heat transfer efficiency of the cooling water circuit. Specifically, when the heat generated by the equipment exceeds the heat consumed by the cooling water, and the equipment temperature exceeds the safe range, the system first acquires a first equipment temperature change to establish a temperature response benchmark under the current abnormal operating condition. Subsequently, by introducing changes in instantaneous flow rate and combining it with the first equipment temperature change, a second equipment temperature change is calculated. This second equipment temperature change effectively isolates the impact of heat transfer obstruction caused by factors such as scale accumulation on the equipment temperature. For example, when the flow rate changes specifically, if there is blockage in the cooling water circuit, the equipment temperature response will differ from normal conditions; this difference is quantified by the second equipment temperature change. Therefore, by analyzing the second equipment temperature change, the heat transfer obstruction value of the cooling water circuit can be accurately determined, thereby characterizing the degree of blockage caused by scale accumulation.

[0026] In some embodiments described above, intelligent temperature control of the equipment is achieved by acquiring the electrical power input, cooling water inlet temperature, cooling water outlet temperature, total instantaneous cooling water flow rate, and equipment temperature, and adjusting the cooling water flow rate command based on the calculated heat generated by the equipment and the heat consumed by the cooling water, as well as the determined heat transfer resistance value. However, in harsh industrial environments, in addition to blockages caused by scale accumulation, cooling systems may experience other forms of anomalies, such as partial blockages, pump or valve malfunctions, etc. These anomalies may not be fully and timely identified solely by changes in heat transfer resistance value or equipment temperature. Failure to detect and address these anomalies in a timely manner may lead to equipment overheating, increased energy consumption, or even shutdown. Therefore, this application further proposes a method for determining the presence of anomalies in the cooling system by monitoring the cooling water circuit pressure difference, providing a more comprehensive system health assessment and early warning capability.

[0027] The above methods also include: Differential pressure sensors are installed at various sections of the cooling water circuit to collect initial differential pressure data; Establish a baseline relationship between the initial differential pressure data and the total instantaneous flow rate of cooling water; Collect the current total instantaneous flow rate of cooling water and the actual pressure difference of each segment. Based on the current total instantaneous flow rate of cooling water, find the corresponding initial pressure difference data from the above baseline relationship and calculate the real-time pressure difference deviation. The system is assessed for any abnormalities based on the real-time differential pressure deviation, equipment temperature, and electrical power input.

[0028] Specifically, differential pressure sensors are deployed at various sections of the cooling water circuit to monitor the pressure drop as water flows through these sections in real time. During the initial phase of normal system operation, differential pressure data for each section is collected under different total instantaneous cooling water flow rates; this data is considered initial differential pressure data. Based on this initial differential pressure data, a baseline model or curve reflecting the relationship between differential pressure and total instantaneous cooling water flow rate under normal operating conditions can be established. This baseline relationship characterizes the pressure loss that each section of the cooling water circuit should have at a specific flow rate under normal conditions. During subsequent operation, the system continuously collects the current total instantaneous cooling water flow rate and the actual differential pressure for each section. By substituting the current total instantaneous cooling water flow rate into the pre-established baseline relationship, the corresponding initial differential pressure data at that flow rate can be found. Then, the actual differential pressure is compared with the found initial differential pressure data to calculate the real-time differential pressure deviation. This real-time differential pressure deviation directly reflects the difference between the current flow resistance of each section of the cooling water circuit and that under normal conditions. Ultimately, by combining multiple parameters such as real-time differential pressure deviation, current equipment temperature, and electrical power input, the system can comprehensively determine whether there are any abnormalities in the cooling system. For example, when the real-time differential pressure deviation increases significantly, and the equipment temperature rises abnormally while the electrical power input remains relatively stable, it can be determined that the cooling system may have abnormalities such as blockage or decreased efficiency.

[0029] This application's solution, by introducing differential pressure monitoring of different sections of the cooling water circuit, can more directly and sensitively reflect the flow state within the cooling water circuit. Traditional temperature control methods mainly rely on equipment temperature and heat balance to infer system status. Their ability to identify anomalies such as localized blockages caused by non-scale factors, or decreased pump or valve performance, may be lagging or insufficient. By installing differential pressure sensors in key sections of the cooling water circuit and establishing a baseline relationship between differential pressure and flow rate, any real-time differential pressure deviation from the baseline can quickly indicate a change in flow resistance in that section. This change may be caused by various reasons such as mechanical impurities clogging, abnormal valve opening, pipe deformation, or insufficient pump head. Furthermore, by comprehensively analyzing this differential pressure deviation in conjunction with equipment temperature and electrical power input, different types of anomalies can be effectively distinguished. For example, if the differential pressure deviation increases but the heat transfer resistance value does not change significantly, it may indicate blockage caused by non-scale factors; if the differential pressure deviation and equipment temperature both rise abnormally simultaneously, it strongly indicates a decrease in cooling efficiency. This multi-dimensional data fusion judgment mechanism enables the system to identify potential faults in the cooling system earlier and more accurately, thereby avoiding misjudgments and delays that may result from relying solely on temperature or heat balance judgments.

[0030] In some preferred embodiments, it is assumed that the cooling water circuit of an industrial device is divided into three main sections, each corresponding to a different cooling zone. Differential pressure sensors are deployed at the inlet and outlet of each section. After the device is first put into operation or undergoes a major overhaul, the system collects the initial differential pressure data of each section under various typical operating conditions (e.g., different power inputs and total instantaneous flow rates of cooling water), and establishes a detailed differential pressure-flow rate baseline database accordingly. For example, for a certain section, the normal differential pressure is 0.5 bar when the total instantaneous flow rate of cooling water is 10 m³ / h; and 1.5 bar when it is 20 m³ / h. During daily operation, if the system detects that the current total instantaneous flow rate of cooling water is 15 m³ / h, but the actual differential pressure of a certain section reaches 1.8 bar (while according to the baseline relationship, the normal differential pressure corresponding to 15 m³ / h should be 1.0 bar), then the real-time differential pressure deviation is calculated to be 0.8 bar. Simultaneously, if the equipment temperature also shows a continuous upward trend, even if the electrical power input does not change significantly, the system will issue a warning, indicating that there may be an abnormal blockage in that section. This abnormality may not be caused by scale, but rather by foreign objects in the pipes or valves that are not fully open. In this way, maintenance personnel can use the warning information to specifically check and handle problems in specific sections, thereby avoiding the need for a complete shutdown for inspection and improving the efficiency and accuracy of fault diagnosis.

[0031] This application further proposes a method for intelligent temperature control of equipment in harsh industrial environments, the method further comprising: Acquire data on the workpiece's thermal capacity and environmental noise. The intensity range of the flow disturbance is calculated based on the electrical power input, the workpiece's heat capacity, the cooling water inlet temperature, and the cooling water outlet temperature. Under the condition of minimum disturbance intensity, obtain the equipment temperature corresponding to the instantaneous flow rate, and obtain the equipment temperature response curve; The response signal in the response curve is filtered based on environmental noise data to obtain the filtered equipment temperature.

[0032] Specifically, obtaining the workpiece's heat capacity and environmental noise data refers to determining the workpiece's heat capacity by pre-measuring, consulting material databases, or using online estimation techniques to obtain parameters such as the specific heat capacity and mass of the workpiece under current operating conditions. Simultaneously, environmental sensors (such as acoustic sensors and vibration sensors) are used to collect noise data from the equipment's operating environment in real time. This noise may exist in the form of thermal noise, electromagnetic noise, or mechanical vibration, and may interfere with the temperature measurement signal.

[0033] This process involves calculating the intensity range of flow disturbance based on the electrical power input, the workpiece's heat capacity, and the inlet and outlet temperatures of the cooling water. Essentially, given the equipment's input power, the workpiece's heat absorption capacity, and the temperature difference between the inlet and outlet cooling water, the maximum and minimum potential flow disturbance amplitudes are estimated using heat balance equations or heat transfer models, while maintaining stable equipment temperature or within permissible fluctuation ranges. The aim is to provide a safe and effective flow disturbance range for subsequent response curve acquisition.

[0034] In practical applications, under conditions of minimum disturbance intensity, the equipment temperature corresponding to the instantaneous flow rate is obtained, resulting in the equipment temperature response curve. Specifically, this involves applying a preset, small-amplitude instantaneous disturbance to the cooling water flow rate while simultaneously recording the change in equipment temperature over time, ensuring that it does not significantly affect the normal operation of the equipment. Through multiple experiments or continuous monitoring, a dynamic response curve of the equipment temperature to changes in cooling water flow rate can be plotted. This curve characterizes the equipment's thermal inertia and its sensitivity to changes in cooling water flow rate.

[0035] Furthermore, filtering the response signal in the response curve based on environmental noise data to obtain the filtered equipment temperature refers to using the collected environmental noise data to design or select a suitable digital filter (such as a Kalman filter, wavelet filter, or moving average filter) to denoise the equipment temperature signal extracted from the response curve. The purpose is to eliminate the interference of environmental noise on temperature measurement and response curve analysis, thereby obtaining more accurate and realistic equipment temperature response characteristics.

[0036] This application's solution, by introducing the acquisition of workpiece heat capacity and environmental noise data, combined with the analysis of equipment temperature response curves under flow disturbances, enables a more comprehensive understanding of the equipment's dynamic thermal behavior. Specifically, by calculating the intensity range of flow disturbances, it ensures that during response curve testing, the disturbance amplitude effectively stimulates the equipment response without negatively impacting the production process. Obtaining the equipment temperature response curve under minimum disturbance intensity allows the system to identify the equipment's true thermal response characteristics under minute flow changes, which is crucial for refined control. Furthermore, filtering the response signal based on environmental noise data effectively removes measurement noise, ensuring the accuracy of the obtained equipment temperature response curve, thus providing a more reliable basis for subsequent flow command adjustments. It is precisely because of the precise quantification and processing of these dynamic factors that the system can more accurately predict equipment temperature change trends and make more precise adjustments to the cooling water flow rate, thereby overcoming the lag and inaccuracy that may exist when controlling solely based on heat balance.

[0037] In some preferred embodiments, this application is implemented as follows: Assume a high-temperature alloy forging workshop where an induction heating furnace needs to precisely control the workpiece temperature. First, by consulting material handbooks or conducting experiments, the heat capacity data of the high-temperature alloy workpiece to be forged, such as its specific heat capacity and mass, is obtained. Simultaneously, multiple microphones or vibration sensors are deployed near the heating furnace to continuously collect environmental noise data within the workshop; this noise may originate from the operation of other equipment or environmental vibrations.

[0038] Next, based on the current electrical power input of the induction heating furnace, the known heat capacity of the workpiece, and the inlet and outlet temperatures of the cooling water, a safe range for flow disturbance intensity is calculated using a preset heat transfer model. For example, it is determined that the workpiece temperature fluctuation remains within an acceptable range under a ±5% change in the total instantaneous flow rate of the cooling water.

[0039] Then, in actual operation, the minimum disturbance intensity within this range is selected, for example, by making a slight adjustment to the speed of the cooling water pump to cause a 1% step change in its instantaneous flow rate. When this disturbance occurs, the surface temperature of the workpiece (i.e., the equipment temperature) is continuously monitored and recorded over time to obtain a response curve for the equipment temperature.

[0040] Finally, the temperature signal in this response curve is digitally filtered using the previously collected environmental noise data. For example, an adaptive Kalman filter can be used, dynamically adjusting the filtering parameters based on real-time noise characteristics to remove noise interference to the maximum extent, resulting in a smooth and accurate filtered equipment temperature response curve. This filtered response curve will be used to more accurately evaluate the actual thermal response characteristics of the workpiece, guiding the adjustment of subsequent cooling water flow commands, thereby achieving precise temperature control in the high-temperature alloy forging process.

[0041] In some existing implementations, when calculating the intensity range of flow disturbances, preset workpiece heat capacity and electrical power input are typically used directly. However, in harsh industrial environments, the actual heat capacity of the workpiece material may dynamically change due to phase transitions or compositional variations, and the electrical power input of the equipment may also fluctuate. If these dynamic factors are not considered and static or average values ​​are used directly for calculation, the calculation of the intensity range of flow disturbances may be inaccurate, thereby affecting the adjustment effect of cooling water flow commands and reducing the accuracy and robustness of equipment temperature control.

[0042] In response, this application further proposes a method for calculating the intensity range of flow disturbances, which includes: Acquire information on workpiece surface temperature distribution and power fluctuation data; Based on the workpiece surface temperature distribution information, the phase transition point or composition change of the workpiece material is identified. Based on the phase transition point or compositional change of the workpiece material, the effective heat capacity of the workpiece is corrected to obtain the corrected effective heat capacity of the workpiece. The power input is adjusted based on the power fluctuation data to obtain the adjusted power input. The intensity range of the flow disturbance is calculated by using the corrected effective heat capacity of the workpiece, the adjusted electrical power input, the inlet temperature of the cooling water, and the outlet temperature of the cooling water.

[0043] Specifically, workpiece surface temperature distribution information refers to the set of temperature data at different locations on the workpiece surface acquired through non-contact sensors (such as infrared thermal imagers), which reflects the real-time thermal state of the workpiece during processing. Power fluctuation data refers to the record of changes in the electrical power input of the equipment over time during operation, which may be caused by factors such as load changes and power instability. Identifying the phase transition point or compositional change of the workpiece material can be understood as analyzing the workpiece surface temperature distribution information, such as observing temperature gradients, local temperature anomalies, or changes in specific temperature thresholds, to determine whether the workpiece material has undergone crystal structure transformation, melting, solidification, or other chemical compositional changes. These changes directly affect the physical properties of the material, especially its heat capacity. Furthermore, correcting the effective heat capacity of the workpiece refers to dynamically adjusting the theoretical or initial heat capacity of the workpiece based on the identified phase transition point or compositional change of the workpiece material. For example, when a material undergoes a phase transition, its specific heat capacity changes significantly. In this case, it is necessary to update the heat capacity value according to the actual phase transition state to more accurately reflect the actual heat storage capacity of the workpiece. Adjusted power input refers to the correction or predictive adjustment of the power input of the equipment based on real-time monitored power fluctuation data, in order to obtain a more accurate instantaneous power value.

[0044] The solution presented in this application dynamically identifies the phase transition point or compositional changes of the workpiece material by acquiring workpiece surface temperature distribution information and power fluctuation data, and corrects the workpiece's effective heat capacity accordingly. Simultaneously, by adjusting the electrical power input in conjunction with the power fluctuation data, the input parameters used to calculate the intensity range of flow disturbances (i.e., the corrected effective heat capacity of the workpiece and the adjusted electrical power input) more closely reflect actual operating conditions. It is precisely because of the improved accuracy of these parameters that the calculation results of the intensity range of flow disturbances are more accurate, thus providing a more reliable basis for subsequent adjustments to cooling water flow commands.

[0045] In some preferred embodiments, it is assumed that the device is heat-treating an alloy material. During the heat treatment process, the alloy material may undergo a phase transition from solid to liquid, or its internal components may diffuse and recombine. Traditional methods may only use the alloy's heat capacity at room temperature for calculation, which obviously cannot accurately reflect the heat capacity of the high-temperature phase transition region. This application specifically implements the following: First, an infrared thermal imager deployed on the workpiece surface acquires real-time information on the workpiece surface temperature distribution. When the system detects that a local temperature on the workpiece reaches or exceeds the melting point of the alloy, it identifies that a phase transition is occurring in that region based on a preset material phase transition database. For example, when the temperature rapidly rises from 1000℃ to 1050℃ and remains there for a period of time, while the thermal image shows a significant temperature plateau or gradient change in that region, it can be determined that a phase transition has occurred. Furthermore, based on the identified phase transition information, the system retrieves the effective heat capacity of the alloy in the phase transition state from the database and uses it to replace or correct the original heat capacity parameters. For example, if the solid-state heat capacity is C1, the liquid-state heat capacity is C2, and the latent heat of phase change is L, then during the phase change process, the effective heat capacity will be corrected to a dynamic value that considers the release or absorption of latent heat. Simultaneously, power fluctuation data of the equipment is collected in real time by current and voltage sensors, and algorithms such as moving average filtering or Kalman filtering are used to adjust the original electrical power input to eliminate instantaneous noise and fluctuations, resulting in a more stable and accurate adjusted electrical power input. Finally, using the corrected effective heat capacity of the workpiece, the adjusted electrical power input, and the real-time acquired inlet and outlet temperatures of the cooling water, the intensity range of the flow disturbance is recalculated. For example, by establishing a dynamic model based on energy conservation, these corrected parameters are substituted to solve for the permissible disturbance range of the cooling water flow rate under the current operating conditions to maintain stable equipment temperature. In this way, even when the workpiece material undergoes a phase change or the electrical power input fluctuates, the calculation results of the flow disturbance intensity range can be ensured to be highly accurate, thus providing a precise control basis for the cooling system.

[0046] In some embodiments of this application, when identifying the phase transition point or compositional change of the workpiece material based on the workpiece surface temperature distribution information, traditional methods may result in errors or inaccuracies in the acquired workpiece surface temperature distribution information due to variations in workpiece surface emissivity under harsh industrial environments, environmental radiation interference, and the limitations of the sensors themselves. If these problems are not addressed, the phase transition point or compositional change of the workpiece material identified based on inaccurate temperature information may not be precise enough, thus affecting the correction of the workpiece's effective heat capacity and ultimately leading to inaccurate calculation of the flow disturbance intensity range, thereby reducing the accuracy and reliability of the equipment's intelligent temperature control. Therefore, this application further proposes a more accurate method for identifying the phase transition point or compositional change of the workpiece material to improve the robustness of temperature control.

[0047] Specifically, the identification of phase transition points or compositional changes in workpiece materials based on workpiece surface temperature distribution information includes: The radiation intensity data of the workpiece surface is obtained by using a multispectral infrared sensor array; Based on the radiation intensity data and the preset material spectral emissivity, the effective emissivity of the workpiece surface at different wavelengths is calculated; The temperature data corresponding to the radiation intensity data is compensated based on the effective emissivity to obtain the corrected workpiece surface temperature distribution information. Based on the corrected workpiece surface temperature distribution information, the phase transition point or composition change of the workpiece material is identified.

[0048] Multispectral infrared sensor arrays refer to sensor systems capable of simultaneously acquiring radiation intensity data across multiple different infrared wavelength ranges. Their purpose is to provide a more comprehensive data foundation for subsequent temperature calculations and material property identification by acquiring richer spectral information. Radiation intensity data refers to the energy intensity information radiated outward from the workpiece surface at different wavelengths. The preset material spectral emissivity refers to the known radiation emission capability parameter of a specific material at different wavelengths. By combining the actually measured radiation intensity data with the preset material spectral emissivity, the effective emissivity of the workpiece surface at different wavelengths can be calculated. Effective emissivity can be understood as the ratio of the actual radiation capability of the workpiece surface at a specific wavelength to the radiation capability of an ideal blackbody under actual measurement conditions. Its purpose is to correct for emissivity variations caused by factors such as material surface characteristics, oxidation levels, or coatings, thereby more accurately reflecting the true temperature of the workpiece. In practical applications, compensating for the temperature data corresponding to the radiation intensity data based on the effective emissivity means using the calculated effective emissivity to correct the apparent temperature data directly converted from radiation intensity, eliminating errors caused by emissivity uncertainty, and thus obtaining corrected workpiece surface temperature distribution information. The corrected workpiece surface temperature distribution information more closely approximates the actual temperature distribution of the workpiece, aiming to provide reliable input for subsequent accurate identification of phase transition points or compositional changes in the workpiece material. Ultimately, based on the corrected workpiece surface temperature distribution information, the phase transition points or compositional changes of the workpiece material can be identified more accurately. For example, by analyzing abrupt changes or gradients in the corrected temperature distribution within a specific region, it can be determined whether a phase transition has occurred in the material, or by comparing it with the temperature-composition curve of a known material, changes in composition can be identified.

[0049] This application's solution, by introducing a multispectral infrared sensor array, can acquire radiation intensity data of the workpiece surface at multiple wavelengths, providing richer spectral information compared to single-wavelength or broadband infrared measurements. Given that the emissivity of the workpiece surface may vary with temperature, oxidation level, or surface condition in harsh industrial environments, this solution further combines a preset material spectral emissivity with actual radiation intensity data to calculate the effective emissivity of the workpiece surface at different wavelengths. It is precisely because of the ability to dynamically or more accurately acquire the effective emissivity that it becomes possible to compensate for the temperature data corresponding to the radiation intensity data, thereby eliminating the main error caused by emissivity uncertainty in traditional infrared thermometry. This results in a more realistic and accurate corrected temperature distribution information of the workpiece surface. In this way, this solution overcomes the limitations of traditional methods in complex industrial environments where temperature measurement inaccuracies are caused by emissivity variations, laying a solid foundation for subsequent accurate identification of phase transition points or compositional changes in workpiece materials.

[0050] Through the above technical solution, this application can significantly improve the accuracy and reliability of workpiece surface temperature measurement, especially in harsh industrial environments where emissivity is unknown or varies. Because it obtains corrected and more accurate workpiece surface temperature distribution information, it enables more precise identification of phase transition points or compositional changes in the workpiece material.

[0051] In some preferred embodiments, a specific example is given below. Suppose a high-temperature melting furnace requires precise temperature control of the workpiece to prevent overheating or incomplete phase transformation. Traditional infrared thermometers may exhibit inaccurate temperature measurements due to emissivity fluctuations caused by factors such as furnace dust and changes in the oxide layer on the workpiece surface. The solution proposed in this application deploys a multispectral infrared sensor array, for example, containing sensors with 3-5 different wavelength channels, to continuously collect radiation intensity data from the workpiece surface. Simultaneously, a database of the workpiece material's spectral emissivity at different temperatures and oxidation levels is pre-established. Once the sensor array acquires radiation intensity data, the system calculates the effective emissivity of the workpiece surface at various wavelengths in real time based on this data and the preset material spectral emissivity in the database. For example, if the radiation intensity of the workpiece surface is abnormally high at a certain wavelength but normal at other wavelengths, the system can determine that it is a localized emissivity change rather than a true temperature increase. Subsequently, these calculated effective emissivities are used to compensate for the temperature data converted from the original radiation intensity data, thereby obtaining a corrected workpiece surface temperature distribution information that is closer to the true value. Based on this corrected temperature distribution information, the system can accurately identify whether the workpiece has reached its melting point or undergone a solid-state phase transition, for example, by detecting plateau periods or points of abrupt change in the temperature distribution curve. This accurate identification makes subsequent corrections to the effective heat capacity of the workpiece more reliable, thus providing a more accurate basis for adjusting cooling water flow commands and ensuring the temperature control precision of the melting process.

[0052] In some embodiments of this application, when determining the heat transfer resistance value of the cooling water path, it is necessary to obtain the first equipment temperature change based on the cooling water inlet temperature and the equipment temperature. However, in harsh industrial environments, the cooling water inlet temperature sensor may experience drift or calibration errors, leading to inaccurate cooling water inlet temperature data. This, in turn, affects the calculation accuracy of the first equipment temperature change, and may ultimately reduce the accuracy of determining the heat transfer resistance value and the effectiveness of cooling water flow command adjustments. Therefore, this application further proposes an optimized method for obtaining the first equipment temperature change.

[0053] In the above method, obtaining the first equipment temperature change based on the cooling water inlet temperature and the equipment temperature includes: Deploy multiple cooling water inlet temperature sensors; By identifying the drift or calibration error of the temperature sensor, the cooling water inlet temperature data is corrected to obtain the corrected cooling water inlet temperature data. Establish a dynamic heat transfer relationship between the corrected cooling water inlet temperature data and the equipment temperature, and obtain the first equipment temperature change based on the dynamic heat transfer relationship.

[0054] Specifically, deploying multiple cooling water inlet temperature sensors means installing more than one temperature sensor at the inlet end of the cooling water circuit. For example, at least two temperature sensors can be deployed at multiple different locations in the cooling water inlet pipe or at different depths at the same location to obtain redundant cooling water inlet temperature data. The purpose is to provide multi-source data, providing a basis for subsequent sensor calibration.

[0055] This process involves identifying drift or calibration errors in temperature sensors and correcting the cooling water inlet temperature data to obtain corrected cooling water inlet temperature data. This can be understood as a quality assessment and correction of the raw temperature data acquired from multiple sensors. Various methods can be used, such as detecting drift by comparing the consistency of readings from different sensors under the same operating conditions, or periodically calibrating against a standard thermometer. When drift or calibration errors are detected in a sensor, data fusion algorithms (such as Kalman filtering, weighted averaging, etc.) or compensation based on historical calibration data can be used to obtain more accurate and reliable cooling water inlet temperature data. The aim is to eliminate or reduce the impact of sensor defects on measurement results and improve data accuracy.

[0056] In practical applications, establishing a dynamic heat transfer relationship between the corrected cooling water inlet temperature data and the equipment temperature, and obtaining the first equipment temperature change based on this dynamic heat transfer relationship, involves further considering the heat transfer delay and dynamic response characteristics within the cooling system after obtaining high-precision cooling water inlet temperature data. For example, a mathematical model describing how changes in cooling water inlet temperature affect equipment temperature changes can be established using system identification methods based on historical operating data and physical models. This model can be a transfer function, a state-space model, or a machine learning-based model. This dynamic heat transfer relationship can reflect the dynamic characteristics such as the time lag and amplitude attenuation of cooling water temperature changes in the equipment temperature response. By inputting the corrected cooling water inlet temperature data into this dynamic heat transfer relationship model, combined with the current equipment temperature, the first equipment temperature change under the current cooling water inlet conditions can be predicted or calculated more accurately. The aim is to more accurately reflect the actual impact of cooling water on equipment temperature and improve the accuracy of temperature change calculation.

[0057] The solution presented in this application achieves a more accurate measurement of the temperature change of the first piece of equipment because it firstly provides redundant temperature measurement data by deploying multiple cooling water inlet temperature sensors, laying the foundation for subsequent data correction. The presence of multiple sensors allows for the identification and correction of drift or calibration errors in individual or partial sensors, resulting in more accurate and reliable corrected cooling water inlet temperature data, effectively avoiding measurement deviations caused by sensor malfunctions or insufficient accuracy. Furthermore, by establishing a dynamic heat transfer relationship between the corrected cooling water inlet temperature data and the equipment temperature, the complexity and dynamism of heat transfer processes in harsh industrial environments, such as thermal inertia and heat transfer delay, can be fully considered. This dynamic heat transfer relationship allows for deeper analysis and prediction of the temperature change of the first piece of equipment, in addition to relying on instantaneous measurements, by incorporating the system's dynamic response characteristics. This ensures that the obtained temperature change of the first piece of equipment more accurately reflects the actual impact of the cooling water on the equipment temperature.

[0058] As a specific implementation, suppose three cooling water inlet temperature sensors are deployed in the cooling system of a high-temperature furnace, located at different positions on the inlet pipe. During the initial stage of system operation, these three sensors are synchronously calibrated, and their initial deviations are recorded. During daily operation, the system continuously collects real-time temperature data from these three sensors. When a sustained and significant deviation is found between the readings of one sensor (e.g., sensor A) and the other two sensors (sensors B and C), the system determines that sensor A may be drifting or malfunctioning. In this case, the average value of sensors B and C can be used as a benchmark to correct the data for sensor A, or the data for sensor A can be directly excluded, and only the data from B and C can be used for a weighted average to obtain the corrected cooling water inlet temperature data.

[0059] Furthermore, the system pre-trains a neural network-based dynamic heat transfer model using historical data. This model can predict the temperature change trend of the equipment over a future period based on the corrected cooling water inlet temperature data and the current equipment temperature. When it is necessary to calculate the first temperature change of the equipment, the corrected cooling water inlet temperature data is input into the model. Combined with the current equipment temperature, the model outputs an accurate predicted temperature change value, which is the first temperature change of the equipment. For example, when the corrected cooling water inlet temperature rises from 20℃ to 22℃, the model will predict, based on its internally established dynamic heat transfer relationship, that the equipment temperature will rise from the current value by 0.5℃. This 0.5℃ is the first temperature change of the equipment. This approach ensures that even with potential sensor problems or complex heat transfer processes, a high-precision temperature change can be obtained, thereby improving the accuracy of determining the heat transfer resistance value.

[0060] Specifically, this application further proposes an intelligent temperature control method for equipment in harsh industrial environments, the method further comprising: Deploy multiple cooling water inlet temperature sensors and temperature sensors for multiple devices; Consistency detection is performed on the real-time data of the multiple cooling water inlet temperature sensors to obtain the corrected cooling water inlet temperature data; Consistency testing is performed on the real-time data from the temperature sensors of the multiple devices to obtain corrected device temperature data.

[0061] Specifically, deploying multiple cooling water inlet temperature sensors and multiple device temperature sensors refers to strategically installing multiple temperature sensors with the same or different measurement principles at key locations where cooling water enters the equipment and on the equipment itself. These sensors are configured to operate in parallel to provide redundant temperature measurement data. The multiple cooling water inlet temperature sensors are used to acquire temperature information when cooling water enters the equipment, while the multiple device temperature sensors are used to monitor the real-time temperature inside or on the surface of the equipment.

[0062] Furthermore, the consistency detection of real-time data from the multiple cooling water inlet temperature sensors involves comparing and analyzing real-time measurements from different sensors. This detection process aims to identify and eliminate erroneous readings caused by sensor malfunctions, drift, noise interference, or local anomalies. For example, this can be achieved by calculating the average, median, or weighted average of the sensor readings and setting an allowable deviation range. When a sensor reading exceeds this range, it is considered an outlier and is either discarded or corrected. In this way, more reliable and accurate corrected cooling water inlet temperature data can be obtained.

[0063] Similarly, consistency testing of real-time data from the temperature sensors of the multiple devices involves comparing and analyzing real-time measurements from different device temperature sensors. The aim is to ensure the accuracy and reliability of the device temperature data, thereby obtaining corrected device temperature data. This consistency testing can employ various algorithms, such as statistical methods (e.g., standard deviation analysis, outlier detection), model-based prediction methods, or machine learning methods, to adapt to different industrial environments and sensor characteristics.

[0064] This application's solution effectively addresses the accuracy issues that may arise from individual sensor data by deploying multiple temperature sensors and performing real-time data consistency checks. Specifically, the deployment of multiple sensors provides data redundancy; even if one sensor malfunctions or displays abnormal readings, the system can still obtain valid data from other sensors, thereby improving the robustness of data acquisition. The consistency check mechanism can identify and correct deviations or errors in the sensor data in real time. For example, by comparing readings from multiple sensors, random noise can be effectively filtered out, sensor drift or malfunctions can be identified, and abnormal data can be discarded or corrected. As a result, the corrected cooling water inlet temperature data and the corrected equipment temperature data have higher accuracy and reliability. This corrected temperature data is used for subsequent calculations of the first equipment temperature change, ensuring the accuracy of this change. Furthermore, based on a more accurate first equipment temperature change, the determination of the heat transfer resistance value will be more precise, ultimately making the adjustment of the cooling water flow command more reasonable and effective, thereby achieving precise control of the equipment temperature.

[0065] In some preferred embodiments, this application is implemented as follows: Suppose that in a certain industrial equipment, three cooling water inlet temperature sensors, labeled T_in_A, T_in_B, and T_in_C, are deployed to accurately monitor the cooling water inlet temperature. Simultaneously, three equipment temperature sensors, labeled T_dev_X, T_dev_Y, and T_dev_Z, are deployed to monitor the equipment temperature.

[0066] During real-time data acquisition, the system simultaneously acquires readings from these six sensors. For cooling water inlet temperature data, the system first checks the readings of T_in_A, T_in_B, and T_in_C. For example, if the reading of T_in_A is 25.1℃, the reading of T_in_B is 25.3℃, and the reading of T_in_C is 30.5℃, the system will identify that the reading of T_in_C deviates significantly from the other two sensors (e.g., exceeding a preset 0.5℃ threshold). In this case, the system will mark the reading of T_in_C as abnormal and may discard it, or use the average of T_in_A and T_in_B (25.2℃) as the corrected cooling water inlet temperature data.

[0067] Similarly, for device temperature data, if the readings of T_dev_X, T_dev_Y, and T_dev_Z are 150.2℃, 150.5℃, and 140.1℃ respectively, the system will identify an anomaly in the reading of T_dev_Z. After removing the reading of T_dev_Z, the system will use the average of T_dev_X and T_dev_Y (150.35℃) as the corrected device temperature data.

[0068] Through this consistency detection and data correction mechanism, even if a sensor malfunctions or displays abnormal readings, the system can still obtain highly accurate and reliable cooling water inlet temperature data and equipment temperature data. This corrected data is then used to calculate the first equipment temperature change, ensuring the accurate determination of heat transfer resistance values ​​and ultimately guiding the precise adjustment of cooling water flow commands, resulting in more stable and efficient equipment temperature control.

[0069] In some embodiments described above, the first equipment temperature change is obtained based on the cooling water inlet temperature and the equipment temperature. However, in harsh industrial environments, the operating conditions of equipment (e.g., instantaneous flow rate and electrical power input) are often dynamically changing, and there is a time lag effect in heat transfer between the cooling water inlet temperature and the equipment temperature. If these dynamic factors and time lags are not considered, directly calculating the first equipment temperature change based on the original cooling water inlet temperature and equipment temperature data may lead to insufficient accuracy in the calculation results, thereby affecting the accurate judgment of the heat transfer resistance value of the cooling water circuit and the effective adjustment of the cooling water flow command. Therefore, this application further proposes an optimized method for obtaining the first equipment temperature change by classifying the operating conditions and performing time synchronization processing to improve the calculation accuracy of this change.

[0070] The temperature change of the first equipment obtained above based on the cooling water inlet temperature and the equipment temperature specifically includes: Based on the instantaneous flow rate and the electrical power input of the equipment, the operating conditions of the cooling water inlet temperature and the equipment temperature are classified to obtain multiple operating condition categories; Under each of the aforementioned operating conditions, the time relationship between the cooling water inlet temperature and the equipment temperature is analyzed to determine the time lag parameter; Based on the time lag parameter, the cooling water inlet temperature and equipment temperature are synchronized in time to obtain time-aligned cooling water inlet temperature and equipment temperature. The first equipment temperature change is obtained based on the time-aligned cooling water inlet temperature and equipment temperature.

[0071] Specifically, operating condition classification refers to dividing the operating state of equipment at different time periods into several categories with similar thermodynamic characteristics based on key operating parameters such as instantaneous flow rate and electrical power input. For example, it can be classified according to the level of instantaneous flow rate (e.g., high flow rate, medium flow rate, low flow rate) and the magnitude of electrical power input (e.g., high power, medium power, low power), forming different operating condition categories such as "high flow rate-high power" and "medium flow rate-low power". The purpose is to identify the different heat transfer characteristics and response modes that may exist between the cooling water inlet temperature and the equipment temperature under different operating conditions.

[0072] Within each operating condition category, the time relationship between the cooling water inlet temperature and the equipment temperature is analyzed to determine the time lag parameter. The time lag parameter characterizes the time required for a change in cooling water inlet temperature to affect the equipment temperature. For example, cross-correlation analysis, system identification methods, or simulations based on physical models can be used to quantify the time required for a change in cooling water temperature to propagate to the equipment and trigger a temperature response under specific operating conditions. The aim is to accurately capture the dynamic delay in the heat transfer process, providing a basis for subsequent data synchronization.

[0073] In practical applications, the cooling water inlet temperature and equipment temperature are synchronized based on the determined time lag parameter. This means shifting the cooling water inlet temperature data forward or backward by the corresponding time lag to align it with the equipment temperature data on the time axis. For example, if it is determined that a change in the cooling water inlet temperature requires T seconds to affect the equipment temperature, the cooling water inlet temperature data can be shifted forward by T seconds to correspond to the current equipment temperature data. The purpose is to eliminate data misalignment caused by heat transfer delays and ensure that the cooling water inlet temperature and equipment temperature data used when calculating the first change in equipment temperature are physically related and synchronized.

[0074] Therefore, by using the time-aligned cooling water inlet temperature and equipment temperature, the first equipment temperature change can be obtained more accurately. This change reflects the actual impact of the cooling water inlet temperature change on the equipment temperature under specific operating conditions, providing a more reliable input for subsequent determination of heat transfer resistance values.

[0075] This application's solution effectively addresses the challenges posed by the complex and delayed heat transfer relationship between cooling water inlet temperature and equipment temperature in dynamically changing, harsh industrial environments by introducing operating condition classification, time lag parameter determination, and time synchronization processing. Specifically, by classifying operating conditions based on instantaneous flow rate and equipment power input, the system can identify the unique heat transfer characteristics of equipment under different operating states, avoiding the limitations of using a single model or parameter to describe all operating conditions. Under each specific operating condition category, in-depth analysis of the time relationship between cooling water inlet temperature and equipment temperature accurately quantifies the time lag effect in the heat transfer process, thus providing crucial time calibration information for subsequent data processing. It is precisely the determination of these time lag parameters that makes time synchronization processing of cooling water inlet temperature and equipment temperature possible, ensuring that the temperature data used in calculating the first equipment temperature change are physically correlated and time-aligned, thereby significantly improving the accuracy and reliability of this change.

[0076] Through the above technical solution, this application overcomes the inaccuracy problem of traditional methods in calculating the temperature change of the first piece of equipment under dynamic operating conditions. By refining the operating condition classification and time synchronization processing, the actual impact of cooling water inlet temperature changes on equipment temperature can be captured more accurately, thus making the obtained temperature change of the first piece of equipment more realistically reflect the actual thermal state of the equipment. This higher accuracy directly improves the reliability of determining the heat transfer resistance value of the subsequent cooling water circuit, thereby optimizing the adjustment accuracy of the cooling water flow command, making equipment temperature control more intelligent and stable. Especially in harsh industrial environments, it can effectively avoid overcooling or overheating caused by misjudgment, extending equipment service life and improving production efficiency.

[0077] In some preferred embodiments, a specific example is given below. Suppose that during the operation of an industrial device, its electrical power input and total instantaneous flow rate of cooling water periodically switch between two main operating conditions: "high power-high flow rate" and "low power-low flow rate".

[0078] First, the system identifies the current operating status as the corresponding operating condition category based on real-time power input and instantaneous flow data. For example, when the power input is greater than a certain threshold and the instantaneous flow is greater than another threshold, it is determined to be a "high power-high flow" operating condition; otherwise, it is determined to be a "low power-low flow" operating condition.

[0079] Under "high power-high flow" conditions, due to the high heat load and cooling capacity, the effect of changes in cooling water inlet temperature on equipment temperature may exhibit a short time lag. For example, through historical data analysis or experimental calibration, the time lag parameter may be determined to be T1 seconds. However, under "low power-low flow" conditions, with lower heat load and cooling capacity, the thermal response may be relatively slow, and the time lag parameter may be T2 seconds (T2>T1).

[0080] When the system is in "high power-high flow" operation, the cooling water inlet temperature data will be shifted forward by T1 seconds based on the time lag parameter T1 seconds, so that it is time-aligned with the current equipment temperature data. For example, if the current equipment temperature is measured at time t, then the cooling water inlet temperature data used to calculate the first change in equipment temperature will be the data measured at time (t-T1).

[0081] Similarly, when the system switches to "low power-low flow" mode, a time lag parameter of T2 seconds will be used for time synchronization.

[0082] In this way, regardless of the equipment's operating conditions, the cooling water inlet temperature and the equipment temperature data used to calculate the first equipment temperature change are physically synchronized, resulting in a more accurate first equipment temperature change. For example, under "high power-high flow" conditions, if the cooling water inlet temperature rises by ΔT_in at time (t-T1), and the equipment temperature rises by ΔT_dev at time t, the first equipment temperature change can be calculated based on this time-aligned data. This precise time synchronization significantly improves the accuracy of equipment thermal state assessment, providing a solid data foundation for subsequent intelligent temperature control.

[0083] Secondly, referring to Figure 2 This application further proposes an intelligent temperature control system for equipment in harsh industrial environments, the system comprising: The parameter acquisition module 201 is used to acquire the electrical power input of the equipment, the cooling water inlet temperature, the cooling water outlet temperature, the total instantaneous flow rate of cooling water, and the equipment temperature. The first heat calculation module 202 is used to calculate the heat generated by the device based on the electrical power input; The second heat calculation module 203 is used to calculate the heat consumed by the cooling water based on the cooling water inlet temperature, cooling water outlet temperature, and total instantaneous flow rate of the cooling water. The obstacle value determination module 204 is used to determine the heat transfer obstacle value of the cooling water circuit when the heat generated by the device is greater than the heat consumed by the cooling water and the device temperature exceeds a preset range; wherein, the heat transfer obstacle value characterizes the degree of blockage caused by scale accumulation inside the cooling water circuit; The flow control module 205 is used to adjust the cooling water flow command and control the cooling water pump and regulating valve according to the heat generated by the device and the heat transfer resistance value.

[0084] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for intelligent temperature control of equipment in harsh industrial environments, characterized in that, include: Acquire the equipment's electrical power input, cooling water inlet temperature, cooling water outlet temperature, total instantaneous cooling water flow rate, and equipment temperature; The heat generated by the device is calculated based on the electrical power input; The heat consumed by the cooling water is calculated based on the cooling water inlet temperature, cooling water outlet temperature, and total instantaneous flow rate of the cooling water. When the heat generated by the device exceeds the heat consumed by the cooling water and the device temperature exceeds a preset range, the heat transfer resistance value of the cooling water circuit is determined; wherein, the heat transfer resistance value characterizes the degree of blockage caused by scale accumulation inside the cooling water circuit. Based on the heat generated by the device and the heat transfer resistance value, adjust the cooling water flow command and control the cooling water pump and regulating valve; When the heat generated by the device exceeds the heat consumed by the cooling water and the device temperature exceeds a preset range, determining the heat transfer resistance value of the cooling water path includes: When the heat generated by the device is greater than the heat consumed by the cooling water and the device temperature exceeds the preset range, the first device temperature change is obtained based on the cooling water inlet temperature and the device temperature. The temperature change of the second equipment is obtained based on the temperature change of the equipment corresponding to the instantaneous flow rate change and the temperature change of the first equipment. The heat transfer resistance value of the cooling water circuit is determined by the temperature change of the second device.

2. The intelligent temperature control method for equipment in harsh industrial environments according to claim 1, characterized in that, The method further includes: Differential pressure sensors are installed at various sections of the cooling water circuit to collect initial differential pressure data; Establish a baseline relationship between the initial differential pressure data and the total instantaneous flow rate of cooling water; Collect the current total instantaneous flow rate of cooling water and the actual pressure difference of each segment. Based on the current total instantaneous flow rate of cooling water, find the corresponding initial pressure difference data from the baseline relationship and calculate the real-time pressure difference deviation. The system is assessed for any abnormalities based on the real-time differential pressure deviation, equipment temperature, and electrical power input.

3. The intelligent temperature control method for equipment in harsh industrial environments according to claim 1, characterized in that, The method further includes: Acquire data on the workpiece's thermal capacity and environmental noise. The intensity range of the flow disturbance is calculated based on the electrical power input, the workpiece's heat capacity, the cooling water inlet temperature, and the cooling water outlet temperature. Under the condition of minimum disturbance intensity, obtain the equipment temperature corresponding to the instantaneous flow rate, and obtain the equipment temperature response curve; The response signal in the response curve is filtered based on environmental noise data to obtain the filtered equipment temperature.

4. The intelligent temperature control method for equipment in harsh industrial environments according to claim 3, characterized in that, The calculation of the intensity range of the flow disturbance based on the electrical power input, the workpiece's heat capacity, the cooling water inlet temperature, and the cooling water outlet temperature includes: Acquire information on workpiece surface temperature distribution and power fluctuation data; Based on the workpiece surface temperature distribution information, the phase transition point or composition change of the workpiece material is identified. Based on the phase transition point or compositional change of the workpiece material, the effective heat capacity of the workpiece is corrected to obtain the corrected effective heat capacity of the workpiece. The power input is adjusted based on the power fluctuation data to obtain the adjusted power input. The intensity range of the flow disturbance is calculated by using the corrected effective heat capacity of the workpiece, the adjusted electrical power input, the inlet temperature of the cooling water, and the outlet temperature of the cooling water.

5. The intelligent temperature control method for equipment in harsh industrial environments according to claim 4, characterized in that, The step of identifying the phase transition point or composition change of the workpiece material based on the workpiece surface temperature distribution information includes: The radiation intensity data of the workpiece surface is obtained by using a multispectral infrared sensor array; Based on the radiation intensity data and the preset material spectral emissivity, the effective emissivity of the workpiece surface at different wavelengths is calculated; The temperature data corresponding to the radiation intensity data is compensated based on the effective emissivity to obtain the corrected workpiece surface temperature distribution information. Based on the corrected workpiece surface temperature distribution information, the phase transition point or composition change of the workpiece material is identified.

6. The intelligent temperature control method for equipment in harsh industrial environments according to claim 1, characterized in that, The step of obtaining the first equipment temperature change based on the cooling water inlet temperature and the equipment temperature includes: Deploy multiple cooling water inlet temperature sensors; By identifying the drift or calibration error of the temperature sensor, the cooling water inlet temperature data is corrected to obtain the corrected cooling water inlet temperature data. Establish a dynamic heat transfer relationship between the corrected cooling water inlet temperature data and the equipment temperature, and obtain the first equipment temperature change based on the dynamic heat transfer relationship.

7. The intelligent temperature control method for equipment in harsh industrial environments according to claim 1, characterized in that, The method further includes: Deploy multiple cooling water inlet temperature sensors and temperature sensors for multiple devices; Consistency detection is performed on the real-time data of the multiple cooling water inlet temperature sensors to obtain the corrected cooling water inlet temperature data; Consistency testing is performed on the real-time data from the temperature sensors of the multiple devices to obtain corrected device temperature data.

8. The intelligent temperature control method for equipment in harsh industrial environments according to claim 1, characterized in that, The step of obtaining the first equipment temperature change based on the cooling water inlet temperature and the equipment temperature includes: Based on the instantaneous flow rate and the electrical power input of the equipment, the operating conditions of the cooling water inlet temperature and the equipment temperature are classified to obtain multiple operating condition categories; Under each of the aforementioned operating conditions, the time relationship between the cooling water inlet temperature and the equipment temperature is analyzed to determine the time lag parameter; Based on the time lag parameter, the cooling water inlet temperature and equipment temperature are synchronized in time to obtain time-aligned cooling water inlet temperature and equipment temperature. The first equipment temperature change is obtained based on the time-aligned cooling water inlet temperature and equipment temperature.

9. An intelligent temperature control system for equipment in harsh industrial environments, characterized in that, The system includes: The parameter acquisition module is used to acquire the electrical power input, cooling water inlet temperature, cooling water outlet temperature, total instantaneous flow rate of cooling water, and equipment temperature of the equipment. The first heat calculation module is used to calculate the heat generated by the device based on the electrical power input; The second heat calculation module is used to calculate the heat consumed by the cooling water based on the cooling water inlet temperature, cooling water outlet temperature, and total instantaneous flow rate of the cooling water. The obstacle value determination module is used to determine the heat transfer obstacle value of the cooling water circuit when the heat generated by the device is greater than the heat consumed by the cooling water and the device temperature exceeds a preset range; wherein, the heat transfer obstacle value characterizes the degree of blockage caused by scale accumulation inside the cooling water circuit; When the heat generated by the device exceeds the heat consumed by the cooling water and the device temperature exceeds a preset range, determining the heat transfer resistance value of the cooling water path includes: When the heat generated by the device is greater than the heat consumed by the cooling water and the device temperature exceeds the preset range, the first device temperature change is obtained based on the cooling water inlet temperature and the device temperature. The temperature change of the second equipment is obtained based on the temperature change of the equipment corresponding to the instantaneous flow rate change and the temperature change of the first equipment. The heat transfer resistance value of the cooling water circuit is determined by the temperature change of the second device; The flow control module is used to adjust the cooling water flow command and control the cooling water pump and regulating valve according to the heat generated by the device and the heat transfer resistance value.

Images