Intelligent speed regulation stirring control method and system and computer equipment

Abstract

The invention belongs to the technical field of stirring control, and particularly relates to an intelligent speed regulation stirring control method and system and computer equipment, and the method comprises the steps: determining a target control value of stirring control according to the requirements of a stirring technology; various sensors are installed on the stirring equipment, it is ensured that key parameters in the stirring process are accurately collected in real time, the data collection frequency is set, and it is ensured that dynamic changes in the stirring process are captured; filtering processing is carried out on the collected sensor data, noise interference is removed, the sensor data is corrected, and the accuracy of the data is ensured; key features in the stirring process of the combustion furnace are extracted through a data analysis method, and a mathematical model of the stirring process is established for prediction and control; a closed-loop control system is established, the stirring speed of the combustion furnace is adjusted according to data monitored in real time, the stability and accuracy of the stirring process are ensured through an intelligent algorithm and real-time parameter monitoring, insufficient stirring or excessive stirring is avoided, and therefore the product quality and the production efficiency are improved.

Description

Technical Field

[0001] The invention relates to the technical field of stirring control, and in particular to an intelligent speed regulating stirring control method, system and computer equipment. Background Art

[0002] In thermal power plants, the tumbling or stirring of combustion materials is very critical, as it directly affects combustion efficiency, power generation efficiency and safety. During the combustion process, the fuel (such as coal powder) needs to be fully in contact with the oxygen in the air to be completely burned. Stirring can enhance the dispersion and uniformity of the fuel particles, thereby increasing the contact area between the fuel and oxygen and promoting the combustion reaction. Therefore, in thermal power plants, the stirring of combustion materials is a key step to ensure the full combustion of the fuel and optimize the power generation efficiency.

[0003] Traditional stirring control often relies on manual adjustment of stirring speed, which has problems such as high labor cost, low efficiency, and imprecise control. Especially under complex working conditions, it is necessary to dynamically adjust the speed according to various factors such as the properties of the combustion materials of the stirring thermal power generation, the shape of the stirring container, temperature, viscosity, etc. It is difficult for manual control to dynamically adjust the speed according to the real-time stirring process information, and it is impossible to achieve accurate and efficient stirring control. The traditional stirring control method lacks real-time monitoring and feedback mechanism, and it is impossible to understand the stirring process in real time, resulting in the inability to dynamically adjust the speed according to the actual situation. The root cause is the lack of intelligent control algorithms and information collection, processing, and feedback mechanisms.

[0004] In view of the above technical defects, an intelligent speed regulating stirring control method, system and computer equipment solution are proposed. Summary of the invention

[0005] To solve the above problems, the present invention provides the following technical solutions:

[0006] An intelligent speed regulating stirring control method, comprising:

[0007] Obtaining stirring process requirements of the combustion furnace, and determining a target control value of stirring control according to the stirring process requirements;

[0008] Calculate mixing uniformity, production efficiency and energy consumption according to the target control value of the combustion furnace, and obtain the architecture of the entire intelligent mixing control system, wherein the architecture includes sensor arrangement, data acquisition system, control algorithm and actuator;

[0009] Install various sensors on the mixing equipment to collect key parameters of the mixing process in real time and set the data collection frequency to ensure that dynamic changes in the mixing process are captured;

[0010] Filter the collected sensor data to remove noise interference and correct the sensor data to ensure the accuracy of the data;

[0011] Extract key features of the combustion furnace stirring process by data analysis method, wherein the key features include fluidity and mixing uniformity of thermal power generation combustion products;

[0012] A mathematical model of the combustion furnace stirring process is established based on the key characteristics for prediction and control;

[0013] The stirring speed of the combustion furnace is adjusted according to the real-time monitoring data, and the stirring speed is dynamically adjusted according to the real-time parameter changes during the stirring process to adapt to different working conditions.

[0014] Furthermore, the step of installing various sensors on the stirring device includes:

[0015] The speed sensor is used to monitor the speed of the stirrer to ensure that the stirring speed meets the set requirements. The speed sensor is installed on the stirring shaft;

[0016] The temperature of the combustion material of the stirred thermal power generation is monitored by a temperature sensor to prevent overheating or overcooling from affecting the stirring effect. The temperature sensor is installed on the wall of the stirring container;

[0017] The viscosity of the thermal power generation combustion product is measured by a viscosity sensor to help adjust the stirring speed to adapt to the thermal power generation combustion products of different viscosities. The viscosity sensor is installed inside the stirring container and directly contacts the thermal power generation combustion product.

[0018] The liquid level in the stirring container is monitored by a liquid level sensor to prevent overflow and material shortage. The liquid level sensor is installed on the side wall and bottom of the stirring container;

[0019] The torque of the stirring shaft is measured by a torque sensor to reflect the load condition during the stirring process. The torque sensor is installed between the stirring shaft and the motor;

[0020] The pressure in the stirring container is monitored by a pressure sensor to ensure safe operation, and the pressure sensor is installed on the side wall of the stirring container;

[0021] The flow rate of feed and discharge is monitored by flow sensors to control the input and output of combustion materials for thermal power generation. The flow sensors are installed on the feed pipe and the discharge pipe.

[0022] The density of the combustion products of thermal power generation is measured by a density sensor to assist in controlling the stirring process. The density sensor is installed inside the stirring container.

[0023] The pH value of the thermal power generation combustion product is monitored by a pH sensor, which is particularly important for the stirring process that requires the control of the pH value. The pH sensor is directly immersed in the thermal power generation combustion product;

[0024] The composition ratio of the combustion products of thermal power generation is monitored in real time by a composition analysis sensor installed inside the stirring container to ensure uniform mixing.

[0025] Furthermore, the step of filtering the collected sensor data to remove noise interference includes:

[0026] The sensor data is filtered to remove noise interference in the sensor data and retain useful signals. The data curve is smoothed by taking the average value of a certain number of continuous data points. The calculation formula is as follows:

[0027]

[0028] Among them, y(t) is the filtered data, x(ti) is the data at time (ti), and n is the size of the translation window;

[0029] Perform data correction on the collected data to eliminate the inherent errors of the sensor and improve the accuracy of the data;

[0030] Adjust the sensor output to zero, measure the sensor output value under zero input condition, and use it as the offset to subtract from subsequent measurements, where the calculation formula is as follows:

[0031] x1=x0-x;

[0032] Among them, x1 is the correction data, x0 is the measurement data, and x' is the zero point offset;

[0033] Eliminate the zero offset of the sensor and adjust the sensitivity of the sensor so that its output matches the actual value;

[0034] According to the characteristics of the sensor, linear and nonlinear corrections are performed, and the corrected data is filtered to remove noise interference.

[0035] Furthermore, before the step of extracting key features of the combustion furnace stirring process by a data analysis method, the method includes:

[0036] Use statistical methods to remove outlier data points and scale the data to the same range for easier subsequent processing;

[0037] Interpolation of missing data to fill in the gaps, feature extraction is to extract parameters from the original data that can reflect the key characteristics of the mixing process;

[0038] Based on the extracted features, a mathematical model is established for prediction and control. The calculation formula for linear data is as follows:

[0039] y=β0+β1x1+β2x2+…+β n x n +ε;

[0040] Among them, y is the target variable, β n is the model parameter, x n is the characteristic parameter, ε is the error term;

[0041] The calculation formula for nonlinear data is as follows:

[0042] y=f(W2·g(W1·x+b1)+b2);

[0043] Among them, W1 and W2 are weight matrices, y is the target variable, f is the activation function of the output layer, b1 and b2 are biases, and g is the activation function;

[0044] The data set is divided into a training set and a test set for model training and verification. The training set data is used to fit the model parameters, and the test set data is used to evaluate the performance of the model.

[0045] Furthermore, the step of adjusting the stirring speed of the combustion furnace according to the real-time monitoring data includes:

[0046] A control signal is calculated according to a control algorithm, and a stirring speed is adjusted according to the control signal;

[0047] The actuator receives the control signal, adjusts the speed of the stirring device, and feeds back the actual speed to the controller, and feeds back the adjusted actual stirring speed to the controller to form a closed-loop control;

[0048] Dynamically adjust the control signal according to the actual stirring speed to ensure that the stirring process is always in the best state;

[0049] Through experiments and simulations, the controller parameters are optimized to improve the control accuracy and stability of the system. Under actual working conditions, the closed-loop control system is debugged to ensure that it can adapt to different working conditions.

[0050] Through the monitoring system, the key parameters and control effects of the mixing process can be viewed in real time. When the system is abnormal, the alarm mechanism is triggered to remind the operator to intervene.

[0051] Furthermore, the step of dynamically adjusting the stirring speed according to the real-time parameter changes during the stirring process includes:

[0052] Through the PID control algorithm, the three parameters of proportion, integration and differentiation are adjusted to achieve precise control of the system. The calculation formula is as follows:

[0053]

[0054] Among them, u(t) is the control signal, that is, the adjusted stirring speed, e(t) is the error signal, K p , Ki With K d are proportional, integral and derivative gains respectively, is the integral term, is the differential term.

[0055] According to another aspect of the present invention, there is provided an intelligent speed regulating stirring control system, comprising:

[0056] An acquisition module, used for acquiring the stirring process requirements of the combustion furnace, and determining a target control value of the stirring control according to the stirring process requirements;

[0057] A calculation module, used to calculate the mixing uniformity, production efficiency and energy consumption according to the target control value of the combustion furnace, and obtain the architecture of the entire intelligent mixing control system, wherein the architecture includes sensor arrangement, data acquisition system, control algorithm and actuator;

[0058] The acquisition module is used to install various sensors on the mixing equipment, collect key parameters of the mixing process in real time, set the data acquisition frequency, and ensure that the dynamic changes in the mixing process are captured;

[0059] The correction module is used to filter the collected sensor data, remove noise interference, and correct the sensor data to ensure the accuracy of the data;

[0060] An extraction module, used to extract key features in the stirring process of the combustion furnace by a data analysis method, wherein the key features include fluidity and mixing uniformity of the combustion products of thermal power generation;

[0061] Establishing a module for establishing a mathematical model of the combustion furnace stirring process according to the key characteristics for prediction and control;

[0062] The adjustment module is used to adjust the stirring speed of the combustion furnace according to the real-time monitoring data, and dynamically adjust the stirring speed according to the real-time parameter changes during the stirring process to adapt to different working conditions.

[0063] Furthermore, the adjustment module includes:

[0064] A first adjustment unit, configured to adjust the stirring speed according to a control signal calculated by a control algorithm;

[0065] The feedback unit is used for the actuator to receive the control signal, adjust the speed of the stirring device, and feed back the actual speed to the controller, and feed back the adjusted actual stirring speed to the controller to form a closed-loop control;

[0066] A second adjustment unit is used to dynamically adjust the control signal according to the actual stirring speed to ensure that the stirring process is always in an optimal state;

[0067] The debugging unit is used to optimize the controller parameters through experiments and simulations, improve the control accuracy and stability of the system, and debug the closed-loop control system under actual working conditions to ensure that it can adapt to different working conditions;

[0068] The warning unit is used to view the key parameters and control effects of the mixing process in real time through the monitoring system, and trigger the alarm mechanism when the system is abnormal to remind the operator to intervene.

[0069] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned intelligent speed regulation and stirring control method when executing the computer program.

[0070] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned intelligent speed regulation and stirring control method are implemented.

[0071] Compared with the prior art, the present invention has the following beneficial effects:

[0072] In an intelligent speed-regulating stirring control method of the present invention, a target control value of stirring control is determined according to the requirements of the stirring process; various sensors are installed on the stirring equipment to ensure accurate and real-time collection of key parameters in the stirring process, and the data collection frequency is set to ensure that dynamic changes in the stirring process are captured; the collected sensor data are filtered to remove noise interference, and the sensor data are corrected to ensure data accuracy; key features in the stirring process of the combustion furnace are extracted through a data analysis method, and a mathematical model of the stirring process is established for prediction and control; a closed-loop control system is established to adjust the stirring speed of the combustion furnace according to real-time monitored data, and the stability and accuracy of the stirring process are ensured through intelligent algorithms and real-time parameter monitoring, and insufficient or excessive stirring is avoided, thereby improving product quality and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0074] Figure 1 The figure is a schematic diagram of a method flow according to an embodiment of the present invention.

[0075] Figure 2 FIG. 1 is a schematic diagram of a device structure according to an embodiment of the present invention.

[0076] Figure 3 A schematic diagram of the internal structure of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0077] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0078] like Figure 1-Figure 3 As shown, the present application provides an intelligent speed regulating stirring control method, comprising:

[0079] S1. Obtaining the stirring process requirements of the combustion furnace, and determining the target control value of the stirring control according to the stirring process requirements;

[0080] S2. Calculate mixing uniformity, production efficiency and energy consumption according to the target control value of the combustion furnace, and obtain the architecture of the entire intelligent mixing control system, wherein the architecture includes sensor arrangement, data acquisition system, control algorithm and actuator;

[0081] S3. Install various sensors on the mixing equipment, collect key parameters of the mixing process in real time, set the data collection frequency, and ensure that the dynamic changes in the mixing process are captured;

[0082] S4, filtering the collected sensor data to remove noise interference, and correcting the sensor data to ensure the accuracy of the data;

[0083] S5. Extracting key features of the combustion furnace stirring process by a data analysis method, wherein the key features include fluidity and mixing uniformity of the thermal power generation combustion products;

[0084] S6. Establishing a mathematical model of the combustion furnace stirring process according to the key characteristics for prediction and control;

[0085] S7. Adjust the stirring speed of the combustion furnace according to the real-time monitoring data, and dynamically adjust the stirring speed according to the real-time parameter changes during the stirring process to adapt to different working conditions.

[0086] As described in the above steps S1-S7, in a thermal power plant, the stirring or stirring of the combustion material is very critical, which directly affects the combustion efficiency, power generation efficiency and safety. During the combustion process, the fuel needs to be fully in contact with the oxygen in the air to completely burn. Stirring can enhance the dispersion and uniformity of the fuel particles, thereby increasing the contact surface between the fuel and oxygen and promoting the combustion reaction. Therefore, in a thermal power plant, the stirring of the combustion material is a key step to ensure that the fuel is fully burned and optimize the power generation efficiency. However, traditional stirring control often relies on manual adjustment of the stirring speed, which has the problems of high labor cost, low efficiency, and inaccurate control. Especially under complex working conditions, it is necessary to dynamically adjust the speed according to various factors such as the properties of the stirring thermal power generation combustion material, the shape of the stirring container, temperature, and viscosity. Manual control is difficult to dynamically adjust the speed according to the real-time stirring process information, and accurate and efficient stirring control cannot be achieved. The traditional stirring control method lacks real-time monitoring and feedback mechanisms, and cannot understand the stirring process in real time, resulting in the inability to dynamically adjust the speed according to the actual situation. The root cause is the lack of intelligent control algorithms and information collection, processing, and feedback mechanisms. The present invention obtains the stirring process requirements of the combustion furnace, determines the target control value of the stirring control according to the stirring process requirements, calculates the mixing uniformity, production efficiency and energy consumption according to the targets, and obtains the architecture of the entire intelligent stirring control system. By dynamically adjusting the stirring speed according to real-time stirring process information (such as mixing uniformity, temperature, viscosity, etc.), the intelligent stirring control system can optimize the stirring effect in real time to ensure that the uniformity of the mixture meets the expected standard. This dynamic adjustment not only improves the stirring accuracy, but also avoids excessive or insufficient stirring, reduces the waste of combustion materials and process deviations in thermal power generation. Through real-time monitoring and feedback mechanisms, the system can automatically adjust the stirring conditions, such as speed, time, etc., according to real-time data, thereby reducing the intervention of manual operations and shortening the production cycle. The intelligent control system can adjust the process parameters in real time according to the actual mixing state, thereby increasing the production speed and increasing production without reducing the quality. The efficiency of the line is improved by accurately calculating and dynamically adjusting the speed, avoiding excessive or low energy consumption and improving the energy efficiency of the mixing process. By integrating sensors, data acquisition modules and feedback mechanisms, comprehensive monitoring of the mixing process is achieved. This real-time monitoring can not only provide process data, but also promptly alarm and adjust when abnormalities occur, avoiding quality problems caused by human negligence or equipment failure in the production process. Through the feedback mechanism, the system can continuously optimize various parameters in the mixing process to maintain the long-term stability of the process. By installing various sensors on the mixing equipment and collecting key parameters in the mixing process in real time, setting the data collection frequency, ensuring that the dynamic changes in the mixing process are captured, filtering the collected sensor data, removing noise interference, and correcting the sensor data to ensure data accuracy, the system can dynamically adjust the mixing speed according to real-time data through the feedback mechanism.Ensure that the mixing process is always carried out under the best working conditions, thereby improving the mixing efficiency and quality. By filtering the collected data, these noises can be removed to ensure the smoothness and accuracy of the data, which is crucial for dynamically adjusting the mixing parameters, because only with the support of accurate data can the intelligent control algorithm make effective adjustments. By collecting data in real time and applying intelligent control algorithms, the mixing system can achieve a high degree of intelligence. Intelligent algorithms (such as machine learning, deep learning, etc.) can predict the changing trends in the mixing process based on historical data and real-time data, and automatically adjust the key parameters of mixing. This intelligent control not only improves the accuracy of the mixing process, but also can effectively respond to different production batches, different thermal power generation combustion characteristics, etc. Changes, automatically optimize the mixing process, through real-time dynamic adjustment of the mixing speed, the intelligent control system can select the optimal speed according to the actual state of the mixing thermal power generation combustion, which not only avoids the waste caused by excessive mixing, but also improves the mixing efficiency and shortens the production cycle. By optimizing the speed and mixing parameters, the system can also reduce energy consumption and reduce unnecessary energy waste. The key features of the mixing process of the combustion furnace are extracted through data analysis methods, and a mathematical model of the mixing process is established based on the key features for prediction and control. The mixing speed of the combustion furnace is adjusted according to the real-time monitoring data. According to the real-time parameter changes during the mixing process, the mixing speed is dynamically adjusted to adapt to different working conditions. Through real-time monitoring data (such as temperature, pressure, viscosity, state of the stirring material), the mixing speed of the combustion furnace can be adjusted according to the real-time monitoring data. The stirring speed can be adjusted dynamically under different working conditions to make the stirring process more precise and ensure the best stirring quality. Real-time adjustment of the stirring speed can reduce unnecessary energy waste or over-stirring, avoiding the low production efficiency caused by improper speed setting in traditional methods, thereby improving the overall production efficiency. The algorithm automatically analyzes the data and dynamically adjusts the stirring speed according to the actual situation, reducing the interference of human factors and the possibility of operating errors. By collecting various parameters in the stirring process in real time (such as temperature, viscosity, pressure, rheological properties of the stirring material, etc.), the dynamic changes of the stirring process can be fully understood. These data provide sufficient basis for dynamically adjusting the stirring speed, avoiding the low production efficiency caused by the lack of real conditions in traditional methods. The real-time monitoring data can be fed back to the control system to form a closed-loop control. By comparing the data deviation between the prediction model and the actual mixing process, the system can quickly adjust the rotation speed to ensure that the process control is within the expected range, thereby improving the stability and reliability of mixing. In the actual production process, factors such as raw material quality and external environment often change. Traditional control methods are often unable to adapt to these changes quickly. The intelligent control system based on data analysis can respond quickly to these changes, automatically adjust the mixing speed, and ensure the smooth operation of the production process. By real-time monitoring of the system status and key features of the mixing process, the intelligent control system can identify potential faults or abnormalities, issue warnings in advance, and avoid system failures.In order to improve the reliability and maintainability of the equipment, appropriate control algorithms are selected according to the system characteristics, such as PID control, fuzzy control, adaptive control, neural network control, etc. The parameters of the selected control algorithm are adjusted to obtain the best control performance. By establishing a closed-loop control system, the stirring speed of the combustion furnace is adjusted according to the real-time monitoring data. According to the real-time parameter changes during the stirring process, the stirring speed is dynamically adjusted to adapt to different working conditions. By designing a user-friendly operation interface, it is convenient for operators to monitor and control the stirring process. By displaying the key parameters in the stirring process in the form of a chart, it is convenient for operators to understand the stirring state in real time. By integrating all hardware and software components together, ensure that all parts work together, and test the system to verify whether it can achieve the predetermined control target. According to the actual operation data, the control algorithm and system parameters are continuously optimized. By regularly maintaining sensors and equipment, the long-term stable operation of the system is ensured. By designing a safety protection mechanism, abnormal conditions such as overload and overheating are prevented. By establishing a fault diagnosis system, system faults can be discovered and handled in a timely manner. The above methods can effectively solve the problems existing in traditional stirring control and achieve more accurate, efficient and reliable stirring control. ,

[0087] In one embodiment, the step S3 of installing various sensors on the stirring device includes:

[0088] S31. Set a speed sensor to monitor the speed of the stirrer to ensure that the stirring speed meets the set requirements and install it on the stirring shaft or motor;

[0089] S32, setting a temperature sensor to monitor the temperature of the stirred thermal power generation combustion material to prevent overheating or overcooling from affecting the stirring effect, and immersing the temperature sensor in the thermal power generation combustion material or installing it on the wall of the stirring container;

[0090] S33, setting a viscosity sensor to measure the viscosity of the thermal power generation combustion product, helping to adjust the stirring speed to adapt to the thermal power generation combustion products of different viscosities, and installing the sensor inside the stirring container to directly contact the thermal power generation combustion product;

[0091] S34, a liquid level sensor is provided to monitor the liquid level in the stirring container to prevent overflow or lack of material, and is installed on the side wall or bottom of the stirring container;

[0092] S35, setting a torque sensor to measure the torque of the stirring shaft to reflect the load condition during the stirring process, and installing it between the stirring shaft and the motor;

[0093] S36. Set up a pressure sensor to monitor the pressure in the mixing container to ensure safe operation, and install it on the side wall or other pressure-sensitive points of the mixing container;

[0094] S37, set a flow sensor to monitor the flow of feed or discharge, control the input and output of thermal power generation combustion materials, and install it on the feed pipe or discharge pipe;

[0095] S38. A density sensor is provided to measure the density of the combustion products of thermal power generation and assist in controlling the stirring process. The sensor is installed inside the stirring container or on the relevant pipeline;

[0096] S39, setting a pH sensor to monitor the pH value of the thermal power generation combustion product, which is particularly important for the stirring process that requires pH control, and directly immersing it in the thermal power generation combustion product;

[0097] S310. Set up a component analysis sensor to monitor the composition ratio of thermal power generation combustion products in real time to ensure uniform mixing. Install it inside the stirring container or at relevant sampling points.

[0098] As described in the above steps S31-S310, the rotation speed of the agitator is monitored by a rotation speed sensor to ensure that the stirring speed meets the set requirements, the temperature of the stirred thermal power generation combustion material is monitored by a temperature sensor to prevent overheating and overcooling from affecting the stirring effect, the viscosity of the thermal power generation combustion material is measured by a viscosity sensor to help adjust the stirring speed to adapt to thermal power generation combustion materials with different viscosities, the liquid level in the stirring container is monitored by a liquid level sensor to prevent overflow and lack of material, the torque of the stirring shaft is measured by a torque sensor to reflect the load condition during the stirring process, the pressure in the stirring container is monitored by a pressure sensor to ensure safe operation, the flow rate of feed and discharge is monitored by a flow sensor to control the input and output of the thermal power generation combustion material, and the seal The pH sensor measures the density of the thermal power generation combustion products and assists in controlling the stirring process. The pH sensor monitors the pH value of the thermal power generation combustion products, which is particularly important for the stirring process that requires control of the acidity and alkalinity. The component analysis sensor monitors the component ratio of the thermal power generation combustion products in real time to ensure uniform mixing. Through the monitoring of the speed sensor, viscosity sensor and other key parameters, the system can adjust the speed, temperature and other variables of the agitator in real time to ensure that they are always within the optimal range. By real-time monitoring of various parameters (such as temperature, viscosity, pressure, density, etc.), the system can intelligently adjust the stirring conditions according to the real-time status of the thermal power generation combustion products to ensure that each stirring achieves the best effect. Dynamic adjustment can avoid excessive or insufficient stirring. Stirring, reducing the ineffective working time in the stirring process, thereby improving efficiency. Temperature sensors, pressure sensors and liquid level sensors can detect abnormal conditions that may occur during the stirring process (such as overheating, overcooling, overflow or excessive pressure, etc.) in real time, and take timely measures, such as automatic shutdown or adjustment of operating parameters, to prevent equipment damage or loss of thermal power generation combustion products. Through the real-time data of viscosity, pH, density and component analysis sensors, it is possible to ensure the uniform mixing of thermal power generation combustion products, avoid uneven components, and ensure the quality of the final product. For the stirring process that requires strict control of pH or the proportion of thermal power generation combustion products, pH sensors and component analysis sensors provide accurate monitoring data and support dynamic adjustment to ensure each All batches meet the quality standards. Through the application of these sensors, the system can automatically collect and process data, conduct real-time feedback and adjustments, greatly improving the level of intelligent operation. Automated adjustment not only reduces errors caused by human intervention, but also responds more quickly to changing production needs and adapts to the characteristics of different thermal power generation combustion products. Precise speed control and real-time feedback mechanisms help avoid excessive stirring, thereby saving energy. Reasonable temperature, pressure and flow control can also help reduce waste of thermal power generation combustion products, reduce energy consumption, and improve resource utilization efficiency. Real-time monitoring of sensors such as pressure, temperature, and liquid level can ensure that the mixing vessel operates within a safe range, prevent dangerous situations such as overflow and overpressure, and ensure the safety of operators and equipment.

[0099] In one embodiment, in order to capture the dynamic changes in the stirring process, it is necessary to set an appropriate data acquisition frequency. The setting of the data acquisition frequency should consider the following factors:

[0100] Agitation speed: Higher agitation speeds require more frequent data acquisition to capture rapid changes.

[0101] Characteristics of thermal power generation combustibles: Different thermal power generation combustibles have different reaction speeds. The thermal power generation combustibles with high viscosity or slow reaction can adopt a lower collection frequency.

[0102] Control accuracy: Higher control accuracy requires more frequent data collection.

[0103] System response time: The response time of the control system will also affect the setting of data collection frequency.

[0104] Usually, the data collection frequency can range from several times to dozens of times per second, depending on actual needs. By reasonably arranging these sensors and setting a suitable data collection frequency, comprehensive monitoring and control of the mixing process can be achieved, thereby improving the mixing effect and production efficiency.

[0105] The step S4 of filtering the collected sensor data to remove noise interference includes:

[0106] S41, filter the collected data of the sensor to remove the noise interference in the sensor data, retain the useful signal, and smooth the data curve by taking the average value of a certain number of continuous data points. The calculation formula is as follows:

[0107]

[0108] Among them, y(t) is the filtered data, x(ti) is the data at time (ti), and n is the size of the translation window;

[0109] S42, perform data correction on the collected data to eliminate the inherent error of the sensor and improve the accuracy of the data. In the absence of an input signal, adjust the sensor output to zero, measure the output value of the sensor in the zero input state, and use it as an offset to subtract from subsequent measurements. The calculation formula is as follows:

[0110] x1=x0-x;

[0111] Among them, x1 is the correction data, x0 is the measurement data, and x' is the zero point offset;

[0112] S43. First, eliminate the zero offset of the sensor, adjust the sensitivity of the sensor so that its output is consistent with the actual value, perform linear or nonlinear correction according to the characteristics of the sensor, filter the corrected data, and remove noise interference.

[0113] As described in the above steps S41-S43, the sensor output is affected by temperature. Temperature drift is eliminated by temperature compensation, and the temperature sensor collects temperature data. Establish a relationship model between temperature and sensor output. Correct the sensor output based on the temperature data. Use statistical methods such as z-score, IQR, etc. to identify and remove abnormal data points. For the removed outliers, use the previous and next data for interpolation. Check the data range: ensure that the data is within a reasonable range. Check the data trend: analyze whether the data change trend is in line with expectations. Through the above steps, the sensor data can be effectively filtered and corrected to improve the accuracy and reliability of the data, providing a solid foundation for subsequent control and analysis. The sensor data is filtered to remove noise interference in the sensor data and retain useful signals. By averaging a certain number of consecutive data points, the data curve is smoothed, and data correction is performed on the collected data to eliminate the inherent error of the sensor and improve the accuracy of the data. The sensor output is adjusted to zero, and the output value of the sensor under zero input state is measured as an offset and subtracted from subsequent measurements. By averaging a certain number of consecutive data points, the noise and interference in the sensor data can be effectively removed. In practical applications, random fluctuations caused by environmental factors, equipment vibration, external disturbances and other factors can be reduced to obtain a more stable and reliable signal. Data smoothing and filtering not only make the signal more stable, but also improve the response speed and accuracy of the system in real-time control, thereby avoiding over-adjustment due to data fluctuations. By correcting the sensor output and removing its inherent deviation, the accuracy of the data can be improved.For example, by adjusting the zero point of the sensor and subtracting the zero drift of the sensor, the accuracy of the measured value in the absence of input is ensured. Through correction, the error of sensor measurement is reduced and the overall measurement accuracy of the system is improved, thereby providing more reliable data support for subsequent intelligent control decisions. By acquiring and processing sensor data in real time, the system can dynamically adjust the speed of the agitator to adapt to different mixing environments and needs. Intelligent real-time adjustment can make the mixing process more efficient, avoid over-mixing or under-mixing, and help improve product consistency and quality. The introduction of intelligent control algorithms and real-time monitoring systems can build a closed-loop feedback mechanism to monitor and adjust various parameters in real time during the mixing process. This feedback mechanism enables the system to automatically adjust parameters such as speed, mixing time, and feed amount according to the current mixing state, forming an adaptive control strategy. By collecting and processing data in real time, it can respond quickly to various changes in the mixing process (such as temperature, pressure, concentration of thermal power generation combustion products, etc.), thereby optimizing control decisions and making each operation more in line with current actual needs. Through data correction and filtering processing, the system can correct the errors of the external environment or the sensor itself. It has stronger adaptability. Through real-time monitoring and intelligent control, the system can not only detect abnormal situations, but also make self-corrections according to the set feedback rules. Intelligent control improves the automation of the production process, reduces manual intervention and monitoring costs, improves overall production efficiency, and thus reduces production costs. It eliminates the zero offset of the sensor, adjusts the sensitivity of the sensor so that its output is consistent with the actual value, performs linear and nonlinear corrections according to the characteristics of the sensor, filters the corrected data, and removes noise interference. The sensor may have deviations in the initial state. By eliminating the zero offset, the reference value of the sensor output can be guaranteed to be accurate, thereby ensuring the accuracy of subsequent data. Sensitivity adjustment helps to ensure that the sensor can provide accurate output within different measurement ranges, so that the system can reflect the actual state of the mixing process and avoid errors caused by insensitive or overly sensitive sensor responses. The output of many sensors is not completely linear with the actual physical quantity. Therefore, through linear or nonlinear correction, the difference between the output of the sensor and the actual value can be minimized to ensure that the control system makes decisions based on accurate data. Sensors are usually interfered by noise, which affects the accuracy of the data. Through the filtering algorithm, noise can be effectively removed to ensure the clarity and availability of input data. By introducing real-time data collection and feedback mechanism, the control system can be dynamically adjusted according to the information in the actual mixing process. By combining the intelligent control algorithm, the speed of the agitator can be dynamically adjusted according to the real-time monitoring data to achieve more accurate and efficient mixing control. Through intelligent algorithms and real-time data feedback, the system can adjust the speed and mixing mode according to the real-time environment and operating status.For example, in different stirring stages (such as mixing, dissolving, dispersing, etc.), the stirring speed can be adjusted specifically to ensure the best effect. Accurate real-time adjustment can not only ensure the stirring effect, but also avoid excessive or insufficient stirring, improve energy efficiency and material utilization, and reduce unnecessary waste.

[0114] Before the step S5 of extracting the key features of the combustion furnace stirring process by the data analysis method, the method includes:

[0115] S51. Use statistical methods to remove abnormal data points, scale the data to the same range for subsequent processing, interpolate missing data, and fill in the gaps. Feature extraction is to extract parameters that can reflect the key characteristics of the mixing process from the original data. Based on the extracted features, a mathematical model is established for prediction and control. The calculation for linear data is as follows:

[0116] y=β0+β1x1+β2x2+…+β n x n +ε;

[0117] Among them, y is the target variable, β n is the model parameter, x n is the characteristic parameter, ε is the error term;

[0118] S52. The calculation for nonlinear data is as follows:

[0119] y=f(W2·g(W1·x+b1)+b2);

[0120] Among them, W1 and W2 are weight matrices, y is the target variable, f is the activation function of the output layer, b1 and b2 are biases, and g is the activation function;

[0121] S53. Divide the data set into a training set and a test set for model training and verification. Use the training set data to fit the model parameters, and use the test set data to evaluate the performance of the model.

[0122] As described in the above steps S51-S53, the dynamic characteristics of the system are described by nonlinear relationships. Data are mapped to high-dimensional space through kernel functions to build classification or regression models. Complex nonlinear relationships are fitted through multi-layer neural networks. The uncertainty of data is described by Gaussian processes, which is suitable for small sample data sets. Cross-validation: The generalization ability of the model is evaluated through cross-validation. Error analysis: Calculate model prediction errors, such as mean square error (MSE), mean absolute error (MAE), etc. Hyperparameter tuning: Adjust model hyperparameters through grid search, random search or Bayesian optimization. Model integration: Improve the prediction performance of the model through integrated learning methods (such as Bagging, Boosting). The above methods can effectively pre-process the collected data, extract features, and establish mathematical models to achieve prediction and control of the mixing process. Statistical methods are used to remove abnormal data points and scale the data to the same range for subsequent processing. Missing data are interpolated to fill in the gaps. Feature extraction is to extract parameters that can reflect the key characteristics of the mixing process from the original data. According to the extracted features, a mathematical model is established. For prediction and control, the data set is divided into a training set and a test set for model training and verification. The training set data is used to fit the model parameters, and the test set data is used to evaluate the performance of the model. The statistical method is used to remove abnormal data, which can effectively reduce noise interference, ensure the quality of the data, and improve the accuracy of model prediction. Abnormal data may come from sensor failure, environmental changes, or data collection errors. Removing these data points helps to improve the reliability of subsequent processing and model training. The interpolation method of missing data (such as linear interpolation, interpolation method, etc.) can maintain the continuity of the data, avoid inaccurate or invalid models due to missing values, and further improve the stability of the model. Scaling the data to the same range can avoid certain features affecting the results during model training due to dimensional differences.For example, the numerical range of some features is very large, while others are smaller. After standardization, the impact of all features on the model is relatively balanced, which helps the algorithm converge better. After the data is scaled, model training will become more efficient and can find the optimal solution in a shorter time. By extracting key features from the original data and providing real-time feedback, it can help the control system adjust the speed according to the current state of the mixing process. The introduction of this intelligent control algorithm can improve the accuracy and efficiency of the mixing process and achieve dynamic adjustment to adapt to different working conditions and environmental changes. By establishing a mathematical model and using training set data for training, the system can learn the mixing process based on historical data. When the model is continuously verified and optimized in practical applications, it can continuously improve its accuracy and robustness. This autonomous learning ability makes the mixing process control more intelligent. Through precise prediction and control, the speed can be dynamically adjusted according to the real-time mixing process data to reduce over-mixing or under-mixing, thereby improving production efficiency and product quality. By dividing the data set into a training set and a test set, the generalization ability of the model can be tested to ensure the performance of the model in practical applications. Therefore, it can not only improve the quality and efficiency of the mixing process, but also reduce human intervention, reduce operational risks, and ultimately improve the automation level and stability of the production process.

[0123] The step S7 of adjusting the stirring speed of the combustion furnace according to the real-time monitoring data comprises:

[0124] S71, adjusting the stirring speed by the control signal calculated by the control algorithm, the actuator receiving the control signal, adjusting the speed of the stirring device, and feeding back the actual speed to the controller, and feeding back the adjusted actual stirring speed to the controller to form a closed-loop control;

[0125] S72. According to the actual speed of the feedback, dynamically adjust the control signal to ensure that the mixing process is always in the best state; optimize the controller parameters through experiments and simulations to improve the control accuracy and stability of the system; debug the closed-loop control system under actual working conditions to ensure that it can adapt to different working conditions; and view the key parameters and control effects of the mixing process in real time through the monitoring system;

[0126] S73. When an abnormality occurs in the system, an alarm mechanism is triggered to remind the operator to intervene.

[0127] The step S7 of dynamically adjusting the stirring speed according to the real-time parameter changes during the stirring process includes:

[0128] S74, through the PID control algorithm, adjust the three parameters of proportion, integration and differentiation to achieve precise control of the system, the calculation is as follows:

[0129]

[0130] Among them, u(t) is the control signal, that is, the adjusted stirring speed, e(t) is the error signal, K p , K i With K d are proportional, integral and derivative gains respectively, is the integral term, is the differential term.

[0131] As described in the above steps S71-S74, the present invention calculates a control signal according to the control algorithm and adjusts the stirring speed according to the control signal. The actuator receives the control signal, adjusts the speed of the stirring equipment, and feeds back the actual speed to the controller. The adjusted actual stirring speed is fed back to the controller to form a closed-loop control. Traditional stirring control methods usually use a preset speed value, and are unable to dynamically adjust the speed according to the real-time stirring process. After introducing control signal feedback and closed-loop control, the system can dynamically adjust the speed according to the data information collected in real time during the stirring process (such as the viscosity, temperature, and stirrer load of the combustion products of thermal power generation). This means that the stirring process can be accurately controlled according to the actual working conditions, avoiding the problem of over-stirring or under-stirring. Through closed-loop control and intelligent algorithms, the system can realize real-time Monitor the stirring effect and automatically adjust according to the feedback signal. This precise feedback adjustment mechanism can significantly improve the efficiency of the stirring process and avoid the waste or uneven stirring caused by too fast or too slow speed in traditional methods. By dynamically adjusting the stirring speed, the system can achieve optimal use of energy. Under traditional control methods, the speed of the stirrer is often fixed, which may waste a lot of energy. Through intelligent control algorithms, the system will adjust the speed according to actual conditions to reduce unnecessary energy waste. Energy conservation and emission reduction not only reduce production costs, but also meet the trend of green production. The introduction of intelligent control algorithms and real-time monitoring mechanisms can make the entire stirring process more automated and intelligent. Through real-time monitoring of equipment status and stirring process, the system can detect abnormal conditions early and issue fault warnings. For example, when the load of the stirrer is abnormal or the speed fluctuates, the system will automatically remind maintenance personnel to check and maintain it. This early warning mechanism can avoid production stoppages and losses caused by equipment failure, improve the operating reliability and service life of the equipment, dynamically adjust the control signal according to the actual stirring speed, and ensure that the stirring process is always in the best state. Through experiments and simulations, optimize the controller parameters, improve the control accuracy and stability of the system, and debug the closed-loop control system under actual working conditions to ensure that it can adapt to different working conditions. By real-time monitoring of the stirring process, the intelligent control system can adjust the stirring speed according to real-time feedback to ensure that the stirring is always in the best state. By dynamically adjusting the control signal, the closed-loop control system can respond to changes in the external environment or process conditions in real time to ensure that the stirring system maintains a stable working state under variable working conditions and reduce instability or system oscillations. By optimizing the controller parameters through experiments and simulations, the system can automatically adjust the control strategy to adapt to different working conditions without manual intervention, which can significantly improve the adaptability and flexibility of the stirring system under various working conditions. Through the application of intelligent control algorithms, the stirring system can autonomously obtain and process real-time data, automatically adjust the speed or other control parameters, reduce the need for manual operation, improve the degree of automation, and reduce the impact of human factors on the stirring quality. By intelligently adjusting the stirring speed,It can ensure the optimization of energy consumption during the mixing process. Compared with the fixed speed control method, dynamic speed adjustment helps to avoid over-mixing or under-mixing, thereby reducing unnecessary energy consumption and mechanical wear, and improving the energy efficiency and overall production efficiency of the mixing process. Traditional mixing control methods often lack real-time monitoring and feedback mechanisms, resulting in the inability to accurately understand the real-time situation of the mixing process. The intelligent control method collects data in the mixing process in real time (such as speed, temperature, pressure, uniformity of the mixture, etc.), and provides feedback and adjustments based on these data, so that the mixing process is always in the best state. This real-time feedback can not only improve the mixing accuracy, but also monitor the equipment status and detect potential faults in advance. Through the monitoring system, the key parameters and control effects of the mixing process can be viewed in real time. When the system is abnormal, the alarm mechanism is triggered to remind the operator to intervene. Through the PID control algorithm, the three parameters of proportion, integration and differentiation are adjusted. Achieve precise control of the system. By real-time monitoring of key parameters in the mixing process (such as temperature, pressure, viscosity, flow rate, etc.), the system can dynamically adjust the mixing speed according to the current situation. This flexible control method makes the mixing process more precise and can adapt to different process requirements and raw material changes without relying on fixed, preset speeds. The PID control algorithm can make high-precision adjustments to the mixing system based on real-time feedback to ensure process stability and avoid over-mixing or under-mixing. The proportional part adjusts the proportional relationship between output and deviation, the integral part eliminates continuous deviations, and the differential part makes predictive adjustments based on the rate of change of the deviation, thereby achieving refined control. Through real-time monitoring and data acquisition, the system can monitor and record key parameters in the mixing process, reflect the system status in real time, and ensure the stability and consistency of the mixing process. Traditional mixing systems often rely on manually set fixed parameters or manually adjust the speed, and lack flexible adaptive capabilities. After the introduction of PID control algorithm and real-time data feedback, the system can automatically adjust the speed and other key parameters without human intervention, optimize production efficiency and reduce human errors. Through the analysis of real-time data, the system can not only respond to abnormal situations, but also predict the mixing demand based on historical data and trends, further optimize the mixing process, and improve the overall production efficiency. Accurate control of the mixing speed can reduce over-mixing or under-mixing and avoid unnecessary energy waste. At the same time, a reasonable mixing speed can improve production efficiency and make the production process more efficient. Through PID control, the system can reduce the wear of equipment due to excessive mixing or improper operation, thereby extending the service life of the equipment and reducing maintenance costs. Through the integrated monitoring system, operators can remotely view the key parameters and control effects of the mixing process, monitor and diagnose faults in real time, which helps to improve the efficiency of the overall production process, product quality and long-term maintainability of equipment, while reducing production costs and equipment losses.

[0132] According to another aspect of the present invention, there is provided an intelligent speed regulating stirring control system, comprising:

[0133] An acquisition module, used for acquiring the stirring process requirements of the combustion furnace, and determining a target control value of the stirring control according to the stirring process requirements;

[0134] A calculation module, used to calculate the mixing uniformity, production efficiency and energy consumption according to the target control value of the combustion furnace, and obtain the architecture of the entire intelligent mixing control system, wherein the architecture includes sensor arrangement, data acquisition system, control algorithm and actuator;

[0135] The acquisition module is used to install various sensors on the mixing equipment, collect key parameters of the mixing process in real time, set the data acquisition frequency, and ensure that the dynamic changes in the mixing process are captured;

[0136] The correction module is used to filter the collected sensor data, remove noise interference, and correct the sensor data to ensure the accuracy of the data;

[0137] An extraction module, used to extract key features in the stirring process of the combustion furnace by a data analysis method, wherein the key features include fluidity and mixing uniformity of the combustion products of thermal power generation;

[0138] Establishing a module for establishing a mathematical model of the combustion furnace stirring process according to the key characteristics for prediction and control;

[0139] The adjustment module is used to adjust the stirring speed of the combustion furnace according to the real-time monitoring data, and dynamically adjust the stirring speed according to the real-time parameter changes during the stirring process to adapt to different working conditions.

[0140] An intelligent speed regulating stirring control system further comprises:

[0141] Sensor and information acquisition module,

[0142] Including speed sensor, temperature sensor, viscosity sensor, liquid level sensor, torque sensor, used to collect key parameters in the mixing process in real time. According to the dynamic characteristics of the mixing process, a high-speed, real-time data acquisition system is designed to ensure that subtle changes in the mixing process can be captured;

[0143] Data processing and analysis module,

[0144] Perform pre-processing operations such as filtering and correction on the collected sensor data to remove noise and errors and ensure data reliability. Through data mining technology or machine learning algorithms, extract key features of the mixing process, such as the fluidity of thermal power generation combustion products and mixing uniformity, for subsequent control decisions;

[0145] Intelligent control algorithm module,

[0146] According to the real-time state of the combustion materials in the thermal power generation, the stirring speed is adjusted dynamically. Commonly used algorithms include PID control, fuzzy control, adaptive control, and neural network control. Based on historical data and current state, the future stirring process is predicted, and the control parameters are optimized to ensure the best stirring effect.

[0147] Real-time feedback and adjustment module,

[0148] By real-time monitoring of various parameters during the stirring process, a closed-loop control is formed. When the monitored parameters deviate from the set values, the control system can adjust the stirring speed in time to ensure that the stirring process is always in the best state. According to the real-time feedback information of the stirring process, the speed of the stirring motor is dynamically adjusted;

[0149] Human-computer interaction and visualization module,

[0150] Provides a friendly operation interface to facilitate operators to monitor the mixing process in real time and adjust control parameters.

[0151] The changes of key parameters in the mixing process are displayed through charts and curves to help operators intuitively understand the mixing status. When abnormalities occur during the mixing process, alarms are issued in time to prevent equipment damage or mixing failure.

[0152] Specifically, the control system includes machine learning or deep learning technology, and the control system can continuously optimize the control strategy and improve the mixing effect according to historical data and current operating experience;

[0153] Combining the knowledge and experience of industry experts, we build an expert system to assist the control system in making more reasonable decisions. Through the Internet of Things technology, we can realize remote monitoring and control of mixing equipment, and improve the adaptability and flexibility of the system in complex working conditions or unattended scenarios.

[0154] Upload the data of the mixing process to the cloud and use big data analysis technology to further optimize the mixing process and control strategy;

[0155] Efficiently integrate sensors, controllers, motor hardware devices and intelligent control algorithms to ensure the stability and reliability of system operation.

[0156] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned intelligent speed regulation and stirring control method when executing the computer program.

[0157] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned intelligent speed regulation and stirring control method are implemented.

[0158] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0159] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0160] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent speed regulating stirring control method, characterized in that: include: Obtaining stirring process requirements of the combustion furnace, and determining a target control value of stirring control according to the stirring process requirements; Calculate mixing uniformity, production efficiency and energy consumption according to the target control value of the combustion furnace, and obtain the architecture of the entire intelligent mixing control system, wherein the architecture includes sensor arrangement, data acquisition system, control algorithm and actuator; Install various sensors on the mixing equipment to collect key parameters of the mixing process in real time and set the data collection frequency to ensure that dynamic changes in the mixing process are captured; Filter the collected sensor data to remove noise interference and correct the sensor data to ensure the accuracy of the data; Extract key features of the combustion furnace stirring process by data analysis method, wherein the key features include fluidity and mixing uniformity of thermal power generation combustion products; A mathematical model of the combustion furnace stirring process is established based on the key characteristics for prediction and control; The stirring speed of the combustion furnace is adjusted according to the real-time monitoring data, and the stirring speed is dynamically adjusted according to the real-time parameter changes during the stirring process to adapt to different working conditions.

2. The intelligent speed regulating stirring control method according to claim 1 is characterized in that: The steps of installing various sensors on the stirring device include: The speed sensor is used to monitor the speed of the stirrer to ensure that the stirring speed meets the set requirements. The speed sensor is installed on the stirring shaft; The temperature of the combustion material of the stirred thermal power generation is monitored by a temperature sensor to prevent overheating or overcooling from affecting the stirring effect. The temperature sensor is installed on the wall of the stirring container; The viscosity of the thermal power generation combustion product is measured by a viscosity sensor to help adjust the stirring speed to adapt to the thermal power generation combustion products of different viscosities. The viscosity sensor is installed inside the stirring container and directly contacts the thermal power generation combustion product. The liquid level in the stirring container is monitored by a liquid level sensor to prevent overflow and material shortage. The liquid level sensor is installed on the side wall and bottom of the stirring container; The torque of the stirring shaft is measured by a torque sensor to reflect the load condition during the stirring process. The torque sensor is installed between the stirring shaft and the motor; The pressure in the stirring container is monitored by a pressure sensor to ensure safe operation, and the pressure sensor is installed on the side wall of the stirring container; The flow rate of feed and discharge is monitored by flow sensors to control the input and output of combustion materials for thermal power generation. The flow sensors are installed on the feed pipe and the discharge pipe. The density of the combustion products of thermal power generation is measured by a density sensor to assist in controlling the stirring process. The density sensor is installed inside the stirring container. The pH value of the thermal power generation combustion product is monitored by a pH sensor, which is particularly important for the stirring process that requires the control of the pH value. The pH sensor is directly immersed in the thermal power generation combustion product; The composition ratio of the combustion products of thermal power generation is monitored in real time by a composition analysis sensor installed inside the stirring container to ensure uniform mixing.

3. The intelligent speed regulating stirring control method according to claim 1 is characterized in that: The step of filtering the collected sensor data to remove noise interference includes: The sensor data is filtered to remove noise interference in the sensor data and retain useful signals. The data curve is smoothed by taking the average value of a certain number of continuous data points. The calculation formula is as follows: Among them, y(t) is the filtered data, x(ti) is the data at time (ti), and n is the size of the translation window; Perform data correction on the collected data to eliminate the inherent errors of the sensor and improve the accuracy of the data; Adjust the sensor output to zero, measure the sensor output value under zero input condition, and use it as the offset to subtract from subsequent measurements, where the calculation formula is as follows: x1 = x0 - x'; Among them, x1 is the correction data, x0 is the measurement data, and x' is the zero point offset; Eliminate the zero offset of the sensor and adjust the sensitivity of the sensor so that its output matches the actual value; According to the characteristics of the sensor, linear and nonlinear corrections are performed, and the corrected data is filtered to remove noise interference.

4. The intelligent speed regulating stirring control method according to claim 1 is characterized in that: Before the step of extracting key features of the combustion furnace stirring process by a data analysis method, the method includes: Use statistical methods to remove outlier data points and scale the data to the same range for easier subsequent processing; Interpolation of missing data to fill in the gaps, feature extraction is to extract parameters from the raw data that can reflect the key characteristics of the mixing process; Based on the extracted features, a mathematical model is established for prediction and control. The calculation formula for linear data is as follows: y=β0+β1x1+β2x2+…+β n x n +e; Among them, y is the target variable, β n is the model parameter, x n is the characteristic parameter, ε is the error term; The calculation formula for nonlinear data is as follows: y=f(W2·g(W1·x+b1)+b2); Among them, W1 and W2 are weight matrices, y is the target variable, f is the activation function of the output layer, b1 and b2 are biases, and g is the activation function; The data set is divided into a training set and a test set for model training and verification. The training set data is used to fit the model parameters, and the test set data is used to evaluate the performance of the model.

5. The intelligent speed regulating stirring control method according to claim 1, characterized in that: The step of adjusting the stirring speed of the combustion furnace according to the real-time monitoring data includes: A control signal is calculated according to a control algorithm, and a stirring speed is adjusted according to the control signal; The actuator receives the control signal, adjusts the speed of the stirring device, and feeds back the actual speed to the controller, and feeds back the adjusted actual stirring speed to the controller to form a closed-loop control; Dynamically adjust the control signal according to the actual stirring speed to ensure that the stirring process is always in the best state; Through experiments and simulations, the controller parameters are optimized to improve the control accuracy and stability of the system. Under actual working conditions, the closed-loop control system is debugged to ensure that it can adapt to different working conditions. Through the monitoring system, the key parameters and control effects of the mixing process can be viewed in real time. When the system is abnormal, the alarm mechanism is triggered to remind the operator to intervene.

6. The intelligent speed regulating stirring control method according to claim 1 is characterized in that: The step of dynamically adjusting the stirring speed according to the real-time parameter changes during the stirring process includes: Through the PID control algorithm, the three parameters of proportion, integration and differentiation are adjusted to achieve precise control of the system. The calculation formula is as follows: Among them, u(t) is the control signal, that is, the adjusted stirring speed, e(t) is the error signal, K p , K i With K d are proportional, integral and derivative gains respectively, is the integral term, is the differential term.

7. An intelligent speed regulating stirring control system, characterized in that: include: An acquisition module, used for acquiring the stirring process requirements of the combustion furnace, and determining a target control value of the stirring control according to the stirring process requirements; A calculation module, used to calculate the mixing uniformity, production efficiency and energy consumption according to the target control value of the combustion furnace, and obtain the architecture of the entire intelligent mixing control system, wherein the architecture includes sensor arrangement, data acquisition system, control algorithm and actuator; The acquisition module is used to install various sensors on the mixing equipment, collect key parameters of the mixing process in real time, set the data acquisition frequency, and ensure that the dynamic changes in the mixing process are captured; The correction module is used to filter the collected sensor data, remove noise interference, and correct the sensor data to ensure the accuracy of the data; An extraction module, used to extract key features in the stirring process of the combustion furnace by a data analysis method, wherein the key features include fluidity and mixing uniformity of the combustion products of thermal power generation; Establishing a module for establishing a mathematical model of the combustion furnace stirring process according to the key characteristics for prediction and control; The adjustment module is used to adjust the stirring speed of the combustion furnace according to the real-time monitoring data, and dynamically adjust the stirring speed according to the real-time parameter changes during the stirring process to adapt to different working conditions.

8. The intelligent speed regulating stirring control system according to claim 7, characterized in that: The adjustment module comprises: A first adjustment unit, configured to adjust the stirring speed according to a control signal calculated by a control algorithm; The feedback unit is used for the actuator to receive the control signal, adjust the speed of the stirring device, and feed back the actual speed to the controller, and feed back the adjusted actual stirring speed to the controller to form a closed-loop control; A second adjustment unit is used to dynamically adjust the control signal according to the actual stirring speed to ensure that the stirring process is always in an optimal state; The debugging unit is used to optimize the controller parameters through experiments and simulations, improve the control accuracy and stability of the system, and debug the closed-loop control system under actual working conditions to ensure that it can adapt to different working conditions; The warning unit is used to view the key parameters and control effects of the mixing process in real time through the monitoring system, and trigger the alarm mechanism when the system is abnormal to remind the operator to intervene.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent speed regulating stirring control method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent speed regulating stirring control method according to any one of claims 1 to 6 are implemented.

Images