Boiler steam supply control method and system based on data driving, computer and medium

Abstract

The invention discloses a boiler steam supply control method and system based on data driving, a computer and a medium, and the method comprises the steps: S1, collecting key state parameters of boiler operation in real time through an upper communication system of a boiler; s2, a steam demand prediction model is constructed, and the model calculates the steam demand in the future preset time through historical data and key state parameters of the production line; s3, calculating a steam pressure set point according to the steam demand calculated in the step S2, and calculating an opening instruction of a gas valve according to the steam pressure set point; and S4, the opening degree instruction obtained through calculation in the step S3 is issued to a regulating valve controller of the boiler through a communication link, and the steam pressure of the boiler is controlled. The steam demand of the downstream production line can be evaluated in real time, the gas consumption and the operation state of the boiler can be accurately regulated and controlled according to the steam demand, and therefore on the premise that production is guaranteed, energy is saved to the maximum extent, and the operation cost is reduced to the maximum extent.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial production energy conversion control, and in particular relates to a boiler steam supply control method, system, computer and medium based on data driving. BACKGROUND

[0002] In industrial production, the boiler is the core energy conversion equipment, which provides the necessary steam for the downstream production line (such as the anodic oxidation production line in the present case). In the traditional control mode, in order to ensure the continuous and stable operation of the production line, the boiler is often in a constant high-load operation state, and natural gas is continuously burned to produce steam far exceeding the actual demand. This "unlimited supply" mode has significant drawbacks: 1. Energy waste is huge: the boiler still maintains high energy consumption during non-full production or low demand period, resulting in a large amount of invalid consumption of natural gas.

[0003] 2. High operating cost: fuel cost is the main expense of boiler operation, and unnecessary burning directly increases production cost.

[0004] 3. Device wear and tear is intensified: continuous high-load operation will accelerate the aging and wear of the boiler body and auxiliary equipment (such as the burner, water pump, valve).

[0005] 4. Environmental pressure increases: unnecessary fuel burning will produce additional emissions of pollutants such as nitrogen oxides (NO x ), carbon dioxide (CO2), etc.

[0006] That is, in the prior art, although the boiler itself has basic automatic control function, it lacks deep coupling and forward-looking regulation with the actual demand of the downstream production line. Therefore, there is an urgent need for an intelligent control method that can accurately match supply and demand and realize on-demand supply to achieve the purpose of reducing cost and increasing efficiency. SUMMARY

[0007] In view of the above shortcomings of the prior art, the technical problem to be solved by the present application is to provide a boiler steam supply control method, system, computer and medium based on data driving, which can real-time evaluate the steam demand of the downstream production line, and accurately regulate the gas consumption and operation state of the boiler accordingly, so as to maximize energy saving and reduce operating cost under the premise of ensuring production.

[0008] One of the technical solutions adopted by the present application is: a boiler steam supply control method based on data driving, the method comprising the following steps: S1: through the upper communication system of the boiler, real-time acquisition of the key state parameters of the boiler operation, including process parameters, equipment state and system flag; S2: Construct a steam demand prediction model, which calculates the steam demand in the future preset time through the historical data and key state parameters of the production line; S3: According to the steam demand calculated in S2, calculate the steam pressure set point required to meet the steam demand through a control algorithm, and calculate the opening command of the gas valve according to the steam pressure set point; S4: The opening command calculated in S3 is sent to the boiler's regulating valve controller through a communication link to control the boiler's steam pressure.

[0009] Further, the method further comprises the following steps: S5: Repeat steps S2-S4 every preset interval.

[0010] Further, the key state parameters include process parameters, device states and system flags, wherein the process parameters include steam pressure, exhaust gas temperature and feed water temperature; the device state includes the running state of the air blower, the feed water pump, the combustion valve and the concentrated blowdown valve; the system flag includes data validity flag and alarm state.

[0011] Further, the S2 step comprises the following sub-steps: S21: Construct a steam demand prediction model: ; Wherein, represents the steam demand in the future preset time, represents the basic heat preservation demand, represents the temperature rise coefficient, represents the target process temperature, represents the real-time temperature of the electrolyte of the anodizing production line, represents the future preset time, represents the quality of the electrolyte of the anodizing production line; S22: Input the real-time production parameters and historical production parameters of the current anodizing production line into the steam demand prediction model to calculate the steam demand in the future preset time.

[0012] Further, the S3 step comprises the following sub-steps: S31: Calculate the target steam pressure set value according to the steam demand and the fixed parameters of the boiler: ; Wherein, represents the target steam pressure set value, represents the minimum pressure required to ensure that steam can be delivered to the most remote production line equipment, and a represents the pressure-flow coefficient, This indicates the steam demand within a predetermined timeframe. S32: Calculate the boiler opening command based on the target steam pressure setpoint. ; ; Where Output represents the boiler's PID opening command. This indicates the pressure deviation at the current moment. This indicates the pressure deviation at the previous moment. This indicates the real-time steam pressure of the boiler. This represents the proportional coefficient of the PID controller. This represents the integral coefficient of the PID controller. This represents the differential coefficient of the PID controller.

[0013] Furthermore, in step S4, the opening command is sent to the boiler's regulating valve controller via Modbus communication to control the boiler steam pressure.

[0014] The second technical solution adopted in this invention is a data-driven boiler steam supply control system, which includes the following modules: The boiler parameter acquisition module is used to acquire key status parameters of boiler operation in real time through the boiler's host communication system. The steam demand forecasting module is used to build a steam demand forecasting model. This model calculates the steam demand within a preset time period using historical data and key status parameters of the production line. The opening command calculation module is used to calculate the steam pressure setpoint required to meet the steam demand based on the steam demand calculated in the steam demand prediction module, and to calculate the opening command of the gas valve based on the steam pressure setpoint. The boiler control module is used to send the opening command calculated by the opening command calculation module to the boiler's regulating valve controller through the communication link to control the boiler steam pressure.

[0015] Furthermore, the system also includes the following modules: The periodic control module is used to repeat the steam demand prediction module, the opening command calculation module, and the boiler control module at each preset interval.

[0016] The third technical solution adopted by the present application is a computer device, which comprises a processor and a memory, and the memory stores at least one instruction, at least one program, a code set or an instruction set, which is loaded and executed by the processor to realize the data-driven boiler steam supply control method according to any one of the above.

[0017] The fourth technical solution adopted by the present application is a computer-readable storage medium, which stores at least one instruction, at least one program, a code set or an instruction set, which is loaded and executed by a processor to realize the data-driven boiler steam supply control method according to any one of the above.

[0018] The data-driven boiler steam supply control method, system, computer and medium of the present application have at least the following beneficial effects: 1. Significant energy saving: "on-demand supply" is realized, and unnecessary combustion is completely avoided, which is expected to save 15% to 30% of natural gas consumption.

[0019] 2. Reduce operating costs: directly reduce fuel costs, and at the same time, because the equipment runs more smoothly, maintenance costs are reduced.

[0020] 3. Prolong the service life of the equipment: avoid long-term high-load operation of the boiler, reduce thermal stress and mechanical wear and tear.

[0021] 4. Improve the automation level: realize the intelligent upgrading from "continuous combustion" to "fine".

[0022] 5. Environmental benefits: reduce the emission of greenhouse gases and pollutants, and meet the development trend of green manufacturing. BRIEF DESCRIPTION OF DRAWINGS

[0023] The drawings described herein are used to provide further understanding of the present application, and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation on the present application. In the drawings: Figure 1 The flowchart of the data-driven boiler steam supply control method of the present application.

[0024] Figure 2 The sub-flowchart of S2 in the above method. Figure 1

[0025] The sub-flowchart of S3 in the above method. Figure 3 Figure 1

[0026] ​​Figure 4 A data-driven based boiler steam supply control system block diagram of the present application. DETAILED DESCRIPTION

[0027] The present application will be further described below with reference to the accompanying drawings.

[0028] Referring to Figure 1 A data-driven based boiler steam supply control method flow chart of the present application. The method can include the following steps: S1: Real-time acquisition of key state parameters of boiler operation through the upper communication system of the boiler, including process parameters, equipment status and system flags. This S1 step acquires real-time key state parameters of boiler operation through the upper communication system of the boiler (such as Modbus RTU over RS-485).

[0029] Specifically, the key state parameters in this S1 step include process parameters, equipment status and system flags, wherein the process parameters include steam pressure, flue gas temperature and feedwater temperature; the equipment status includes the running status of the air blower, the feedwater pump, the combustion valve and the concentrated blowdown valve; and the system flags include data validity flags and alarm status. Real-time data acquisition ensures the timeliness and accuracy of the control system, enabling the system to quickly respond to changes based on the latest operating status, avoiding control lag caused by data delay. This improves the dynamic performance of the boiler and reduces steam supply fluctuations. And comprehensive coverage of multiple types of parameters (process, equipment, system) provides a complete picture of boiler operation, which helps to achieve comprehensive monitoring and fault warning. Based on the knowledge in the art, such multi-parameter acquisition is the basis of industrial Internet of Things, supports predictive maintenance, reduces downtime risk, and optimizes energy efficiency, for example, by monitoring flue gas temperature to indirectly reflect combustion efficiency, thereby adjusting and optimizing.

[0030] S2: Steam demand prediction model, which calculates the steam demand in the future preset time through historical data of the production line and key state parameters. This S2 step establishes an anode production line steam demand model. Based on historical production data, production scheduling, real-time working conditions (such as the current type, quantity and process stage of the anode product being processed), etc., the model predicts the accurate steam demand in the future period (such as the next 15 minutes or 1 hour). The steam demand prediction model allows the system to estimate steam demand in advance, enabling forward-looking control to avoid steam supply shortages or surpluses, thereby optimizing energy consumption and reducing waste. Based on data-driven, the model can adaptively learn historical patterns to improve prediction accuracy and reduce dependence on human experience.

[0031] Referring to Figure 2 A sub-flow chart of S2 step, this S2 step can include the following sub-steps: S21: Construct a steam demand prediction model: ; where, represents the steam demand in the future preset time (unit: m 3 / h), which is the final output of our model. represents the basic insulation demand (unit: m 3 / h), which refers to the natural gas consumed by the production line to maintain the tank liquid temperature during the constant temperature process stage. This value is obtained by analyzing the average natural gas consumption during the constant temperature stage in the historical data. represents the temperature rise coefficient (unit: m 3 ·℃ / kJ), which is an empirical parameter representing the natural gas volume required to raise 1 ton of tank liquid by 1℃. This coefficient is obtained by linear regression fitting of the natural gas consumption and temperature rise data during the "temperature rise stage" in the historical data. represents the target process temperature (unit: ℃), which is obtained from the process recipe table in the M system according to the current product type and process stage. represents the real-time temperature of the anodizing production line (unit: ℃), which is read in real time from the field temperature sensor. represents the future preset time (unit: hours), which is 0.25 hours (15 minutes) in this example. represents the tank liquid mass of the anodizing production line (unit: tons), which is a fixed equipment parameter determined by the production line design. This S21 step quantifies the demand calculation, converting complex process parameters into calculable variables, making the prediction process objective and efficient. Considering temperature deviation and mass factors, the model is more consistent with actual production dynamics, such as in the anodizing production line, where tank liquid temperature changes directly reflect heating demand, thereby improving prediction accuracy. Based on control theory, this linear plus deviation model structure is simple to implement, suitable for real-time systems, and reduces computational overhead.

[0032] S22: Input the real-time production parameters and historical production parameters of the current anodizing production line into the steam demand prediction model to calculate the steam demand in the future preset time. This S2 step inputs the current production parameters (such as real-time tank liquid temperature) and historical data into the constructed model to automatically calculate the steam demand in the future preset time. By automating the calculation, human errors are reduced, ensuring consistent and reliable prediction results. Real-time parameter input enables the model to quickly respond to process changes, such as when the production line accelerates, the temperature deviation increases, and the model adjusts demand prediction in real time, enhancing system agility. Based on big data analysis, the use of historical data improves the model's generalization ability, avoiding overfitting.

[0033] S3: Based on the steam demand calculated in S2, use a control algorithm to calculate the steam pressure setpoint needed to meet this demand, and from this setpoint, calculate the gas valve opening command. This S3 step compares the steam demand forecast from S2 with the real-time boiler state (particularly the current steam pressure) collected in S1. Using an advanced control algorithm (such as PID control, fuzzy logic control, or model predictive control, MPC), calculate the target steam pressure setpoint that the boiler needs to reach to meet the target demand, and further calculate the gas valve opening command. This converts the demand forecast into an actual control variable, enabling closed-loop control and ensuring that steam supply matches demand, improving system stability. The use of control algorithms optimizes response speed, reduces overshoot or oscillation, and is suitable for industrial environments with large fluctuations.

[0034] Please refer to Figure 3 For the subflowchart of this S3 step, this S3 step can also include the following substeps: S31: Calculate the target steam pressure setpoint based on the steam demand and boiler fixed parameters: ; Where, Ptarget represents the target steam pressure setpoint, Pmin represents the minimum pressure required to ensure that steam can be delivered to the most remote production line equipment, and a represents the pressure-flow coefficient, Q represents the steam demand over a future preset time; this S31 step calculates the pressure based on the square root relationship of the demand, which approximates the flow-pressure characteristics in fluid mechanics, making the pressure setting smoother and avoiding system shocks caused by sudden changes. For example, the square root function can effectively handle nonlinear flow changes, improving the accuracy of pressure control. The introduction of the minimum pressure ensures that steam can be delivered to remote equipment, enhancing system reliability, and based on pipeline engineering knowledge, this reduces the risk of pressure drop.

[0035] S32: Calculate the boiler opening command based on the target steam pressure setpoint: ; ; Where, Output represents the PID opening command of the boiler, e represents the pressure error at the current time, e represents the pressure error at the previous time, P represents the real-time steam pressure of the boiler, Kp represents the proportional coefficient of the PID, Ki represents the integral coefficient of the PID, The differential coefficient of the PID. The PID control in this S32 step provides proportional, integral, and derivative actions, which can quickly eliminate steady-state errors (integral term), suppress oscillations (derivative term), and improve response speed (proportional term), making the control process smooth and accurate. Based on control engineering, PID is an industrial standard algorithm with simple structure and easy debugging, suitable for boiler inertia systems, which can effectively handle load changes and improve energy efficiency.

[0036] S4: The opening degree command calculated in the S3 step is transmitted to the boiler's regulating valve controller through a communication link to control the boiler's steam pressure.

[0037] Specifically, in this S4 step, the opening degree command is transmitted to the boiler's regulating valve controller through Modbus communication to control the boiler's steam pressure. This S4 step transmits the opening degree command calculated in the S3 step to the boiler's regulating valve controller through a communication link (such as Modbus protocol) to directly control the gas valve opening degree, thereby adjusting the boiler's steam pressure. The communication link enables remote transmission and automated execution of instructions, reducing manual intervention and improving control efficiency. Using standard protocols such as Modbus ensures compatibility with existing industrial equipment, facilitating system integration and maintenance. Based on industrial communication knowledge, this transmission method supports real-time monitoring and fault diagnosis, such as reading valve status through Modbus, enhancing system safety.

[0038] S5: Repeat the S2-S4 steps every preset interval. This S5 step is periodically executed to make the control system adaptive and continuously optimized to respond to environmental changes (such as changes in production rhythm). Based on real-time system theory, periodic updates prevent models or control parameters from becoming outdated, improving long-term stability and energy efficiency. For example, in continuous production, periodic repetition can prevent the accumulation of single prediction errors, ensuring smooth steam supply.

[0039] Please refer to Figure 4 The present application is a data-driven boiler steam supply control system structure diagram, and the present application also provides a data-driven boiler steam supply control system, which is used to implement the above-mentioned data-driven boiler steam supply control method, and specifically can include a boiler parameter acquisition module 100, a steam demand prediction module 200, an opening degree command calculation module 300, a boiler control module 400, and a periodic control module 500. Specifically: The boiler parameter acquisition module 100 is used to acquire key state parameters of the boiler in real time through the upper communication system of the boiler; The steam demand prediction module 200 is used to construct a steam demand prediction model, which calculates the steam demand in a future preset time through historical data of the production line and key state parameters; The opening degree instruction calculation module 300 is configured to calculate, by a control algorithm, a steam pressure set point required to meet the steam demand quantity calculated by the steam demand prediction module, and calculate an opening degree instruction of the gas valve according to the steam pressure set point; The boiler control module 400 is configured to send the opening degree instruction calculated by the opening degree instruction calculation module to a regulating valve controller of the boiler through a communication link, and control the steam pressure of the boiler. The periodic control module 500 is configured to repeat the steam demand prediction module, the opening degree instruction calculation module and the boiler control module at each preset interval.

[0040] In an embodiment of the present application, a computer device is provided, which includes a memory and a processor, and the memory stores a computer program, and the processor implements the data-driven boiler steam supply control method according to any of the above embodiments when executing the computer program.

[0041] In an embodiment of the present application, a computer readable storage medium is provided, which stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set are loaded and executed by a processor to implement the data-driven boiler steam supply control method according to any of the above embodiments.

[0042] It can be understood by those skilled in the art that all or part of the processes of the above-mentioned embodiments can be completed by a computer program instructing related hardware, and the computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments can be included. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), 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.

[0043] The above merely expresses the preferred embodiments of the present application, which are described in a more specific and detailed manner, but should not be understood as limiting the scope of the patent. It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application patent should be subject to the appended claims.

Claims

1. A data-driven boiler steam supply control method, comprising the following steps: S1: Collect key status parameters of boiler operation in real time through the boiler's upper-level communication system, including process parameters, equipment status and system flags; S2: Construct a steam demand forecasting model. This model calculates the steam demand within a preset time period using historical data and key status parameters of the production line. S3: Based on the steam demand calculated in step S2, the control algorithm calculates the steam pressure setpoint required to meet the steam demand, and calculates the opening command of the gas valve based on the steam pressure setpoint. S4: The opening command obtained in step S3 is sent to the boiler's regulating valve controller via the communication link to control the boiler steam pressure.

2. The data-driven boiler steam supply control method as described in claim 1, characterized in that, This method also Includes the following steps: S5: Repeat steps S2 to S4 at each preset interval.

3. The data-driven boiler steam supply control method as described in claim 1, characterized in that, The key status parameters include process parameters, equipment status, and system flags. The process parameters include steam pressure, flue gas temperature, and feedwater temperature. The equipment status includes the operating status of the blower, feedwater pump, combustion valve, and concentrate discharge valve. The system flags include data validity flags and alarm status.

4. The data-driven boiler steam supply control method as described in claim 1, characterized in that, Step S2 includes the following sub-steps: S21: Constructing a steam demand forecasting model: ； in, This indicates the steam demand over a predetermined period of time. Indicates basic insulation requirements. Indicates the temperature rise coefficient. Indicates the target process temperature. This indicates the real-time temperature of the bath solution in the anodizing production line. Indicates a future preset time. This indicates the quality of the bath solution in the anodizing production line; S22: Input the real-time and historical production parameters of the current anodizing production line into the steam demand prediction model to calculate the steam demand within a preset time period in the future.

5. The data-driven boiler steam supply control method as described in claim 1, characterized in that, Step S3 includes the following sub-steps: S31: Calculate the target steam pressure setpoint based on steam demand and boiler fixed parameters: ； in, This indicates the target steam pressure setpoint. This represents the minimum pressure required to ensure steam can be delivered to the furthest production line equipment; 'a' represents the pressure-flow coefficient. This indicates the steam demand within a predetermined timeframe. S32: Calculate the boiler opening command based on the target steam pressure setpoint. ； ； Where Output represents the boiler's PID opening command. This indicates the pressure deviation at the current moment. This indicates the pressure deviation at the previous moment. This indicates the real-time steam pressure of the boiler. This represents the proportional coefficient of the PID controller. This represents the integral coefficient of the PID controller. This represents the differential coefficient of the PID controller.

6. The data-driven boiler steam supply control method as described in claim 1, characterized in that, In step S4, the opening command is sent to the boiler's regulating valve controller via Modbus communication to control the boiler steam pressure.

7. A data-driven boiler steam supply control system, characterized in that, The system includes the following modules: The boiler parameter acquisition module is used to acquire key status parameters of boiler operation in real time through the boiler's host communication system. The steam demand forecasting module is used to build a steam demand forecasting model. This model calculates the steam demand within a preset time period using historical data and key status parameters of the production line. The opening command calculation module is used to calculate the steam pressure setpoint required to meet the steam demand based on the steam demand calculated in the steam demand prediction module, and to calculate the opening command of the gas valve based on the steam pressure setpoint. The boiler control module is used to send the opening command calculated by the opening command calculation module to the boiler's regulating valve controller through the communication link to control the boiler steam pressure.

8. The data-driven boiler steam supply control system as described in claim 7, characterized in that, The system also includes the following modules: The periodic control module is used to repeat the steam demand prediction module, the opening command calculation module, and the boiler control module at each preset interval.

9. A computer device, characterized in that, The computer device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the data-driven boiler steam supply control method as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or instruction set is loaded and executed by a processor to implement the data-driven boiler steam supply control method as described in any one of claims 1-6.

Images