Intelligent regulation and control system and method for alkalinity of circulating water of thermal power plant
By building an intelligent regulation system in the circulating water system of the thermal power plant and combining with the LSTM network prediction model, real-time monitoring and precise regulation of the alkalinity of circulating water is achieved, the problems of lag in response and insufficient regulation accuracy are solved, and the safety and economicality of equipment operation are improved.
Patent Information
- Application Number
- CN202510566573.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-30
- Publication Date
- 2025-08-01
AI Technical Summary
There are problems of hysteresis response and insufficient pH regulation accuracy in the circulating water system of thermal power plants, which lead to scaling or corrosion, affecting equipment life and energy consumption. At the same time, traditional regulation relies on manual experience to waste or insufficient dose, making it difficult to meet the water-saving needs.
An intelligent control system is constructed using sampling electric regulating valves, online alkalinity analyzers, multi-parameter water quality sensors and control modules. Combined with the LSTM network prediction model, the alkalinity of circulating water is monitored and predicted in real time, and precise regulation is achieved through dilute sulfuric acid and concentrated sulfuric acid plus acid pumps.
Real-time monitoring and precise regulation of circulating water alkalinity is achieved, reducing waste of drugs, improving the safety and economicality of equipment operation, and reducing water resources costs.
Smart Images

Figure CN120406599A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of industrial circulating water regulation, and relates to an intelligent regulation system and method for the alkalinity of circulating water in a thermal power plant. Background Art
[0002] As the main force of power supply, the operating efficiency and environmental protection performance of thermal power plants directly affect the sustainable development of the energy industry. In the thermal cycle system of a thermal power plant, the circulating water system undertakes the important function of cooling the exhaust steam of the steam turbine. The water quality control of circulating water, especially the precise regulation of alkalinity, is the key link to ensure cooling efficiency and prevent equipment corrosion and scaling. However, the traditional circulating water alkalinity regulation technology faces multiple challenges and urgently needs to achieve technological breakthroughs through intelligent means.
[0003] Limitations of traditional regulation technologies: At present, the control of circulating water alkalinity in thermal power plants mainly relies on the extensive management mode of manual sampling, laboratory analysis, and chemical reagent dosing. Specific problems include: Response lag: The manual detection period is long (usually once every 4 - 8 hours), making it difficult to capture the dynamic changes of water quality in a timely manner (such as alkalinity anomalies caused by water source switching, scaling, temperature changes, microbial growth, etc.), resulting in lagged regulation and prone to scaling or corrosion. According to statistics, for a 600MW unit, the condenser end difference increases by 1.5℃ due to circulating water scaling, and the annual power generation coal consumption increases by about 12,000 tons. Among them, scaling will lead to a decrease in heat transfer efficiency (for every 0.1mm scale layer, the energy consumption increases by 3% - 5%), and frequent pickling for scale removal will accelerate pipeline corrosion and shorten the equipment life. The titanium tubes of the condenser in a certain power plant suffered pitting corrosion due to local alkalinity out - of - control, and the single - time replacement cost exceeded 5 million yuan.
[0004] Over - reliance on experience: The dosing amount depends on the experience of operators and lacks the support of a quantitative model, prone to reagent waste or insufficient dosage. Data from a certain power plant shows that the annual over - expenditure of reagent costs due to improper alkalinity control reaches 800,000 yuan, and excessive addition of phosphates may cause eutrophication problems in water bodies. Moreover, the traditional "over - dosing + large - discharge and large - make - up" mode faces compliance risks, and it is urgent to reduce the sewage discharge through precise regulation.
[0005] Difficulty in multi - factor coupling regulation: The alkalinity of circulating water is affected by multiple variables such as water temperature, concentration ratio, and makeup water composition (such as the mixed use of surface water and reclaimed water). It is difficult for traditional PID control to establish a non - linear dynamic model, resulting in insufficient regulation accuracy.
[0006] Rising water resource costs: In water - scarce areas, increasing the concentration ratio (from 3 times to 6 times) can save 40% of water, but higher - precision alkalinity control is required to prevent salt scaling, and traditional technologies are difficult to meet the requirements.
[0007] In summary, in the thermal cycle system of a thermal power plant, there are problems of response lag and insufficient accuracy in regulating the pH value in the circulating water system. Summary of the Invention
[0008] The purpose of the present invention is to provide an intelligent control system and method for the alkalinity of circulating water in a thermal power plant to solve the technical problems of response lag and insufficient accuracy in regulating the pH value in the circulating water system.
[0009] To achieve the above purpose, the present invention adopts the following technical solutions: The present invention discloses an intelligent control system for the alkalinity of circulating water in a thermal power plant, including: A sampling electric control valve, the inlet of the sampling electric control valve is used to connect to the circulating water pipeline, and the outlet of the sampling electric control valve is respectively connected to the inlet of an online alkalinity analyzer and the inlet of a multi-parameter water quality sensor, and the multi-parameter water quality sensor is used to obtain the conductivity, pH value and water temperature of the circulating water; A sulfuric acid dilution tank, the inlet of the sulfuric acid dilution tank is connected to a concentrated sulfuric acid inlet electric control valve and a demineralized water inlet electric control valve, the outlet of the sulfuric acid dilution tank is respectively connected to the inlet of a dilute sulfuric acid adding pump and the inlet of at least one concentrated sulfuric acid adding pump, the outlet of the concentrated sulfuric acid adding pump is used to connect to the circulating water pool, and the outlet of the dilute sulfuric acid adding pump is used to connect to the circulating water pipeline; A control module, the control module is electrically connected to the sampling electric control valve, the online alkalinity analyzer, the multi-parameter water quality sensor, the concentrated sulfuric acid inlet electric control valve, the demineralized water inlet electric control valve, the dilute sulfuric acid adding pump and the concentrated sulfuric acid adding pump.
[0010] Further, the inlet of the sampling electric control valve is connected to the circulating water pipeline through a circulating water sampling pipeline.
[0011] Further, the outlet of the sampling electric control valve is connected to a pipeline self-cleaning filter through a booster pump, the outlet of the pipeline self-cleaning filter is respectively connected to the inlet of the online alkalinity analyzer and the inlet of the multi-parameter water quality sensor, second drain valves are provided at the outlets of the online alkalinity analyzer and the multi-parameter water quality sensor, and the outlets are connected to the control module through the booster pump and the pipeline self-cleaning filter.
[0012] Further, the outlet of the pipeline self-cleaning filter is also connected to the inlet of a first drain valve.
[0013] Further, an inlet and outlet differential pressure sensor is provided in the pipeline self-cleaning filter, and when the inlet and outlet differential pressure is greater than the set value, the pipeline self-cleaning filter starts automatic backwashing.
[0014] Further, there are two concentrated sulfuric acid addition pumps. The outlets of the two concentrated sulfuric acid addition pumps are both connected to the inlets of the electric control valves at the outlets of the concentrated sulfuric acid addition pumps. The outlets of the electric control valves at the outlets of the concentrated sulfuric acid addition pumps are used to connect to the circulating water pool, and the electric control valves at the outlets of the concentrated sulfuric acid addition pumps are electrically connected to the control module.
[0015] Further, the connection ports of the outlets of the two electric control valves at the outlets of the concentrated sulfuric acid addition pumps and the circulating water pool are respectively located at both ends of the circulating water pool.
[0016] Further, the outlet of the dilute sulfuric acid addition pump passes through the inlet of the electric control valve at the outlet of the dilute sulfuric acid addition pump. The outlet of the electric control valve at the outlet of the dilute sulfuric acid addition pump is used to connect to the circulating water pipeline, and the electric control valve at the outlet of the dilute sulfuric acid addition pump is electrically connected to the control module.
[0017] The present invention also discloses an intelligent control method for the alkalinity of circulating water in a thermal power plant. According to the intelligent control system for the alkalinity of circulating water in a thermal power plant, it includes the following steps: Obtain historical and current water quality data. The circulating water data includes the unit load and the alkalinity, pH value, water temperature, chloride ion content, conductivity, and cumulative acid addition amount of the circulating water. Use the historical water quality data combined with the LSTM network prediction model to generate a dedicated control parameter library. Obtain the predicted alkalinity of the circulating water based on the current water quality data and the dedicated control parameter library. Generate the acid addition demand based on the predicted alkalinity of the circulating water combined with the current water quality data, and obtain the concentrated sulfuric acid demand and demineralized water demand according to the acid addition demand.
[0018] Further, the step of generating the acid addition demand based on the predicted alkalinity of the circulating water combined with the current water quality data, and obtaining the concentrated sulfuric acid demand and demineralized water demand according to the acid addition demand is as follows: Generate the frequency of the acid addition pump and the opening degree of the electric control valve at the outlet of the concentrated sulfuric acid addition pump based on the predicted alkalinity of the circulating water combined with the current water quality data. Obtain the concentrated sulfuric acid demand, demineralized water demand, the opening degree of the electric control valve at the concentrated sulfuric acid inlet, and the opening degree of the electric control valve at the demineralized water inlet according to the acid addition demand.
[0019] Compared with the prior art, the present invention has the following beneficial effects: The present invention collects circulating water by sampling an electric control valve and controls the amount of circulating water entering an on-line alkalinity analyzer and a multi-parameter water quality sensor. The multi-parameter water quality sensor is used to obtain the conductivity, pH value and water temperature of the circulating water, and the on-line alkalinity analyzer is used to obtain the pH value of the circulating water, so as to obtain the water quality data of the circulating water, which is convenient for assisting the intelligent regulation and real-time monitoring of the alkalinity of the circulating water. The sulfuric acid dilution tank is used to prepare dilute sulfuric acid with an appropriate concentration according to the acid addition requirement. The outlet of the concentrated sulfuric acid addition pump is used to connect to the circulating water pool, which is the main acid addition point and is used for quickly adjusting the acidity and alkalinity of the circulating water. The outlet of the dilute sulfuric acid addition pump is used to connect to the circulating water pipeline, which is the auxiliary acid addition point and is used for fine adjustment of the acidity and alkalinity of the circulating water. The settings of the dilute sulfuric acid addition pump and the concentrated sulfuric acid addition pump form a two-stage acid addition control system, which can realize more accurate regulation of the alkalinity of the circulating water. The setting of the control module further improves the automation degree of the device, which is beneficial to ensuring the accuracy and timeliness of the regulation.
[0020] The method of the present invention ensures the timeliness of the model input by real-time updating the data, and avoids control deviation caused by data lag. The historical water quality data is combined with the LSTM network prediction model to generate a dedicated control parameter library, which is convenient for quickly and accurately predicting the alkalinity of the circulating water. The predicted alkalinity of the circulating water is obtained based on the current water quality data and the dedicated control parameter library, and the dynamic adjustment of the acid addition amount is guided by the prediction result to avoid excessive or insufficient acid addition. The acid addition requirement is generated based on the predicted alkalinity of the circulating water and the current water quality data, and the concentrated sulfuric acid requirement and the demineralized water requirement are obtained based on the acid addition requirement. It can realize the intelligent regulation and real-time monitoring of the alkalinity of the circulating water, and can realize the precise and rapid adjustment of the acidity and alkalinity of the circulating water. Description of the Drawings
[0021] Figure 1 It is a schematic structural diagram of the intelligent sampling and analysis unit according to an embodiment of the present invention; Figure 2 It is a schematic structural diagram of the edge control unit according to an embodiment of the present invention; Figure 3 It is a schematic structural diagram of the hierarchical acid addition unit according to an embodiment of the present invention; Figure 4 It is a flowchart of the method according to an embodiment of the present invention.
[0022] Among them: 1. Sampling electric control valve; 2. Booster pump; 3. Pipeline self-cleaning filter; 4. Online alkalinity analyzer; 5. Multi-parameter water quality sensor; 6. Signal output module; 7. Second sewage discharge valve; 8. First sewage discharge valve; 9. Concentrated sulfuric acid inlet electric control valve; 10. Demineralized water inlet electric control valve; 11. Dilute sulfuric acid adding pump; 12. First concentrated sulfuric acid adding pump; 13. Second concentrated sulfuric acid adding pump; 14. Sulfuric acid dilution tank; 15. Control module of the dilution and preparation module; 16. Electric control valve at the outlet of the dilute sulfuric acid adding pump; 17. Electric control valve at the outlet of the first concentrated sulfuric acid adding pump; 18. Electric control valve at the outlet of the second concentrated sulfuric acid adding pump; 19. Hardware module of the edge control unit; 20. LSTM network prediction software module; 21. Circulating water sampling pipeline; 22. Circulating water pipeline; 23. Circulating water tank. Detailed implementation manners
[0023] In order to enable those skilled in the art of the present technology to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0024] It should be noted that the terms "first", "second", etc. in the description and the above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order different from those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.
[0025] The present invention will be further described in detail below in conjunction with the accompanying drawings: The present invention discloses an intelligent control system for the alkalinity of circulating water in a thermal power plant, including: a sampling electric control valve 1 and a sulfuric acid dilution tank 14; See Figure 1, the inlet of the sampling electric control valve 1 is used to connect to the circulating water pipeline 22, and the outlet of the sampling electric control valve 1 is respectively connected to the inlet of the on-line alkalinity analyzer 4 and the inlet of the multi-parameter water quality sensor 5. The sampling electric control valve 1 is used to collect the circulating water and control the amount of circulating water entering the on-line alkalinity analyzer 4 and the multi-parameter water quality sensor 5. The multi-parameter water quality sensor 5 is used to obtain the conductivity, pH and water temperature of the circulating water, and the on-line alkalinity analyzer 4 is used to obtain the pH value of the circulating water. The above structure is used for obtaining the water quality data of the circulating water, so as to assist the intelligent regulation and real-time monitoring of the circulating water alkalinity.
[0026] See Figure 3 , the sulfuric acid dilution tank 14 is used to prepare sulfuric acid dilute with appropriate concentration according to the acid addition requirement. The inlet of the sulfuric acid dilution tank 14 is connected with the concentrated sulfuric acid inlet electric control valve 9 and the demineralized water inlet electric control valve 10. The outlet of the sulfuric acid dilution tank 14 is respectively connected to the inlet of the dilute sulfuric acid addition pump 11 and the inlet of at least one concentrated sulfuric acid addition pump. The outlet of the concentrated sulfuric acid addition pump is used to connect to the circulating water pool 23, which is the main acid addition point and is used for the rapid adjustment of the acidity and alkalinity of the circulating water. The outlet of the dilute sulfuric acid addition pump 11 is used to connect to the circulating water pipeline 22, which is the auxiliary acid addition point and is used for the fine adjustment of the acidity and alkalinity of the circulating water. The settings of the dilute sulfuric acid addition pump 11 and the concentrated sulfuric acid addition pump form a two-stage acid addition control system, which can realize more accurate regulation of the circulating water alkalinity.
[0027] Control module, the control module is electrically connected to the sampling electric control valve 1, the on-line alkalinity analyzer 4, the multi-parameter water quality sensor 5, the concentrated sulfuric acid inlet electric control valve 9, the demineralized water inlet electric control valve 10, the dilute sulfuric acid addition pump 11 and the concentrated sulfuric acid addition pump, which improves the automation degree of the device and is beneficial to ensuring the accuracy and timeliness of the regulation.
[0028] Preferably, see Figure 1 , the inlet of the sampling electric control valve 1 is connected to the circulating water pipeline 22 through the circulating water sampling pipeline 21.
[0029] Preferably, see Figure 1 , the outlet of the sampling electric control valve 1 is connected to a pipeline self-cleaning filter 3 through a booster pump 2. The outlet of the pipeline self-cleaning filter 3 is respectively connected to the inlet of the on-line alkalinity analyzer 4 and the inlet of the multi-parameter water quality sensor 5. Second drain valves 7 are provided at the outlets of the on-line alkalinity analyzer 4 and the multi-parameter water quality sensor 5, and the outlets are both connected to the control module through the booster pump 2 and the pipeline self-cleaning filter 3.
[0030] Preferably, see Figure 1 , the outlet of the pipeline self-cleaning filter 3 is also connected to the inlet of a first drain valve 8, and the first drain valve 8 is used for self-cleaning and draining of the pipeline self-cleaning filter 3.
[0031] Preferably, an inlet and outlet differential pressure sensor is provided in the pipeline self-cleaning filter 3. When the differential pressure between the inlet and outlet is greater than the set value, the pipeline self-cleaning filter 3 starts automatic backwashing. The pipeline self-cleaning filter 3 can be backwashed regularly to wash the dirt deposited in the filter in the water sample clean, realizing automatic sewage discharge.
[0032] Preferably, referring to Figure 3 , there are two concentrated sulfuric acid dosing pumps, including a first concentrated sulfuric acid dosing pump 12 and a second concentrated sulfuric acid dosing pump 13. The outlets of both concentrated sulfuric acid dosing pumps are connected to the inlets of the electric control valves at the outlets of the concentrated sulfuric acid dosing pumps. The outlets of the electric control valves at the outlets of the concentrated sulfuric acid dosing pumps are used to connect to the circulating water pool 23, and the electric control valves at the outlets of the concentrated sulfuric acid dosing pumps are electrically connected to the control module.
[0033] Preferably, referring to Figure 3 , the connection ports of the outlets of the two electric control valves at the outlets of the concentrated sulfuric acid dosing pumps and the circulating water pool 23 are respectively located at both ends of the circulating water pool 23. This is convenient for quickly adjusting the alkalinity of the circulating water in the circulating water pool 23.
[0034] Preferably, referring to Figure 3 , the electric control valve at the outlet of the concentrated sulfuric acid dosing pump includes a first electric control valve 17 at the outlet of the concentrated sulfuric acid dosing pump and a second electric control valve 18 at the outlet of the concentrated sulfuric acid dosing pump.
[0035] Preferably, referring to Figure 3 , the outlet of the dilute sulfuric acid dosing pump 11 passes through the inlet of the electric control valve 16 at the outlet of the dilute sulfuric acid dosing pump. The outlet of the electric control valve at the outlet of the dilute sulfuric acid dosing pump is used to connect to the circulating water pipeline 22, and the electric control valve 16 at the outlet of the dilute sulfuric acid dosing pump is electrically connected to the control module.
[0036] This embodiment also discloses an intelligent control method for the alkalinity of circulating water in a thermal power plant. Based on the above intelligent control system for the alkalinity of circulating water in a thermal power plant, referring to Figure 4 , it includes the following steps: S1. Obtain historical and current water quality data. The circulating water data includes unit load and the alkalinity, pH value, water temperature, chloride ion content, conductivity, and cumulative acid addition amount of the circulating water. By updating the data in real time, the timeliness of the model input is ensured, and control deviation caused by data lag is avoided.
[0037] S2. Use the historical water quality data combined with the LSTM network prediction model to generate a dedicated control parameter library, which is convenient for quickly and accurately predicting the alkalinity of the circulating water.
[0038] S3. Based on the current water quality data and the exclusive control parameter library, obtain the predicted circulating water alkalinity, and guide the dynamic adjustment of the acid addition amount through the prediction results to avoid excessive acid addition (wasting chemicals) or insufficient acid addition (affecting water quality safety).
[0039] S4. Generate the acid addition demand based on the predicted circulating water alkalinity combined with the current water quality data, and obtain the concentrated sulfuric acid demand and demineralized water demand according to the acid addition demand, as follows: Generate the frequency of the acid addition pump and the opening degree of the electric regulating valve at the outlet of the concentrated sulfuric acid addition pump based on the predicted circulating water alkalinity combined with the current water quality data; Obtain the concentrated sulfuric acid demand, demineralized water demand, the opening degree of the electric regulating valve 9 at the concentrated sulfuric acid inlet, and the opening degree of the electric regulating valve 10 at the demineralized water inlet according to the acid addition demand.
[0040] The present invention can realize the intelligent regulation and real-time monitoring of the circulating water alkalinity, and can realize the accurate and rapid adjustment of the pH value of the circulating water.
[0041] Embodiment 2: With the maturity of industrial Internet of Things, edge computing and machine learning technologies, it becomes possible to construct an intelligent regulation system for circulating water alkalinity.
[0042] The present invention collects water quality data in real time through an online alkalinity analyzer (methyl orange method automatic titration device) and multi-parameter water quality sensors (pH, conductivity, temperature), and can construct a dynamic alkalinity prediction model in combination with environmental temperature and unit load parameters.
[0043] The present invention learns the historical data of the circulating water quality through an LSTM neural network, establishes a proprietary database, can perform global collaborative regulation, and can adapt to complex scenarios such as water source switching, seasonal changes, and frequent changes in unit load.
[0044] The present invention aims at the technical pain points of the industry, and proposes a method for regulating the circulating water alkalinity based on multi-modal data fusion and edge intelligent control. By constructing a "terminal-edge-cloud" collaborative architecture, it realizes high-precision prediction of alkalinity, adaptive acid addition control and full-cycle energy efficiency optimization, providing an innovative solution for water saving, consumption reduction, safe and economic operation of thermal power plants.
[0045] As Figure 1 shown, the intelligent sampling and analysis unit of the intelligent regulation system for the circulating water alkalinity of the thermal power plant of the present invention includes a sampling electric regulating valve 1, a pipeline booster pump 2, a pipeline self-cleaning filter 3, an online alkalinity analyzer 4, multi-parameter water quality sensors 5, a signal output module 6, a second blowdown valve 7, and a first blowdown valve 8.
[0046] Among them, the sampling electric control valve 1 is connected to the circulating water sampling pipeline and the inlet of the pipeline booster pump 2 through a pipeline; the outlet of the pipeline booster pump 2 is connected to the pipeline self-cleaning filter 3 through a pipeline; the outlet of the pipeline self-cleaning filter 3 is connected to the online alkalinity analyzer 4 and the multi-parameter water quality sensor 5 through a pipeline.
[0047] Specifically, when the intelligent sampling and analysis unit is connected to the circulating water sampling pipeline through a pipeline, the circulating water first enters the pipeline booster pump 2 through the sampling electric control valve 1, is boosted, and then enters the pipeline self-cleaning filter 3 through a pipeline. After filtering the suspended substances and other impurities in the circulating water in the pipeline self-cleaning filter 3, the circulating water is discharged through the second sewage discharge valve 7 after being analyzed and measured by the online alkalinity analyzer 4 and the multi-parameter water quality sensor 5. The analysis result of the online alkalinity analyzer 4, the conductivity, pH, and temperature signals obtained by the multi-parameter water quality sensor 5 are electrically connected to the edge control unit through the signal output module 6. The sampling interval is 5 min / time.
[0048] The pipeline self-cleaning filter 3 is provided with an inlet and outlet differential pressure sensor. When the inlet and outlet differential pressure is greater than the set value, the self-cleaning filter can be automatically backwashed, and the pollutants intercepted in the filter are discharged through the first sewage discharge valve 8.
[0049] As Figure 2 shown, it is the edge control unit of the circulating water alkalinity intelligent regulation system of the present invention, including the hardware module 19 of the edge control unit and the LSTM network prediction software module 20.
[0050] Specifically, when the intelligent sampling and analysis unit is electrically connected to the industrial-grade PLC input module of the hardware module 19 of the edge control unit in real time, the LSTM network prediction model of the LSTM network prediction software module 20 can adjust and control the concentrated sulfuric acid dilution concentration, acid addition amount, and control the acid addition pump frequency in real time, so as to achieve precise control of the circulating water alkalinity.
[0051] The industrial-grade PLC can accurately control the opening degree of the electric control valve and the frequency of the acid addition pump.
[0052] The LSTM network prediction model can generate a dedicated control parameter library through training of the historical water quality data of the circulating water, and collect real-time (5 min / time) alkalinity (mmol / L), pH value, water temperature (°C), Cl - (mg / L), conductivity (μs / cm), unit load (MW), cumulative acid addition amount (L / h), etc. data, and can predict the alkalinity of the circulating water in the next 15 minutes, and can display the change trend of the alkalinity (rising / stable / falling probability distribution).
[0053] As Figure 3As shown in the figure, it is the step - by - step acid addition unit of the intelligent control system for the alkalinity of circulating water in a thermal power plant of the present invention, including an electric regulating valve 9 for concentrated sulfuric acid inlet, an electric regulating valve 10 for demineralized water inlet, a dilute sulfuric acid addition pump 11, a first concentrated sulfuric acid addition pump 12, a second concentrated sulfuric acid addition pump 13, a sulfuric acid dilution tank 14, a control module 15 of the dilution and preparation module, an electric regulating valve 16 at the outlet of the dilute sulfuric acid addition pump, an electric regulating valve 17 at the outlet of the first concentrated sulfuric acid addition pump, and an electric regulating valve 18 at the outlet of the second concentrated sulfuric acid addition pump.
[0054] Among them, the electric regulating valve 9 for concentrated sulfuric acid inlet is connected to the outlet of the concentrated sulfuric acid (98%) tank configured in the thermal power plant through a pipeline. The electric regulating valve 10 for demineralized water inlet is connected to the demineralized water tank of the thermal power plant through a pipeline and is also connected to the sulfuric acid dilution tank 14 through a pipeline. The valve opening can be adjusted according to the instructions of the control module 15 of the dilution and preparation module to configure sulfuric acid with different concentration gradients (dilute sulfuric acid or concentrated sulfuric acid). The outlet of the sulfuric acid dilution tank 14 is connected to the dilute sulfuric acid addition pump 11, the first concentrated sulfuric acid addition pump 12, and the second concentrated sulfuric acid addition pump 13 through pipelines. The outlets of the first concentrated sulfuric acid addition pump 12 and the second concentrated sulfuric acid addition pump 13 are connected to the circulating water pool through pipelines, which are the main acid addition points. The outlet of the dilute sulfuric acid addition pump 11 is connected to the circulating water outlet pipeline, which is the auxiliary acid addition point.
[0055] The main acid addition points bear 80% - 90% of the main acid addition amount, and the auxiliary acid addition point is for dynamic compensation and bears 20% of the acid addition amount.
[0056] The control module 15 of the dilution and preparation module receives the instruction of the total acid addition amount from the edge control unit and adjusts the opening degrees of the electric regulating valve 16 at the outlet of the dilute sulfuric acid addition pump, the electric regulating valve 17 at the outlet of the first concentrated sulfuric acid addition pump, and the electric regulating valve 18 at the outlet of the second concentrated sulfuric acid addition pump. Among them, the electric regulating valve 17 at the outlet of the first concentrated sulfuric acid addition pump and the electric regulating valve 18 at the outlet of the second concentrated sulfuric acid addition pump are for coarse adjustment, and the electric regulating valve 16 at the outlet of the dilute sulfuric acid addition pump is for fine adjustment, which can achieve precise control of the circulating water acid addition amount.
[0057] The present invention adopts modular assembly, mainly including an intelligent sampling and testing unit, a grading acid addition unit, and an edge control unit. The intelligent sampling and testing unit includes an on-line alkalinity analyzer 4 (methyl orange method automatic titration device), a multi-parameter water quality sensor 5 (pH, conductivity, temperature), a pipeline booster pump 2, and a pipeline self-cleaning filter 3; the on-line alkalinity analyzer 4 samples at a high frequency of 5 minutes / time, can detect and analyze the alkalinity of the water sample in real time, and the alkalinity test accuracy is ±0.05 mmol / L; the multi-parameter water quality sensor 5 analyzes and detects the temperature, pH, and conductivity of the water sample at the same time; the self-cleaning filter can perform backwashing regularly to prevent the sampling pipe from being blocked. The grading acid addition unit includes a dilution and preparation module and 3 groups of distributed acid addition pumps (2-way circulating water tower pool + 1-way main circulating water pipeline), which can dilute the concentration of concentrated sulfuric acid and adjust the frequency of the acid addition pump according to the alkalinity and pH of the circulating water. The edge control unit includes an industrial-grade PLC + AI co-processor, an LSTM neural network prediction model, and a PID fuzzy control algorithm, which can fuse the water quality parameters, circulating water flow, ambient temperature, unit load and other parameters of the circulating water in real time to establish a dynamic alkalinity prediction model of the circulating water; a dedicated control database can be generated through the training of the historical operation data of the circulating water to achieve accurate prediction and control of the circulating water parameters; it supports cloud data access, constructs an "end-edge-cloud" architecture, and realizes diversified multi-terminal monitoring and control.
[0058] Embodiment 3: See Figures 1 to 3 , this embodiment discloses an intelligent regulation system for the alkalinity of circulating water in a thermal power plant, including an intelligent sampling and analysis unit, an edge control unit, and a grading acid addition unit.
[0059] The intelligent sampling and analysis unit includes a sampling electric control valve 1, a pipeline self-cleaning filter 3, a multi-parameter water quality sensor 5, an on-line alkalinity analyzer 4, and a signal output module 6; The sampling electric control valve 1 is connected to the circulating water sampling pipeline 21, and the sampling flow can be automatically adjusted through the sampling electric control valve 1; the pipeline self-cleaning filter 3 is connected to the sampling electric control valve 1 through a pipeline, and the pipeline self-cleaning filter 3 can perform backwashing regularly to wash away the dirt deposited in the pipeline self-cleaning filter 3 in the water sample, realizing automatic sewage discharge; the multi-parameter water quality sensor 5 is installed in the sampling flow-through pool, and can test and analyze parameters such as the pH, conductivity, and temperature of the circulating water, and then is connected to the edge control unit through the signal output module 6; the on-line alkalinity analyzer 4 is connected to the sampling pipeline through a sampling pipeline, can detect and analyze the alkalinity of the water sample in real time, and transmit the test data to the edge control unit.
[0060] The described edge control unit includes an industrial-grade PLC + AI coprocessor and an LSTM neural network prediction model. The industrial-grade PLC mainly includes: a processor, an I / O module, and a real-time control layer; the AI coprocessor module mainly includes: hardware configuration and software stack; the design of the LSTM neural network prediction module mainly includes network structure and model training and deployment.
[0061] The main processor of the PLC selects a dual-core Cortex-A9 processor (main frequency 1.2GHz) and is equipped with a real-time operating system; the I / O module includes analog input: 16 channels (4 - 20mA, supporting the access of pH, conductivity, temperature sensors, and alkalinity signal access), digital output: 8 channels (controlling the start and stop of the acid addition pump and the valve opening), communication interfaces: Profinet, ModbusTCP, OPCUA protocol stacks; the real-time control layer includes the execution of a basic PID control loop (100ms cycle) and a hardware watchdog circuit.
[0062] The AI coprocessor module mainly includes: hardware configuration and software stack. The hardware configuration mainly includes a computing power unit (384-core CUDA + 48 TensorCore), memory (8GB LPDDRx + 16GB eMMC), and an acceleration interface (integrated FPGA, enabling hardware acceleration of the LSTM network).
[0063] The design of the LSTM neural network prediction module mainly includes: network structure design and model training design. The network structure design has an input layer, an LSTM layer, and an output layer. The input layer mainly has inputs of alkalinity, pH, temperature, conductivity, unit load, ambient temperature, and cumulative acid addition amount, and can input test data in real time; the LSTM layer extracts data features and autonomously learns to establish a circulating water quality database; the output layer can output the predicted value of alkalinity and the probability distribution of the change trend in the next 15 minutes. The model training design has training data, online learning, and edge optimization functions. A historical database is established, which can store 100,000 sets of circulating water system operation data (water quality data, unit load, extreme weather and other working conditions), and a data augmentation mechanism is added; it is fine-tuned with the latest data every 24 hours, can update the model by storing data in real time, and performs model lightweight optimization.
[0064] The described acid addition unit with grading includes a dilution and preparation module and three groups of distributed acid addition pumps. The dilution and preparation module and the three groups of distributed acid addition pumps are connected by pipelines, and the pipeline interfaces adopt quick connectors. The dilution module includes the control module 15 of the dilution and preparation module and the sulfuric acid dilution tank 14. The control module 15 of the dilution and preparation module receives the acid addition pump frequency and the opening signal of the electric regulating valve input by the edge control unit; the dilution tank is connected to the concentrated sulfuric acid pipeline and the demineralized water pipeline, and there are electric regulating valves on both pipelines, and sulfuric acid solutions with different concentrations are diluted and configured according to the input signal of the edge control unit. The three groups of distributed acid addition pumps are divided into two coarse adjustment pumps and one fine adjustment pump. The two coarse adjustment valves are connected to the concentrated acid outlet pipeline of the dilution tank, and the acid addition point is in the circulating water pool; the one fine adjustment pump is connected to the dilute acid outlet pipeline of the dilution tank, and the acid addition point is in the circulating water outlet pipeline.
[0065] The object of the present invention is to provide an intelligent control device for the alkalinity of circulating water in a thermal power plant. This device adopts modularization, can adapt to different installation scenarios, and realizes dynamic prediction and precise control of alkalinity by integrating multi-modal data, establishing a data model learning, and an adaptive control algorithm, and constructing a "terminal-edge-cloud" collaborative architecture.
[0066] Embodiment 4: See Figures 1 to 3 , in the circulating water system of a 660MW thermal power plant, the intelligent control device for the alkalinity of circulating water described in the present invention is connected. This device adopts modular control, and each module is respectively connected to the corresponding system of the power plant. An anti-vortex sampling probe is set in the circulating water return pipeline, and the sampling pipeline is connected to the intelligent sampling and analysis unit; the acid addition unit with grading is connected to concentrated sulfuric acid (98%) and demineralized water, the main acid addition points are arranged at the two corners of the distribution trough in the circulating water pool, and the auxiliary acid addition points are arranged 2m downstream of the elbow of the circulating water outlet header. The edge control unit is electrically connected to the intelligent sampling unit and the acid addition unit with grading, and is connected to the chemical workshop control system of the power plant, and can collect circulating water and unit operation data.
[0067] See Table 1 for the control parameter range and sampling frequency set by the edge control unit module; Table 1. Control parameter range and sampling frequency:
[0068] The edge control unit continuously collects the circulating water quality and unit load data of the unit for 120 days (including operating conditions such as unit load adjustment start and stop and summer full load), sets the alkalinity value of the circulating water, and at the same time introduces the circulating water concentration ratio (k = Cl - 循环水 / Cl - 补水As a derivative feature, the differential processing is performed on the unit load change rate. The dynamic acid addition strategy is adopted, and the flow rate ratio of the concentrated sulfuric acid addition pump and the dilute sulfuric acid addition pump is automatically adjusted with the circulating water flow rate. During the load fluctuation period, the response speed of the dilute sulfuric acid addition pump is increased to 500 ms / time; at the same time, it has the multi-parameter fusion function. When the conductivity of the circulating water suddenly increases, the model automatically reduces the upper limit of the alkalinity control to prevent scaling.
[0069] The intelligent control device for the alkalinity of circulating water described in the present invention is put into operation after debugging. The specific steps are as follows: The edge control unit is powered on. After collecting the historical operation data, local training is carried out, and at the same time, the control parameter range and the sampling frequency are set. After issuing an instruction, the sampling electric control valve 1 is automatically opened, and the water sample is boosted to about 0.2 Mpa by the pipeline booster pump 2. After passing through the pipeline self-cleaning filter 3 and being filtered, it is measured and analyzed by the on-line alkalinity analyzer 4 and the multi-parameter water quality sensor 5, and then the signal output module 6 transmits it to the edge control unit, with a sampling frequency of once every 5 minutes.
[0070] According to the data model and the actual measured value of the alkalinity, the edge control unit predicts the alkalinity of the circulating water in the next 10 minutes, calculates the acid addition amount, and issues an instruction to the hierarchical acid addition unit. The concentrated sulfuric acid inlet electric control valve 9 and the demineralized water inlet electric control valve 10 are automatically opened, and at the same time, they enter the sulfuric acid dilution tank 14 to configure sulfuric acid solutions with different concentrations. Through the control module 15 of the dilution and preparation module, the first concentrated sulfuric acid addition pump 12 and the second concentrated sulfuric acid addition pump 13 are started, and the outlet electric control valve 17 of the first concentrated sulfuric acid addition pump and the outlet electric control valve 18 of the second concentrated sulfuric acid addition pump are opened, and adjusted to appropriate frequencies and openings; at the same time, the dilute sulfuric acid addition pump 11 is started and the outlet electric control valve 16 of the dilute sulfuric acid addition pump is opened, and adjusted to appropriate frequencies and openings. The acid addition amount to the circulating water is accurately controlled.
[0071] Test data under typical working conditions: For the first working condition, the summer full-load test is carried out at an ambient temperature of 38 °C. In the full-load operation condition of the unit, the control accuracy of the circulating water alkalinity is ±0.01 mmol / L. For relevant parameters, see Table 2; Table 2. Control parameter table of the circulating water alkalinity in the full-load operation condition of the unit:
[0072] For the first working condition, the load mutation response test is carried out with a change from 500 MW to 620 MW. For relevant parameters, see Table 3; Table 3. Control parameter table of the circulating water alkalinity in the dynamic load operation condition of the unit:
[0073] The edge control unit predicts the upward trend of the circulating water alkalinity 2 minutes in advance and increases the acid addition amount in advance. The peak value of the circulating water alkalinity only rises to 8.12 mmol / L and then returns to the set value within 10 minutes.
[0074] The present invention can realize the intelligent regulation of the circulating water alkalinity without manual intervention. The alkalinity fluctuation range is controlled within ±0.05 mmol / L. At the same time, compared with the traditional acid addition method, the acid addition amount is reduced, which has certain economic benefits.
[0075] The above content is only to illustrate the technical idea of the present invention and cannot be used to limit the protection scope of the present invention. Any modification made on the basis of the technical solution according to the technical idea proposed by the present invention falls within the protection scope of the present invention.
Claims
1. The intelligent control system for the alkalinity of circulating water in a thermal power plant is characterized in that, Including: A sampling electric control valve (1), the inlet of the sampling electric control valve (1) is used to connect to a circulating water pipeline (22), the outlet of the sampling electric control valve (1) is respectively connected to the inlet of an on-line alkalinity analyzer (4) and the inlet of a multi-parameter water quality sensor (5), and the multi-parameter water quality sensor (5) is used to obtain the conductivity, pH value and water temperature of the circulating water; A sulfuric acid dilution tank (14), the inlet of the sulfuric acid dilution tank (14) is connected to a concentrated sulfuric acid inlet electric control valve (9) and a demineralized water inlet electric control valve (10), the outlet of the sulfuric acid dilution tank (14) is respectively connected to the inlet of a dilute sulfuric acid adding pump (11) and the inlet of at least one concentrated sulfuric acid adding pump, the outlet of the concentrated sulfuric acid adding pump is used to connect to a circulating water tank (23), and the outlet of the dilute sulfuric acid adding pump (11) is used to connect to the circulating water pipeline (22); A control module, the control module is electrically connected to the sampling electric control valve (1), the on-line alkalinity analyzer (4), the multi-parameter water quality sensor (5), the concentrated sulfuric acid inlet electric control valve (9), the demineralized water inlet electric control valve (10), the dilute sulfuric acid adding pump (11) and the concentrated sulfuric acid adding pump.
2. The intelligent control system for the alkalinity of circulating water in a thermal power plant according to claim 1, wherein The inlet of the sampling electric control valve (1) is connected to the circulating water pipeline (22) through a circulating water sampling pipeline (21).
3. The intelligent control system for the alkalinity of circulating water in a thermal power plant according to claim 1, characterized in that The outlet of the sampling electric control valve (1) is connected to a pipeline self-cleaning filter (3) through a booster pump (2), the outlet of the pipeline self-cleaning filter (3) is respectively connected to the inlet of the on-line alkalinity analyzer (4) and the inlet of the multi-parameter water quality sensor (5), second drain valves (7) are provided at the outlets of the on-line alkalinity analyzer (4) and the multi-parameter water quality sensor (5), and the outlets are both connected to the control module through the booster pump (2) and the pipeline self-cleaning filter (3).
4. The intelligent regulation system for the alkalinity of circulating water in a thermal power plant according to claim 3, wherein, The outlet of the pipeline self-cleaning filter (3) is also connected to the inlet of a first drain valve (8).
5. The intelligent control system for the alkalinity of circulating water in a thermal power plant according to claim 3, wherein An inlet and outlet differential pressure sensor is provided in the pipeline self-cleaning filter (l), and when the inlet and outlet differential pressure is greater than a set value, the pipeline self-cleaning filter (3) starts automatic backwashing.
6. The intelligent regulation system for the alkalinity of circulating water in a thermal power plant according to claim 1, wherein There are two concentrated sulfuric acid adding pumps, the outlets of the two concentrated sulfuric acid adding pumps are both connected to the inlet of a concentrated sulfuric acid adding pump outlet electric control valve, the outlet of the concentrated sulfuric acid adding pump outlet electric control valve is used to connect to the circulating water tank (23), and the concentrated sulfuric acid adding pump outlet electric control valve is electrically connected to the control module.
7. The intelligent regulation system for the alkalinity of circulating water in a thermal power plant according to claim 6, characterized in that, The connection ports of the outlets of the two concentrated sulfuric acid adding pump outlet electric control valves to the circulating water tank (23) are respectively located at both ends of the circulating water tank (23).
8. The intelligent control system for the alkalinity of circulating water in a thermal power plant according to claim 1, wherein The outlet of the dilute sulfuric acid adding pump (11) passes through the inlet of a dilute sulfuric acid adding pump outlet electric control valve (16), the outlet of the dilute sulfuric acid adding pump outlet electric control valve is used to connect to the circulating water pipeline (22), and the dilute sulfuric acid adding pump outlet electric control valve (16) is electrically connected to the control module.
9. The intelligent regulation method for the alkalinity of circulating water in a thermal power plant, based on the intelligent regulation system for the alkalinity of circulating water in a thermal power plant according to any one of claims 1 to 8, is characterized in that, Including the following steps: Obtain historical and current water quality data, and the circulating water data includes unit load and the alkalinity, pH value, water temperature, chloride ion content, conductivity and cumulative acid addition amount of the circulating water; Generate a dedicated control parameter library by using historical water quality data combined with the LSTM network prediction model; Obtain the predicted circulating water alkalinity based on the current water quality data and the dedicated control parameter library; Generate the acid addition demand based on the predicted circulating water alkalinity combined with the current water quality data, and obtain the concentrated sulfuric acid demand and demineralized water demand based on the acid addition demand.
10. The intelligent control method for the alkalinity of circulating water in a thermal power plant according to claim 9, characterized in that, The generation of the acid addition demand based on the predicted circulating water alkalinity combined with the current water quality data, and the obtaining of the concentrated sulfuric acid demand and demineralized water demand based on the acid addition demand are specifically as follows: Generate the frequency of the acid addition pump and the opening degree of the electric control valve at the outlet of the concentrated sulfuric acid addition pump based on the predicted circulating water alkalinity combined with the current water quality data; Obtain the concentrated sulfuric acid demand, demineralized water demand, the opening degree of the electric control valve (9) at the concentrated sulfuric acid inlet, and the opening degree of the electric control valve (10) at the demineralized water inlet based on the acid addition demand.