Scar cleaning decision optimization method and system for aluminum oxide evaporator and medium

Abstract

The invention discloses a scab cleaning decision optimization method and system for an aluminum oxide evaporator and a medium, and relates to the technical field of decision optimization. The method comprises the following steps: determining a precipitation rate model and a re-diffusion rate model of the aluminum oxide evaporator, and establishing a scabbing mechanism model based on the precipitation rate model and the re-diffusion rate model; a first evaporation income model with continuous time is established in combination with the scabbing mechanism model and preset cleaning and maintenance cost; converting the first evaporation income model into a periodic second evaporation income model; and dynamically solving the second evaporation model to obtain a target cleaning plan. By implementing the technical scheme provided by the invention, the operation efficiency and the economic benefit of the evaporator are improved.

Description

Technical Field

[0001] The present application relates to the technical field of decision optimization, and in particular to a method, system and medium for optimizing decision making for cleaning of a scab of an alumina evaporator. Background Art

[0002] In the alumina production process, the evaporator is a key equipment, and its heat transfer efficiency directly affects the energy consumption and cost of production. However, as the production progresses, the inner wall of the evaporator will gradually form scars (scaling) composed of substances such as silicates and sodium salts, which not only reduces the heat transfer efficiency, but also increases the frequency and cost of equipment maintenance.

[0003] Traditional cleaning methods are usually based on fixed cycles or empirical rules, lack of systematic and scientific basis, and often lead to excessive or insufficient cleaning, affecting production efficiency and economic benefits. Therefore, there is an urgent need for a scientific and effective dynamic decision-making optimization method for cleaning the alumina evaporator, so as to improve the operating efficiency and economic benefits of the evaporator. Summary of the invention

[0004] The present application provides a method, system, medium and equipment for optimizing the decision of cleaning the scab of an alumina evaporator, thereby improving the operation efficiency and economic benefits of the evaporator.

[0005] In a first aspect, the present application provides a method for optimizing the decision-making of cleaning of alumina evaporator, the method comprising: Determining a precipitation rate model and a redispersion rate model of an alumina evaporator, and establishing a scarring mechanism model based on the precipitation rate model and the redispersion rate model; A time-continuous first evaporation benefit model is established in combination with the scarring mechanism model and the preset cleaning and maintenance cost; converting the first evaporation profit model into a periodic second evaporation profit model; The second evaporation model is dynamically solved to obtain a target cleaning plan.

[0006] By adopting the above technical scheme, a scaling mechanism model of the alumina evaporator is established through the precipitation rate model and the redistribution rate model, which can accurately describe the scaling formation mechanism inside the evaporator. On this basis, combined with the preset cleaning and maintenance costs, a time-continuous first evaporation benefit model is established, which is converted into a periodic second evaporation benefit model, and then the second evaporation benefit model is dynamically solved to finally obtain the optimal target cleaning plan for the alumina evaporator. Compared with the traditional empirical cleaning method, this technical scheme realizes the scientific optimization of the evaporator scaling cleaning plan, which can reduce the number of cleaning times and energy consumption, while improving the operating efficiency and economic benefits of the evaporator.

[0007] Optionally, the method for determining the precipitation rate model of the alumina evaporator comprises: Obtaining the fouling substance concentration at the interface between the deposition layer of the alumina evaporator and the heat exchanger, the temperature of the liquid-solid interface, and the concentration of the fouling substance at saturation; Determining the precipitation rate model based on the fouling material concentration at the interface between the sediment layer and the heat exchanger, the temperature of the liquid-solid interface, and the concentration of the fouling material at saturation; The precipitation rate model is: In the formula, is the precipitation rate, A′ is the Ahrendts constant, E is the activation energy, R T is the universal gas constant, T s is the temperature of the liquid-solid interface, C s is the fouling concentration at the interface between the deposition layer and the heat exchanger, C cat T s The concentration of scaling substances at lower saturation, n is the order of chemical reaction.

[0008] By adopting the above technical scheme, the concentration of fouling substances at the interface of the alumina evaporator heat exchanger, the temperature of the liquid-solid interface and the concentration of scaling substances at saturation are obtained. Based on these data, a precipitation rate model of scaling is established, which takes into account the influence of multiple factors such as interface concentration, temperature and saturation concentration on the precipitation rate.

[0009] By combining multiple parameters to establish a scaling mechanism model, the scaling generation and accumulation process can be predicted more accurately.

[0010] Optionally, determine the redispersion rate model for the alumina evaporator, including: Based on the friction coefficient of the alumina evaporator and the fluid density, the shear stress of the fluid on the solid surface is constructed; The shear stress is: In the formula, τ w is shear stress, f is friction coefficient, ρ is fluid density, and u is flow velocity; a redispersion rate model of an alumina evaporator is constructed based on the shear stress; The re-diffusion rate model is: is the redispersion rate, B0 is a preset constant, is the precipitation structure function.

[0011] By adopting the above technical scheme, a shear stress model of the fluid on the solid surface was constructed according to the friction coefficient and fluid density of the alumina evaporator, and further based on the shear stress model, a scaling redispersion rate model was established. The redispersion model takes into account the influence of the flow rate and friction of the fluid in the evaporator on the redispersion of scaling. Compared with the simple preset redispersion rate, this scheme reflects the redispersion mechanism model of the actual process conditions, can dynamically predict the scaling regrowth process, and more accurately describe the overall mechanism of scaling accumulation.

[0012] Optionally, the first evaporation benefit model with continuous time is established in combination with the scarring mechanism model and the preset cleaning and maintenance cost, including: Based on the scarring mechanism model and the parameters of the pipeline connecting the alumina evaporator, calculating the overall heat transfer coefficient of the alumina evaporator; Calculating a total heat transfer amount based on the total heat transfer coefficient; Based on the total heat transfer amount and the preset cleaning and maintenance cost, a time-continuous first evaporation profit model is established; The first evaporation profit model is: Among them, M n is the total revenue under plan n, T is the total time, Q t' is the total heat transfer at t', ΔH t' is the thermal enthalpy of water in the liquid, e is the revenue per ton of water, m is the number of cleanings, and w is the preset cleaning and maintenance cost.

[0013] By adopting the above technical solution, based on the pre-established scaling mechanism model and the parameters of the pipeline connecting the evaporator, the total heat transfer coefficient of the alumina evaporator is calculated, and on this basis, the total heat transfer is calculated, and combined with the preset cleaning and maintenance costs, a time-continuous first evaporation benefit model is established, which takes into account the comprehensive impact of scaling degree, heat transfer parameters and cleaning costs on evaporation benefits. Compared with the simple empirical preset benefit model, this solution, by combining scaling mechanism, heat transfer parameters and economic factors to establish the first evaporation benefit model, can more accurately describe the dynamically changing economic benefits during the evaporation process.

[0014] Optionally, the total heat transfer coefficient of the alumina evaporator is calculated based on the scarring mechanism model and the parameters of the pipeline connecting the alumina evaporator, including: Substituting the scarring mechanism model and the pipeline parameters of the alumina evaporator into the heat transfer coefficient calculation formula to obtain the total heat transfer coefficient of the alumina evaporator; The heat transfer coefficient calculation formula is: Among them, the K t' is the total heat transfer coefficient, α1 is the condensation convection heat transfer coefficient of steam, α2 is the falling film side convection heat transfer coefficient, λ bis the thermal conductivity of the pipe wall material, δ b is the tube wall thickness, R f (t') is the scarring mechanism model.

[0015] By adopting the above technical solution, the pre-established scaling mechanism model and evaporator pipeline parameters are substituted into the heat transfer coefficient calculation formula to calculate the total heat transfer coefficient of the alumina evaporator. This formula takes into account the condensation heat transfer coefficient, convection heat transfer coefficient, tube wall thermal conductivity, tube wall thickness and scaling mechanism model, and can accurately describe the impact of scaling degree on heat transfer performance. By combining the heat transfer calculation formula with multiple influencing factors, the heat transfer parameters that change during the scaling process can be dynamically calculated, thereby more accurately characterizing the heat transfer law.

[0016] Optionally, converting the first evaporation profit model into a periodic second evaporation profit model includes: dividing the time in the first evaporation profit model according to preset periods to obtain a plurality of fixed periods, and establishing a periodic second evaporation profit model; The second evaporation profit model is: Where c represents a fixed cycle number, and the cycle time range of c is from (c-1)T s +1 day to cT s Day, n c Indicates the cleaning plan for cycle number c, n c ∈{0,1,2,...,T s},u c is a label indicating whether the alumina evaporator is cleaned during this cycle, A is the heat transfer area, is the heat transfer temperature difference, ΔH is the thermal enthalpy of water in the liquid, is the scarring degree of the day in the cycle time numbered c, t'∈[1,T s ].

[0017] By adopting the above technical solution, the time in the first evaporation profit model is divided according to the preset period to obtain multiple fixed periods. Then, based on the fixed period, a periodic second evaporation profit model is established. The second profit model takes into account factors affecting the profit, such as the period number, the corresponding cleaning plan, the heat transfer parameters, and the degree of scaling. By establishing a periodic profit model, the impact of different cleaning plans in different periods on the evaporation profit can be quantitatively evaluated, and the infinite time domain problem can be converted into a solvable form.

[0018] Optionally, the dynamically solving the second evaporation model to obtain a target cleaning plan includes: Determining historical data of the alumina evaporator, and predicting a first cleaning plan corresponding to each cycle time in the entire cycle based on the historical data; Dynamically solving the second evaporation model and the second cleaning plan corresponding to each cycle time; Determine whether the first cleaning plan corresponding to each cycle time is consistent with the second cleaning plan; If they are consistent, the first cleaning plan is used as the target cleaning plan; If they are inconsistent, the second cleaning plan is used as the target cleaning plan.

[0019] By adopting the above technical solution, the first cleaning plan and the second cleaning plan corresponding to each cycle time are compared. If the two plans are consistent, it means that the historical experience and the current optimization results are consistent. At this time, the first cleaning plan is used as the target cleaning plan. In this case, the decision has a high degree of credibility because it conforms to historical rules and meets the current optimization requirements. If the two plans are inconsistent, the second cleaning plan is selected as the target cleaning plan because the second cleaning plan is based on the latest production data and optimization results and can better adapt to the current production status and market environment.

[0020] In a second aspect of the present application, a system for optimizing the decision-making of cleaning a scab of an alumina evaporator is provided, the system comprising: A scarring mechanism model building module is used to determine a precipitation rate model and a redispersion rate model of an alumina evaporator, and to build a scarring mechanism model based on the precipitation rate model and the redispersion rate model; A first revenue model establishment module, used to establish a time-continuous first evaporation revenue model in combination with the scarring mechanism model and the preset cleaning and maintenance cost; The second profit model establishment module is used to convert the first evaporation profit model into a periodic second evaporation profit model; the cleaning plan determination module is used to dynamically solve the second evaporation model to obtain a target cleaning plan.

[0021] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above method steps.

[0022] In a fourth aspect of the present application, an electronic device is provided, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: The present application establishes a scarring mechanism model of an alumina evaporator through a precipitation rate model and a rediffusion rate model, which can accurately describe the formation mechanism of scaling inside the evaporator. On this basis, combined with the preset cleaning and maintenance costs, a time-continuous first evaporation benefit model is established, which is converted into a periodic second evaporation benefit model, and then the second evaporation benefit model is dynamically solved to finally obtain the optimal target cleaning plan for the alumina evaporator. Compared with the traditional empirical cleaning method, the present technical solution realizes the scientific optimization of the evaporator scaling cleaning plan, which can reduce the number of cleaning times and energy consumption, while improving the operating efficiency and economic benefits of the evaporator. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flow chart of a method for optimizing the decision of cleaning alumina evaporator scars provided in an embodiment of the present application; Figure 2 This is a schematic diagram of a slow time-varying process of scarring provided in an embodiment of the present application; Figure 3 It is a schematic diagram of a decision optimization process within a scheduling cycle provided by an embodiment of the present application; Figure 4 It is a module schematic diagram of a scar cleaning decision optimization system for an alumina evaporator provided in an embodiment of the present application; Figure 5 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0025] Description of reference numerals: 500, electronic device; 501, processor; 502, communication bus; 503, user interface; 504, network interface; 505, memory. DETAILED DESCRIPTION

[0026] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0027] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0028] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0029] The following will provide a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0030] Please refer to Figure 1 , a flowchart of a method for optimizing the cleaning decision of alumina evaporator is proposed. The method can be implemented by a computer program, a single-chip microcomputer, or run on a system for optimizing the cleaning decision of alumina evaporator. The computer program can be integrated into a smart device or run as an independent tool application. Specifically, the method includes steps 10 to 40, and the steps are as follows: Step 10: Determine the precipitation rate model and redistribution rate model of the alumina evaporator, and establish a scarring mechanism model based on the precipitation rate model and the redistribution rate model.

[0031] In the present embodiment, the alumina evaporator refers to an evaporation device used in the alumina production process, and its main function is to concentrate the alumina solution. In this process, due to the increase in solution concentration and the changes in temperature and flow rate, substances such as silicon salts and sodium salts will precipitate from the solution and adhere to the inner wall of the evaporator to form scars.

[0032] In the embodiment of the present application, the precipitation rate model refers to the deposition rate of fouling substances on the heat exchange surface of the evaporator; the redispersion rate model in the embodiment of the present application refers to the rate at which deposited fouling substances fall off due to fluid flushing.

[0033] Specifically, scarring refers to hard solid substances attached to various production equipment. These scaling substances are attached to the surface of the equipment, which significantly reduces the heat transfer coefficient of the heat exchange equipment, reduces the effective heat transfer area of ​​the equipment, reduces the production capacity, and damages the equipment, affecting the stable operation of the process. Therefore, the embodiment of the present application establishes a scarring mechanism model, the purpose of which is to provide a theoretical basis for subsequent optimization decisions, so that cleaning decisions can be more accurate and efficient. First, the relevant parameters of the alumina evaporator are obtained, including the concentration of fouling substances at the interface between the deposition layer and the heat exchanger, the temperature of the liquid-solid interface, and the concentration of scaling substances at saturation, and then a precipitation rate model is established based on these parameters. Next, in order to describe the shedding process of deposited fouling substances, this embodiment constructs a redispersion rate model, based on the friction coefficient and fluid density of the alumina evaporator, a shear stress model of the fluid on the solid surface is constructed, and then a redispersion rate model is constructed based on the shear stress. Finally, based on the precipitation rate model and the redispersion rate model, a scarring mechanism model is established. The scarring mechanism model established in this way can more accurately reflect the formation and change process of scarring on the inner wall of the alumina evaporator.

[0034] During the evaporation of alumina, as the concentration of the solution increases and the temperature and flow rate change, substances such as silicon salts and sodium salts precipitate from the solution and adhere to the inner wall of the evaporator, gradually forming hardened scars. The formation of scale can be divided into two parts: deposition and removal. On the one hand, the fouling substances in the logistics will be deposited on the heat exchange surface, and on the other hand, the fouling substances will also fall off due to the scouring of the logistics fluid. Therefore, the net scaling rate can be expressed as the difference between the precipitation rate and the redistribution rate. The net scaling rate is: In the formula is the precipitation rate, is the redispersion rate, the dirt precipitation rate It is related to factors such as liquid-solid interface temperature and precipitation formation, and the diffusion rate It is related to factors such as the viscosity of the dirt, the flow velocity in the pipe, and the shear force.

[0035] like Figure 2 As shown, it is a schematic diagram of a slow time-varying process of scarring provided in an embodiment of the present application, such as Figure 2 As shown, it can be observed from the curve that the scaling rate shows a trend of slow change over time, especially in the early stage of the curve, the scaling process is relatively slow and stable. This phenomenon shows that the scaling process has significant slow time-varying characteristics; the volatility of the curve reflects the dynamic balance of the precipitation and redistribution processes. While the scaling material is deposited, it will also be partially shed due to the scouring of the fluid. The net scaling rate is determined by the difference between the precipitation rate and the redistribution rate; in the initial stage of the evaporator operation, the scaling material accumulates slowly, and the slope of the curve is small, indicating that the scaling rate is low; the obvious drop point in the middle of the curve represents a cleaning process, which removes a large amount of scaling material, resulting in an instantaneous reduction in the amount of scaling.

[0036] Based on the above embodiment, as an optional embodiment, the step of determining the precipitation rate model of the alumina evaporator may further include the following steps: Step 1011: Obtain the fouling substance concentration at the interface between the deposition layer of the alumina evaporator and the heat exchanger, the temperature of the liquid-solid interface, and the concentration of the fouling substance at saturation.

[0037] Specifically, a variety of methods can be used to comprehensively obtain these parameters. The concentration of fouling substances at the interface between the deposition layer and the heat exchanger can be measured in real time by an online monitoring system. This system can use conductivity or optical sensors, installed at key positions of the evaporator, to continuously monitor the changes in the concentration of fouling substances at the interface. The temperature of the liquid-solid interface can be measured by thermocouples or infrared temperature sensors, which can be arranged at multiple positions on the inner wall of the evaporator to obtain more comprehensive temperature distribution data. The concentration of scaling substances at saturation can be obtained by laboratory analysis or by consulting relevant physical property databases, or by theoretical calculation by establishing a material balance model. In order to improve the accuracy and reliability of parameter acquisition, this embodiment adopts data fusion technology. The data from different sensors and measurement methods are comprehensively analyzed, and algorithms such as Kalman filtering are used to eliminate noise and outliers, so as to obtain more accurate parameter estimates. At the same time, considering the dynamic characteristics of the evaporation process, this embodiment also introduces an adaptive sampling strategy. In the stage where the scarring speed is faster, the sampling frequency is increased; in the stage where the scarring speed is slower, the sampling frequency is appropriately reduced, which not only ensures the timeliness of the data, but also avoids the generation of redundant data.

[0038] Step 1012: Determine a precipitation rate model based on the fouling substance concentration at the interface between the sediment layer and the heat exchanger, the temperature of the liquid-solid interface, and the concentration of the fouling substance at saturation.

[0039] Specifically, this embodiment uses a method combining the Alenius equation and mass transfer theory to construct a precipitation rate model. First, considering that the scaling process is essentially a chemical reaction, its rate is closely related to temperature and concentration. Therefore, the Alenius equation is introduced to describe the effect of temperature on the reaction rate. At the same time, considering the mass transfer process of scaling substances from the solution to the solid surface, the concentration difference term is introduced to describe the mass transfer driving force. Combining these factors, the expression of the precipitation rate model is obtained. First, according to the physical and chemical transport law, it can be known that: From the Arenius theorem, we know that K r =A′exp-(E / R T T S ), combining the above two formulas, we can get the precipitation rate model: In the formula, is the precipitation rate, A′ is the Ahrendts constant, E is the activation energy, R T is the universal gas constant, T s is the temperature of the liquid-solid interface, C s is the fouling concentration at the interface between the deposition layer and the heat exchanger, C cat T s The concentration of scaling substances at lower saturation, n is the order of chemical reaction.

[0040] Based on the above embodiment, as an optional embodiment, the step of determining the redispersion rate model of the aluminum oxide evaporator may further include the following steps: Step 1021: Based on the friction coefficient of the alumina evaporator and the fluid density, construct the shear stress of the fluid on the solid surface.

[0041] Specifically, this embodiment adopts the theory of fluid mechanics, combined with the special working conditions of the alumina evaporator, to establish a shear stress model. First, the friction coefficient and fluid density of the alumina evaporator are obtained. The friction coefficient can be obtained by experimental measurement or consulting relevant literature. It is related to factors such as the roughness of the inner wall of the evaporator and the viscosity of the fluid. The fluid density can be measured in real time by an online density meter, or obtained by table interpolation based on temperature and concentration. Next, the fluid flow rate is introduced. This parameter can be measured and converted by a flow meter. Based on these parameters, a shear stress model is constructed. The shear stress (N / m2) of the fluid on the solid surface is related to the Reynolds number of the fluid and the roughness of the wall, that is: τ w is shear stress, friction coefficient f=0.0792Re -0.25 , ρ is the density of the fluid, and u is the flow velocity.

[0042] Step 1022: Construct a redispersion rate model of the alumina evaporator based on shear stress.

[0043] Specifically, the dirt is removed by the scouring of the logistics fluid. The shearing effect at the heat exchange surface during the removal process is related to the structural function ψ of the sediment. is the redispersion rate, and B0 is a preset constant.

[0044] Among them, when is a time-independent constant, With R f The net scaling rate can be expressed as: When the boundary condition t=0, R f =0, integrating both ends yields the asymptotic relationship: From the above analysis, we can see that the steady-state asymptotic value R * The temperature of the liquid-solid interface is T SPositively correlated, τ=Ψ / B0τ w It is negatively correlated with the fluid flow rate u. Therefore, the scarring mechanism model of the evaporation process can be described as follows: Where k1, k2, and k3 are constants related to the properties of steam and feed liquid; C(t) represents the concentration of the feed liquid, and G(t) and θ(t) represent the flow rate and temperature of the steam.

[0045] Step 20: Establish a time-continuous first evaporation benefit model by combining the scarring mechanism model and the preset cleaning and maintenance costs.

[0046] Specifically, cleaning the evaporator can improve the heat transfer efficiency of the evaporation process, but cleaning will also incur labor costs. For the same evaporator, it is generally believed that the cleaning workload and difficulty are fixed over a relatively long period of time. Therefore, it can be assumed that the single cleaning and maintenance cost of this evaporator is a fixed value within a certain planning period, that is, the preset cleaning and maintenance cost, represented by w; assume that the profit for each ton of water evaporated is e. For an evaporation system, the net profit within a certain time range can be expressed as the profit of evaporated water minus the cleaning cost. First, it is necessary to calculate the total heat transfer coefficient of the alumina evaporator based on the scarring mechanism model and the parameters of the pipeline connecting the alumina evaporator, and then calculate the total heat transfer based on the total heat transfer coefficient. Finally, based on the total heat transfer and the preset cleaning and maintenance cost, a time-continuous first evaporation profit model is established.

[0047] By establishing the first evaporation benefit model, the scarring mechanism model can be directly linked to the economic benefits, so that the cleaning decision can be based on a solid theoretical foundation. Secondly, by introducing mechanisms such as dynamic pricing and fuzzy cost, the model has strong adaptability and robustness, and can cope with various uncertainties in actual production.

[0048] Based on the above embodiment, as an optional embodiment, the step of establishing a time-continuous first evaporation benefit model in combination with the scarring mechanism model and the preset cleaning and maintenance cost may further include the following steps: Step 201: Calculate the total heat transfer coefficient of the alumina evaporator based on the scarring mechanism model and the parameters of the pipeline connecting the alumina evaporator.

[0049] Specifically, the embodiment of the present application adopts the thermal resistance series model in the heat transfer theory, and combines the special working conditions of the alumina evaporator to establish a total heat transfer coefficient calculation model. The heat transfer coefficient of the falling film evaporator is an important parameter to measure the production performance of the evaporator, which refers to the amount of heat passing through a unit area per unit time. In addition to being related to the structure of the evaporator equipment itself, the evaporator heat transfer coefficient is also affected by the material's own property parameters, such as viscosity, density, tension, liquid film thickness, etc. Changes in many process control parameters will also cause changes in the total heat transfer coefficient, such as effective temperature difference, feed liquid flow rate, etc.

[0050] First, obtain the pipe parameters connecting the alumina evaporator, including the thermal conductivity of the wall material and the wall thickness. These parameters can be directly obtained from the equipment design specifications. Next, estimate the condensation convection heat transfer coefficient of the steam and the falling film side convection heat transfer coefficient through online monitoring or empirical models. Then, obtain the scarring thermal resistance from the previously established scarring mechanism model. Based on these parameters, substitute them into the heat transfer coefficient calculation formula to obtain the total heat transfer coefficient of the alumina evaporator. The heat transfer coefficient calculation formula is: Among them, K t' is the total heat transfer coefficient, α1 is the condensation convection heat transfer coefficient of steam, α2 is the falling film side convection heat transfer coefficient, λ b is the thermal conductivity of the pipe wall material, δ b is the tube wall thickness, R f (t') is the scarring mechanism model. f Here we only consider the relationship between the thermal resistance of scarring and time, and the other parameters are determined according to the material of the evaporator.

[0051] Step 202: Calculate the total heat transfer amount based on the total heat transfer coefficient.

[0052] Specifically, for the total heat transfer, according to the heat exchange principle, it can be obtained by multiplying the heat transfer coefficient, the heat transfer area and the heat transfer temperature difference: Q t' =K t' AΔt t' , where Q t' is the total heat transfer at t', ΔH t' is the thermal enthalpy of water in the liquid, and A is the heat transfer area.

[0053] Step 203: Based on the total heat transfer amount and the preset cleaning and maintenance cost, a time-continuous first evaporation profit model is established.

[0054] Specifically, the embodiment of the present application adopts the net present value theory and combines the characteristics of alumina evaporation production to construct a time-continuous first evaporation income model: Where M n is the total revenue under plan n, T is the total time, Q t' is the total heat transfer at t', ΔH t' is the enthalpy of water in the feed liquid, e is the revenue per ton of water, m is the number of cleanings, and w is the preset cleaning maintenance cost. The model comprehensively considers the revenue and cleaning costs of evaporation production, and can intuitively reflect the long-term economic benefits under different cleaning strategies.

[0055] Step 30: Convert the first evaporation profit model into a periodic second evaporation profit model.

[0056] Specifically, when scheduling the cleaning operation of the alumina evaporator, first in the first time period, that is, from t = 1 to t = T s The optimization decision is made within the time range of the previous cleaning, and then the optimization decision is transferred to the next cycle until the entire time range for cleaning optimization is completed. It is worth noting that each cycle here is fixed, rather than sliding forward every day. This design is to better utilize the feature that the prediction accuracy will improve over time. For the rolling cycle strategy, every time a cleaning decision is made, the window rolls forward, and the length of the time range to be optimized does not change. For the time range to be optimized, the overall prediction accuracy has not improved because new and more distant dates are added. If a fixed cycle is selected, for a certain scheduling cycle, as time goes by, we are getting closer and closer to all future dates, and the prediction information is getting more and more accurate; for the dates that have passed, more and more historical data can be obtained, and the historical data is absolutely accurate and there is no prediction error. In other words, as this fixed cycle becomes more and more understood, the decisions made will become more optimized as uncertainty decreases and certain information accumulates.

[0057] This embodiment adopts the discretization and period division method, combined with the actual operation characteristics of alumina evaporation production, to construct a periodic profit model. First, according to production practice and management requirements, the appropriate decision cycle length is determined, and the continuous time in the first evaporation profit model is divided into multiple fixed cycles according to the preset cycle. Use c (c = 1, 2, ... C) to represent each fixed cycle number. The period numbered c includes the time range from (c-1)T s +1 day to cT s Days. Therefore, the degree of scarring each day can be expressed by a periodic symbol: R f (t') = R f ((c-1)T s +t'),t'∈[1,T s ]. The heat transfer coefficient and heat transfer temperature difference can also be expressed using periodic symbols, respectively and According to the actual operation and maintenance needs of the on-site evaporation station, for a 15-day cycle design, an evaporator will be cleaned at most once in a cycle, or it will not be cleaned at all. Cleaning twice or more in a cycle can be directly judged as unreasonable based on experience, and the efficiency loss reduced by cleaning is far from making up for such a high-frequency cleaning cost. Therefore, the cleaning schedule n for the cycle numbered c can be simplified to: n c (n c ∈{0,1,2,...,T s}). It indicates the number of the cleaning date. c = 0 means that this evaporator will not be scheduled for cleaning during this cycle. Based on this, the equation for the degree of scarring on each day in cycle c can be simplified to the following periodic form: If n c ≠0: otherwise: If the decision for the evaporator in this fixed cycle is to clean it, that is, n c ≠0, then from t=(c-1)T s +1 to t = cT s The time period between the two is divided into two parts by the cleaning date. The scar status on the cleaning day is The scarring degree on the last day of the cycle before this cycle was This scarring degree is also the starting scarring degree of this cycle. If the evaporator is not cleaned during this scheduling cycle, that is, n c = 0, then the scar will continue to accumulate during this period. c The net income in the scheduling period c, that is, the second evaporation income model is: Where c represents a fixed cycle number, and the cycle time range of c is from (c-1)T s +1 day to cT s Day, n c Indicates the cleaning plan for cycle number c, n c ∈{0,1,2,...,T s},u c is a label indicating whether the alumina evaporator is cleaned during this cycle, A is the heat transfer area, is the heat transfer temperature difference, ΔH is the thermal enthalpy of water in the liquid, is the scarring degree of the day in the cycle time numbered c, t'∈[1,T s ].

[0058] For an evaporation station in actual operation, if cleaning is to be performed, it is often necessary to make a decision and make reservations in advance to prepare. c (T c <T s ) is the shortest time that needs to be booked in advance, so this brings a constraint to the cleaning schedule, called the preparation constraint, which is expressed as follows: n c ∈{T c ,T c +1,...,Ts} However, the net income within a cycle cannot be Directly as the optimization target of evaporation scar cleaning. Because the scarring process is continuous, although the cleaning cycle is divided, the scarring process is not independent. When deciding whether to perform scar cleaning in an optimization cycle, the effect of the cleaning behavior is not limited to this cycle. Its effect will persist. As described in the above formula, the initial scarring degree of the cleaning cycle numbered c is It is actually the ending scarring degree of the previous cycle (number c-1). The scar cleaning of this cycle will affect the initial scarring degree of the next cycle, which is a fact that cannot be changed by further decision-making in the next cycle. Therefore, the decision of one cycle will restrict the optimization range of the next cycle. Since this association exists between every two consecutive cycles, when making a decision for a certain cycle, its impact on the next cycle must be considered. That is, the heat transfer efficiency brought by the initial scarring degree of the current cycle is calculated, and the historical expected values ​​are used for the heat transfer temperature difference, the thermal enthalpy of the feed liquid, and the cleaning schedule, so that overall optimization is achieved between all cycles. Therefore, the economic benefit brought by the initial scarring degree of the current cycle is defined as: In summary, the decision optimization objective function for the cleaning cycle c can be modeled as:

[0059] Step 40: Dynamically solve the second evaporation model to obtain a target cleaning plan.

[0060] Specifically, since the decision is made in the early stage of the cycle, the data for the latter part of the cycle is unknown, so the Transformer model is used in the embodiment of the present application to predict future data. Based on the previously constructed optimization model, at the beginning of the scheduling cycle, an optimized cleaning strategy for the entire cycle is formulated based on current information and predicted information, which is called a "preliminary plan". As time goes by, at the end of the next day, the operating conditions, heat transfer temperature difference, and enthalpy of the material fluid of the previous day become fixed historical data. As the time span of the remaining days shortens, the model is able to obtain more accurate prediction data. With the update of historical and predicted data, there is an opportunity to review and optimize the cleaning strategy. If the optimized strategy is consistent with the "preliminary plan" formulated previously, the original plan will continue to be executed. However, if there is a deviation, considering that the new strategy is based on more accurate data, it should be more favorable in terms of probability, so it makes sense to adjust to this new strategy. This daily review and adjustment process will continue until one of the predetermined end conditions is reached. In this way, it can be ensured that the cleaning strategy remains optimal throughout the cycle while adapting to various changes that may occur in actual operations.

[0061] In a feasible embodiment, the present embodiment first determines the historical data of the alumina evaporator, including but not limited to the relevant information such as the past scarring speed, cleaning frequency, production load, environmental conditions, etc. Based on these historical data, a machine learning algorithm (such as a long short-term memory network LSTM or a random forest, etc.) is used to build a prediction model to predict the first cleaning plan corresponding to each cycle time in the entire cycle. This prediction process takes into account long-term trends such as seasonal changes and equipment aging, and provides a reference benchmark based on historical experience for cleaning decisions. At the same time, the present embodiment dynamically solves the second evaporation model to obtain the second cleaning plan corresponding to each cycle time. This process uses real-time collected production data, such as the current scarring status, production load, market demand, etc., to determine the optimal cleaning time by solving the optimization problem. Compare the first cleaning plan and the second cleaning plan corresponding to each cycle time. If the two plans are consistent, it means that the historical experience and the current optimization results are consistent. At this time, the first cleaning plan is used as the target cleaning plan. In this case, the decision has a high degree of credibility because it conforms to historical laws and meets the current optimization requirements. If the two plans are inconsistent, the second cleaning plan is selected as the target cleaning plan because the second cleaning plan is based on the latest production data and optimization results and can better adapt to the current production conditions and market environment.

[0062] like Figure 3 As shown, it is a schematic diagram of a decision optimization process within a scheduling cycle provided by an embodiment of the present application, comprising Figure 3 It can be seen that in the decision preparation stage, if the decision result on the first day is the 22nd day, and the decision premise is 21 days, it means that the optimal time to solve the current model is the 22nd day. However, since the preparation constraint is 21 days, it means that the decision cleaning schedule must be after the 21st day. Since there are a total of four days for cleaning after 21 days, we do not execute the current decision result immediately, but wait for the next decision. When making a decision on the third day, since the historical data has been updated and the data of the first and second days have been added, the data model can be more accurate, thus affecting the decision result. Figure 3 A total of three decision results are shown. When the preparation constraint and the decision result coincide, it means that the result should be executed to avoid missing the optimal solution. Secondly, there is only one solution or no solution after the preparation constraint, which means that the system can only clean up on the last day or not.

[0063] See also Figure 4 , is a module schematic diagram of a scar cleaning decision optimization system for an aluminum oxide evaporator provided in an embodiment of the present application. The scar cleaning decision optimization system for an aluminum oxide evaporator may include: a scar mechanism model establishment module, a first benefit model establishment module, a second benefit model establishment module and a cleaning plan determination module, wherein: A scarring mechanism model building module is used to determine a precipitation rate model and a redispersion rate model of an alumina evaporator, and to build a scarring mechanism model based on the precipitation rate model and the redispersion rate model; A first revenue model establishment module, used to establish a time-continuous first evaporation revenue model in combination with the scarring mechanism model and the preset cleaning and maintenance cost; The second profit model establishment module is used to convert the first evaporation profit model into a periodic second evaporation profit model; the cleaning plan determination module is used to dynamically solve the second evaporation model to obtain a target cleaning plan.

[0064] Optionally, the scaling mechanism model building module is also used to obtain the concentration of scaling substances at the interface between the deposition layer of the alumina evaporator and the heat exchanger, the temperature of the liquid-solid interface, and the concentration of scaling substances at saturation; Determining the precipitation rate model based on the fouling material concentration at the interface between the sediment layer and the heat exchanger, the temperature of the liquid-solid interface, and the concentration of the fouling material at saturation; The precipitation rate model is: In the formula, is the precipitation rate, A′ is the Ahrendts constant, E is the activation energy, R T is the universal gas constant, T s is the temperature of the liquid-solid interface, C s is the fouling concentration at the interface between the deposition layer and the heat exchanger, C cat T s The concentration of scaling substances at lower saturation, n is the order of chemical reaction.

[0065] Optionally, the scarring mechanism model building module is also used to construct the shear stress of the fluid on the solid surface based on the friction coefficient of the alumina evaporator and the fluid density; The shear stress is: In the formula, τ w is shear stress, f is friction coefficient, ρ is fluid density, and u is flow velocity; a redispersion rate model of an alumina evaporator is constructed based on the shear stress; The re-diffusion rate model is: is the redispersion rate, B0 is a preset constant, is the precipitation structure function.

[0066] Optionally, the first revenue model building module is further used to calculate the total heat transfer coefficient of the alumina evaporator based on the scarring mechanism model and the parameters of the pipeline connecting the alumina evaporator; Calculating a total heat transfer amount based on the total heat transfer coefficient; Based on the total heat transfer amount and the preset cleaning and maintenance cost, a time-continuous first evaporation profit model is established; The first evaporation profit model is: Among them, M n is the total revenue under plan n, T is the total time, Q t' is the total heat transfer at t', ΔH t' is the thermal enthalpy of water in the liquid, e is the revenue per ton of water, m is the number of cleanings, and w is the preset cleaning and maintenance cost.

[0067] Optionally, the first revenue model building module is further used to substitute the scarring mechanism model and the pipeline parameters of the alumina evaporator into the heat transfer coefficient calculation formula to obtain the total heat transfer coefficient of the alumina evaporator; The heat transfer coefficient calculation formula is: Among them, the K t' is the total heat transfer coefficient, α1 is the condensation convection heat transfer coefficient of steam, α2 is the falling film side convection heat transfer coefficient, λ b is the thermal conductivity of the pipe wall material, δ b is the tube wall thickness, R f (t') is the scarring mechanism model.

[0068] Optionally, the second revenue model establishing module is further used to divide the time in the first evaporation revenue model according to preset periods to obtain a plurality of fixed periods, and establish a periodic second evaporation revenue model; The second evaporation profit model is: Where c represents a fixed cycle number, and the cycle time range of c is from (c-1)T s +1 day to cT s Day, n c Indicates the cleaning plan for cycle number c, n c ∈{0,1,2,...,T s},u c is a label indicating whether the alumina evaporator is cleaned during this cycle, A is the heat transfer area, is the heat transfer temperature difference, ΔH is the thermal enthalpy of water in the liquid, is the scarring degree of the day in the cycle time numbered c, t'∈[1,T s ].

[0069] Optionally, the cleaning plan determination module is further used to determine historical data of the alumina evaporator, and predict the first cleaning plan corresponding to each cycle time in the entire cycle based on the historical data; Dynamically solving the second evaporation model and the second cleaning plan corresponding to each cycle time; Determine whether the first cleaning plan corresponding to each cycle time is consistent with the second cleaning plan; If they are consistent, the first cleaning plan is used as the target cleaning plan; If they are inconsistent, the second cleaning plan is used as the target cleaning plan.

[0070] It should be noted that: when the system provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0071] An embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded by a processor and executing a method for optimizing the decision of cleaning alumina evaporator for scarring in the above embodiment. The specific execution process can be found in the specific description of the above embodiment and will not be repeated here.

[0072] Please refer to Figure 5 The application also discloses an electronic device. Figure 5 The electronic device 500 may include: at least one processor 501 , at least one network interface 504 , a user interface 503 , a memory 505 , and at least one communication bus 502 .

[0073] The communication bus 502 is used to realize the connection and communication between these components.

[0074] The user interface 503 may include a display screen (Display) and a camera (Camera), and the optional user interface 503 may also include a standard wired interface and a wireless interface.

[0075] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0076] Among them, the processor 501 may include one or more processing cores. The processor 501 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 505, and calling data stored in the memory 505. Optionally, the processor 501 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 501 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 501, and it can be implemented separately through a chip.

[0077] Among them, the memory 505 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 505 includes a non-transitory computer-readable storage medium. The memory 505 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 505 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 505 may also be optionally at least one storage device located away from the aforementioned processor 501. Refer to Figure 5 , the memory 505 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program for a method for optimizing decision-making for cleaning of alumina evaporator scabs.

[0078] exist Figure 5In the electronic device 500 shown, the user interface 503 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 501 can be used to call the application program stored in the memory 505 for a method for optimizing the decision of cleaning a scab of an alumina evaporator. When executed by one or more processors 501, the electronic device 500 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0079] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0080] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0081] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0083] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0084] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0085] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for optimizing the cleaning decision of alumina evaporator, characterized in that: The method comprises: Determining a precipitation rate model and a redispersion rate model of an alumina evaporator, and establishing a scarring mechanism model based on the precipitation rate model and the redispersion rate model; A time-continuous first evaporation benefit model is established in combination with the scarring mechanism model and the preset cleaning and maintenance cost; converting the first evaporation profit model into a periodic second evaporation profit model; The second evaporation model is dynamically solved to obtain a target cleaning plan.

2. The method for optimizing the decision of cleaning the alumina evaporator according to claim 1, characterized in that: The precipitation rate model for determining the alumina evaporator comprises: Obtaining the fouling substance concentration at the interface between the deposition layer of the alumina evaporator and the heat exchanger, the temperature of the liquid-solid interface, and the concentration of the fouling substance at saturation; Determining the precipitation rate model based on the fouling material concentration at the interface between the sediment layer and the heat exchanger, the temperature of the liquid-solid interface, and the concentration of the fouling material at saturation; The precipitation rate model is: In the formula, is the precipitation rate, A′ is the Ahrendts constant, E is the activation energy, R T is the universal gas constant, T s is the temperature of the liquid-solid interface, C s is the fouling concentration at the interface between the deposition layer and the heat exchanger, C cat T s The concentration of scaling substances at lower saturation, n is the order of chemical reaction.

3. The method for optimizing the decision of cleaning the alumina evaporator according to claim 1, characterized in that: Model for determining the redispersion rate in an alumina evaporator, including: Based on the friction coefficient of the alumina evaporator and the fluid density, the shear stress of the fluid on the solid surface is constructed; The shear stress is: In the formula, τ w is shear stress, f is friction coefficient, ρ is fluid density, and u is flow velocity; a redispersion rate model of an alumina evaporator is constructed based on the shear stress; The re-diffusion rate model is: is the redispersion rate, B0 is a preset constant, is the precipitation structure function.

4. The method for optimizing the decision of cleaning the alumina evaporator according to claim 1, characterized in that: The first evaporation benefit model with continuous time is established by combining the scarring mechanism model and the preset cleaning and maintenance cost, including: Based on the scarring mechanism model and the parameters of the pipeline connecting the alumina evaporator, calculating the overall heat transfer coefficient of the alumina evaporator; Calculating a total heat transfer amount based on the total heat transfer coefficient; Based on the total heat transfer amount and the preset cleaning and maintenance cost, a time-continuous first evaporation profit model is established; The first evaporation profit model is: Among them, M n is the total revenue under plan n, T is the total time, Q t' is the total heat transfer at t', ΔH t' is the thermal enthalpy of water in the liquid, e is the revenue per ton of water, m is the number of cleanings, and w is the preset cleaning and maintenance cost.

5. The method for optimizing the decision of cleaning the alumina evaporator according to claim 4, characterized in that: The total heat transfer coefficient of the alumina evaporator is calculated based on the scarring mechanism model and the parameters of the pipeline connecting the alumina evaporator, including: Substituting the scarring mechanism model and the pipeline parameters of the alumina evaporator into the heat transfer coefficient calculation formula to obtain the total heat transfer coefficient of the alumina evaporator; The heat transfer coefficient calculation formula is: Among them, the K t' is the total heat transfer coefficient, α1 is the condensation convection heat transfer coefficient of steam, α2 is the falling film side convection heat transfer coefficient, λ b is the thermal conductivity of the pipe wall material, δ b is the tube wall thickness, R f (t') is the scarring mechanism model.

6. The method for optimizing the decision of cleaning the alumina evaporator according to claim 1, characterized in that: The converting the first evaporation profit model into a periodic second evaporation profit model comprises: Dividing the time in the first evaporation profit model into preset periods to obtain a plurality of fixed periods, and establishing a periodic second evaporation profit model; The second evaporation profit model is: Where c represents a fixed cycle number, and the cycle time range of c is from (c-1)T s +1 day to cT s Day, n c Indicates the cleaning plan for cycle number c, n c ∈{0,1,2,...,T s },u c is a label indicating whether the alumina evaporator is cleaned during this cycle, A is the heat transfer area, is the heat transfer temperature difference, ΔH is the thermal enthalpy of water in the liquid, Number is the scarring degree of the day in the cycle time of c, t'∈[1,T s ].

7. The method for optimizing the decision of cleaning the alumina evaporator according to claim 6, characterized in that: The dynamically solving the second evaporation model to obtain a target cleaning plan includes: Determining historical data of the alumina evaporator, and predicting a first cleaning plan corresponding to each cycle time in the entire cycle based on the historical data; Dynamically solving the second evaporation model and the second cleaning plan corresponding to each cycle time; Determine whether the first cleaning plan corresponding to each cycle time is consistent with the second cleaning plan; If they are consistent, the first cleaning plan is used as the target cleaning plan; If they are inconsistent, the second cleaning plan is used as the target cleaning plan.

8. A decision optimization system for cleaning alumina evaporator scabs, characterized in that: The system comprises: A scarring mechanism model building module is used to determine a precipitation rate model and a redispersion rate model of an alumina evaporator, and to build a scarring mechanism model based on the precipitation rate model and the redispersion rate model; A first revenue model establishment module, used to establish a time-continuous first evaporation revenue model in combination with the scarring mechanism model and the preset cleaning and maintenance cost; The second profit model establishment module is used to convert the first evaporation profit model into a periodic second evaporation profit model; the cleaning plan determination module is used to dynamically solve the second evaporation model to obtain a target cleaning plan.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

Images