Sewage treatment process for pulping and papermaking industry

Abstract

The invention discloses a pulping and papermaking industry sewage treatment process, relates to the technical field of sewage treatment, and adopts a dynamic adjustment algorithm and a PID control mechanism to monitor the concentration, flow and water temperature of suspended solids in real time, the dosage of chemicals can be automatically adjusted, the concentration is stabilized to be close to a target value, the waste of chemical chemicals is reduced, and the sewage treatment efficiency is improved. Meanwhile, the stability and effect of sewage treatment are improved, a reinforcement learning RL algorithm is introduced, the aeration intensity and time are adjusted in real time, the ammonia nitrogen concentration is controlled, the organic load is removed, the RL algorithm can continuously optimize the aeration strategy according to the change of the ammonia nitrogen concentration and the organic load, and therefore the removal efficiency is improved to the maximum extent; meanwhile, excessive aeration and unnecessary energy consumption are avoided, predictive control based on a random forest algorithm is adopted, the physical characteristics, including the moisture content, the solid content and the rheological property, of the sludge are analyzed in real time, and the concentration stirring strength and the concentration time are dynamically adjusted.

Description

Technical Field

[0001] The invention relates to the technical field of sewage treatment, in particular to a sewage treatment process in the pulping and papermaking industry. Background Art

[0002] In the wastewater treatment of the pulp and paper industry, sludge dehydration and ammonia nitrogen removal are key links. The sludge contains a large amount of organic matter, cellulose and other difficult-to-degrade substances, which makes the sludge have a high water content and increases the difficulty of treatment. In addition, the ammonia nitrogen concentration in pulp and paper wastewater fluctuates greatly, affecting the effluent water quality.

[0003] Traditional sludge treatment methods mostly use gravity concentration, mechanical dehydration and chemical-assisted dehydration. In the concentration stage, most of the water is removed by gravity concentration or flotation concentration to initially reduce the sludge volume. Subsequently, mechanical dehydration equipment such as belt filter press, centrifugal or spiral filter press is used to further remove water and achieve mud-water separation. Some treatment plans will also add chemical agents, such as coagulants or flocculants, to help enhance the sedimentation and aggregation of solid particles in the sludge, thereby improving the dehydration efficiency and alleviating the problem of high sludge water content to a certain extent.

[0004] However, mechanical dewatering equipment has high operating costs and high maintenance frequency. Due to the high fiber content in pulp and paper sludge, the equipment is easily damaged and the maintenance cost is high. The effects of gravity concentration and chemical-assisted dewatering are also affected by the fluctuation of sludge composition, resulting in unstable treatment effects. In addition, the need for frequent replenishment of chemicals not only increases treatment costs, but may also cause secondary pollution. For the removal of ammonia nitrogen, traditional methods mainly rely on the continuous aeration mode in the biological treatment system. However, due to the large fluctuations in ammonia nitrogen concentration, a fixed aeration intensity is difficult to meet actual needs, resulting in high energy consumption, poor system stability, and unstable treatment effects. Therefore, a pulp and paper industry wastewater treatment process is urgently needed to solve such problems. Summary of the invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] The present invention provides a wastewater treatment process for the pulping and papermaking industry to solve the problems of high operating cost and high maintenance frequency of mechanical dewatering equipment. In view of the high fiber content in pulping and papermaking sludge, the equipment is easily damaged and the maintenance cost is high. The effect of gravity concentration and chemical-assisted dewatering is also affected by the fluctuation of sludge composition, resulting in unstable treatment effect. In addition, the frequent replenishment of chemicals not only increases the treatment cost, but also may cause secondary pollution problems.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] The present invention provides a wastewater treatment process for pulp and paper industry, which comprises:

[0009] Step S1, sewage pretreatment,

[0010] The combined process of air flotation and gravity sedimentation is used to remove large particles, fibers and suspended solids in the sewage. Water quality sensors are installed to monitor the concentration and flow of suspended solids in the sewage, and the dosage of flocculants and coagulants is adjusted using dynamic algorithms.

[0011] Step S2, staged aeration biological treatment,

[0012] The wastewater pretreated in step S1 is subjected to biological treatment, and high-concentration organic matter and ammonia nitrogen are removed by staged aeration;

[0013] Step S3, sludge concentration prediction control,

[0014] The sludge after biological treatment enters the concentration stage. The predictive control based on the random forest algorithm is used to conduct real-time analysis of the sludge's moisture content, solid content and rheological properties, and intelligently adjust the concentration stirring intensity and concentration time.

[0015] Step S4, sludge dehydration adjustment control,

[0016] The sludge concentrated in step S3 enters the dehydration stage, and the moisture content and solid content of the sludge are monitored in real time. The pressure, speed and dosage of the dehydration equipment are adjusted in combination with the simulated annealing SA algorithm;

[0017] Step S5, sludge reduction and resource utilization,

[0018] The dehydrated sludge is treated for volume reduction and resource utilization, and the corresponding resource utilization treatment method is recommended based on the organic content, calorific value and heavy metal concentration of the sludge.

[0019] Furthermore, in step S1, sewage monitoring and data collection are performed, specifically:

[0020] Set up water quality sensors to monitor the suspended solids concentration, flow rate and water temperature in the sewage in real time, and build a dynamic adjustment model for the dosage of the reagent to calculate the dosage of the reagent:

[0021] Among them, F chem (t) represents the dosage of the agent at the current time t, C sus (t) represents the suspended solids concentration at the current time t, Q in (t) represents the sewage flow at the current time t, T(t) represents the water temperature at the current time t, C targetIndicates the target suspended solids concentration, which is the preset maximum allowable concentration. α, β, and γ represent adaptive adjustment parameters, which are adjusted according to the actual needs of the sewage treatment process. It is the integral term of the historical error, representing the accumulated error of suspended matter concentration from the starting time to the current time t.

[0022] Furthermore, in step S1, the dosage of the agent is dynamically adjusted:

[0023] Based on the sensor, the suspended solids concentration, flow rate and water temperature at the current moment are obtained, the target concentration is set, and the historical error term is calculated. When the suspended solids concentration fluctuates, it gradually approaches the target value to avoid large fluctuations; based on real-time data and historical error terms, the PID control algorithm is used to dynamically adjust the parameters (α, β, γ) of the dosage of the reagent.

[0024] Furthermore, in step S2, based on the real-time data obtained by the water quality sensor in step S1 and combined with the reinforcement learning RL algorithm, the aeration intensity and time are continuously adjusted based on the changes in ammonia nitrogen concentration and organic load.

[0025] Furthermore, in step S2, the staged aeration biological treatment is performed in the following manner:

[0026] Based on the real-time water quality data monitored in step S1, it is used as the input of the reinforcement learning algorithm, and the aeration process is divided into pre-aeration, main aeration and post-aeration. Each stage is aerated for different ammonia nitrogen concentrations and organic loads. The aeration intensity and time of each stage are defined as:

[0027] Among them, P aer (t) represents the aeration intensity at the current time t, represents the ammonia nitrogen concentration at the current time t, BOD(t) represents the organic load at the current time t, Q in (t) represents the sewage flow at the current time t, T(t) represents the water temperature at the current time t, α, β, γ represent the empirical adjustment parameters, which control the influence of various factors on the aeration intensity and need to be adjusted according to the actual situation.

[0028] Optimizing aeration intensity P based on real-time feedback aer (t) and aeration time T aer (t), adjust the ammonia nitrogen removal effect, and the objective function of the reinforcement learning model is:

[0029] Among them, R total (t) represents the total reward value at the current time t, represents the ammonia nitrogen concentration at the current time t, BOD(t) represents the organic load at the current time t, C targetIndicates the target ammonia nitrogen concentration, which is the maximum allowable concentration, BOD tar get represents the target organic load, P aer (t) represents the aeration intensity at the current time t, T aer (t) represents the aeration time at the current time t, λ1,λ2,λ3 represent weight coefficients, and based on the RL algorithm, the aeration intensity and time are adjusted according to the environmental state to maximize the reward R total (t), i.e., minimizing the degree to which ammonia nitrogen and organic loads deviate from the target values.

[0030] Furthermore, in step S2, the method of performing segmented aeration biological treatment also includes:

[0031] Update aeration strategy: Among them, Q(s t ,a t ) indicates the current state s t and action a t The Q value indicates that in state s t Next, perform action a t The expected total reward, R total (t) represents the total reward value at the current time t, α represents the learning rate, which controls the response speed of the algorithm to new information, γ represents the discount factor, which represents the weight of future rewards, and s t Represents the system status at the current time t, including water quality data, a t represents the action taken at the current time t, that is, the adjusted aeration intensity and time, and updates Q(s) in the process of continuous interaction with the system environment. t ,a t ) value to optimize aeration operation;

[0032] According to the optimization of RL strategy, the final aeration control formula is:

[0033] Among them, ΔQ(s t ,a t ) represents the adjustment amount calculated by the RL algorithm, which indicates the aeration intensity adjustment of the current decision relative to the previous moment.

[0034] Furthermore, in step S3, sludge concentration and prediction control are performed:

[0035] A random forest model is constructed to predict the sludge characteristics: Y(t)=f(X(t),θ)+∈(t), where Y(t) represents the prediction results of the sludge physical characteristics at the current time t, including moisture content, solid content and rheological properties, X(t) represents the set of operating parameters at the current time t, f(X(t),θ) represents the prediction function based on the operating parameters and the random forest algorithm, the learned model function, θ represents the parameters of the model, and ∈(t) represents the model error, that is, the prediction error;

[0036] The physical properties and operating parameters of sludge are obtained in real time, and the moisture content, solid content and rheological properties are predicted in real time using the random forest algorithm. Then, based on the prediction results, the concentration stirring intensity and concentration time are adjusted. The control formula is: P stir (t)=α1·W(t)+α2·S(t)+α3·R(t)+β·Q sludge (t)+γ·T conc (t), T conc (t)=δ1·W(t)+δ2·S(t)+δ3·R(t)+∈·Q sludge (t), where P stir (t) represents the stirring intensity at the current time t, T conc (t) represents the concentration time at the current time t, which is determined by the physical properties of the sludge and the flow rate. W(t) represents the water content at the current time t. S(t) represents the solid content at the current time t. R(t) represents the rheological properties at the current time t. Q sludge (t) represents the sludge flow rate at the current time t, T conc (t) represents the concentration time, and α1, α2, α3, β, γ, δ1, δ2, and δ3 represent the adjustment coefficients of the model, which are used to adjust the influence of each parameter on the stirring intensity and concentration time.

[0037] Furthermore, in step S3, the stirring intensity and the concentration time are adjusted according to the real-time predicted physical properties of the sludge:

[0038] J(t)=λ1·(W tar get -W(t) 2 +λ2·(S tar get -S(t)) 2 +λ3·(R tar get -R(t)) 2 +λ4·P stir (t)+λ5·T conc (t), where J(t) represents the optimization objective function at the current time t, i.e., the deviation between the target state and the actual state and the operation cost, and W tar get ,S tar get ,R tar getrepresents the target sludge characteristic value, λ1,λ2,λ3,λ4,λ5 represent weight coefficients, balance the relationship between sludge characteristic optimization and operating cost, minimize the objective function J(t), and optimize the stirring intensity and concentration time;

[0039] According to the results of the optimization process, the final concentration process control formula is:

[0040] P stir (t)=α1·W(t)+α2·S(t)+α3·R(t)+β·Q sludge (t)+γ·T conc (t),

[0041] T conc (t)=δ1·W(t)+δ2·S(t)+δ3·R(t)+∈·Q sludge (t).

[0042] Furthermore, in step S4, based on the real-time monitored sludge moisture content and solid content, the simulated annealing SA algorithm is used to adjust the dehydration equipment parameters:

[0043] Define the optimization objective function J(t) to describe the sludge dehydration effect. The goal is to minimize the moisture content of the sludge. The objective function form is: J(t) = w1·H(t)+w2·E(t)+w3·T(t), where H(t) represents the sludge moisture content at time point t, E(t) represents the energy consumption of the dehydration equipment at time point t, T(t) represents the total duration of the dehydration process, and w1, w2, w3 represent weight coefficients;

[0044] The optimal solution is searched in the global solution space through a simulated annealing process, and the steps include:

[0045] Set the initial solution P(0), N(0), C(0), and calculate the initial objective function value J(0). Based on the current solution, randomly adjust P(t), N(t), and C(t) to generate new solutions P′(t), N′(t), C′(t). Calculate the new objective function value J′(t) according to the new operating parameters.

[0046] The decision on whether to accept a new solution is based on the change in the objective function value. The probability of accepting a new solution is P. accept :

[0047] Among them, J′(t) represents the new objective function value, J(t) represents the current objective function value, and T(t) represents the current temperature, which gradually decreases as the iteration proceeds. The "temperature" in simulated annealing represents the amplitude of exploring the new solution space;

[0048] According to P acceptThe value of determines whether to accept the new solution. If J′(t) is smaller, or a worse solution is accepted with a certain probability, P(t), N(t) and C(t) are updated to P′(t), N′(t), C′(t);

[0049] With each iteration, the temperature T(t) gradually decreases, T(t) = T0·α t , where T0 represents the initial temperature, α represents the attenuation coefficient, and t represents the current number of iterations; when the temperature T(t) is less than the set threshold or the objective function value changes less than a certain threshold, the algorithm is terminated and the final parameter combination P(t), N(t) and C(t) is output.

[0050] Furthermore, sludge reduction is performed in step S5:

[0051] The comprehensive optimization objective function G(t) is defined to minimize the environmental risks in the treatment process and maximize the resource recovery efficiency. The objective function is:

[0052] G(t)=w1·O(t)+w2·H(t)+w3·R(t)+w4·M(t), where O(t) represents the organic matter content of the sludge at time t, H(t) represents the calorific value of the sludge, R(t) represents the resource recovery rate, M(t) represents the heavy metal concentration, and w1, w2, w3, and w4 represent weight coefficients;

[0053] The goal is to minimize G(t), giving priority to the recovery of organic matter and energy in the sludge resource recovery process, while controlling the risk of heavy metals;

[0054] Estimate the relationship between the calorific value of sludge and the recovery of organic matter, H(t) = α·O(t) + β, where α represents the correlation coefficient between calorific value and organic matter content, and β represents the basic calorific value of sludge. Adjust the recovery of organic matter to optimize the calorific value improvement;

[0055] The heavy metal concentration is taken as the optimization constraint, and the heavy metal risk control function M(t) is defined as the restriction item in the treatment process. The heavy metal concentration does not exceed the environmental protection standard, that is, M(t)≤M limit , where M(t) represents the heavy metal concentration in sludge at time t, M limit Indicates the environmental concentration standard of heavy metals;

[0056] Resource recovery rate is defined as: R(t) = γ·H(t)-δ·M(t), where γ represents the calorific value recovery efficiency coefficient and δ represents the heavy metal impact coefficient;

[0057] Based on the optimization objective function G(t) and constraints, a multi-objective optimization algorithm is used to evaluate and select various sludge resource recovery schemes. The treatment scheme parameters are adjusted during each iteration. Finally, the best resource recovery scheme is selected based on the above optimization process.

[0058] The beneficial effects of the present invention are:

[0059] The present invention adopts a dynamic adjustment algorithm and a PID control mechanism to monitor the suspended matter concentration, flow rate and water temperature in real time. The dosage of the agent can be automatically adjusted to stabilize the concentration near the target value, effectively avoiding the phenomenon of frequent adjustment or excessive addition of agents in traditional methods, reducing the waste of chemical agents, and also improving the stability and effect of sewage treatment.

[0060] The present invention introduces a reinforcement learning (RL) algorithm to adjust aeration intensity and time in real time, control ammonia nitrogen concentration, and remove organic load. The RL algorithm can continuously optimize the aeration strategy according to changes in ammonia nitrogen concentration and organic load, thereby maximizing the removal efficiency while avoiding excessive aeration and unnecessary energy consumption.

[0061] The present invention adopts predictive control based on random forest algorithm to analyze the physical properties of sludge in real time, including moisture content, solid content and rheological properties, and dynamically adjusts the concentration stirring intensity and concentration time, thus overcoming the challenges brought by changes in sludge properties.

[0062] The present invention introduces a simulated annealing algorithm SA, searches for the optimal solution in the global solution space, optimizes the working parameters of the dehydration equipment, including pressure, rotation speed and dosage, and significantly improves the dehydration efficiency. At the same time, a comprehensive optimization objective function is introduced, and weight coefficients of organic matter content, calorific value and heavy metal concentration are combined to evaluate different resource processing schemes based on a multi-objective optimization algorithm, effectively balance organic matter recovery, calorific value enhancement and heavy metal concentration control, reduce waste emissions, and improve resource utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0064] Figure 1 It is a schematic diagram of the process flow of wastewater treatment in the pulping and papermaking industry of the present invention. DETAILED DESCRIPTION

[0065] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0066] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0067] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0068] Example 1, reference Figure 1 , this embodiment provides a wastewater treatment process for the pulp and paper industry, comprising the following steps:

[0069] Step S1, sewage pretreatment,

[0070] The combined process of air flotation and gravity sedimentation is used to remove large particles, fibers and suspended solids in the sewage. Water quality sensors are installed to monitor the concentration and flow of suspended solids in the sewage, and the dosage of flocculants and coagulants is adjusted using dynamic algorithms.

[0071] In step S1, sewage monitoring and data collection are performed, specifically:

[0072] Set up water quality sensors to monitor the suspended solids concentration, flow rate and water temperature in the sewage in real time, and build a dynamic adjustment model for the dosage of the reagent to calculate the dosage of the reagent:

[0073] Among them, F chem (t) represents the dosage of the agent at the current time t, C sus (t) represents the suspended solids concentration at the current time t, Q in (t) represents the sewage flow at the current time t, T(t) represents the water temperature at the current time t, C target Indicates the target suspended solids concentration, which is the preset maximum allowable concentration. α, β, and γ represent adaptive adjustment parameters, which are adjusted according to the actual needs of the sewage treatment process. is the integral term of the historical error, representing the accumulated error of suspended matter concentration from the start time to the current time t;

[0074] In step S1, the dosage of the agent is dynamically adjusted:

[0075] Based on the sensor, the current suspended solids concentration, flow rate and water temperature are obtained, the target concentration is set, and the historical error term is calculated. When the suspended solids concentration fluctuates, it gradually approaches the target value to avoid large fluctuations; according to real-time data and historical error terms, the PID control algorithm is used to dynamically adjust the parameters (α, β, γ) of the dosage of the reagent;

[0076] Specifically, in step S1, the suspended solids concentration, flow rate and water temperature in the sewage are monitored in real time, and the dosage of flocculants and coagulants is dynamically adjusted. Combined with the PID control algorithm, the suspended solids concentration in the sewage can be stabilized within the target range. Through PID control, large fluctuations in the dosage can be avoided, thereby ensuring the stability and efficiency of the treatment process.

[0077] Step S2, staged aeration biological treatment,

[0078] The wastewater pretreated in step S1 is subjected to biological treatment, and high-concentration organic matter and ammonia nitrogen are removed by staged aeration;

[0079] In step S2, based on the real-time data obtained by the water quality sensor in step S1, combined with the reinforcement learning RL algorithm, the aeration intensity and time are continuously adjusted based on the changes in ammonia nitrogen concentration and organic load;

[0080] In step S2, the staged aeration biological treatment is performed in the following manner:

[0081] Based on the real-time water quality data monitored in step S1, it is used as the input of the reinforcement learning algorithm, and the aeration process is divided into pre-aeration, main aeration and post-aeration. Each stage is aerated for different ammonia nitrogen concentrations and organic loads. The aeration intensity and time of each stage are defined as:

[0082] Among them, P aer (t) represents the aeration intensity at the current time t, represents the ammonia nitrogen concentration at the current time t, BOD(t) represents the organic load at the current time t, Q in (t) represents the sewage flow at the current time t, T(t) represents the water temperature at the current time t, α, β, γ represent the empirical adjustment parameters, which control the influence of various factors on the aeration intensity and need to be adjusted according to the actual situation.

[0083] Optimizing aeration intensity P based on real-time feedback aer (t) and aeration time T aer (t), adjust the ammonia nitrogen removal effect, and the objective function of the reinforcement learning model is:

[0084] Among them, R total (t) represents the total reward value at the current time t, represents the ammonia nitrogen concentration at the current time t, BOD(t) represents the organic load at the current time t, Ctar get Indicates the target ammonia nitrogen concentration, which is the maximum allowable concentration, BOD tar get represents the target organic load, P aer (t) represents the aeration intensity at the current time t, T aer (t) represents the aeration time at the current time t, λ1,λ2,λ3 represent weight coefficients, and based on the RL algorithm, the aeration intensity and time are adjusted according to the environmental state to maximize the reward R total (t), i.e., minimizing the deviation of ammonia nitrogen and organic loads from target values;

[0085] In step S2, the method of performing segmented aeration biological treatment also includes:

[0086] Update aeration strategy: Among them, Q(s t ,a t ) indicates the current state s t and action a t The Q value indicates that in state s t Next, perform action a t The expected total reward, R total (t) represents the total reward value at the current time t, α represents the learning rate, which controls the response speed of the algorithm to new information, γ represents the discount factor, which represents the weight of future rewards, and s t Represents the system status at the current time t, including water quality data, a t represents the action taken at the current time t, that is, the adjusted aeration intensity and time, and updates Q(s) in the process of continuous interaction with the system environment. t ,a t ) value to optimize aeration operation;

[0087] According to the optimization of RL strategy, the final aeration control formula is:

[0088] Among them, ΔQ(s t ,a t ) represents the adjustment amount calculated by the RL algorithm, which represents the aeration intensity adjustment of the current decision relative to the previous moment;

[0089] Specifically, in step S2, a segmented aeration method is adopted in combination with a reinforcement learning algorithm, and the aeration intensity and aeration time are adjusted according to real-time water quality data, which significantly improves the removal efficiency of ammonia nitrogen and organic load in sewage. The reinforcement learning model can continuously optimize the aeration process according to changes in ammonia nitrogen concentration and organic load, which not only improves the treatment efficiency but also avoids energy waste caused by excessive aeration; by continuously updating the aeration strategy, the removal effect of ammonia nitrogen and organic load is maximized.

[0090] Step S3, sludge concentration prediction control,

[0091] The sludge after biological treatment enters the concentration stage. The predictive control based on the random forest algorithm is used to conduct real-time analysis of the sludge's moisture content, solid content and rheological properties, and intelligently adjust the concentration stirring intensity and concentration time.

[0092] In step S3, sludge concentration and prediction control are performed:

[0093] A random forest model is constructed to predict the sludge characteristics: Y(t)=f(X(t),θ)+∈(t), where Y(t) represents the prediction results of the sludge physical characteristics at the current time t, including moisture content, solid content and rheological properties, X(t) represents the set of operating parameters at the current time t, f(X(t),θ) represents the prediction function based on the operating parameters and the random forest algorithm, the learned model function, θ represents the parameters of the model, and ∈(t) represents the model error, that is, the prediction error;

[0094] The physical properties and operating parameters of sludge are obtained in real time, and the moisture content, solid content and rheological properties are predicted in real time using the random forest algorithm. Then, based on the prediction results, the concentration stirring intensity and concentration time are adjusted. The control formula is: P stir (t)=α1·W(t)+α2·S(t)+α3·R(t)+β·Q shudge (t)+γ·T conc (t), T conc (t)=δ1·W(t)+δ2·S(t)+δ3·R(t)+∈·Q sludge (t), where P stir (t) represents the stirring intensity at the current time t, T conc (t) represents the concentration time at the current time t, which is determined by the physical properties of the sludge and the flow rate. W(t) represents the water content at the current time t. S(t) represents the solid content at the current time t. R(t) represents the rheological properties at the current time t. Q sludge (t) represents the sludge flow rate at the current time t, T conc (t) represents the concentration time, α1, α2, α3, β, γ, δ1, δ2, δ3 represent the adjustment coefficients of the model, which are used to adjust the influence of each parameter on the stirring intensity and concentration time;

[0095] In step S3, the stirring intensity and the concentration time are adjusted according to the real-time predicted physical properties of the sludge:

[0096] J(t)=λ1·(W tar get -W(t) 2 +λ2·(S tar get -S(t)) 2 +λ3·(R tar get -R(t)) 2+λ4·P stir (t)+λ5·T conc (t), where J(t) represents the optimization objective function at the current time t, i.e., the deviation between the target state and the actual state and the operation cost, and W tar get ,S tar get ,R tar get represents the target sludge characteristic value, λ1,λ2,λ3,λ4,λ5 represent weight coefficients, balance the relationship between sludge characteristic optimization and operating cost, minimize the objective function J(t), and optimize the stirring intensity and concentration time;

[0097] According to the results of the optimization process, the final concentration process control formula is:

[0098] P stir (t)=α1·W(t)+α2·S(t)+α3·R(t)+β·Q sludge (t)+γ·T conc (t),

[0099] T conc (t)=δ1·W(t)+δ2·S(t)+δ3·R(t)+∈·Q sludge (t);

[0100] Specifically, in step S3, through predictive control based on the random forest algorithm, the physical properties of the sludge are analyzed and predicted in real time, and the thickening stirring intensity and thickening time are dynamically adjusted according to the prediction results to effectively optimize the sludge thickening process; timely respond to changes in sludge characteristics, reduce uncertainties in the operation process, and improve the stability and efficiency of sludge thickening.

[0101] Step S4, sludge dehydration adjustment control,

[0102] The sludge concentrated in step S3 enters the dehydration stage, and the moisture content and solid content of the sludge are monitored in real time. The pressure, speed and dosage of the dehydration equipment are adjusted in combination with the simulated annealing SA algorithm;

[0103] In step S4, based on the real-time monitoring of the sludge moisture content and solid content, the simulated annealing SA algorithm is used to adjust the dehydration equipment parameters:

[0104] Define the optimization objective function J(t) to describe the sludge dehydration effect. The goal is to minimize the moisture content of the sludge. The objective function form is: J(t) = w1·H(t)+w2·E(t)+w3·T(t), where H(t) represents the sludge moisture content at time point t, E(t) represents the energy consumption of the dehydration equipment at time point t, T(t) represents the total duration of the dehydration process, and w1, w2, w3 represent weight coefficients;

[0105] The optimal solution is searched in the global solution space through a simulated annealing process, and the steps include:

[0106] Set the initial solution P(0), N(0), C(0), and calculate the initial objective function value J(0). Based on the current solution, randomly adjust P(t), N(t), and C(t) to generate new solutions P′(t), N′(t), C′(t). Calculate the new objective function value J′(t) according to the new operating parameters.

[0107] The decision on whether to accept a new solution is based on the change in the objective function value. The probability of accepting a new solution is P. accept :

[0108] Among them, J′(t) represents the new objective function value, J(t) represents the current objective function value, and T(t) represents the current temperature, which gradually decreases as the iteration proceeds. The "temperature" in simulated annealing represents the amplitude of exploring the new solution space;

[0109] According to P accept The value of determines whether to accept the new solution. If J′(t) is smaller, or a worse solution is accepted with a certain probability, P(t), N(t) and C(t) are updated to P′(t), N′(t), C′(t);

[0110] With each iteration, the temperature T(t) gradually decreases, T(t) = T0·α t , where T0 represents the initial temperature, α represents the attenuation coefficient, and t represents the current iteration number; when the temperature T(t) is less than the set threshold or the objective function value changes less than a certain threshold, the algorithm is terminated and the final parameter combination P(t), N(t) and C(t) is output;

[0111] Specifically, in step S4, the moisture content and solid content of the sludge are monitored in real time, and the pressure, speed and dosage of the dehydration equipment are adjusted in combination with the simulated annealing algorithm, thereby significantly improving the efficiency and effect of sludge dehydration. The introduction of the simulated annealing algorithm enables the dehydration process to find the optimal solution in the global solution space.

[0112] Step S5, sludge reduction and resource utilization,

[0113] The dehydrated sludge is treated for volume reduction and resource utilization, and the corresponding resource utilization treatment method is recommended according to the organic content, calorific value and heavy metal concentration of the sludge;

[0114] Sludge reduction is performed in step S5:

[0115] The comprehensive optimization objective function G(t) is defined to minimize the environmental risks in the treatment process and maximize the resource recovery efficiency. The objective function is:

[0116] G(t)=w1·O(t)+w2·H(t)+W3·R(t)+W4·M(t), where O(t) represents the organic matter content of the sludge at time t, H(t) represents the calorific value of the sludge, R(t) represents the resource recovery rate, M(t) represents the heavy metal concentration, and w1, w2, w3, and w4 represent weight coefficients;

[0117] The goal is to minimize G(t), giving priority to the recovery of organic matter and energy in the sludge resource recovery process, while controlling the risk of heavy metals;

[0118] Estimate the relationship between the calorific value of sludge and the recovery of organic matter, H(t) = α·O(t) + β, where α represents the correlation coefficient between calorific value and organic matter content, and β represents the basic calorific value of sludge. Adjust the recovery of organic matter to optimize the calorific value improvement;

[0119] The heavy metal concentration is taken as the optimization constraint, and the heavy metal risk control function M(t) is defined as the restriction item in the treatment process. The heavy metal concentration does not exceed the environmental protection standard, that is, M(t)≤M limit , where M(t) represents the heavy metal concentration in sludge at time t, M limit Indicates the environmental concentration standard of heavy metals;

[0120] Resource recovery rate is defined as: R(t) = γ·H(t)-δ·M(t), where γ represents the calorific value recovery efficiency coefficient and δ represents the heavy metal impact coefficient;

[0121] Based on the optimization objective function G(t) and constraints, a multi-objective optimization algorithm is used to evaluate and select various sludge resource recovery schemes. The treatment scheme parameters are adjusted during each iteration. Finally, the best resource recovery scheme is selected based on the above optimization process.

[0122] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A wastewater treatment process for pulp and paper industry, characterized by: include, Step S1, sewage pretreatment, The combined process of air flotation and gravity sedimentation is used to remove large particles, fibers and suspended solids in the sewage. Water quality sensors are installed to monitor the concentration and flow of suspended solids in the sewage, and the dosage of flocculants and coagulants is adjusted using dynamic algorithms. Step S2, staged aeration biological treatment, The wastewater pretreated in step S1 is subjected to biological treatment, and high-concentration organic matter and ammonia nitrogen are removed by staged aeration; Step S3, sludge concentration prediction control, The sludge after biological treatment enters the concentration stage. The predictive control based on the random forest algorithm is used to conduct real-time analysis of the sludge's moisture content, solid content and rheological properties, and intelligently adjust the concentration stirring intensity and concentration time. Step S4, sludge dehydration adjustment control, The sludge concentrated in step S3 enters the dehydration stage, and the moisture content and solid content of the sludge are monitored in real time. The pressure, speed and dosage of the dehydration equipment are adjusted in combination with the simulated annealing SA algorithm; Step S5, sludge reduction and resource utilization, The dehydrated sludge is treated for volume reduction and resource utilization, and the corresponding resource utilization treatment method is recommended based on the organic content, calorific value and heavy metal concentration of the sludge.

2. A pulp and paper industry wastewater treatment process according to claim 1, characterized in that: In step S1, sewage monitoring and data collection are performed, specifically: Set up water quality sensors to monitor the suspended solids concentration, flow rate and water temperature in the sewage in real time, and build a dynamic adjustment model for the dosage of the reagent to calculate the dosage of the reagent: Among them, F chem (t) represents the dosage of the agent at the current time t, C sus (t) represents the suspended solids concentration at the current time t, Q in (t) represents the sewage flow at the current time t, T(t) represents the water temperature at the current time t, C target Indicates the target suspended solids concentration, which is the preset maximum allowable concentration. α, β, and γ represent adaptive adjustment parameters, which are adjusted according to the actual needs of the sewage treatment process. It is the integral term of the historical error, representing the accumulated error of suspended matter concentration from the starting time to the current time t.

3. A pulp and paper industry wastewater treatment process according to claim 2, characterized in that: In step S1, the dosage of the agent is dynamically adjusted: Based on the sensor, the suspended solids concentration, flow rate and water temperature at the current moment are obtained, the target concentration is set, and the historical error term is calculated. When the suspended solids concentration fluctuates, it gradually approaches the target value; based on real-time data and historical error terms, the PID control algorithm is used to dynamically adjust the parameters (α, β, γ) of the dosage of the reagent.

4. A pulp and paper industry wastewater treatment process according to claim 3, characterized in that: In step S2, based on the real-time data obtained by the water quality sensor in step S1 and combined with the reinforcement learning RL algorithm, the aeration intensity and time are continuously adjusted based on the changes in ammonia nitrogen concentration and organic load.

5. A pulp and paper industry wastewater treatment process according to claim 4, characterized in that: In step S2, the staged aeration biological treatment is performed in the following manner: Based on the real-time water quality data monitored in step S1, it is used as the input of the reinforcement learning algorithm, and the aeration process is divided into pre-aeration, main aeration and post-aeration. Each stage is aerated for different ammonia nitrogen concentrations and organic loads. The aeration intensity and time of each stage are defined as: Among them, P aer (t) represents the aeration intensity at the current time t, represents the ammonia nitrogen concentration at the current time t, BOD(t) represents the organic load at the current time t, Q in (t) represents the sewage flow at the current time t, T(t) represents the water temperature at the current time t, α, β, γ represent the empirical adjustment parameters, which control the influence of various factors on the aeration intensity and need to be adjusted according to the actual situation. Optimizing aeration intensity P based on real-time feedback aer (t) and aeration time T aer (t), adjust the ammonia nitrogen removal effect, and the objective function of the reinforcement learning model is: Among them, R total (t) represents the total reward value at the current time t, represents the ammonia nitrogen concentration at the current time t, BOD(t) represents the organic load at the current time t, C target Indicates the target ammonia nitrogen concentration, which is the maximum allowable concentration, BOD target represents the target organic load, P ear (t) represents the aeration intensity at the current time t, T aer (t) represents the aeration time at the current time t, and λ1, λ2, and λ3 represent weight coefficients.

6. A pulp and paper industry wastewater treatment process according to claim 5, characterized in that: In step S2, the method of performing segmented aeration biological treatment also includes: Update aeration strategy: Among them, Q(s t ,a t ) indicates the current state s t and action a t The Q value indicates that in state s t Next, perform action a t The expected total reward, R total (t) represents the total reward value at the current time t, α represents the learning rate, which controls the response speed of the algorithm to new information, γ represents the discount factor, which represents the weight of future rewards, and s t Represents the system status at the current time t, including water quality data, a t represents the action taken at the current time t, that is, the adjusted aeration intensity and time, and updates Q(s) in the process of continuous interaction with the system environment. t ,a t ) value to optimize aeration operation; According to the optimization of RL strategy, the final aeration control formula is: Among them, ΔQ(s t ,a t ) represents the adjustment amount calculated by the RL algorithm, which indicates the aeration intensity adjustment of the current decision relative to the previous moment.

7. A pulp and paper industry wastewater treatment process according to claim 6, characterized in that: In step S3, sludge concentration and prediction control are performed: A random forest model is constructed to predict the sludge characteristics: Y(t)=f(X(t),θ)+∈(t), where Y(t) represents the prediction results of the sludge physical characteristics at the current time t, including moisture content, solid content and rheological properties, X(t) represents the set of operating parameters at the current time t, f(X(t),θ) represents the prediction function based on the operating parameters and the random forest algorithm, the learned model function, θ represents the parameters of the model, and ∈(t) represents the model error, that is, the prediction error; The physical properties and operating parameters of sludge are obtained in real time, and the moisture content, solid content and rheological properties are predicted in real time using the random forest algorithm. Then, based on the prediction results, the concentration stirring intensity and concentration time are adjusted. The control formula is: P stir (t)=α1·W(t)+α2·S(t)+α3·R(t)+β·Q sludge (t)+γ·T conc (t), T conc (t)=δ1·W(t)+δ2·S(t)+δ3·R(t)+∈·Q sludge (t), where P stir (t) represents the stirring intensity at the current time t, T conc (t) represents the concentration time at the current time t, which is determined by the physical properties of the sludge and the flow rate. W(t) represents the water content at the current time t. S(t) represents the solid content at the current time t. R(t) represents the rheological properties at the current time t. Q sludge (t) represents the sludge flow rate at the current time t, T conc (t) represents the concentration time, and α1, α2, α3, β, γ, δ1, δ2, and δ3 represent the adjustment coefficients of the model, which are used to adjust the influence of each parameter on the stirring intensity and concentration time.

8. A pulp and paper industry wastewater treatment process according to claim 7, characterized in that: In step S3, the stirring intensity and the concentration time are adjusted according to the real-time predicted physical properties of the sludge: J(t)=λ1·(W target -W(t) 2 +λ2·(S target -S(t)) 2 +λ3·(R target -R(t)) 2 +λ4·P stir (t)+λ5·T conc (t), where J(t) represents the optimization objective function at the current time t, i.e., the deviation between the target state and the actual state and the operation cost, and W target ,S target ,R target represents the target sludge characteristic value, λ1,λ2,λ3,λ4,λ5 represent weight coefficients, balance the relationship between sludge characteristic optimization and operating cost, minimize the objective function J(t), and optimize the stirring intensity and concentration time; According to the results of the optimization process, the final concentration process control formula is: P stir (t)=α1·W(t)+α2·S(t)+α3·R(t)+β·Q sludge (t)+γ·T conc (t), T conc (t)=δ1·W(t)+δ2·S(t)+δ3·R(t)+∈·Q sludge (t)。 9. A pulp and paper industry wastewater treatment process according to claim 8, characterized in that: In step S4, based on the real-time monitoring of the sludge moisture content and solid content, the simulated annealing SA algorithm is used to adjust the dehydration equipment parameters: Define the optimization objective function J(t) to describe the sludge dehydration effect. The goal is to minimize the moisture content of the sludge. The objective function form is: J(t) = w1·H(t)+w2·E(t)+w3·T(t), where H(t) represents the sludge moisture content at time point t, E(t) represents the energy consumption of the dehydration equipment at time point t, T(t) represents the total duration of the dehydration process, and w1, w2, w3 represent weight coefficients; The optimal solution is searched in the global solution space through a simulated annealing process, and the steps include: Set the initial solution P(0), N(0), C(0), and calculate the initial objective function value J(0). Based on the current solution, randomly adjust P(t), N(t), and C(t) to generate new solutions P′(t), N′(t), C′(t). Calculate the new objective function value J′(t) according to the new operating parameters. The decision on whether to accept a new solution is based on the change in the objective function value. The probability of accepting a new solution is P. accept : Among them, J′(t) represents the new objective function value, J(t) represents the current objective function value, and T(t) represents the current temperature, which gradually decreases as the iteration proceeds; According to P accept The value of determines whether to accept the new solution. If J′(t) is smaller, or a worse solution is accepted with a certain probability, P(t), N(t) and C(t) are updated to P′(t), N′(t), C′(t); With each iteration, the temperature T(t) gradually decreases, T(t) = T0·α t , where T0 represents the initial temperature, α represents the attenuation coefficient, and t represents the current number of iterations; when the temperature T(t) is less than the set threshold or the objective function value changes less than a certain threshold, the algorithm is terminated and the final parameter combination P(t), N(t) and C(t) is output.

10. A pulp and paper industry wastewater treatment process according to claim 9, characterized in that: Sludge reduction is performed in step S5: The comprehensive optimization objective function G(t) is defined to minimize the environmental risks in the treatment process and maximize the resource recovery efficiency. The objective function is: G(t)=w1·O(t)+w2·H(t)+w3·R(t)+w4·M(t), where O(t) represents the organic matter content of the sludge at time t, H(t) represents the calorific value of the sludge, R(t) represents the resource recovery rate, M(t) represents the heavy metal concentration, and w1, w2, w3, and w4 represent weight coefficients; The goal is to minimize G(t); Estimate the relationship between the calorific value of sludge and organic matter recovery, H(t) = α·O(t) + β, where α represents the correlation coefficient between calorific value and organic matter content, and β represents the basic calorific value of sludge; The heavy metal concentration is taken as the optimization constraint condition, and the heavy metal risk control function M(t) is defined as the restriction item in the treatment process. The heavy metal concentration does not exceed the environmental protection standard, that is, M(t)≤M limit , where M(t) represents the heavy metal concentration in sludge at time t, M limit Indicates the environmental concentration standard of heavy metals; Resource recovery rate is defined as: R(t) = γ·H(t)-δ·M(t), where γ represents the calorific value recovery efficiency coefficient and δ represents the heavy metal impact coefficient; Based on the optimization objective function G(t) and constraints, a multi-objective optimization algorithm is used to evaluate and select various sludge resource utilization schemes, and the treatment scheme parameters are adjusted during each iteration.

Images