Control system and control method of suspension aeration fan

Abstract

The invention provides a control system and a control method for a suspension aeration fan, and relates to the technical field of intelligent control, and the system comprises an intelligent control module which is used for carrying out the automatic analysis of the operation state of the suspension aeration fan through a fuzzy control algorithm according to the real-time operation parameters of the suspension aeration fan and the environment parameters of an aeration tank, generating a fan adjusting instruction; the execution module is used for adjusting the rotating speed and air flow operating parameters of the fan according to the fan adjusting instruction so as to control aeration; and the coupling module is used for constructing a multiphase flow coupling model, realizing real-time solution of the oxygen transfer coefficient and performing reverse optimization adjustment on the operating parameters according to a simulation result of the multiphase flow coupling model. Through the synergistic effect of the intelligent control module, the execution adjustment module, the multiphase flow coupling optimization module and the fault early warning module, intelligent, efficient and stable operation of the aeration process is achieved, and the reliability and safety of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and particularly to a control system and a control method for a suspended aeration blower. Background Art

[0002] Most traditional control technologies rely on manual experience or fixed parameter settings to adjust the operation of the blower, and it is difficult to make dynamic adjustments according to real-time water quality changes, dissolved oxygen requirements, or aeration tank load. For example, in the case of large fluctuations in influent water quality, if the blower speed and air flow rate still operate in a fixed mode, it may lead to excessive aeration (energy consumption waste) or insufficient aeration (decrease in treatment effect).

[0003] In addition, relying on regular inspections or alarms after failures, it is impossible to monitor the key parameters of the blower in real time (such as abnormal motor current, increased bearing vibration) and give early warnings of potential failures.

[0004] For example, a sewage treatment plant failed to detect abnormal fluctuations in the motor current of the blower in time (possibly caused by bearing wear or impeller imbalance), resulting in the motor burning out and shutting down. Such incidents expose the deficiencies of traditional control technologies in fault prediction and proactive maintenance. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a control system and a control method for a suspended aeration blower, which improve the operation reliability and stability of the blower.

[0006] To solve the above technical problems, the technical solution of the present invention is as follows:

[0007] In the first aspect, a control system for a suspended aeration blower includes:

[0008] An intelligent control module, configured to automatically analyze the operation state of the suspended aeration blower through a fuzzy control algorithm according to the real-time operation parameters of the suspended aeration blower and the environmental parameters of the aeration tank, and generate a blower adjustment instruction;

[0009] An execution module, configured to adjust the operation parameters of the blower speed and air flow rate according to the blower adjustment instruction to achieve the control of aeration;

[0010] A coupling module, configured to construct a multiphase flow coupling model, realize the real-time solution of the oxygen transfer coefficient, and perform reverse optimization adjustment on the operation parameters according to the simulation results of the multiphase flow coupling model;

[0011] An early warning module, configured to continuously monitor the operation state of the suspended aeration blower, and discover and give early warnings of potential fault situations through a rule-based fault diagnosis algorithm.

[0012] Further, according to the operating parameters of the real-time suspended aeration blower and the environmental parameters of the aeration tank, the operating state of the suspended aeration blower is automatically analyzed through a fuzzy control algorithm to generate a blower adjustment instruction, including:

[0013] Define the input variables and output variables of the fuzzy control;

[0014] For each input variable and output variable, define the value range and divide the value range into several fuzzy sets;

[0015] Determine the corresponding membership function for each fuzzy set, and formulate a set of fuzzy rules in combination with the fuzzy sets of the input variables and output variables,

[0016] Take the operating parameters of the real-time collected suspended aeration blower and the environmental parameters of the aeration tank as the input data of the fuzzy control;

[0017] Substitute the input data into the fuzzy control algorithm, perform fuzzy inference according to the fuzzy rules and membership functions, and obtain the fuzzy output value;

[0018] Defuzzify the fuzzy output value to generate a blower adjustment instruction.

[0019] Further, according to the blower adjustment instruction, adjust the operating parameters of the blower's rotational speed and air flow rate to achieve the control of aeration, including:

[0020] Analyze the blower adjustment instruction to identify the adjusted operating parameters, including rotational speed, air flow rate and the corresponding adjustment amount;

[0021] Generate the corresponding control signal according to the adjusted operating parameters and send the control signal to the actuator of the blower;

[0022] The actuator of the blower performs corresponding actions according to the signal instruction to achieve the control of aeration.

[0023] Further, construct a multiphase flow coupling model to achieve the real-time solution of the oxygen transfer coefficient, and perform reverse optimization adjustment of the operating parameters according to the simulation results of the multiphase flow coupling model, including:

[0024] According to the operating conditions of the aeration tank, including influent flow rate, sewage properties, aeration method, set the geometric parameters of the multiphase flow coupling model, including tank body size, aerator position, and determine the boundary conditions of the multiphase flow coupling model, including the fluid flow and mass transfer characteristics at the inlet, outlet, and tank wall;

[0025] Set the initial conditions of the multiphase flow coupling model, including the gas-liquid-solid three-phase distribution, temperature, and oxygen concentration in the tank at the initial moment, and obtain the physical property parameters of the gas-liquid-solid three phases, including density and viscosity;

[0026] Establish a multiphase flow coupling model according to the set geometric parameters, boundary conditions and initial conditions;

[0027] In the multiphase flow coupling model, analyze the dynamic characteristics of the movement trajectory, velocity and acceleration of bubbles in the liquid phase, and calculate the oxygen transfer coefficient;

[0028] According to the dynamic characteristics and oxygen transfer coefficient, obtain the simulation results, including the distribution of the oxygen transfer coefficient in the aeration tank, the distribution of gas holdup and the distribution of oxygen concentration in the liquid phase, and determine the key factors affecting the aeration efficiency by comparing the simulation results under different operating parameters, including fan speed, gas flow rate, aeration tank depth, aerator layout;

[0029] Take the brainstorm optimization algorithm as the reverse optimization algorithm, take the aeration efficiency as the goal, take the key factors as the optimization variables, optimize and solve the key operating parameters, and obtain the final operating parameter combination;

[0030] According to the final operating parameter combination, adjust the key control parameters of the fan speed and gas flow rate.

[0031] Furthermore, take the brainstorm optimization algorithm as the reverse optimization algorithm, take the aeration efficiency as the goal, take the key factors as the optimization variables, optimize and solve the key operating parameters, and obtain the final operating parameter combination, including:

[0032] Set the size of the brainstorm group, that is, determine the number of solutions participating in the optimization;

[0033] Randomly generate a set of initial solution sets, where each solution represents a combination of key process parameters, including fan speed, gas flow rate, aeration tank depth, aerator layout;

[0034] Perform creative generation operations on each solution in the initial solution set, including random mutation and cross combination, to form a new creative solution set;

[0035] Calculate the aeration efficiency value corresponding to each creative solution in the new creative solution set, and update the solution set according to the aeration efficiency value of the creative solution;

[0036] In each iteration, sort the original solutions and creative solutions in descending order of aeration efficiency;

[0037] Repeat the processes of creative generation, fitness evaluation, solution update and selection, and sorting until the preset maximum number of iterations is reached, and determine the final operating parameter combination from the solution set according to the aeration efficiency of the solutions.

[0038] Furthermore, the aeration efficiency value corresponding to each creative solution, including:

[0039] For each region, calculate three factors related to oxygen mass transfer, including temperature, pressure, and bubble size, to obtain a comprehensive oxygen mass transfer coefficient for each region;

[0040] Calculate the difference between the inlet flow rate and the outlet flow rate, and combine it with the area of the region to obtain the flow rate per unit area;

[0041] Combine the flow rate per unit area with the flow velocity to obtain the flow rate factor for each region;

[0042] Fuse the comprehensive oxygen mass transfer coefficient of each region with the flow rate factor to obtain the oxygen mass transfer amount of each region, and sum up the oxygen mass transfer amounts of all regions to obtain an overall oxygen mass transfer value;

[0043] For each region, calculate the fan efficiency to obtain the comprehensive power consumption coefficient for each region;

[0044] Combine the comprehensive power consumption coefficient of each region with the flow velocity and current to calculate the power consumption of each region, and sum up the power consumptions of all regions to obtain an overall power consumption value;

[0045] Compare the overall oxygen mass transfer value with the overall power consumption value to obtain the aeration efficiency value.

[0046] Furthermore, continuously monitor the operating status of the suspended aeration fan, and through a rule-based fault diagnosis algorithm, detect and warn of potential fault situations, including:

[0047] Collect various operating parameters of the fan, including rotational speed, air flow rate, motor current, aeration tank water level, dissolved oxygen concentration;

[0048] Match the various operating parameters of the fan with the rules in the fault diagnosis rule base to obtain the matching results of the fault diagnosis rules;

[0049] According to the matching results of the fault diagnosis rules, automatically identify potential abnormal situations during the operation of the fan. If potential fault situations are detected, trigger a warning mechanism, including generating corresponding fault alarm information.

[0050] In a second aspect, a control method for a suspended aeration fan includes:

[0051] According to the operating parameters of the suspended aeration fan and the environmental parameters of the aeration tank, use a fuzzy control algorithm to automatically analyze and make decisions on the operating status of the suspended aeration fan, and generate a fan adjustment instruction;

[0052] According to the fan adjustment instruction, adjust the operating parameters of the fan's rotational speed and air flow rate to achieve precise control of aeration;

[0053] Build a multiphase flow coupling model, realize the real-time solution of the oxygen transfer coefficient through numerical twin technology, and perform reverse optimization adjustment on the operating parameters according to the simulation results;

[0054] Continuously monitor the operating status of the suspended aeration fan, match the operating parameters of the fan with the rules in the fault diagnosis rule base, automatically identify potential abnormal situations during the operation of the fan, and trigger an early warning mechanism when a potential fault is detected, generating corresponding fault alarm information.

[0055] In a third aspect, a computing device includes:

[0056] One or more processors;

[0057] A storage device for storing one or more programs, which when executed by the one or more processors cause the one or more processors to implement the system described above.

[0058] In a fourth aspect, a computer-readable storage medium stores a program that, when executed by a processor, implements the system described above.

[0059] The above solution of the present invention has at least the following beneficial effects:

[0060] The intelligent control module automatically analyzes the operating status of the suspended aeration fan through the fuzzy control algorithm, can dynamically adjust the fan operation according to the real-time operating parameters and the aeration tank environment parameters, improve the control accuracy and response speed, and the generated fan adjustment instructions can accurately adjust the rotation speed and air flow of the fan to ensure that the aeration effect meets the process requirements. The execution module adjusts the operating parameters of the fan in real time according to the fan adjustment instructions to ensure the efficiency and stability of the aeration process. By accurately controlling the rotation speed and air flow of the fan, over-aeration or under-aeration is avoided, reducing energy consumption and operating costs. The multiphase flow coupling model constructed by the coupling module can solve the oxygen transfer coefficient in real time, providing a scientific basis for the optimization of the aeration process.

[0061] According to the simulation results of the multiphase flow coupling model, the operating parameters are adjusted reversely and optimized to further improve the aeration efficiency and oxygen transfer effect. The warning module continuously monitors the operating status of the suspended aeration blower and promptly discovers potential fault conditions. Through a rule-based fault diagnosis algorithm, the fault type is accurately identified and the warning mechanism is triggered to avoid the expansion of faults and reduce the downtime. The warning function can detect equipment hidden dangers in advance, take measures in a timely manner, and improve the reliability and safety of the system. Each module works in coordination to form a closed-loop control system, realizing the intelligentization, high efficiency, and stability of the aeration process. The system can adapt to different working conditions and aeration tank environments, automatically adjust the operating parameters, and ensure the consistency and stability of the aeration effect. The intelligent control system reduces the frequency of manual inspections and manual adjustments, and reduces the labor cost. Through precise control and fault warning, the operating time of the equipment in abnormal conditions is reduced, and the service life of the equipment is extended. Description of the Drawings

[0062] Figure 1 FIG. is a schematic diagram of a control system for a suspended aeration blower provided by an embodiment of the present invention.

[0063] Figure 2 FIG. is a schematic flow chart of a control method for a suspended aeration blower provided by an embodiment of the present invention. Detailed Embodiments

[0064] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0065] As Figure 1 shown, an embodiment of the present invention provides a control system for a suspended aeration blower, including:

[0066] An intelligent control module 1, configured to automatically analyze the operating status of the suspended aeration blower through a fuzzy control algorithm according to the real-time operating parameters of the suspended aeration blower and the environmental parameters of the aeration tank, and generate a blower adjustment instruction;

[0067] An execution module 2, configured to adjust the rotational speed and air flow operating parameters of the blower according to the blower adjustment instruction to achieve the control of aeration;

[0068] A coupling module 3, configured to construct a multiphase flow coupling model, realize the real-time solution of the oxygen transfer coefficient, and reversely optimize and adjust the operating parameters according to the simulation results of the multiphase flow coupling model;

[0069] The early warning module 4 is used to continuously monitor the operating status of the suspended aeration blower, and through a rule-based fault diagnosis algorithm, discover and give early warnings of potential fault situations.

[0070] In the embodiment of the present invention, the intelligent control module 1 can, through a fuzzy control algorithm, automatically analyze the operating status of the blower according to the real-time operating parameters of the suspended aeration blower (such as rotational speed, air flow rate, etc.) and the environmental parameters of the aeration tank (such as dissolved oxygen concentration, water quality, etc.). This intelligent analysis method not only improves the accuracy and efficiency of decision-making, but also can quickly respond to environmental changes, generate accurate blower adjustment instructions. This helps to achieve optimal control of the aeration process, improve aeration efficiency, reduce energy consumption, and enhance the overall effect of sewage treatment.

[0071] The execution module 2 can quickly and accurately adjust the operating parameters of the blower, such as rotational speed and air flow rate, according to the blower adjustment instructions generated by the intelligent control module 1. This real-time adjustment ability makes the aeration process more flexible and efficient, and can be accurately controlled according to the requirements under different working conditions. Through the precise regulation of the execution module 2, it can be ensured that the aeration volume matches the actual demand, avoiding the situations of over-aeration or under-aeration, thereby improving energy utilization efficiency and reducing operating costs.

[0072] The coupling module 3 realizes the real-time solution of the oxygen transfer coefficient by constructing a multiphase flow coupling model. This model can comprehensively consider various factors in the aeration process, such as bubble size, distribution, water flow velocity, etc., so as to more accurately describe the oxygen transfer process. Based on the simulation results of the model, the coupling module 3 can also perform reverse optimization adjustment on the operating parameters to further improve the aeration efficiency. This model-based optimization method not only improves the scientific nature of the aeration process, but also helps to discover potential problems and improvement spaces, providing strong support for the continuous optimization of the aeration system.

[0073] The early warning module 4 can, by continuously monitoring the operating status of the suspended aeration blower and using a rule-based fault diagnosis algorithm, timely discover and give early warnings of potential fault situations. This early warning mechanism helps to take measures in advance to avoid the occurrence or expansion of faults, thereby ensuring the stable operation of the aeration system. At the same time, the early warning module 4 can also provide fault diagnosis information, helping maintenance personnel quickly locate problems, shorten the maintenance time, and reduce the maintenance cost. Through the effective operation of the early warning module 4, the reliability and safety of the aeration system can be significantly improved, providing strong guarantee for the continuous and stable operation of the sewage treatment plant.

[0074] In a preferred embodiment of the present invention, according to the real-time operating parameters of the suspended aeration blower and the environmental parameters of the aeration tank, automatically analyzing the operating status of the suspended aeration blower through a fuzzy control algorithm and generating blower adjustment instructions may include:

[0075] Define the input variables and output variables of the fuzzy control;

[0076] For each input variable and output variable, define the value range and divide the value range into several fuzzy sets;

[0077] Determine the corresponding membership function for each fuzzy set, and combine the fuzzy sets of the input variables and output variables to formulate a set of fuzzy rules,

[0078] Take the operating parameters of the suspended aeration blower and the environmental parameters of the aeration tank collected in real time as the input data of the fuzzy control;

[0079] Substitute the input data into the fuzzy control algorithm, perform fuzzy inference according to the fuzzy rules and membership functions, and obtain the fuzzy output value;

[0080] Perform defuzzification on the fuzzy output value to generate a blower adjustment instruction.

[0081] In the embodiment of the present invention, identify and define the key operating parameters of the suspended aeration blower (such as rotational speed, air flow rate) and the environmental parameters of the aeration tank (such as dissolved oxygen concentration, temperature, pH value) as input variables. Determine the blower adjustment instruction (such as rotational speed increment, air flow rate adjustment amount) as the output variable, which is used to directly control the operating state of the blower. According to historical data and equipment characteristics, set the physical range for each input / output variable (such as rotational speed 0 - 3000 rpm, dissolved oxygen 0 - 10 mg / L). Divide the value range into several fuzzy sets (such as "low", "medium", "high"), and each fuzzy set covers a sub-interval (such as dissolved oxygen "low" is 0 - 3 mg / L, "medium" is 3 - 7 mg / L, "high" is 7 - 10 mg / L). Assign a membership function (such as triangular, trapezoidal) to each fuzzy set to quantify the degree to which the input value belongs to a certain fuzzy set (such as the membership degree of dissolved oxygen 5 mg / L to "medium" is 1, and to "low" and "high" is 0).

[0082] Formulate a rule base (such as "if the dissolved oxygen is low and the rotational speed is low, then increase the rotational speed"). The rules adopt the "IF - THEN" form, associating the input fuzzy sets with the output fuzzy sets. Real - time collect the blower operating parameters and the aeration tank environmental parameters through sensors, convert them into digital signals and normalize them to the value range of the fuzzy sets. Substitute the input data into the fuzzy rule base, match the antecedents of the rules one by one (such as "the dissolved oxygen is low and the rotational speed is low" is true), and activate the corresponding consequents of the rules (such as "increase the rotational speed"). Through fuzzy inference (such as Mamdani method), aggregate the output fuzzy sets of the activated rules to obtain the fuzzy distribution of the output variable (such as the membership degree of rotational speed increment being "small increase" is 0.7, and "medium increase" is 0.3).

[0083] The center of gravity method (COG) is used to defuzzify the fuzzy output distribution, calculate the exact output value (such as a rotational speed increment of +80 rpm), convert the output value into a control signal, and drive the execution module to adjust the fan.

[0084] Suppose the dissolved oxygen concentration in the aeration tank of a sewage treatment plant continuously remains below 2 mg / L (fuzzy set "low"), the rotational speed of the fan is 1500 rpm (fuzzy set "medium"), and it is necessary to improve the aeration efficiency. The membership degree of the dissolved oxygen concentration of 2 mg / L to "low" is 1, and the membership degree to "medium" is 0. The membership degree of the rotational speed of 1500 rpm to "medium" is 1, and the membership degrees to "low" and "high" are 0.

[0085] Activation rule: "If the dissolved oxygen is low and the rotational speed is medium, then increase the rotational speed (small)", and the membership degree of the output fuzzy set "small increase" is 1. The instruction generated by defuzzification is: the rotational speed increment range corresponding to the "small increase" fuzzy set is +50 - 100 rpm. Calculated by the center of gravity method, it is +75 rpm, and the rotational speed of the fan is adjusted to 1575 rpm.

[0086] Fuzzy control can flexibly respond to uncertainties such as water quality fluctuations (such as a sudden increase in influent COD) and equipment aging (such as a decrease in fan efficiency) by real-time analyzing multi-variable inputs, and avoid overshoot or lag caused by fixed parameters of traditional PID control. By precisely adjusting the rotational speed and air flow rate of the fan, excessive aeration is reduced (such as reducing the rotational speed when the dissolved oxygen > 8 mg / L), power consumption is reduced (a certain case shows a 15% - 20% reduction in energy consumption), sludge bulking caused by insufficient aeration is avoided, the dosage of chemicals and the sludge treatment cost are reduced. The fuzzy rule base is designed based on expert experience, which can prevent extreme working conditions (such as quickly increasing the rotational speed when the dissolved oxygen drops suddenly) and avoid the DO collapse in the aeration tank. The smooth transition characteristic of the membership function reduces the sudden change of control actions and prolongs the service life of the equipment (such as reducing the bearing wear caused by frequent start and stop of the fan). By linking with the early warning module, fuzzy control can identify abnormal working conditions (such as the rotational speed remaining high but the dissolved oxygen not increasing), trigger fault diagnosis in advance, shorten the maintenance response time, and the historical data record provides a basis for optimizing the fuzzy rules to achieve the iterative upgrade of the control strategy.

[0087] In a preferred embodiment of the present invention, according to the fan adjustment instruction, adjusting the rotational speed and air flow rate operating parameters of the fan to achieve the control of aeration may include:

[0088] Analyze the fan adjustment instruction to identify the adjusted operating parameters, including the rotational speed, air flow rate, and the corresponding adjustment amount;

[0089] Generate a corresponding control signal according to the adjusted operating parameters, and send the control signal to the actuator of the fan;

[0090] The actuator of the fan performs corresponding actions according to the signal instruction to achieve the control of aeration.

[0091] In an embodiment of the present invention, a fan adjustment instruction from a control module is received through a communication interface (such as RS485, CAN bus), and the instruction is transmitted in a specific protocol format (such as Modbus, JSON). The instruction string or data packet is parsed to extract key fields (such as "speed adjustment amount: +100 rpm", "air flow adjustment amount: -5%"), and it is verified whether the adjustment amount is within the allowable range (such as a speed upper limit of 3000 rpm and an air flow lower limit of 20%). If it exceeds the range, an exception handling mechanism is triggered. The parsed adjustment amount is converted into a signal type recognizable by the actuator (such as a 4-20 mA current signal, a 0-10V voltage signal). According to the actuator protocol (such as frequency control of the frequency converter, valve opening control), the adjustment amount is encoded into a specific signal value (such as a speed of +100 rpm corresponding to a 4.5 mA current increment). The signal is sent to actuators such as the fan frequency converter and pneumatic valve through an analog output module (AO) or a digital output module (DO).

[0092] The actuator (such as a frequency converter) receives the control signal and decodes it into an actual adjustment amount (such as 4.5 mA corresponding to +100 rpm). The actuator drives the motor or valve to adjust the speed or air flow to the target value (such as the frequency converter adjusts the output frequency to increase the fan speed from 1500 rpm to 1600 rpm). The actuator monitors the actual value in real time through sensors (such as a speed encoder, a flow meter), and performs closed-loop control on the data.

[0093] Suppose the dissolved oxygen concentration in a certain aeration tank drops from 3 mg / L to 2 mg / L, and the control module issues an instruction "increase the speed by 150 rpm and increase the air flow by 8%". After receiving the instruction, the speed adjustment amount of +150 rpm and the air flow adjustment amount of +8% are parsed. It is verified that both adjustment amounts are within the allowable range (speed upper limit of 3000 rpm, air flow upper limit of 120%). The +150 rpm is converted into a frequency signal of the frequency converter. Assuming that 1 rpm corresponds to 0.01 Hz, a frequency increment of +1.5 Hz is sent (such as the original frequency is 30 Hz, and after adjustment it is 31.5 Hz). The +8% is converted into a valve opening signal. Assuming that the valve opening of 0-100% corresponds to 4-20 mA, a current increment of +0.96 mA is sent (such as the original current is 12 mA, and after adjustment it is 12.96 mA). The frequency converter receives the 31.5 Hz signal and adjusts the motor speed to 1650 rpm (original 1500 rpm). The valve receives the 12.96 mA signal, and the opening increases to 52% (original 48%), the air flow is increased to the target value, and the speed encoder and flow meter monitor the data in real time and send back a confirmation that the adjustment is in place.

[0094] By real-time analysis of instructions and precise adjustment of parameters, it can quickly respond to changes in water quality (such as dissolved oxygen fluctuations), maintain aeration volume within the optimal range (within ±5% error), and avoid over-aeration or under-aeration. The rotation speed and air flow rate are adjusted in conjunction (such as high rotation speed with atmospheric flow rate) to improve oxygen transfer efficiency (one case shows that oxygen utilization rate increased by 12%), reduce energy consumption per unit aeration volume, avoid imbalance caused by single parameter adjustment (such as only increasing the rotation speed but insufficient air flow), and extend equipment life. The actuator state feedback mechanism forms a closed-loop control, which can correct deviations in real time (such as automatic compensation when the actual speed is 5rpm lower than the target value) to ensure control accuracy. The abnormal detection function (such as signal loss, actuator failure) can quickly trigger an alarm to prevent the system from losing control. Parameter adjustment records (such as speed change history) provide a basis for equipment maintenance, and predictive maintenance (such as frequent adjustments may indicate valve wear) reduces downtime. Standardized signal interfaces reduce the cost of actuator replacement and are compatible with different brands of equipment (such as inverters that support Modbus protocol).

[0095] In a preferred embodiment of the present invention, a multiphase flow coupling model is constructed to achieve real-time solution of the oxygen transfer coefficient, and reverse optimization adjustment of the operating parameters is performed according to the simulation results of the multiphase flow coupling model, which may include:

[0096] According to the operating conditions of the aeration tank, including the inlet flow rate, sewage properties, and aeration method, the geometric parameters of the multiphase flow coupling model, including the tank size and aerator position, are set, and the boundary conditions of the multiphase flow coupling model, including the fluid flow and mass transfer characteristics at the inlet, outlet, and tank wall, are determined;

[0097] Set the initial conditions of the multiphase flow coupling model, including the gas-liquid-solid three-phase distribution, temperature, and oxygen concentration in the pool at the initial moment, and obtain the physical property parameters of the gas-liquid-solid three-phase, including density and viscosity;

[0098] Establish a multiphase flow coupling model based on the set geometric parameters, boundary conditions and initial conditions;

[0099] In the multiphase flow coupling model, the motion trajectory, velocity and acceleration dynamics of the bubble in the liquid phase are analyzed, and the oxygen transfer coefficient is calculated;

[0100] According to the kinetic characteristics and oxygen transfer coefficient, the simulation results are obtained, including the distribution of oxygen transfer coefficient in the aeration tank, the distribution of gas holdup and the distribution of oxygen concentration in the liquid phase. By comparing the simulation results under different operating parameters, the key factors affecting aeration efficiency, including fan speed, gas flow, aeration tank depth and aerator layout, are determined;

[0101] Taking the brainstorm optimization algorithm as the reverse optimization algorithm, with the aeration efficiency as the goal and the key factors as the optimization variables, optimize and solve the key operating parameters to obtain the final combination of operating parameters;

[0102] According to the final combination of operating parameters, adjust the key control parameters such as the rotational speed and air flow rate of the blower.

[0103] In the embodiment of the present invention, according to the design drawings of the aeration tank, automatically extract parameters such as the tank body dimensions (length × width × depth) and the positions of the aerators (coordinates and spacing), and generate a three-dimensional grid model. Combining the influent flow rate (m 3 / h), sewage properties (COD, SS concentration), and aeration methods (micro-pore aeration, jet aeration), the machine sets the flow velocity distribution at the inlet, the pressure conditions at the outlet, and the no-slip boundary and mass transfer coefficient (such as the oxygen mass transfer coefficient k_L) at the pool wall. Collect the initial gas-liquid-solid three-phase distribution (such as the gas volume fraction 0.1), temperature (25 °C), and dissolved oxygen concentration (2 mg / L) in the pool through sensors and input them into the model. Retrieve parameters such as the densities of the gas-liquid-solid three phases (such as air 1.2 kg / m 3 and water 1000 kg / m 3 ) and viscosities (water 0.001 Pa·s) from the database and assign them to the model. Using computational fluid dynamics (CFD) software (such as ANSYS Fluent) or self-written code, based on the Navier-Stokes equation and the mass transfer equation, couple the gas-liquid two-phase flow (VOF model) with the solid phase deposition (discrete phase model) to generate a multi-physics field coupling model.

[0104] Simulate the rising process of bubbles in the liquid phase and calculate their velocity (u b ), acceleration (a b ) and deformation (such as spherical → ellipsoidal).

[0105] Among them, different flow regions are distinguished according to the Reynolds number (Re); Stokes region (Re < 1): ρ l is the liquid phase, ρ g is the gas phase density; g is the acceleration due to gravity; d b is the bubble diameter; μ l is the dynamic viscosity of the liquid phase. Intermediate transition region (1 < Re < 1000): Numerical iteration is required. Newton region (Re > 1000): C D is the drag coefficient (for spherical bubbles, take 0.44). Based on Newton's second law, considering the balance of buoyancy and drag: F D is the drag; V bis the volume of the bubble. Based on the Higbie penetration theory, combined with the bubble size distribution and the liquid-phase turbulence intensity (ε), the local oxygen transfer coefficient is calculated. D L is the diffusion coefficient of oxygen in the liquid phase.

[0106] By changing parameters such as the fan speed (e.g., 1000 - 3000 rpm) and the gas flow rate (e.g., 10 - 50 m 3 / min), comparing the simulation results, the factors that have the greatest impact on the aeration efficiency are identified. The Brain Storm Optimization (BSO) algorithm is called. With the maximization of the aeration efficiency as the goal, the key factors (speed, gas flow rate, aerator depth) are used as optimization variables, and the constraint conditions are set (e.g., speed ≤ 3000 rpm). Through swarm intelligence iteration, the BSO algorithm generates the final operating parameter combination (e.g., speed 2200 rpm, gas flow rate 35 m 3 / min, aerator depth 4 m). The optimization results are sent to the execution module to adjust the fan speed and gas flow rate, and the dissolved oxygen concentration is continuously monitored to close-loop correct the model parameters (such as empirical coefficients).

[0107] Suppose the aeration efficiency of the aeration tank in a sewage treatment plant decreases, and the operating parameters need to be optimized.

[0108] The tank size is 20 m × 10 m × 5 m, there are 40 aerators (evenly distributed at the bottom), the influent flow rate is 500 m 3 / h, COD = 300 mg / L, and microporous aeration is adopted. The gas-phase volume fraction is 0.05, the temperature is 20 °C, and the dissolved oxygen is 1.5 mg / L. The simulation finds that bubble coalescence is serious in some areas, resulting in k L locally as low as 0.002 m / s. The dissolved oxygen concentration gradient at the bottom of the tank is large (1 - 4 mg / L), indicating uneven mass transfer. The weight of the speed on k L is 60%, the weight of the gas flow rate is 30%, and the weight of the aerator depth is 10%. After 100 iterations, the final parameters are obtained (speed 2400 rpm, gas flow rate 40 m 3 / min, aerator depth 3.5 m). After the parameter adjustment, the dissolved oxygen concentration is increased to 5 mg / L, the aeration efficiency is increased by 25%, and the energy consumption is reduced by 18%.

[0109] By solving the oxygen transfer coefficient k L, the mass transfer efficiency of different regions can be quantified, and the aeration intensity can be adjusted accordingly (such as increasing the gas flow rate at the bottom of the pool) to make the dissolved oxygen distribution uniform (with an error of ±0.5 mg / L). The reverse optimization algorithm avoids over-aeration (such as 30% over-dose in traditional methods). A certain case shows that the energy consumption is reduced by 22%, and the annual electricity cost savings exceed 100,000 yuan. The model simulates the influence of different layouts of aerators (such as spacing, depth) on the gas holdup, guides the transformation plan (such as changing from uniform distribution to zonal intensification), and improves the oxygen utilization rate by 15%. The model can predict the influence of influent water quality fluctuations (such as sudden increase in COD) on mass transfer, adjust parameters in advance (such as increasing the rotation speed), and maintain stable aeration. The BSO algorithm combines machine learning, can autonomously learn the optimal parameter combination, reduce the cost of manual trial and error, and shorten the commissioning cycle (from weeks to days).

[0110] In another preferred embodiment of the present invention, the brainstorming optimization algorithm is used as the reverse optimization algorithm. Taking the aeration efficiency as the goal and the key factors as the optimization variables, the key operating parameters are optimized and solved to obtain the final operating parameter combination, which may include:

[0111] Set the scale of the brainstorming group, that is, determine the number of solutions participating in the optimization;

[0112] Randomly generate a set of initial solution sets, where each solution represents a combination of key process parameters, including fan rotation speed, gas flow rate, aeration tank depth, and aerator layout;

[0113] Perform creative generation operations on each solution in the initial solution set, including random mutation and cross combination, to form a new creative solution set;

[0114] Calculate the aeration efficiency value corresponding to each creative solution in the new creative solution set, and update the solution set according to the aeration efficiency value of the creative solution;

[0115] In each iteration, sort the original solutions and creative solutions in descending order of aeration efficiency;

[0116] Repeat the processes of creative generation, fitness evaluation, solution update and selection, and sorting until the preset maximum number of iterations is reached, and determine the final operating parameter combination from the solution set according to the aeration efficiency of the solutions.

[0117] In the embodiment of the present invention, set the population scale N (such as N = 50), which represents the number of solutions participating in the optimization, and allocate storage space for storing the solution set and its corresponding aeration efficiency value.

[0118] Define the range of key process parameters:

[0119] Fan rotation speed: [v min ,v max ;

[0120] Gas flow rate: [qmin , q max ;

[0121] Aeration tank depth: [h min , h max

[0122] Aerator layout (such as position coordinates): [x min , x max , [y min , y max ;

[0123] Randomly generate N sets of solutions, each set of solutions contains a combination of the above parameters, and store the initial solution set S o .

[0124] For each solution s i ∈S0, randomly select one or more parameters for slight perturbation (such as adding or subtracting a random number). Randomly select two solutions s i , s j ∈S0, exchange one or more parameter values of them to form new solutions, generate a new set of creative solutions S new , which contains N new solutions. Calculate the aeration efficiency of each solution s in S new . Obtain the aeration efficiency value through simulation, merge the original solution set S0 and S new , and form a merged solution set. Sort the merged solution set according to the aeration efficiency value, and select the first N solutions as the new solution set. Repeat the process of creative generation, fitness evaluation, solution update and selection, and sorting until the preset maximum number of iterations is reached. In each iteration, record the final solution and its aeration efficiency value. Select the solution with the highest aeration efficiency from the solution set of the last iteration as the final operating parameter combination, and output the final parameter combination and its corresponding aeration efficiency value.

[0125] Assume the optimization goal is: maximize the aeration efficiency.

[0126] The key process parameters include the fan speed v ∈ [1000, 3000] RPM, the air flow rate q ∈ [50, 150] m 3 / h, the aeration tank depth h ∈ [3, 6] m, and the aerator layout (position): x, y ∈ [0, 10] m (assuming a two-dimensional plane). Set N = 50, and randomly generate 50 sets of solutions, each set of solutions contains a combination of v, q, h, x, and y.

[0127] Mutate the solution s1 = (v = 1500, q = 80, h = 4, x = 2, y = 3) to obtain s'1 = (v = 1550, q = 82, h = 4.1, x = 2.1, y = 3.2).

[0128] ​Cross the solutions s2 = (v = 2000, q = 100, h = 5, x = 5, y = 5) and s3 = (v = 2500, q = 120, h = 5.5, x = 7, y = 8) to obtain s ew = (v = 2000, q = 120, h = 5.5, x = 5, y = 8). Calculate the aeration efficiency of each new solution. Assume it is predicted by a surrogate model, merge and sort them, and select the top 50 solutions as the new solution set. Repeat the iteration until reaching T max = 100 iterations, and output the final solution, such as s best = (v = 2200, q = 110, h = 5.2, x = 6, y = 7), and the aeration efficiency is 85%.

[0129] By optimizing the key process parameters, improve the oxygen transfer efficiency of the aeration system, reduce energy consumption, the algorithm automatically searches for the final solution, reduces the cost of manual trial and error, and improves the optimization efficiency. It can adapt to aeration systems of different scales. By adjusting the parameter range and population size, personalized optimization can be achieved. Record the optimal solution and its parameter combination for each iteration during the optimization process, which is convenient for analyzing the influence law of parameters on the aeration efficiency. If combined with real-time data acquisition and feedback mechanism, the algorithm can adjust parameters online to adapt to the dynamic changes during operation. By optimizing the operating parameters, reduce unnecessary energy consumption and equipment wear, and reduce the operating cost.

[0130] In another preferred embodiment of the present invention, the aeration efficiency values corresponding to each creative solution include:

[0131] For each region, calculate three factors related to oxygen mass transfer, including temperature, pressure, and bubble size, to obtain a comprehensive oxygen mass transfer coefficient for each region;

[0132] By calculating the difference between the inlet flow rate and the outlet flow rate, and combining with the area of the region, obtain the flow rate per unit area;

[0133] Combine the flow rate per unit area with the flow velocity to obtain the flow rate factor for each region;

[0134] Fuse the comprehensive oxygen mass transfer coefficient of each region with the flow rate factor to obtain the oxygen mass transfer amount of each region, and sum up the oxygen mass transfer amounts of all regions to obtain an overall oxygen mass transfer value;

[0135] For each region, calculate the fan efficiency to obtain the comprehensive power consumption coefficient for each region;

[0136] Combine the comprehensive power consumption coefficient of each region with the flow velocity and current to calculate the power consumption of each region, and sum up the power consumptions of all regions to obtain an overall power consumption value;

[0137] Compare the overall oxygen mass transfer value with the overall power consumption value to obtain the aeration efficiency value.

[0138] In an embodiment of the present invention, the temperature (T i ) of each region, pressure (P i ), and bubble size S i data are collected, and coefficients (a i , b i , c i ) related to oxygen mass transfer are determined. Assume a i = 1.2, b i = 1.2, c i = 0.8, and these coefficients are obtained through experience.

[0139] Normalize the temperature (T i ), pressure (P i ), and bubble size S i to convert parameters with different units into a dimensionless form, eliminating the influence of dimensions on the calculation results, that is:

[0140] Temperature normalization:

[0141] Pressure normalization:

[0142] Bubble size normalization:

[0143] where T min , T max , P min , P max , S min , S max are the minimum and maximum values of temperature, pressure, and bubble size respectively.

[0144] For each region i, use the normalized parameters to calculate the quantified oxygen mass transfer capacity value: Collect the inlet flow rate (Q n,i ) and outlet flow rate Q o,i of each region and the area A i of the region. For each region i, use the formula to obtain the flow rate per unit area of each region. Collect the flow velocity V i of each region and use the formula to obtain the flow rate factor of each region. For each region i, sum up the oxygen mass transfer

[0145] Collect the fan efficiency (η f,i ) and motor efficiency (η m,i), determine the coefficient related to power consumption (e i , f i ) Assume e i = 2.0, f i = 1.5. For each region i, use the formula to obtain the comprehensive power consumption coefficient. For each region i, use the formula to calculate the power consumption. Aggregate the power consumption of all regions Use the obtained overall oxygen mass transfer value and the obtained overall power consumption value to calculate the aeration efficiency value

[0146] By comprehensively considering oxygen mass transfer and power consumption, the overall performance of the aeration system can be evaluated more accurately. By analyzing the oxygen mass transfer coefficient and power consumption coefficient of each region, parameters such as temperature, pressure, and flow rate can be adjusted targeted to optimize the system efficiency. Independent analysis of each region can identify performance bottlenecks or inefficient regions, providing a basis for local optimization. By reducing power consumption, the usage efficiency of equipment can be improved, the equipment life can be extended, and the maintenance cost can be reduced. The provided aeration efficiency value can be used as decision support to help engineers or operators select the optimal operation strategy or equipment configuration. The optimized aeration system can reduce unnecessary energy consumption, lower carbon emissions, meet environmental protection requirements. By balancing oxygen mass transfer and power consumption, the stability and reliability of the system can be improved, and the occurrence of faults can be reduced. The operation cost can be reduced, and the production efficiency can be improved, thus bringing direct economic benefits. It is applicable to aeration systems of different scales and configurations and has wide applicability.

[0147] In a preferred embodiment of the present invention, continuously monitor the operating status of the suspended aeration fan, and through a rule-based fault diagnosis algorithm, discover and warn of potential fault situations, which may include:

[0148] Collect various operating parameters of the fan, including rotational speed, air flow rate, motor current, aeration tank water level, dissolved oxygen concentration;

[0149] Match the various operating parameters of the fan with the rules in the fault diagnosis rule library to obtain the matching results of the fault diagnosis rules;

[0150] According to the matching results of the fault diagnosis rules, automatically identify potential abnormal situations during the operation of the fan. If potential fault situations are detected, trigger an early warning mechanism, including generating corresponding fault alarm information.

[0151] In the embodiments of the present invention, sensors for monitoring the operating state of a fan are connected and initialized, including a rotational speed sensor, an air flow sensor, a motor current sensor, a water level sensor, and a dissolved oxygen concentration sensor, to ensure that sensor data is transmitted to the data processing module in real time. The following parameters are collected at a fixed frequency (such as per second or per minute), including rotational speed, air flow, motor current, water level in the aeration tank, and dissolved oxygen concentration. The collected data is filtered to remove noise, and the data is standardized or normalized. A predefined fault diagnosis rule library is loaded from a storage medium (such as a database or a file), and the rule library contains multiple rules, and each rule defines a set of conditions and the corresponding fault types.

[0152] For each rule, check whether the currently collected parameters meet the rule conditions. For example, the rule is defined as: if the rotational speed > the maximum rotational speed and the motor current > the threshold of the motor current, then there may be an "overload" fault, and record the rule that meets the conditions and its matching result. According to the rule matching result, identify potential abnormal situations. If multiple rules point to the same fault type, increase the confidence level of this fault. Classify the identified abnormal situations into specific fault types, such as "overload", "blockage", "leakage", etc. If a potential fault is detected, generate corresponding fault alarm information, including the fault type, the fault occurrence time, relevant parameter values, and recommended countermeasures. Send the alarm information to the monitoring interface or the terminal device of the operation and maintenance personnel, and you can choose to trigger an audible and visual alarm or send a text message / email notification. Record the fault information in the log database.

[0153] Assume that the monitoring object is: a suspended aeration fan

[0154] Monitoring parameters: rotational speed v = 1800 RPM, air flow q = 120 m 3 / h, motor current I = 15 A, water level in the aeration tank h = 4.5 m, dissolved oxygen concentration DO = 6 mg / L.

[0155] Example of the rule library

[0156] Rule 1: Condition: v > 1700 RPM and I > 12 A, fault type: "overload"; Rule 2: Condition: q < 100 m 3 / h and h > 4 m, fault type: "blockage"; Rule 3: Condition: DO < 5 mg / L and q > 150 m 3 / h, fault type: "low oxygen mass transfer efficiency".

[0157] Collected parameters: v = 1800 RPM, I = 15 A, q = 120 m 3 / h, h = 4.5 m, DO = 6 mg / L. Rule matching: Rule 1 matches successfully (v = 1800 > 1700 and I = 15 > 12); Rule 2 does not match (q = 120 < 100); Rule 3 does not match (DO = 6 < 5); The "overload" fault is identified. Generate an alarm message: "An overload fault is detected. It is recommended to check the fan load and reduce the speed." Trigger an audible and visual alarm and send a text message to notify the operation and maintenance personnel.

[0158] Through real-time monitoring and early warning, potential faults can be discovered and handled in a timely manner, reducing downtime. Preventive maintenance reduces sudden failures, lowers maintenance costs and equipment replacement frequency, avoids equipment operation in abnormal states, extends equipment service life, optimizes fan operation parameters, improves aeration efficiency, reduces energy consumption, discovers and handles safety hazards in a timely manner, ensures the safety of personnel and equipment, and provides fault information and recommended measures to help operation and maintenance personnel respond quickly and make decisions. The rule library can be customized according to different fan models and operating environments, with strong adaptability. Real-time monitoring and early warning ensure that faults are discovered and handled in the initial stage.

[0159] As Figure 2 shown, an embodiment of the present invention also provides a control method for a suspended aeration fan, including:

[0160] According to the operating parameters of the real-time suspended aeration fan and the environmental parameters of the aeration tank, use the fuzzy control algorithm to automatically analyze and make decisions on the operating state of the suspended aeration fan, and generate a fan adjustment instruction;

[0161] According to the fan adjustment instruction, adjust the operating parameters such as the speed and air flow rate of the fan to achieve precise control of aeration;

[0162] Construct a multiphase flow coupling model, realize the real-time solution of the oxygen transfer coefficient through numerical twin technology, and perform reverse optimization adjustment on the operating parameters according to the simulation results;

[0163] Continuously monitor the operating state of the suspended aeration fan, match the operating parameters of the fan with the rules in the fault diagnosis rule library, automatically identify potential abnormal situations during the operation of the fan, and trigger an early warning mechanism when potential faults are detected, generating corresponding fault alarm messages.

[0164] It should be noted that this method corresponds to the above system. All implementation methods in the above system embodiment are applicable to this embodiment and can achieve the same technical effects.

[0165] An embodiment of the present invention also provides a computing device, including: a processor and a memory storing a computer program. When the computer program is run by the processor, it executes the above-mentioned system. All implementation methods in the above system embodiment are applicable to this embodiment and can achieve the same technical effects.

[0166] An embodiment of the present invention also provides a computer-readable storage medium storing instructions that, when run on a computer, cause the computer to execute the system described above. All implementation manners in the above system embodiment are applicable to this embodiment and can also achieve the same technical effects.

[0167] The above are the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A control system for a suspended aeration fan, characterized in that, including: An intelligent control module, which is used to automatically analyze the operating state of the suspended aeration blower through a fuzzy control algorithm according to the operating parameters of the real-time suspended aeration blower and the environmental parameters of the aeration tank, and generate a blower adjustment instruction; An execution module, which is used to adjust the operating parameters of the blower's rotational speed and air flow rate according to the blower adjustment instruction to achieve the control of aeration; A coupling module, which is used to construct a multiphase flow coupling model, realize the real-time solution of the oxygen transfer coefficient, and reversely optimize and adjust the operating parameters according to the simulation results of the multiphase flow coupling model; An early warning module, which is used to continuously monitor the operating state of the suspended aeration blower, and discover and give early warning of potential fault conditions through a rule-based fault diagnosis algorithm.

2. The control system of the suspended aeration fan according to claim 1, wherein, Automatically analyzing the operating state of the suspended aeration blower through a fuzzy control algorithm according to the operating parameters of the real-time suspended aeration blower and the environmental parameters of the aeration tank, and generating a blower adjustment instruction, including: Defining the input variables and output variables of the fuzzy control; For each input variable and output variable, defining the value range and dividing the value range into several fuzzy sets; Determining the corresponding membership function for each fuzzy set, and formulating a set of fuzzy rules in combination with the fuzzy sets of the input variables and output variables; Taking the operating parameters of the real-time collected suspended aeration blower and the environmental parameters of the aeration tank as the input data of the fuzzy control; Substituting the input data into the fuzzy control algorithm, performing fuzzy inference according to the fuzzy rules and membership functions, and obtaining the fuzzy output value; Defuzzifying the fuzzy output value to generate a blower adjustment instruction.

3. The control system of the suspended aeration fan according to claim 2, characterized in that, Adjusting the operating parameters of the blower's rotational speed and air flow rate according to the blower adjustment instruction to achieve the control of aeration, including: Parsing the blower adjustment instruction to identify the adjusted operating parameters, including rotational speed, air flow rate and the corresponding adjustment amount; Generating the corresponding control signal according to the adjusted operating parameters and sending the control signal to the actuator of the blower; The actuator of the blower performs corresponding actions according to the signal instruction to achieve the control of aeration.

4. The control system of the suspended aeration blower according to claim 3, characterized in that, Constructing a multiphase flow coupling model, realizing the real-time solution of the oxygen transfer coefficient, and reversely optimizing and adjusting the operating parameters according to the simulation results of the multiphase flow coupling model, including: According to the operating conditions of the aeration tank, including influent flow rate, sewage properties, aeration mode, setting the geometric parameters of the multiphase flow coupling model, including tank body size, aerator position, and determining the boundary conditions of the multiphase flow coupling model, including the fluid flow and mass transfer characteristics at the inlet, outlet, and tank wall; Setting the initial conditions of the multiphase flow coupling model, including the gas-liquid-solid three-phase distribution, temperature, and oxygen concentration in the tank at the initial moment, and obtaining the physical property parameters of the gas-liquid-solid three phases, including density and viscosity; Establishing a multiphase flow coupling model according to the set geometric parameters, boundary conditions and initial conditions; Analyzing the dynamic characteristics of the movement trajectory, velocity and acceleration of bubbles in the liquid phase in the multiphase flow coupling model, and calculating the oxygen transfer coefficient. According to the kinetic characteristics and oxygen transfer coefficient, obtain the simulation results, including the distribution of the oxygen transfer coefficient in the aeration tank, the distribution of the gas holdup, and the distribution of the oxygen concentration in the liquid phase. By comparing the simulation results under different operating parameters, determine the key factors affecting the aeration efficiency, including the fan speed, gas flow rate, aeration tank depth, and aerator layout; Take the brainstorm optimization algorithm as the reverse optimization algorithm. With the aeration efficiency as the goal and the key factors as the optimization variables, optimize and solve the key operating parameters to obtain the final combination of operating parameters; According to the final combination of operating parameters, adjust the key control parameters of the fan speed and gas flow rate.

5. The control system of the suspended aeration fan according to claim 4, characterized in that, Take the brainstorm optimization algorithm as the reverse optimization algorithm. With the aeration efficiency as the goal and the key factors as the optimization variables, optimize and solve the key operating parameters to obtain the final combination of operating parameters, including: Set the size of the brainstorm group, that is, determine the number of solutions participating in the optimization; Randomly generate a set of initial solution sets, where each solution represents a combination of key process parameters, including fan speed, gas flow rate, aeration tank depth, and aerator layout; Perform creative generation operations on each solution in the initial solution set, including random mutation and cross combination, to form a new set of creative solutions; Calculate the aeration efficiency value corresponding to each creative solution in the new set of creative solutions, and update the solution set according to the aeration efficiency value of the creative solution; In each iteration, sort the original solutions and creative solutions in descending order of aeration efficiency; Repeat the process of creative generation, fitness evaluation, solution update and selection, and sorting until the preset maximum number of iterations is reached. Determine the final combination of operating parameters from the solution set according to the aeration efficiency of the solutions.

6. The control system of the suspended aeration fan according to claim 5, characterized in that, The aeration efficiency value corresponding to each creative solution, including: For each region, calculate three factors related to oxygen mass transfer, including temperature, pressure, and bubble size, to obtain a comprehensive oxygen mass transfer coefficient for each region; Calculate the difference between the inlet flow rate and the outlet flow rate, and combine it with the area of the region to obtain the flow rate per unit area; Combine the flow rate per unit area with the flow velocity to obtain the flow rate factor for each region; Fuse the comprehensive oxygen mass transfer coefficient of each region with the flow rate factor to obtain the oxygen mass transfer amount of each region, and sum up the oxygen mass transfer amounts of all regions to obtain an overall oxygen mass transfer value; For each region, calculate the fan efficiency to obtain the comprehensive power consumption coefficient for each region; Combine the comprehensive power consumption coefficient of each region with the flow velocity and current to calculate the power consumption of each region, and sum up the power consumptions of all regions to obtain an overall power consumption value; Compare the overall oxygen mass transfer value with the overall power consumption value to obtain the aeration efficiency value.

7. The control system of the suspended aeration blower according to claim 6, characterized in that, Continuously monitor the operating status of the suspended aeration fan, and through a rule-based fault diagnosis algorithm, discover and warn of potential fault situations, including: Collect various operating parameters of the fan, including speed, gas flow rate, motor current, aeration tank water level, dissolved oxygen concentration; Match the various operating parameters of the fan with the rules in the fault diagnosis rule base to obtain the matching results of the fault diagnosis rules; Automatically identify potential abnormal situations during the operation of the fan according to the matching results of the fault diagnosis rules. If potential fault situations are detected, trigger an early warning mechanism, including generating corresponding fault alarm information.

8. A control method for a suspended aeration blower, the method implementing the system according to any one of claims 1 to 7, characterized in that, Including: Automatically analyze and make decisions on the operating state of the suspended aeration fan by using the fuzzy control algorithm according to the operating parameters of the real-time suspended aeration fan and the environmental parameters of the aeration tank, and generate fan adjustment instructions; Adjust the rotational speed and air flow operating parameters of the fan according to the fan adjustment instructions to achieve precise control of aeration; Construct a multiphase flow coupling model, realize the real-time solution of the oxygen transfer coefficient through numerical twin technology, and perform reverse optimization adjustment on the operating parameters according to the simulation results; Continuously monitor the operating state of the suspended aeration fan, match the operating parameters of the fan with the rules in the fault diagnosis rule base, automatically identify potential abnormal situations during the operation of the fan, and trigger an early warning mechanism when potential faults are detected, generating corresponding fault alarm information.

9. A computing device, characterized in that, Including: One or more processors; A storage device for storing one or more programs, which when executed by the one or more processors cause the one or more processors to implement the system according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A program is stored in the computer-readable storage medium, and when the program is executed by a processor, the system according to any one of claims 1 to 7 is implemented.

Images