Pneumatic conveying system optimization method and system based on multi-target particle swarm

Abstract

The invention provides a pneumatic conveying system optimization method and system based on a multi-target particle swarm, and relates to the technical field of pneumatic transportation, and the method comprises the steps: collecting key transportation data affecting the conveying efficiency, the energy consumption and the system stability, employing a particle swarm algorithm, regarding each particle as a group of optimizable parameter combinations, and obtaining a particle swarm optimization parameter combination; the method comprises the following steps: calculating a pneumatic transport performance index based on an engineering formula, generating a fitness value by adopting a weighted summation method, comparing the fitness value with a preset threshold value, determining whether optimization is needed or not, carrying out iterative optimization by updating particle positions and speeds by taking minimization of pipeline wear, energy consumption and pressure fluctuation as targets, and when the fitness value meets a threshold value condition, carrying out iterative optimization on the particle positions and speeds. And selecting an optimal solution based on a minimum deviation method. The pneumatic conveying system is optimized based on the multi-target particle swarm algorithm, and the conveying efficiency and the system stability are improved under the target of minimizing pipeline abrasion, energy consumption and pressure fluctuation.

Description

Technical Field

[0001] The present invention relates to the field of pneumatic transportation technology, and in particular to a pneumatic transportation system optimization method and system based on multi-objective particle swarm. Background Art

[0002] Pneumatic conveying system is a solid material conveying method widely used in the industrial field. Its optimization design needs to comprehensively consider multiple performance indicators such as energy consumption, pipeline wear and pressure fluctuation. However, traditional optimization methods are difficult to effectively deal with the complex coupling and conflict between these performance indicators. As an intelligent optimization algorithm, multi-objective particle swarm optimization has powerful global search capabilities and efficient multi-objective solving characteristics, providing a compromise solution for complex multi-objective problems. Introducing multi-objective particle swarm optimization into the optimization of pneumatic conveying system, the parameter configuration with the lowest energy consumption, the lowest wear and the best pressure fluctuation can be obtained by iterating the position and speed of particles, thus greatly improving the system performance.

[0003] The pneumatic conveying system optimization method based on multi-objective particle swarm has broad application prospects in the future. With the development of industrial automation and intelligence, the combination of optimization algorithms with technologies such as the Internet of Things, big data, and digital twins will further improve the optimization efficiency and accuracy, making dynamic adjustment and real-time optimization possible. In addition, the widespread demand for pneumatic conveying systems in the fields of chemical, pharmaceutical, and food has promoted the research and application of intelligent optimization methods. In the future, multi-objective particle swarm optimization technology can be combined with green and energy-saving design concepts to achieve efficient, reliable, and low-cost operation of pneumatic conveying systems, providing technical support for the sustainable development of industrial production.

[0004] Existing technologies usually only focus on a single performance indicator, such as energy consumption or pipeline wear, while ignoring the balance between system stability and multiple objectives, lacking comprehensive consideration of the system's multi-dimensional performance, and often relying on fixed parameter combinations and a single empirical formula during the optimization process, lacking flexible adaptability.

[0005] In addition, the existing technology often ignores the control of system stability during the optimization process of pneumatic conveying systems, which may lead to unstable working conditions in the optimization scheme, increase the risk of system failure, and lack of comprehensive consideration of the interaction between equipment and operating parameters. Finally, the selection of optimization results usually relies on manually set empirical values ​​or simple model evaluations, which makes it difficult to achieve accurate optimization effects.

[0006] Therefore, it is necessary to provide a pneumatic conveying system optimization method and system based on multi-objective particle swarm to solve the above problems.

[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0008] The purpose of the present invention is to provide a method and system for optimizing a pneumatic conveying system based on a multi-objective particle swarm, so as to solve the problems raised in the above-mentioned background technology.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] A pneumatic conveying system optimization method based on multi-objective particle swarm, the specific steps include:

[0011] Step 1: Obtain the pneumatic conveying parameters in the pneumatic conveying system, determine the optimizable parameters that need to be optimized in the pneumatic conveying system, establish a functional relationship between the optimizable parameters and the performance coefficient, and establish a functional relationship between the performance coefficient and the pneumatic conveying fitness value. The pneumatic conveying parameters are divided into optimizable parameters and fixed value parameters. The optimizable parameters include conveying gas velocity, fan efficiency, gas volume flow rate, system operating pressure drop, and system average pressure. The fixed value parameters include pipeline diameter, total material mass, conveying distance, material particle concentration, and material density. The performance coefficient includes pipeline wear coefficient, energy consumption coefficient, and pressure fluctuation coefficient.

[0012] Step 2: Set the effective range of the optimizable parameters, take minimizing the pneumatic transport fitness value as the optimization goal, randomly generate multiple particles based on the multi-objective particle swarm optimization algorithm and perform iterative optimization, wherein the particles are a set of optimizable parameter combinations;

[0013] Step 3: Set the pneumatic transport threshold and the ideal threshold of each performance coefficient. Based on the performance coefficient and the ideal threshold, calculate the comprehensive deviation coefficient of each solution whose pneumatic transport fitness value is less than the pneumatic transport threshold, and take the solution corresponding to the minimum value of the comprehensive deviation coefficient as the optimal optimizable parameter combination.

[0014] Furthermore, a functional relationship between the optimizable parameters and the performance coefficient is established, and the method based on this is:

[0015] The functional relationship between the pipeline wear coefficient and the material particle concentration, conveying gas velocity, material density, and pipeline diameter is as follows:

[0016]

[0017] Where W represents the pipe wear coefficient, k c is the material wear constant, and k c ∈[10 -6 ,10 -3 ], Cp is the particle concentration of the material, v is the conveying gas velocity, n represents the velocity index, which is determined by the material characteristics, and n∈[2,3], ρ m is the material density, d is the pipe diameter;

[0018] The functional relationship between the energy consumption coefficient and the fan efficiency, system operating pressure, and gas flow volume is as follows:

[0019]

[0020] Where E represents the energy consumption coefficient, p y is the system operating pressure drop, Q is the gas flow volume, η is the system fan efficiency, the system fan efficiency is determined by the transportation equipment, the value range of η is (0, 1), and M is the total mass of the material;

[0021] The functional relationship between the pressure fluctuation coefficient and the conveying gas velocity, pipeline diameter, gas flow volume, conveying distance, system operation average pressure, material particle concentration and material density is as follows:

[0022]

[0023] Where P represents the pressure fluctuation coefficient, k P is the empirical coefficient of pressure fluctuation, which is related to the system complexity of the pipeline, and k P ∈[0.1,0.3], p avg is the average operating pressure of the system, and L is the conveying distance.

[0024] Furthermore, the effective range of the optimizable parameters is set according to the following method:

[0025] The optimization constraints are set for the pneumatic conveying system, including: the value interval of the conveying gas velocity is set to [10m / s, 40m / s]; the value interval of the gas volume flow rate is set to [500m / s] 3 / h,1000m 3 / h]; the value range of fan efficiency η is set to (0, 1); the value range of system operating pressure drop is set to [0.1MPa, 0.5MPa]; the value range of system average pressure is set to [0.2MPa, 0.6MPa].

[0026] Furthermore, taking minimizing the pneumatic transport fitness value as the optimization goal, a functional relationship between the performance coefficient and the pneumatic transport fitness value is established, based on the following formula:

[0027] F syd =w 1 *W+w 2 *E+w 3 *P

[0028] Among them, F syd represents the minimum pneumatic transport fitness value, w 1 、w 2 、w 3 represent the proportional weights of pipeline wear coefficient, energy efficiency coefficient, and pressure fluctuation coefficient, respectively, and w 1 +w 2 +w 3 =1.

[0029] Furthermore, based on the multi-objective particle swarm optimization algorithm, multiple particles are randomly generated and iteratively optimized, and the method is based on:

[0030] The initial position x of the particle is randomly generated within the valid range of each optimizable parameter i , set the number of particles to N, the maximum number of iterations to max iter , inertia weight ω, learning factor c 1 and c 2 , calculate the performance coefficient of each particle, and use the following formula to update the velocity and position of the particle. The formula is:

[0031]

[0032] in, represents the speed of the i-th particle after iterative update, ω is the inertia weight, which is used to control the influence of the current speed of the particle on the new speed, and h i is the current velocity of the ith particle, c 1 、c 2 are the individual learning factor and the group learning factor, respectively. They are random numbers between [0,1] and are used to introduce randomness to ensure the diversity of particles in the search process. i represents the best historical position of the i-th particle, gbest i represents the global optimal position of the i-th particle, that is, the best position found in the entire particle swarm; represents the position of the i-th particle after iterative update, x i is the current position of the i-th particle, i is the index of the number of particles, i∈[1,N].

[0033] Furthermore, the comprehensive deviation coefficient of each solution whose pneumatic transport fitness value is less than the pneumatic transport threshold is calculated, and the solution corresponding to the minimum value of the comprehensive deviation coefficient is taken as the optimal optimizable parameter combination, based on the following method:

[0034] Based on the Euclidean distance method, the optimal solution close to the optimal performance index is selected, based on the formula:

[0035]

[0036] in, represents the comprehensive deviation coefficient of the jth performance index in the i-th particle, is the value of the jth performance index in the ith particle, is the ideal threshold value of the jth performance indicator in the i-th particle, j is the index of the performance indicator, when j = 1, it represents the pipeline wear coefficient; when j = 2, it represents the energy consumption coefficient; when j = 3, it represents the pressure fluctuation coefficient;

[0037] After calculating the comprehensive deviation coefficient of all fitness values ​​less than the given pneumatic transport threshold, all calculated Compare the values ​​and find the minimum value of each solution After the minimum value is determined, the corresponding solution is the best optimizable parameter combination.

[0038] The present invention also provides a pneumatic conveying and transportation system optimization system based on a multi-objective particle swarm, wherein the optimization system is used to execute the above-mentioned pneumatic conveying and transportation system optimization method based on a multi-objective particle swarm:

[0039] A pneumatic data acquisition module, the pneumatic data acquisition module is used to obtain pneumatic transport parameters in the pneumatic transport system, determine the optimizable parameters that need to be optimized in the pneumatic transport system, establish a functional relationship between the optimizable parameters and the performance coefficient, and establish a functional relationship between the performance coefficient and the pneumatic transport fitness value. The pneumatic transport parameters are divided into optimizable parameters and fixed parameters. The optimizable parameters include conveying gas velocity, fan efficiency, gas volume flow, system operating pressure drop, and system average pressure. The fixed parameters include pipeline diameter, total material mass, conveying distance, material particle concentration, and material density. The performance coefficient includes pipeline wear coefficient, energy consumption coefficient, and pressure fluctuation coefficient;

[0040] A performance coefficient optimization module, which is used to set the effective range of the operation of the optimizable parameters, with minimizing the pneumatic transport fitness value as the optimization target, randomly generating multiple particles based on a multi-objective particle swarm optimization algorithm and performing iterative optimization, wherein the particles are a group of optimizable parameter combinations;

[0041] The threshold determination and optimal solution selection module is used to set the pneumatic transport threshold and the ideal threshold of each performance coefficient. Based on the performance coefficient and the ideal threshold, the pneumatic transport fitness value is calculated to be less than the comprehensive deviation coefficient of each solution in the pneumatic transport threshold, and the solution corresponding to the minimum value of the comprehensive deviation coefficient is used as the optimal optimizable parameter combination.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] The present invention can comprehensively optimize multiple influencing factors in the pneumatic conveying system based on a multi-objective particle swarm algorithm. This method collects historical pneumatic conveying data, uses engineering empirical formulas to calculate the performance coefficient, and adjusts it through a multi-objective optimization function, so that the system can minimize pipeline wear, energy consumption, and pressure fluctuations while meeting physical constraints. This method is more accurate than traditional optimization methods and can provide a more reasonable combination of parameters, thereby effectively improving the overall performance and stability of the pneumatic conveying system;

[0044] By setting optimization goals, fitness evaluation and threshold judgment mechanisms, the present invention can timely determine whether optimization is needed during system operation and select the optimal solution according to the minimum deviation method. This process helps to reduce unnecessary energy consumption and pressure fluctuations, improve fan efficiency, reduce pipeline wear, optimize material transportation, and ultimately achieve the effect of reducing the cost of the pneumatic conveying system and improving system stability;

[0045] The present invention comprehensively optimizes multiple factors such as pipeline wear, energy consumption and pressure fluctuation in the pneumatic conveying system based on a multi-objective particle swarm algorithm, calculates the performance coefficient and adjusts the optimization function using historical data and engineering experience formulas, thereby achieving efficient improvement of system performance and enhanced stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the overall method flow of the present invention.

[0047] Figure 2 It is a schematic diagram of the system module flow of the present invention. DETAILED DESCRIPTION

[0048] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0049] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0050] Example:

[0051] See also Figure 1 , a pneumatic conveying system optimization method based on multi-objective particle swarm, the specific steps include:

[0052] Step 1: Obtain the pneumatic conveying parameters in the pneumatic conveying system, determine the optimizable parameters that need to be optimized in the pneumatic conveying system, establish a functional relationship between the optimizable parameters and the performance coefficient, and establish a functional relationship between the performance coefficient and the pneumatic conveying fitness value. The pneumatic conveying parameters are divided into optimizable parameters and fixed value parameters. The optimizable parameters include conveying gas velocity, fan efficiency, gas volume flow rate, system operating pressure drop, and system average pressure. The fixed value parameters include pipeline diameter, total material mass, conveying distance, material particle concentration, and material density. The performance coefficient includes pipeline wear coefficient, energy consumption coefficient, and pressure fluctuation coefficient.

[0053] Step 2: Set the effective range of the optimizable parameters, take minimizing the pneumatic transport fitness value as the optimization goal, randomly generate multiple particles based on the multi-objective particle swarm optimization algorithm and perform iterative optimization, wherein the particles are a set of optimizable parameter combinations;

[0054] Step 3: Set the pneumatic transport threshold and the ideal threshold of each performance coefficient. Based on the performance coefficient and the ideal threshold, calculate the comprehensive deviation coefficient of each solution whose pneumatic transport fitness value is less than the pneumatic transport threshold, and take the solution corresponding to the minimum value of the comprehensive deviation coefficient as the optimal optimizable parameter combination.

[0055] It should be noted that the evaluation formulas for pipeline wear coefficient, energy consumption coefficient and pressure fluctuation coefficient in pneumatic conveying systems reflect the actual influence of various key optimizable parameters, providing a scientific basis for optimizing the transportation system. These formulas combine historical transportation data and engineering experience, and clarify the quantitative relationship between actual parameters such as material particle concentration, conveying gas velocity, pipeline diameter and system performance. They can accurately evaluate the changing trend of each performance indicator during transportation. The parameter range is set based on experiments or industry standards to ensure the effectiveness and universality of the formula. At the same time, it provides a reasonable search space for exploring equilibrium solutions in multi-objective optimization. Through this method, system optimization can achieve an effective trade-off between wear, energy consumption and pressure fluctuation, laying a solid foundation for improving the efficiency and stability of pneumatic conveying systems.

[0056] Therefore, based on the multi-objective particle swarm algorithm, each particle in the particle swarm represents a set of parameter combinations composed of different transportation data. The performance coefficient corresponding to each set of parameter combinations is calculated according to the engineering experience formula. The method is based on:

[0057] Based on the collected historical transportation data, the material particle concentration, conveying gas velocity, material density, and pipeline diameter are used as the first group of parameter combinations to evaluate the pipeline wear coefficient of the system in pneumatic conveying. The formula is:

[0058]

[0059] Where W represents the pipe wear coefficient, k c is the material wear constant, and k c ∈[10 -6 ,10 -3 ], C p is the particle concentration of the material, v is the conveying gas velocity, n represents the velocity index, which is determined by the material characteristics, and n∈[2,3], ρ m is the material density, d is the pipe diameter; in the above formula, W and C p There is a positive relationship, that is, the higher the material particle concentration, the more serious the pipe wear. This is because high concentration will cause more particles to contact the wall in the pipe, increasing wear; v n It is exponentially related to W, indicating that the effect of gas velocity on wear is particularly significant. The increase in gas velocity will increase the frequency and intensity of material particles hitting the pipe wall, resulting in a significant increase in wear. m There is a direct proportional relationship, that is, the greater the material density, the more serious the pipe wear. This is because the particles with greater density have greater momentum when colliding with the pipe wall, and the impact and wear on the pipe wall are more obvious; W and d are inversely proportional, that is, the larger the pipe diameter, the smaller the wear. This is because the larger pipe diameter makes the material particles more dispersed, reducing the probability and force of impact on the unit pipe wall area;

[0060] Based on the fan efficiency, system operating pressure, and gas flow volume in the historical transportation data obtained as the second group of parameters, combined with the time required for pneumatic transportation, the energy consumption coefficient of the system in pneumatic transportation is evaluated. The formula is:

[0061]

[0062] Where E represents the energy consumption coefficient, p y is the system operating pressure drop, Q is the gas flow volume, η is the system fan efficiency, the system fan efficiency is determined by the transportation equipment, the value range of η is (0, 1], M is the total mass of the material; in the above formula, E and p yE is proportional to Q, that is, the greater the operating pressure drop of the system, the higher the energy consumption coefficient. This is because a greater pressure drop requires the fan to provide higher power to maintain transportation, resulting in increased energy consumption; E is proportional to Q, that is, the greater the gas flow rate, the higher the energy consumption coefficient. This is because an increase in gas flow will directly increase the load of the fan, which in turn leads to an increase in system energy consumption; E is proportional to M, that is, the greater the material mass, the heavier the system load, the more energy required for airflow transportation, and the greater the energy consumption coefficient; E is inversely proportional to η, that is, the higher the fan efficiency, the lower the energy consumption coefficient. This is because a high-efficiency fan can more effectively convert electrical energy into mechanical energy required for gas transportation, reduce energy loss, and thus reduce system energy consumption;

[0063] The pressure fluctuation coefficient of the system in pneumatic conveying is evaluated based on the third parameter combination of the conveying gas velocity, pipeline diameter, gas flow volume, conveying distance, system operating average pressure, material particle concentration and material density in the historical transportation data. The formula is:

[0064]

[0065] Where P represents the pressure fluctuation coefficient, k P is the empirical coefficient of pressure fluctuation, which is related to the system complexity of the pipeline, and k P ∈[0.1~0.3],p avg is the average pressure of the system operation, L is the conveying distance; in the above formula, P and C p The relationship between P and v is proportional, that is, the higher the particle concentration, the greater the pressure fluctuation. This is because the increase in concentration will lead to enhanced interaction between particles in the conveying pipeline, and the non-steady-state characteristics of gas-solid two-phase flow will be more significant, thus causing greater pressure fluctuations. n It is an exponential relationship, indicating that the effect of gas velocity on pressure fluctuation is more significant. The increase of gas velocity will increase the collision frequency and intensity between particles and pipe wall, as well as the turbulence of flow field, thus leading to a significant increase in pressure fluctuation coefficient. P is proportional to L, that is, the longer the transportation distance, the more significant the pressure fluctuation. In long-distance transportation, due to factors such as friction in the pipeline, particle deposition and flow non-uniformity, the pressure change along the way will be aggravated, thereby amplifying the pressure fluctuation. P and p avg Inversely proportional to d, that is, the higher the system average pressure, the smaller the pressure fluctuation. This is because a higher average pressure can better maintain the stability of the gas-solid two-phase flow and suppress the fluctuation effect in the flow; P is inversely proportional to d, that is, the larger the pipeline diameter, the smaller the pressure fluctuation. A larger pipeline diameter can reduce the particle impact and flow unevenness per unit area, making the pressure distribution of the gas-solid two-phase flow more uniform, thereby reducing pressure fluctuations; P is inversely proportional to Q, that is, the larger the gas flow rate, the smaller the pressure. A larger gas flow rate helps to dilute the distribution of material particles in the pipeline, reduce the interaction intensity between particles, and thus reduce pressure fluctuations.

[0066] It should be noted that these constraints are based on the physical limitations and operational safety of the equipment, including the range setting of gas velocity, pipe diameter and material concentration, which can not only ensure the efficiency and stability of material transportation, but also prevent system failure, wear or excessive energy consumption due to excessively high or low parameters. At the same time, setting upper limits for energy consumption and pressure fluctuations can not only control operating costs, but also ensure the safety of the system and long-term stable operation. The setting of this optimization constraint reflects the comprehensive consideration of safety, economy and system performance, and provides a scientific and feasible optimization direction for the pneumatic conveying system.

[0067] Therefore, it is necessary to set the effective range of the optimizable parameters, based on the following method:

[0068] The optimization constraints are set for the pneumatic conveying system, including: the value interval of the conveying gas velocity is set to [10m / s, 40m / s]; the value interval of the gas volume flow rate is set to [500m / s] 3 / h,1000m 3 / h]; the value range of fan efficiency η is set to (0, 1); the value range of system operating pressure drop is set to [0.1MPa, 0.5MPa]; the value range of system average pressure is set to [0.2MPa, 0.6MPa].

[0069] The conveying gas velocity interval is set to [10m / s, 40m / s] because too low a conveying gas velocity may cause material deposition or blockage, affecting the fluidity of the system, while too high a gas velocity may cause material damage, increased wear and increased pneumatic noise. Within this range, the system can minimize energy consumption while ensuring effective conveying; the effective range of gas volume flow is set to [500m / s, 40m / s]. 3 / h,1000m 3 / h], because exceeding this range may cause excessive equipment load, increase the risk of failure or reduce the conveying efficiency, and this flow range can adapt to the material conveying needs of different particle concentrations to ensure the flexibility of the system; the value range of the fan efficiency η is (0, 1), because the fan efficiency cannot reach 100%, so it is set to a range of 0 to 1, reflecting the performance of the fan in actual applications, and for economic considerations, higher fan efficiency can significantly reduce operating costs, so choosing a high-efficiency fan is the goal of optimization, setting this range prompts the selection of a reasonable fan model; the effective range interval setting of the system operating pressure drop The minimum pressure drop is set to [0.1MPa, 0.5MPa], and the minimum pressure drop is set to 0.1MPa to ensure that the gas has sufficient driving force during the transportation process to prevent insufficient flow or material deposition, and the maximum pressure drop is set to 0.5MPa to ensure operation within the design pressure range to avoid equipment damage or safety accidents; the average pressure effective range of the system is set to [0.2MPa, 0.6MPa], which takes into account the design safety pressure of the equipment to ensure that no leakage or failure occurs during operation, and within this range, it can meet the requirements of different materials and process conditions to ensure the stability and reliability of the system.

[0070] It should be noted that the goal of calculating the minimum pneumatic conveying fitness value is to comprehensively evaluate and optimize the performance of the pneumatic conveying system. By establishing a functional relationship between the performance coefficient and the fitness value, the impact of different factors on the operation of the system can be effectively quantified, and the importance of different performance indicators can be flexibly adjusted according to actual application requirements, thereby achieving a balance of various performance indicators in the optimization process, ensuring that the pneumatic conveying system meets process requirements while reducing energy consumption, extending equipment service life, and improving overall operating efficiency.

[0071] Therefore, it is necessary to take minimizing the pneumatic transport fitness value as the optimization goal and establish a functional relationship between the performance coefficient and the pneumatic transport fitness value. The formula is:

[0072] F syd =w 1 *W+w 2 *F+w 3 *P

[0073] Among them, F syd represents the minimum pneumatic transport fitness value, w 1 、w 2 、w 3 represent the proportional weights of pipeline wear coefficient, energy efficiency coefficient, and pressure fluctuation coefficient, respectively, and w 1 +w 2 +w 3 =1; In the above formula, the weight ratio is set to w 2 >w 1 >w3 This is because energy efficiency is directly related to the operating cost and economy of the system. An efficient pneumatic conveying system can significantly reduce energy consumption, thereby reducing operating costs and environmental impact. Therefore, a higher weight is given to the energy efficiency coefficient. 2 Pipeline wear directly affects the maintenance cost and service life of the equipment. Although the wear problem is critical, the wear of the system may be controlled under good energy efficiency. Therefore, the second weight ratio w is set next to energy efficiency. 1 Pressure fluctuations may affect the stability of pneumatic conveying and the efficiency of material conveying, and may even cause equipment failure in severe cases. Although pressure fluctuations are also important, their impact on overall operating costs and long-term performance is usually smaller than that on energy efficiency and wear, and they are controllable factors, so they can be given a relatively low weight. 3 .

[0074] It should be noted that the optimization of the pneumatic conveying system based on the multi-objective particle swarm optimization algorithm can effectively search for the global optimal solution in the high-dimensional parameter space by randomly generating multiple particles and performing iterative optimization. This method ensures diversity and flexibility in the search process by adjusting the initial position and velocity of the particles and combining the learning mechanism of individuals and groups. In particular, by setting the inertia weight, individual and group learning factors, the exploration and development processes can be balanced, thereby improving the convergence speed and optimization effect. Each particle in the particle swarm represents a potential solution. The introduction of its historical best position and global best position enables the algorithm to quickly adapt to environmental changes and avoid falling into local optimality.

[0075] Therefore, it is necessary to randomly generate multiple particles based on the multi-objective particle swarm optimization algorithm and perform iterative optimization based on the following method:

[0076] The initial position x of the particle is randomly generated within the valid range of each optimizable parameter i , set the number of particles to N, the maximum number of iterations to max iter , inertia weight ω, learning factor c 1 and c 2 , calculate the performance coefficient of each particle, and use the following formula to update the velocity and position of the particle. The formula is:

[0077]

[0078] in, represents the speed of the i-th particle after iterative update, ω is the inertia weight, which is used to control the influence of the current speed of the particle on the new speed, and h i is the current velocity of the ith particle, c 1 、c 2are the individual learning factor and the group learning factor, respectively. They are random numbers between [0,1] and are used to introduce randomness to ensure the diversity of particles in the search process. i represents the best historical position of the i-th particle, gbest i represents the global optimal position of the i-th particle, that is, the best position found in the entire particle swarm; represents the position of the i-th particle after iterative update, x i is the current position of the i-th particle, i is the index of the number of particles, i∈[1,N].

[0079] It should be noted that by comparing the degree of deviation of each solution in each performance indicator from the ideal threshold, the performance of each solution can be quantified, so as to more accurately identify the solution closest to the ideal state. Minimizing the comprehensive deviation coefficient not only helps to improve the overall performance of the pneumatic conveying system, but also ensures that energy consumption and equipment wear are minimized while meeting safety and economic requirements.

[0080] Therefore, it is necessary to calculate the comprehensive deviation coefficient of each solution whose pneumatic transport fitness value is less than the pneumatic transport threshold, and take the solution corresponding to the minimum value of the comprehensive deviation coefficient as the optimal optimizable parameter combination. The method is as follows:

[0081] Based on the Euclidean distance method, the optimal solution close to the optimal performance index is selected, based on the formula:

[0082]

[0083] in, represents the comprehensive deviation coefficient of the jth performance index in the i-th particle, is the value of the jth performance index in the ith particle, is the ideal threshold value of the jth performance index in the i-th particle, j is the index of the performance index, when j = 1, it represents the pipeline wear coefficient; when j = 2, it represents the energy consumption coefficient; when j = 3, it represents the pressure fluctuation coefficient; in the above formula, By comprehensively considering the deviation of multiple performance indicators, based on the Euclidean distance, an effective evaluation criterion is provided for multi-objective optimization. It can intuitively reflect the distance between the current solution and the ideal solution, emphasize the impact of large deviations, and prompt the optimization algorithm to adjust the performance indicators to reduce the total deviation. In addition, the introduction of the ideal solution sets a clear goal for optimization, guiding the particle swarm to quickly find a parameter combination close to the optimal solution, making this method have good applicability and versatility, and is suitable for pneumatic conveying systems and other multi-objective optimization problems.

[0084] After calculating the comprehensive deviation coefficient of all fitness values ​​less than the given pneumatic transport threshold, all calculated Compare the values ​​and find the minimum value of each solution After the minimum value is determined, the corresponding solution is the best optimizable parameter combination.

[0085] See also Figure 2 The present invention also provides a pneumatic conveying system optimization system based on a multi-objective particle swarm, wherein the optimization system is used to execute the above-mentioned pneumatic conveying system optimization method based on a multi-objective particle swarm:

[0086] A pneumatic data acquisition module, the pneumatic data acquisition module is used to obtain pneumatic transport parameters in the pneumatic transport system, determine the optimizable parameters that need to be optimized in the pneumatic transport system, establish a functional relationship between the optimizable parameters and the performance coefficient, and establish a functional relationship between the performance coefficient and the pneumatic transport fitness value. The pneumatic transport parameters are divided into optimizable parameters and fixed parameters. The optimizable parameters include conveying gas velocity, fan efficiency, gas volume flow, system operating pressure drop, and system average pressure. The fixed parameters include pipeline diameter, total material mass, conveying distance, material particle concentration, and material density. The performance coefficient includes pipeline wear coefficient, energy consumption coefficient, and pressure fluctuation coefficient;

[0087] A performance coefficient optimization module, which is used to set the effective range of the operation of the optimizable parameters, with minimizing the pneumatic transport fitness value as the optimization target, randomly generating multiple particles based on a multi-objective particle swarm optimization algorithm and performing iterative optimization, wherein the particles are a group of optimizable parameter combinations;

[0088] The threshold determination and optimal solution selection module is used to set the pneumatic transport threshold and the ideal threshold of each performance coefficient. Based on the performance coefficient and the ideal threshold, the pneumatic transport fitness value is calculated to be less than the comprehensive deviation coefficient of each solution in the pneumatic transport threshold, and the solution corresponding to the minimum value of the comprehensive deviation coefficient is used as the optimal optimizable parameter combination.

[0089] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0090] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0091] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0092] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A pneumatic conveying system optimization method based on multi-objective particle swarm, characterized in that: The specific steps include: Step 1: Obtain the pneumatic conveying parameters in the pneumatic conveying system, determine the optimizable parameters that need to be optimized in the pneumatic conveying system, establish a functional relationship between the optimizable parameters and the performance coefficient, and establish a functional relationship between the performance coefficient and the pneumatic conveying fitness value. The pneumatic conveying parameters are divided into optimizable parameters and fixed value parameters. The optimizable parameters include conveying gas velocity, fan efficiency, gas volume flow rate, system operating pressure drop, and system average pressure. The fixed value parameters include pipeline diameter, total material mass, conveying distance, material particle concentration, and material density. The performance coefficient includes pipeline wear coefficient, energy consumption coefficient, and pressure fluctuation coefficient. Step 2: Set the effective range of the optimizable parameters, take minimizing the pneumatic transport fitness value as the optimization goal, randomly generate multiple particles based on the multi-objective particle swarm optimization algorithm and perform iterative optimization, wherein the particles are a set of optimizable parameter combinations; Step 3: Set the pneumatic transport threshold and the ideal threshold of each performance coefficient. Based on the performance coefficient and the ideal threshold, calculate the comprehensive deviation coefficient of each solution whose pneumatic transport fitness value is less than the pneumatic transport threshold, and take the solution corresponding to the minimum value of the comprehensive deviation coefficient as the optimal optimizable parameter combination.

2. The pneumatic conveying system optimization method based on multi-objective particle swarm according to claim 1 is characterized in that: The functional relationship between the optimizable parameters and the performance coefficient is established based on the following method: The functional relationship between the pipeline wear coefficient and the material particle concentration, conveying gas velocity, material density, and pipeline diameter is as follows: Where W represents the pipe wear coefficient, k c is the material wear constant, and k c ∈[10 -6 ,10 -3 ], C p is the particle concentration of the material, v is the conveying gas velocity, n represents the velocity index, which is determined by the material characteristics, and n∈[2,3], ρ m is the material density, d is the pipe diameter; The functional relationship between the energy consumption coefficient and the fan efficiency, system operating pressure, and gas flow volume is as follows: Where E represents the energy consumption coefficient, p y is the system operating pressure drop, Q is the gas flow volume, η is the system fan efficiency, the system fan efficiency is determined by the transportation equipment, the value range of η is (0, 1), and M is the total mass of the material; The functional relationship between the pressure fluctuation coefficient and the conveying gas velocity, pipeline diameter, gas flow volume, conveying distance, system operation average pressure, material particle concentration and material density is as follows: Where P represents the pressure fluctuation coefficient, k P is the empirical coefficient of pressure fluctuation, which is related to the system complexity of the pipeline, and k P ∈[0.1,0.3], p avg is the average operating pressure of the system, and L is the conveying distance.

3. The method for optimizing a pneumatic conveying system based on a multi-objective particle swarm according to claim 1, characterized in that: The effective range of the optimizable parameters is set according to the following method: The optimization constraints are set for the pneumatic conveying system, including: the value interval of the conveying gas velocity is set to [10m / s, 40m / s]; the value interval of the gas volume flow rate is set to [500m / s] 3 / h,1000m 3 / h]; the value range of fan efficiency η is set to (0, 1); the value range of system operating pressure drop is set to [0.1MPa, 0.5MPa]; the value range of system average pressure is set to [0.2MPa, 0.6MPa].

4. The method for optimizing a pneumatic conveying system based on a multi-objective particle swarm according to claim 1, characterized in that: Taking minimizing the pneumatic transport fitness value as the optimization goal, a functional relationship between the performance coefficient and the pneumatic transport fitness value is established based on the following formula: F syd =w1*W+w2*E+w3*P Among them, F syd It represents the minimum pneumatic transport fitness value, w1, w2, and w3 represent the proportional weights of pipeline wear coefficient, energy efficiency coefficient, and pressure fluctuation coefficient, respectively, and w1+w2+w3=1, w2>w1>w3.

5. The method for optimizing a pneumatic conveying system based on a multi-objective particle swarm according to claim 1, characterized in that: Based on the multi-objective particle swarm optimization algorithm, multiple particles are randomly generated and iteratively optimized. The method is based on: The initial position x of the particle is randomly generated within the valid range of each optimizable parameter i , set the number of particles to N, the maximum number of iterations to max iter , inertia weight ω, learning factors c1 and c2, calculate the performance coefficient of each particle, and use the following formula to update the speed and position of the particle. The formula is: in, represents the speed of the i-th particle after iterative update, ω is the inertia weight, which is used to control the influence of the current speed of the particle on the new speed, and h i is the current speed of the ith particle, c1 and c2 are the individual learning factor and the group learning factor, respectively, both of which are random numbers between [0,1], used to introduce randomness to ensure the diversity of particles in the search process, pbest i represents the best historical position of the i-th particle, gbest i represents the global optimal position of the i-th particle, that is, the best position found in the entire particle swarm; represents the position of the i-th particle after iterative update, x i is the current position of the i-th particle, i is the index of the number of particles, i∈[1,N].

6. The method for optimizing a pneumatic conveying system based on a multi-objective particle swarm according to claim 5, characterized in that: Calculate the comprehensive deviation coefficient of each solution whose pneumatic transport fitness value is less than the pneumatic transport threshold, and take the solution corresponding to the minimum value of the comprehensive deviation coefficient as the optimal optimizable parameter combination. The method is as follows: Based on the Euclidean distance method, the optimal solution close to the optimal performance index is selected, based on the formula: in, represents the comprehensive deviation coefficient of the jth performance index in the i-th particle, is the value of the jth performance index in the ith particle, is the ideal threshold value of the jth performance indicator in the i-th particle, j is the index of the performance indicator, when j = 1, it represents the pipeline wear coefficient; when j = 2, it represents the energy consumption coefficient; when j = 3, it represents the pressure fluctuation coefficient; After calculating the comprehensive deviation coefficient of each solution whose pneumatic transport fitness value is less than the pneumatic transport threshold, all the calculated Compare values ​​and find the minimum value After the minimum value is determined, the corresponding solution is the best optimizable parameter combination.

7. A pneumatic conveying system optimization system based on multi-objective particle swarm, characterized in that: The optimization system is used to execute the pneumatic conveying system optimization method based on multi-objective particle swarm according to any one of claims 1 to 6: A pneumatic data acquisition module, the pneumatic data acquisition module is used to obtain pneumatic transport parameters in the pneumatic transport system, determine the optimizable parameters that need to be optimized in the pneumatic transport system, establish a functional relationship between the optimizable parameters and the performance coefficient, and establish a functional relationship between the performance coefficient and the pneumatic transport fitness value. The pneumatic transport parameters are divided into optimizable parameters and fixed parameters. The optimizable parameters include conveying gas velocity, fan efficiency, gas volume flow, system operating pressure drop, and system average pressure. The fixed parameters include pipeline diameter, total material mass, conveying distance, material particle concentration, and material density. The performance coefficient includes pipeline wear coefficient, energy consumption coefficient, and pressure fluctuation coefficient; A performance coefficient optimization module, which is used to set the effective range of the operation of the optimizable parameters, with minimizing the pneumatic transport fitness value as the optimization target, randomly generating multiple particles based on a multi-objective particle swarm optimization algorithm and performing iterative optimization, wherein the particles are a group of optimizable parameter combinations; The threshold determination and optimal solution selection module is used to set the pneumatic transport threshold and the ideal threshold of each performance coefficient. Based on the performance coefficient and the ideal threshold, the pneumatic transport fitness value is calculated to be less than the comprehensive deviation coefficient of each solution in the pneumatic transport threshold, and the solution corresponding to the minimum value of the comprehensive deviation coefficient is used as the optimal optimizable parameter combination.

Images