A crude oil depot equipment combined transportation optimization method improved by adaptive genetic algorithm

Abstract

The application relates to a crude oil depot equipment combined operation optimization method of an improved self-adaptive genetic algorithm in the technical field of crude oil depot equipment operation optimization. The method comprises the following steps: establishing a crude oil depot equipment combined operation optimization model with the lowest total energy consumption of the crude oil depot equipment operation as a target; setting parameters of the self-adaptive genetic algorithm; initializing a population by adopting a hybrid coding mechanism; calculating the fitness value of each individual in the population according to a fitness function, and selecting parent individuals by adopting an improved elite reservation bidding race selection method based on the fitness value; adjusting the crossover probability and the mutation probability according to the dispersion degree of the population fitness, and implementing a cooperative evolution operation based on the parent individuals; executing local search on elite individuals, fixing the equipment combination state, checking whether the solution meets the constraint condition, repairing the individuals that do not meet the constraint condition, judging whether a termination condition is reached, and outputting the optimal equipment start-stop combination, the operation parameter and the total energy consumption if yes. The method can effectively reduce the energy consumption of the crude oil depot operation and improve energy utilization efficiency.

Description

Technical Field

[0001] This application relates to the field of crude oil depot equipment operation optimization technology, and in particular to an improved adaptive genetic algorithm-based method for optimizing the joint operation of crude oil depot equipment. Background Technology

[0002] As a core hub of the petroleum storage and transportation system, crude oil depots undertake crucial functions such as receiving, storing, distributing, and transporting crude oil. The economic efficiency and safety of their operation are paramount. The key equipment involved in the technological process of large crude oil depots includes crude oil storage tanks, heating furnaces, oil pump units, and auxiliary systems that ensure safe pipeline transportation. Especially in cold climates, the energy consumption of oil pumps and heating furnaces can account for over 70% of the total energy consumption of the oil depot. Therefore, optimizing the coordinated operation of crude oil depot equipment to achieve energy conservation, cost reduction, and efficiency improvement, thereby enhancing the economic benefits of the oil depot, is of great significance.

[0003] Currently, the main technical issues in optimizing the operation of crude oil storage equipment are as follows:

[0004] 1) Existing models and methods do not adequately characterize the hydraulic-thermal coupling mechanism between equipment. In crude oil depots, storage tanks, pumps, and furnaces constitute a tightly interconnected system: the temperature drop in the storage tanks directly affects the viscosity of the crude oil and the inlet temperature of the furnace, thus altering the power consumption of the pumps and the fuel consumption of the furnace. Current research primarily focuses on scheduling optimization or process flow optimization, without fully considering the coupling mechanism between equipment, which limits the effectiveness of further reducing the energy consumption of oil depot operations.

[0005] 2) The optimization model is characterized by mixed variable types, nonlinearity, and multiple constraints arising from hydraulic-thermal coupling. The start-up and shutdown states of the equipment are discrete variables, while the operating parameters are continuous variables. Traditional genetic algorithms struggle to perform efficient searches within this mixed variable space. Furthermore, the hydraulic-thermal coupling between equipment causes their operating states to mutually constrain each other. Independent optimization using traditional methods can easily lead to premature convergence and getting trapped in local optima, making it difficult to obtain a globally optimal equipment operation optimization solution.

[0006] Therefore, there is an urgent need in related technologies for a way to improve the accuracy of crude oil storage equipment operation optimization. Summary of the Invention

[0007] Therefore, it is necessary to provide an improved adaptive genetic algorithm-based optimization method for the joint operation of crude oil depot equipment, which can improve the accuracy of crude oil depot equipment operation optimization, in order to address the above-mentioned technical problems.

[0008] Firstly, this application provides an improved adaptive genetic algorithm for optimizing the operation of crude oil depot equipment. The method includes:

[0009] To minimize the total energy consumption of crude oil storage equipment, an optimization model for the inter-operation of crude oil storage equipment was established.

[0010] Set the parameters of the adaptive genetic algorithm, including population size, maximum number of iterations, initial crossover probability, initial mutation probability, and number of elite individuals;

[0011] A hybrid coding mechanism is used to initialize the population based on the population size and the crude oil storage equipment interoperability optimization model;

[0012] The fitness value of each individual in the population is calculated based on the fitness function, and the parent individuals are selected based on the fitness value using an improved elite retention competitive selection method.

[0013] The crossover and mutation probabilities are adjusted according to the degree of dispersion of population fitness, and co-evolutionary operations are performed based on the parent individuals;

[0014] Perform local searches on elite individuals, with fixed equipment combinations;

[0015] Check whether the solution meets the constraints, and repair individuals that do not meet the constraints;

[0016] Determine if the termination condition has been met. If so, output the optimal equipment start / stop combination, operating parameters, and total energy consumption.

[0017] Optionally, in one embodiment of this application, the total energy consumption of the crude oil storage equipment includes the power consumption of the oil pump and the fuel consumption of the heating furnace, with the equipment start-up status and operating parameters as decision variables, wherein the combination of equipment start-up status is a discrete variable and the operating parameters are continuous variables, including the output of the oil pump and the outlet temperature of the heating furnace.

[0018] Optionally, in one embodiment of this application, the objective function of the crude oil storage equipment intermodal operation optimization model is:

[0019]

[0020]

[0021]

[0022] in, The total energy consumption for equipment operation is expressed as the total mass of standard coal, tce; To pass the first j Crude oil mass flow rate of the pump, kg / s; Furnace outlet temperature, °C; For the first The on / off status of the external pump. This means the external pump is turned on; This means the external pump is turned on; For the first The operating status of the heating furnace. This means the heating furnace is shut down; This means the heating furnace is turned on; This is the electricity conversion factor; The power consumption of the external pump is expressed in kW·h. This is the natural gas conversion factor; m represents the natural gas consumption of the heating furnace. 3 ; This represents the total number of external pumps. for The head of the external pump is in meters (m); g is the acceleration due to gravity (m / s²). 2 ; Runtime, in hours (h); For the first Pump efficiency of the external transfer pump; For the first The motor efficiency of the external pump; This refers to the number of heating furnaces. To pass the first Mass flow rate of the heating furnace, kg / s; The heat capacity of crude oil is expressed in kJ / (kg·℃). The furnace inlet temperature is ℃; The calorific value of natural gas is expressed in kJ / m³. 3 ; For the first Thermal efficiency of the heating furnace;

[0023] The inlet temperature of the heating furnace is determined by the temperature drop of the crude oil storage tank, and its calculation formula is as follows:

[0024]

[0025] in, The ambient temperature around the storage tank, in °C; The initial temperature of the crude oil in the storage tank, in °C; The heat transfer coefficient of the crude oil storage tank is W / (m²). 2 ·℃); Let m be the surface area of ​​the crude oil storage tank. 2 ; The duration of the temperature drop, in seconds; The total mass of crude oil in the storage tank is expressed in kg.

[0026] Optionally, in one embodiment of this application, the constraints of the crude oil storage equipment intermodal optimization model include throughput constraints, crude oil storage outlet temperature constraints, outlet pressure constraints, external pipeline strength constraints, oil temperature constraints inside storage tanks, characteristic constraints of external pumps and heating furnaces, and hydraulic-thermal coupling constraints between equipment.

[0027] Optionally, in one embodiment of this application, the initialization of the population based on the population size and the crude oil storage equipment intermodal operation optimization model using a hybrid coding mechanism includes:

[0028] Binary encoding is used to represent the start / stop status of the equipment, and real number encoding is used to represent the continuous operating parameters of the equipment.

[0029] 70% of the initial individuals are randomly generated, and the remaining 30% are generated using heuristic rules.

[0030] Optionally, in one embodiment of this application, the fitness function is defined as:

[0031]

[0032]

[0033] in, This represents the total energy consumption for equipment operation. As an adaptive penalty factor, The total number of constraints. For the first The amount of a constraint violation, This represents the number of iterations. The learning rate is initially set to 0.01. This is the initial penalty factor.

[0034] Optionally, in one embodiment of this application, the selection of parent individuals using an improved elite-preservation competitive selection method based on the fitness value includes:

[0035] The elite individual with the highest fitness value is retained, and the remaining individuals are selected based on selection probability.

[0036] The formula for calculating the probability of selection is:

[0037]

[0038] in, For the probability of selection; To select the pressure coefficient, For individual fitness; The average fitness of the population. For population size, For the number of elite individuals, For the firstb The fitness value of a non-elite individual.

[0039] Optionally, in one embodiment of this application, the adjustment formula for adjusting the crossover probability and mutation probability according to the population fitness dispersion is as follows:

[0040]

[0041]

[0042] in, P c , P m These are the crossover probability and the mutation probability, respectively. The standard deviation of population fitness; P c0 , P m0 These are the initial crossover probability and the initial mutation probability, respectively.

[0043] Optionally, in one embodiment of this application, performing co-evolutionary operations based on the parent individual includes:

[0044] Pump combinations that operate in parallel and have a hydraulic-thermal coupling relationship are encoded in adjacent positions on the chromosome, and the coupled equipment combinations are swapped as a whole.

[0045] Optionally, in one embodiment of this application, checking whether the solution satisfies the constraints and repairing individuals that do not satisfy the constraints includes:

[0046] If the hydraulic system is unbalanced, adjust the flow rate of each operating pump.

[0047] If the heat is unbalanced, adjust the outlet temperature of the operating heating furnace.

[0048] The aforementioned improved adaptive genetic algorithm-based optimization method for crude oil depot equipment operation aims to minimize the total energy consumption of crude oil depot equipment operation. It establishes an optimization model for crude oil depot equipment operation; sets parameters for the adaptive genetic algorithm, including population size, maximum number of iterations, initial crossover probability, initial mutation probability, and number of elite individuals; initializes the population based on the population size and the crude oil depot equipment operation optimization model using a hybrid encoding mechanism; calculates the fitness value of each individual in the population according to the fitness function, and selects parent individuals using an improved elite retention competitive selection method based on the fitness value; adjusts the crossover and mutation probabilities according to the population fitness dispersion, and performs co-evolution based on the parent individuals; performs local search on elite individuals to fix the equipment combination state; checks whether the solution meets the constraints, and repairs individuals that do not meet the constraints; determines whether the termination condition has been met, and if so, outputs the optimal equipment start / stop combination, operating parameters, and total energy consumption. In other words, on the one hand, with the goal of minimizing total operating energy consumption, and using constraints such as outlet temperature, tank oil temperature, and equipment operating characteristics, and with equipment operating status and parameters as decision variables, an optimization model for the joint operation of crude oil depot equipment, including the power consumption of oil pumps and the fuel consumption of heating furnaces, is established. An improved adaptive genetic algorithm is then applied to solve this model, yielding optimized joint operation schemes for crude oil depot equipment under different operating conditions, providing a reference for the formulation of on-site oil depot equipment operation plans. On the other hand, to address the difficulty of traditional genetic algorithms in solving optimization problems involving mixed variables and coupling relationships, the adaptive genetic algorithm is improved. A hybrid encoding mechanism combined with heuristic rule initialization improves the quality of the initial population, and the combination of global and local search effectively avoids blind searching in the mixed variable space, improving the algorithm's optimization efficiency. Simultaneously, the introduction of collaborative optimization operations and feasibility repair operators ensures hydraulic-thermal balance during the solution process, overcoming the problems of easily getting trapped in local optima and poor solution feasibility, providing a new method for optimizing the operation of crude oil depot equipment. Attached Figure Description

[0049] Figure 1 This is a flowchart illustrating an improved adaptive genetic algorithm-based optimization method for the intermodal operation of crude oil depot equipment in one embodiment.

[0050] Figure 2 This is a graph showing the energy consumption changes before and after optimization in one embodiment. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0052] In one embodiment, such as Figure 1As shown, an improved adaptive genetic algorithm-based optimization method for the intermodal operation of crude oil depot equipment is provided, comprising the following steps:

[0053] S101: To establish an optimization model for the joint operation of crude oil storage equipment with the goal of minimizing the total energy consumption of the equipment.

[0054] In one embodiment of this application, the total energy consumption of the crude oil storage equipment includes the power consumption of the oil pump and the fuel consumption of the heating furnace. The equipment's on-state and operating parameters are used as decision variables, wherein the combination of the equipment's on-state is a discrete variable and the operating parameters are continuous variables. The operating parameters include the output of the oil pump and the outlet temperature of the heating furnace.

[0055] In one embodiment of this application, the objective function of the crude oil storage equipment intermodal operation optimization model is:

[0056]

[0057]

[0058]

[0059] in, The total energy consumption for equipment operation is expressed as the total mass of standard coal, tce; To pass the first j Crude oil mass flow rate of the pump, kg / s; Furnace outlet temperature, °C; For the first The on / off status of the external pump. This means the external pump is turned on; This means the external pump is turned on; For the first The operating status of the heating furnace. This means the heating furnace is shut down; This means the heating furnace is turned on; This is the electricity conversion factor; The power consumption of the external pump is expressed in kW·h. This is the natural gas conversion factor; m represents the natural gas consumption of the heating furnace. 3 ; This represents the total number of external pumps. for The head of the external pump is in meters (m); g is the acceleration due to gravity (m / s²). 2 ; Runtime, in hours (h); For the first Pump efficiency of the external transfer pump; For the first The motor efficiency of the external pump; This refers to the number of heating furnaces. To pass the first Mass flow rate of the heating furnace, kg / s; The heat capacity of crude oil is expressed in kJ / (kg·℃). The furnace inlet temperature is ℃; The calorific value of natural gas is expressed in kJ / m³. 3 ; For the first Thermal efficiency of the heating furnace;

[0060] The inlet temperature of the heating furnace is determined by the temperature drop of the crude oil storage tank, and its calculation formula is as follows:

[0061]

[0062] in, The ambient temperature around the storage tank, in °C; The initial temperature of the crude oil in the storage tank, in °C; The heat transfer coefficient of the crude oil storage tank is W / (m²). 2 ·℃); Let m be the surface area of ​​the crude oil storage tank. 2 ; The duration of the temperature drop, in seconds; The total mass of crude oil in the storage tank is expressed in kg.

[0063] In one embodiment of this application, the constraints of the crude oil depot equipment intermodal operation optimization model include throughput constraints, crude oil depot outlet temperature constraints, outlet pressure constraints, external pipeline strength constraints, oil temperature constraints inside storage tanks, characteristic constraints of external pumps and heating furnaces, and hydraulic-thermal coupling constraints between equipment.

[0064] In one embodiment of this application, the constraints of the crude oil storage equipment intermodal operation optimization model are as follows:

[0065] 1) The flow rate through each device should be equal to the outflow rate of the crude oil storage facility:

[0066]

[0067]

[0068] in, The total output during the operating time is expressed in kg.

[0069] 2) Crude oil depot outlet temperature constraints:

[0070]

[0071] in, The crude oil temperature at the crude oil depot outlet, in °C; , These are the lower and upper limits of the exit temperature, respectively, in °C;

[0072] 3) Crude oil depot outlet pressure constraints:

[0073]

[0074] in, The pressure at the crude oil depot outlet is measured in MPa. The minimum outlet pressure requirement for the oil depot is MPa;

[0075] 4) Strength constraints of export pipelines:

[0076]

[0077] in, The upper limit of pipeline pressure, in MPa;

[0078] 5) Oil temperature constraints within the storage tank:

[0079]

[0080] in, The storage temperature of crude oil in the storage tank is ℃; The lower limit of the storage temperature for crude oil in the storage tank, in °C;

[0081] 6) Performance constraints of the external pump:

[0082]

[0083]

[0084] in, For the first The flow rate of the pump, m 3 / h; , For the first Upper and lower limits of flow rate of the pump, m 3 / h; For the first The head of the pump, in meters (m); , For the first The upper and lower limits of the pump head, in meters;

[0085] 7) Heating capacity constraints of the heating furnace:

[0086]

[0087] in, For the first The actual heat load of the heating furnace, in kW; , The first The upper and lower limits of the working heat load of the furnace, in kW.

[0088] 8) Hydraulic-thermal coupling constraints:

[0089] Hydraulic coupling constraint: For pumps operating in parallel, their heads must be equal.

[0090]

[0091] Thermo-coupling constraint: The total heat provided by the furnace should be equal to the heat required to raise the temperature of the crude oil from the inlet temperature to the outlet temperature.

[0092]

[0093] in, The mass flow rate of the total output is kg / s.

[0094] Hydraulic-thermal coupling constraint: Crude oil viscosity is a function of oil temperature, while the head and efficiency of the oil pump are functions of flow rate and the viscosity of the crude oil being pumped. This relationship tightly couples the hydraulic and thermal systems.

[0095]

[0096]

[0097] in, This is the formula for how the viscosity of crude oil changes with temperature. , The first j The head characteristic equation and efficiency characteristic equation of the external pump are determined by the pump's performance curve.

[0098] S102: Set the parameters of the adaptive genetic algorithm, including population size, maximum number of iterations, initial crossover probability, initial mutation probability, and number of elite individuals.

[0099] In this embodiment, the parameters of the adaptive genetic algorithm are set, including the population size. N =500, Maximum number of iterations G max =100, initial crossover probability P c0 =0.8, initial mutation probability P m0 =0.2, Number of elite individuals N elite =10.

[0100] S103: The population is initialized based on the population size and the crude oil storage equipment intermodal operation optimization model using a hybrid coding mechanism.

[0101] In one embodiment of this application, the initialization of the population based on the population size and the crude oil storage equipment intermodal operation optimization model using a hybrid coding mechanism includes:

[0102] Binary encoding is used to represent the start / stop status of the equipment, and real number encoding is used to represent the continuous operating parameters of the equipment.

[0103] 70% of the initial individuals are randomly generated, and the remaining 30% are generated using heuristic rules.

[0104] In one embodiment of this application, the first part of the chromosome uses binary encoding to represent the start-stop state of the equipment, where 0 indicates that the equipment is off and 1 indicates that the equipment is on. The second part uses real number encoding to represent the continuous operating parameters of the equipment. 70% of the initial individuals are randomly generated, and the remaining 30% are generated using heuristic rules, prioritizing the selection of equipment combinations with lower energy consumption from historical data. The operating parameters are set within the high-efficiency range of the equipment based on the equipment characteristic curve. Specifically, the first part of the chromosome uses 8-bit binary encoding to represent the start-stop state of the oil pump and the heating furnace, and the second part uses real number encoding to represent the flow rate of each operating external pump and the outlet temperature of the operating heating furnace.

[0105] S104: Calculate the fitness value of each individual in the population according to the fitness function, and select parent individuals based on the fitness value using an improved elite retention competitive selection method.

[0106] In one embodiment of this application, the fitness function is defined as:

[0107]

[0108]

[0109] in, This represents the total energy consumption for equipment operation. As an adaptive penalty factor, The total number of constraints. For the first The amount of a constraint violation, This represents the number of iterations. The learning rate is initially set to 0.01. The initial penalty factor is set to 100.

[0110] In one embodiment of this application, the selection of parent individuals using an improved elite-retention competitive selection method based on the fitness value includes:

[0111] The elite individual with the highest fitness value is retained, and the remaining individuals are selected based on selection probability.

[0112] The formula for calculating the probability of selection is:

[0113]

[0114] in, To select the probability, To select a pressure coefficient, the initial value is 0.5. For individual fitness; The average fitness of the population. For population size, For the number of elite individuals, For the first b The fitness value of a non-elite individual.

[0115] In one embodiment of this application, an improved elite retention competitive selection method is used to select parent individuals; firstly, the top 10 elite individuals are retained, and the remaining individuals are selected according to their probability. The selection probability is calculated using the following formula:

[0116]

[0117] in, For individual fitness; The average fitness of the population.

[0118] S105: Adjust the crossover probability and mutation probability according to the degree of population fitness dispersion, and perform co-evolution operation based on the parent individuals.

[0119] In one embodiment of this application, the adjustment formula for adjusting the crossover probability and mutation probability based on the population fitness dispersion is as follows:

[0120]

[0121]

[0122] in, P c , P m These are the crossover probability and the mutation probability, respectively. The standard deviation of population fitness; P c0 , P m0 These are the initial crossover probability and the initial mutation probability, respectively.

[0123] In one embodiment of this application, performing co-evolutionary operations based on the parent individual includes:

[0124] Pump combinations that operate in parallel and have a hydraulic-thermal coupling relationship are encoded in adjacent positions on the chromosome, and the coupled equipment combinations are swapped as a whole.

[0125] In one embodiment of this application, the co-evolution operation includes co-crossover and co-mutation, performing a global exchange on the coupled device combination, with the crossover probability and mutation probability being:

[0126]

[0127]

[0128] in, , These are the cooperative crossover probability and the cooperative mutation probability, respectively. This is the coupling strength coefficient, set to 1.2 in the application. A random number between [0,1]; This is the coupling sensitivity coefficient, set to 0.5 in the application. It is a random number between [0,1].

[0129] S106: Perform a local search on elite individuals, with fixed equipment combination status.

[0130] In this embodiment, a local search is performed on the elite individual, fixing its equipment combination state, i.e., the binary part, and the gradient descent method is used to search within its continuous parameter neighborhood. The continuous parameters refer to the flow rate of the oil pump and the outlet temperature of the heating furnace. The gradient descent formula is:

[0131]

[0132] in, For the current continuous parameter vector, For the updated continuous parameter vector, The objective function; adaptive step size factor Initial step size for local search =0.1, attenuation coefficient =0.01, The magnitude of the gradient vector; For the objective function, the continuous function is The gradient at that point.

[0133] S107: Check whether the solution meets the constraints, and repair individuals that do not meet the constraints.

[0134] In this embodiment, a feasibility preservation strategy is applied to check whether the solution meets the constraints. If it does not, a repair operator is used for adjustment.

[0135] Specifically, in one embodiment of this application, checking whether the solution satisfies the constraints and repairing individuals that do not satisfy the constraints includes:

[0136] If the hydraulic system is unbalanced, adjust the flow rate of each operating pump.

[0137] If the heat is unbalanced, adjust the outlet temperature of the operating heating furnace.

[0138] In one embodiment of this application, for a solution of hydraulic imbalance, the flow rate of the external pump is adjusted:

[0139]

[0140] in, For current traffic, For the adjusted flow rate, This is the flow adjustment factor, set to 0.5 in the application. For pressure deviation;

[0141] For solutions to thermal imbalances, adjust the furnace outlet temperature coefficient:

[0142]

[0143] in, This is the current furnace outlet temperature. The adjusted furnace outlet temperature. This is the temperature adjustment factor, set to 0.5 in the application. This refers to temperature deviation.

[0144] S108: Determine whether the termination condition has been met. If so, output the optimal equipment start / stop combination, operating parameters, and total energy consumption.

[0145] In this embodiment, the termination condition is determined when the number of iterations reaches 100 or the optimal fitness change rate is reached. At that time, among them For the first k The average fitness value of the population. For the first k The algorithm terminates when the average fitness of the first generation population is reached, and the optimal combination of device start / stop, operating parameters, and total energy consumption are output.

[0146] In one embodiment of this application, a large crude oil depot in northern China is used as an example. Its total storage capacity exceeds 690,000 cubic meters and it is equipped with two different types of heating furnaces, namely No. 1 and No. 2 heating furnaces, and six different types of centrifugal oil pumps, namely No. 1 to No. 6 external pumps. The basic parameters set in the optimization model are shown in Table 1, and the set operating conditions are shown in Table 2.

[0147] Table 1. Basic parameters in the optimization model

[0148]

[0149] Table 2. Operating Condition Parameters

[0150]

[0151] The basic parameters and operating conditions shown in Tables 1 and 2 were input into the established optimization model. The improved adaptive genetic algorithm was applied to repeatedly calculate this instance, and each iteration converged to a similar optimal solution within 100 iterations. The optimization results were compared with the operating plan developed by the oil depot based on operational experience under the same conditions. The optimization results and energy consumption changes are shown in Tables 3 and 4. Figure 2 As shown.

[0152] Table 3. Comparison of Crude Oil Storage Equipment Operation Scheme Before and After Optimization

[0153]

[0154] As shown in Table 3, after optimization using the method of this invention, the operation combination of the oil pump changed, and the outlet temperature of the heating furnace decreased from 27.0℃ to the lower limit of the outlet temperature constraint of 25.5℃. Ultimately, the power consumption of the oil pump decreased by 10.2%, the natural gas consumption of the heating furnace decreased by 19.3%, and the total energy consumption of the equipment was reduced by 15.12%. This result verifies the feasibility of the optimization model and provides strong technical support for energy conservation and consumption reduction in crude oil depots.

[0155] In the aforementioned improved adaptive genetic algorithm-based optimization method for crude oil depot equipment operation, a crude oil depot equipment operation optimization model is established with the goal of minimizing the total energy consumption of the crude oil depot equipment. Parameters of the adaptive genetic algorithm are set, including population size, maximum number of iterations, initial crossover probability, initial mutation probability, and number of elite individuals. A hybrid encoding mechanism is used to initialize the population based on the population size and the crude oil depot equipment operation optimization model. The fitness value of each individual in the population is calculated according to the fitness function, and a modified elite retention competitive selection method is used to select parent individuals based on the fitness value. The crossover probability and mutation probability are adjusted according to the population fitness dispersion, and a co-evolution operation is performed based on the parent individuals. Local search is performed on the elite individuals to fix the equipment combination state. The solution is checked to see if it meets the constraints, and individuals that do not meet the constraints are repaired. The termination condition is determined; if so, the optimal equipment start-stop combination, operating parameters, and total energy consumption are output. In other words, on the one hand, with the goal of minimizing total operating energy consumption, and using constraints such as outlet temperature, tank oil temperature, and equipment operating characteristics, and with equipment operating status and parameters as decision variables, an optimization model for the joint operation of crude oil depot equipment, including the power consumption of oil pumps and the fuel consumption of heating furnaces, is established. An improved adaptive genetic algorithm is then applied to solve this model, yielding optimized joint operation schemes for crude oil depot equipment under different operating conditions, providing a reference for the formulation of on-site oil depot equipment operation plans. On the other hand, to address the difficulty of traditional genetic algorithms in solving optimization problems involving mixed variables and coupling relationships, the adaptive genetic algorithm is improved. A hybrid encoding mechanism combined with heuristic rule initialization improves the quality of the initial population, and the combination of global and local search effectively avoids blind searching in the mixed variable space, improving the algorithm's optimization efficiency. Simultaneously, the introduction of collaborative optimization operations and feasibility repair operators ensures hydraulic-thermal balance during the solution process, overcoming the problems of easily getting trapped in local optima and poor solution feasibility, providing a new method for optimizing the operation of crude oil depot equipment.

[0156] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0157] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0158] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0159] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0160] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A crude oil tank farm equipment unit train optimization method that improves on adaptive genetic algorithms, characterized by, The method comprises: A crude oil depot equipment joint operation optimization model is established with the lowest total energy consumption of the crude oil depot equipment operation as the target; Parameters of the adaptive genetic algorithm are set, including population size, maximum iteration number, initial crossover probability, initial mutation probability, and elite individual number; A population is initialized based on the population size and the crude oil depot equipment joint operation optimization model using a hybrid coding mechanism; The fitness value of each individual in the population is calculated according to a fitness function, and parent individuals are selected based on the fitness value using an improved elite reservation tournament selection method; The crossover probability and the mutation probability are adjusted according to the dispersion degree of the population fitness, and a cooperative evolution operation is implemented based on the parent individuals; Local search is performed on the elite individuals, and the equipment combination state is fixed; It is checked whether the solution meets the constraint condition, and the individuals that do not meet the constraint are repaired; It is judged whether the termination condition is reached, and if yes, the optimal equipment start-stop combination, operation parameters, and total energy consumption are outputted; The fitness function is defined as: wherein, is the total energy consumption of the device operation, is the adaptive penalty factor, is the total number of constraints; is the violation of the th constraint, is the number of iterations; is the learning rate, the initial value is 0.01; is the initial penalty factor; The parent individuals are selected based on the fitness value using the improved elite reservation tournament selection method, which comprises: The elite individual with the highest fitness value is reserved, and the remaining individuals are selected according to a selection probability; The calculation formula of the selection probability is: wherein, is a selection probability, is a selection pressure coefficient, is an individual fitness; is a population average fitness, is a population size, is an elite individual number, is a fitness value of the b th non-elite individual; The adjustment formula of the crossover probability and the mutation probability according to the dispersion degree of the population fitness is: wherein, P c , P m are the crossover probability and mutation probability, respectively; is the population fitness standard deviation; P c0 , P m0 are the initial crossover probability and initial mutation probability, respectively.

2. The crude oil tank farm equipment intermodal optimization method of claim 1, wherein, The total energy consumption of the crude oil depot equipment includes the power consumption of the oil pump and the fuel consumption of the heating furnace, and the equipment start state and the operation parameters are decision variables, wherein the combination of the equipment start state is a discrete variable, and the operation parameters are continuous variables, and the operation parameters include the delivery volume of the oil pump and the outlet temperature of the heating furnace.

3. The crude oil tank farm equipment intermodal optimization method of claim 2, wherein, The objective function of the crude oil depot equipment joint operation optimization model is: in, The total energy consumption for equipment operation is expressed as the total mass of standard coal, tce; To pass the first j Crude oil mass flow rate of the pump, kg / s; Furnace outlet temperature, °C; For the first The on / off status of the external pump. This means the external pump is shut down; This means the external pump is turned on; For the first The operating status of the heating furnace. This means the heating furnace is shut down; This means the heating furnace is turned on; This is the electricity conversion factor; The power consumption of the external pump is expressed in kW·h. This is the natural gas conversion factor; m represents the natural gas consumption of the heating furnace. 3 ; This represents the total number of external pumps. for The head of the external pump is in meters (m); g is the acceleration due to gravity (m / s²). 2 ; Runtime, in hours (h); For the first Pump efficiency of the external transfer pump; For the first The motor efficiency of the external pump; This refers to the number of heating furnaces. To pass the first Mass flow rate of the heating furnace, kg / s; The heat capacity of crude oil is expressed in kJ / (kg·℃). The furnace inlet temperature is ℃; The calorific value of natural gas is expressed in kJ / m³. 3 ; For the first Thermal efficiency of the heating furnace; The inlet temperature of the heating furnace is determined by the temperature drop of the crude oil storage tank, and the calculation formula is: wherein, Tambient is the ambient temperature around the tank, °C; Tinitial is the initial temperature of the crude oil inside the tank, °C; Ktank is the heat transfer coefficient of the crude oil tank, W / (m 2 ·°C); Atank is the surface area of the crude oil tank, m 2 ; Tduration is the temperature drop duration, s; Mtotal is the total mass of the crude oil inside the tank, kg.

4. The crude oil tank farm equipment intermodal optimization method of claim 3, wherein, The constraint conditions of the crude oil depot equipment joint operation optimization model include the delivery volume constraint, the outlet temperature constraint of the crude oil depot, the outlet pressure constraint, the strength constraint of the delivery pipeline, the oil temperature constraint in the storage tank, the characteristics constraint of the delivery pump and the heating furnace, and the hydraulic-thermal coupling constraint between the equipment.

5. The crude oil tank farm equipment intermodal optimization method of claim 1, wherein, The population is initialized based on the population size and the crude oil depot equipment joint operation optimization model using the hybrid coding mechanism, which comprises: The start-stop state of the equipment is represented by binary coding, and the continuous operation parameters of the equipment are represented by real number coding; 70% of the initial individuals are randomly generated, and the remaining 30% of the initial individuals are generated using heuristic rules.

6. The crude oil tank farm equipment intermodal optimization method of claim 1, wherein, The cooperative evolution operation is implemented based on the parent individuals, which comprises: The pump combination with parallel operation and hydraulic-thermal coupling relationship is coded in the adjacent positions of the chromosome, and the overall exchange is performed on the coupled equipment combination.

7. The crude oil tank farm equipment intermodal optimization method of claim 1, wherein, It is checked whether the solution meets the constraint condition, and the individuals that do not meet the constraint are repaired, which comprises: If the hydraulic imbalance occurs, the flow rate of each operating pump is adjusted; If the thermal imbalance occurs, the outlet temperature of the operating heating furnace is adjusted.

Images