Electric farm machine composite power energy optimization management method and device

Abstract

The application provides an electric agricultural machine composite power energy optimization management method and device, the method comprises the following steps: generating a chromosome population; decoding each chromosome in the chromosome population respectively to obtain fuzzy control parameters corresponding to each chromosome; obtaining the fitness of each chromosome corresponding to each preset test working condition according to the fuzzy control parameters and based on multiple preset test working conditions and vehicle control models; judging whether the chromosome population corresponding to each preset test working condition converges, and based on the convergence, selecting the fuzzy control parameters corresponding to the chromosome with the highest fitness to perform energy management on the electric agricultural machine. The application is based on an improved genetic algorithm, iteratively optimizes fuzzy control rules under different electric agricultural machine working conditions, and then uses the optimized fuzzy control strategy to perform energy management on the electric agricultural machine, thereby reducing the dependence of the fuzzy control strategy on prior experience and quickly matching the optimal fuzzy control parameters under different working conditions.

Description

Technical Field

[0001] This invention relates to the field of electric agricultural machinery technology, and in particular to a method and device for optimizing energy management of composite power sources for electric agricultural machinery. Background Technology

[0002] With the overuse of fossil fuels, the problem of resource shortage is becoming increasingly serious. For a long time, agricultural machinery has mostly used internal combustion engines for power. Traditional fuel-powered agricultural machinery consumes a lot of petroleum resources and also brings a lot of carbon emissions and environmental pollution. Electric agricultural machinery has the characteristics of simple structure, flexible control, low exhaust emissions, low operating noise, low carbon and environmental protection, and low maintenance costs. It saves agricultural operation costs and is a green and environmentally friendly agricultural machinery.

[0003] At present, electric agricultural machinery also faces some technical challenges that urgently need to be addressed. These mainly include energy management technology, motor and its control technology, gearbox and its control technology, and virtual simulation technology. Under existing conditions, the specific power and specific energy of the batteries that have been developed and manufactured are insufficient to meet the actual operating requirements of electric agricultural machinery. Therefore, under limited power, it is of great significance to formulate effective energy management strategies for electric tractor power supplies to reduce the energy consumption of electric agricultural machinery and improve its range.

[0004] Currently, the power source for electric agricultural machinery is mainly the battery. Unlike electric vehicles, electric agricultural machinery, in addition to having the same transportation function as electric vehicles, must also bear the changing and complex operating conditions. Therefore, the power system will switch operating modes when the operating conditions change. At this time, the output torque of the motor may change abruptly, resulting in the generation of instantaneous peak current of the battery. As a result, the battery life will decrease with the increase of the number of high current discharges. Summary of the Invention

[0005] This invention provides a method and device for optimizing the energy management of a composite power supply for electric agricultural machinery, which solves the problem of poor battery life caused by the instantaneous peak current of the power system in the prior art, improves the cycle life of the battery, realizes nonlinear control, and has excellent adaptability and fault tolerance.

[0006] This invention provides a method for optimizing energy management of a composite power supply for electric agricultural machinery, comprising: generating a chromosome population, wherein the chromosome population includes multiple chromosomes, and each chromosome is an encoded string obtained by encoding a single individual in the chromosome population; decoding each chromosome in the chromosome population to obtain fuzzy control parameters corresponding to each chromosome; obtaining the fitness of each chromosome corresponding to each preset test condition based on the fuzzy control parameters and based on multiple preset test conditions and a vehicle control model; determining whether the chromosome population corresponding to each preset test condition has converged, and based on convergence, selecting the fuzzy control parameters corresponding to the chromosome with the highest fitness as the optimal fuzzy control parameters; and performing energy management of the electric agricultural machinery according to each preset test condition and its corresponding optimal fuzzy control parameters.

[0007] According to the present invention, an energy optimization management method for a composite power supply of electric agricultural machinery is provided. The step of obtaining the fitness of each chromosome corresponding to each preset test condition includes: inputting the fuzzy control parameters corresponding to each chromosome into the vehicle control model, and running the vehicle control model based on the preset test conditions; obtaining the SOC and maximum peak current of the battery according to the running vehicle control model; and obtaining the fitness of each chromosome according to the SOC and maximum peak current of the battery.

[0008] According to the present invention, an energy optimization management method for a composite power supply of an electric agricultural machine, after determining whether the chromosome population corresponding to each preset test condition has converged, further includes: updating the chromosome population based on non-convergence; decoding the updated chromosome population to obtain updated fuzzy control parameters for each chromosome in the updated chromosome population; re-obtaining the fitness of each chromosome in the updated chromosome population corresponding to each preset test condition based on the updated fuzzy control parameters and multiple preset test conditions and a vehicle control model; re-determining whether the updated chromosome population has converged, and based on convergence, re-selecting the updated fuzzy control parameter corresponding to the chromosome with the highest fitness in the updated chromosome population as the optimal fuzzy control parameter; and re-managing the energy of the electric agricultural machine according to each preset test condition and its corresponding re-selected optimal fuzzy control parameter.

[0009] According to the present invention, an energy optimization management method for a composite power supply of electric agricultural machinery is provided. The step of updating the chromosome population based on non-convergence includes: retaining the chromosome with the highest fitness in the chromosome population; randomly pairing the other chromosomes in the chromosome population (excluding the chromosome with the highest fitness) to obtain paired chromosome pairs; determining whether to perform a crossover operation on each chromosome pair according to a preset crossover probability, and updating the chromosome pairs according to the determination result; determining whether to perform a mutation operation on each of the other chromosomes according to a preset mutation probability, and updating the corresponding other chromosomes according to the determination result; obtaining a first population based on the chromosome with the highest fitness, the updated chromosome pairs, and the updated other chromosomes; and using a roulette wheel selection mechanism to select chromosomes in the first population to obtain an updated chromosome population.

[0010] According to the present invention, an energy optimization management method for a composite power supply of electric agricultural machinery is provided. The step of determining whether to perform a crossover operation on each chromosome pair based on a preset crossover probability includes: randomly generating a first random number in a first preset interval; and performing a crossover operation if the first random number is less than the preset crossover probability.

[0011] The step of determining whether to perform mutation operations on each of the other chromosomes based on a preset mutation probability includes: randomly generating a second random number within a second preset interval; and performing a mutation operation if the second random number is less than the preset mutation probability.

[0012] According to the present invention, a method for optimizing the energy management of a composite power supply for electric agricultural machinery, wherein determining whether the chromosome population corresponding to each preset test condition has converged includes: convergence if the highest fitness meets a preset optimization range; and / or, convergence if the number of times the chromosome population corresponding to each preset test condition has converged reaches a preset number of iterations.

[0013] According to the present invention, an energy optimization management method for a composite power supply of electric agricultural machinery includes, after generating a chromosome population, removing chromosomes from the chromosome population in order of fitness from low to high according to a preset removal quantity.

[0014] This invention also provides an energy optimization management device for a composite power supply of electric agricultural machinery, comprising: a population generation module for generating a chromosome population, wherein the chromosome population includes multiple chromosomes, and each chromosome is an encoded string obtained by encoding a single individual in the chromosome population; a decoding module for decoding each chromosome in the chromosome population to obtain fuzzy control parameters corresponding to each chromosome; a fitness acquisition module for obtaining the fitness of each chromosome corresponding to each preset test condition based on the fuzzy control parameters and based on multiple preset test conditions and a vehicle control model; a convergence judgment module for judging whether the chromosome population corresponding to each preset test condition has converged, and based on convergence, selecting the fuzzy control parameters corresponding to the chromosome with the highest fitness as the optimal fuzzy control parameters; and an energy management module for performing energy management of the electric agricultural machinery according to each preset test condition and its corresponding optimal fuzzy control parameters.

[0015] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the electric agricultural machinery composite power supply energy optimization management method described above.

[0016] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the electric agricultural machinery composite power supply energy optimization management method as described above.

[0017] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the electric agricultural machinery composite power supply energy optimization management method described above.

[0018] The present invention provides an energy optimization management method and device for hybrid power supplies in electric agricultural machinery. Based on an improved genetic algorithm, it iteratively optimizes fuzzy control rules under different operating conditions of the electric agricultural machinery, and then uses the optimized fuzzy control strategy to manage the energy of the electric agricultural machinery. This reduces the dependence of the fuzzy control strategy on prior experience and can quickly match the optimal fuzzy control parameters under different operating conditions. In addition, the genetic algorithm used for optimization incorporates an elite retention strategy to ensure global convergence of the algorithm, thereby obtaining the globally optimal solution. The battery's SOC and maximum peak current are used as economic evaluation indicators to obtain fuzzy control parameters that can fully utilize the supercapacitor to reduce the battery's peak current, reduce the number of high-current discharges, and extend the battery's service life. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 This is one of the flowcharts illustrating the energy optimization management method for the composite power supply of electric agricultural machinery provided by the present invention;

[0021] Figure 2 This is the second flowchart of the energy optimization management method for the composite power supply of electric agricultural machinery provided by the present invention;

[0022] Figure 3 This is a diagram showing the relationship between the composite power supply fuzzy control strategy provided by the present invention.

[0023] Figure 4 This is a schematic diagram of the fuzzy control rules provided by the present invention;

[0024] Figure 5 This is a schematic diagram of the preset test conditions provided by the present invention;

[0025] Figure 6 This is a schematic diagram of the structure of the electric agricultural machinery composite power supply energy optimization management device provided by the present invention;

[0026] Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0028] Figure 1 A flowchart illustrating an energy optimization management method for a hybrid power supply in electric agricultural machinery according to the present invention is shown. The method includes:

[0029] S11, Generate a chromosome population. The chromosome population consists of multiple chromosomes. A chromosome is an encoded string that encodes a single individual in the chromosome population.

[0030] S12, decode each chromosome in the chromosome population to obtain the fuzzy control parameters for each chromosome;

[0031] S13. Based on the fuzzy control parameters and various preset test conditions and vehicle control models, obtain the fitness of each chromosome corresponding to each preset test condition.

[0032] S14, determine whether the chromosome population corresponding to each preset test condition has converged, and based on convergence, select the fuzzy control parameter corresponding to the chromosome with the highest fitness as the optimal fuzzy control parameter.

[0033] S15, based on each preset test condition and its corresponding optimal fuzzy control parameters, performs energy management on the electric agricultural machinery.

[0034] It should be noted that S1N in this manual does not represent the order of the energy optimization management methods for the combined power supply of electric agricultural machinery. The following details will explain this in conjunction with... Figures 2-5 The present invention describes an energy optimization management method for a composite power supply for electric agricultural machinery.

[0035] Step S11: Generate a chromosome population. The chromosome population consists of multiple chromosomes. A chromosome is an encoded string that encodes a single individual in the chromosome population.

[0036] In this embodiment, reference Figure 2 The process of generating a chromosome population includes: initially setting fuzzy control parameters and membership functions; encoding the initially set fuzzy control parameters to obtain chromosomes corresponding to each fuzzy control parameter; and arranging the chromosomes according to a preset arrangement order to obtain the chromosome population.

[0037] It should be noted that when initially setting the fuzzy control parameters and membership functions, they can be set based on prior experience and the power supply requirements of the electric agricultural machinery, or according to actual design needs; no further limitations are imposed here. Additionally, the number of chromosomes generated can be set according to actual requirements; no further limitations are imposed here.

[0038] In an optional embodiment, the initially set fuzzy control parameters are encoded, including: encoding the fuzzy control parameters using binary encoding to improve encoding accuracy and search range.

[0039] For example, if a three-input, one-output fuzzy controller is selected, then as follows: Figure 3 As shown, there are a total of 45 fuzzy control parameters, for reference. Figure 4 The 45 fuzzy control parameters are arranged in a preset order, with each fuzzy control parameter represented by three binary digits, to obtain a fuzzy control rule represented by a chromosome with a length of 135 bits.

[0040] In one optional embodiment, after generating the chromosome population, the method includes: removing chromosomes from the chromosome population according to their fitness from low to high based on a preset removal number. For example, if there are N chromosomes in the generated chromosome population and the preset removal number is M, then the M chromosomes with the lowest fitness among the N chromosomes are deleted, leaving (NM) chromosomes as the chromosome population.

[0041] Step S12: Decode each chromosome in the chromosome population to obtain the fuzzy control parameters for each chromosome.

[0042] Step S13: Based on the fuzzy control parameters and various preset test conditions and vehicle control models, obtain the fitness of each chromosome corresponding to each preset test condition.

[0043] In this embodiment, obtaining the fitness of each chromosome corresponding to each preset test condition includes: inputting the fuzzy control parameters corresponding to each chromosome into the vehicle control model, and running the vehicle control model based on the preset test conditions; obtaining the SOC and maximum peak current of the battery based on the running vehicle control model; and obtaining the fitness of each chromosome based on the SOC and maximum peak current of the battery.

[0044] It should be noted that before obtaining the fitness of each chromosome corresponding to each preset test condition, a preset test condition is selected to facilitate the execution of step S13 based on the selected preset test condition. Furthermore, the preset test condition can refer to the standard test condition for electric vehicles and be modified to suit the actual operating conditions of electric agricultural machinery. For example, taking the NEDC test condition of the standard test condition for electric vehicles as an example, the speed of the NEDC test condition is reduced according to the actual operating speed required by the electric tractor, resulting in the following... Figure 5 The NEDC operating condition shown is after speed reduction.

[0045] To elaborate further, the fitness of each chromosome is expressed as:

[0046]

[0047] Where ω1 and ω2 represent weighting coefficients, and SOC bat_last ess_current represents the remaining SOC value of the battery when the composite power supply stops working. max This represents the maximum peak current of the battery. It should be added that ω1 and ω2 can be set according to actual design requirements. For example, to reduce the maximum peak current of the battery, and given that the battery's SOC variation is relatively small, ω1 can be set to 0.2 and ω2 can be set to 0.8.

[0048] In an optional embodiment, obtaining the current and battery SOC corresponding to each preset test condition based on the running vehicle control model further includes: obtaining the vehicle power demand and supercapacitor SOC corresponding to each preset test condition. Accordingly, the vehicle power demand, battery SOC, and supercapacitor SOC corresponding to each preset test condition are used as inputs to a fuzzy controller, and the power ratio of the supercapacitor in the composite power supply for each preset test condition is obtained through a fuzzy control inference engine. It should be noted that the fuzzy control parameters are optimized using an improved genetic algorithm to optimize the fuzzy controller, and the optimized fuzzy controller is used to obtain the power ratio of the supercapacitor in the composite power supply for each preset test condition, thereby facilitating energy control of the composite power supply based on the power ratio. Furthermore, the composite power supply includes a supercapacitor and a battery.

[0049] Step S14: Determine whether the chromosome population corresponding to each preset test condition has converged, and based on convergence, select the fuzzy control parameter corresponding to the chromosome with the highest fitness as the optimal fuzzy control parameter.

[0050] In this embodiment, determining whether the chromosome population corresponding to each preset test condition has converged includes: convergence if the highest fitness meets the preset optimization range; and / or convergence if the number of times the chromosome population corresponding to each preset test condition has converged reaches the preset number of iterations.

[0051] It should be noted that when the number of times the chromosome population corresponding to each preset test condition has converged (i.e., the number of population iterations) reaches the preset number of iterations, iteration stops even if the highest fitness does not meet the preset optimization range. Furthermore, after obtaining the optimal fuzzy control parameters, it is determined whether all preset test conditions have been optimized, i.e., whether steps S13 and S14 have been executed for all preset test conditions. If so, step S15 is executed; otherwise, steps S13 and S14 are re-executed.

[0052] It should be noted that the preset optimization range can be either the highest fitness being no less than the preset optimization threshold, or the highest fitness being within the range formed by the first and second preset optimization thresholds. The specific range can be set according to actual design requirements, and no further limitations are made here. Additionally, the preset number of iterations can also be set according to actual design requirements, for example, to 60.

[0053] In an optional embodiment, after determining whether the chromosome population corresponding to each preset test condition has converged, the method further includes: updating the chromosome population based on non-convergence to obtain an updated chromosome population; re-decoding the updated chromosome population to obtain the updated fuzzy control parameters of each chromosome in the corresponding updated chromosome population; re-obtaining the fitness of each chromosome in the updated chromosome population corresponding to each preset test condition based on the updated fuzzy control parameters and multiple preset test conditions and the vehicle control model; re-determining whether the updated chromosome population has converged, and re-selecting the updated fuzzy control parameters corresponding to the chromosome with the highest fitness in the updated chromosome population as the optimal fuzzy control parameters based on convergence; and re-performing energy management of the electric agricultural machinery based on each preset test condition and its corresponding re-selected optimal fuzzy control parameters.

[0054] Specifically, based on the lack of convergence, the chromosome population is updated, including: retaining the chromosome with the highest fitness in the chromosome population; randomly pairing the other chromosomes in the chromosome population (excluding the chromosome with the highest fitness) to obtain paired chromosome pairs; determining whether to perform crossover operation on each chromosome pair according to a preset crossover probability, and updating the chromosome pairs according to the determination result; determining whether to perform mutation operation on each other chromosome according to a preset mutation probability, and updating the corresponding other chromosomes according to the determination result; obtaining the first population based on the chromosome with the highest fitness, the updated chromosome pairs, and the updated other chromosomes; and using a roulette wheel selection mechanism to select chromosomes in the first population to obtain the updated chromosome population.

[0055] Furthermore, the decision to perform crossover on each chromosome pair is based on a preset crossover probability, including: randomly generating a first random number within a first preset interval; and performing crossover if the first random number is less than the preset crossover probability. It should be noted that the first preset interval and the preset crossover probability can be set according to actual design requirements or prior experience. For example, the first preset interval can be [0,1], and the preset crossover probability can be 0.7. Additionally, the crossover operation can use a single-point crossover method to obtain two offspring chromosomes, which can then replace the current chromosome pair.

[0056] It should be noted that if no crossover operation is performed, the current chromosome pair is retained. Furthermore, the process of determining whether to perform a crossover operation on chromosome pairs based on a preset crossover probability is repeated until crossover operations on all other chromosomes are completed, thereby updating the chromosomes in the current chromosome population.

[0057] Additionally, the system determines whether to perform mutation operations on other chromosomes based on a preset mutation probability. This includes: randomly generating a second random number within a second preset interval; and performing a mutation operation if the second random number is less than the preset mutation probability. It should be noted that the second preset interval and mutation probability can be set according to actual design requirements or prior experience. The second preset interval can also be set based on the first preset interval; there are no specific limitations. The mutation probability can be 0.001. Furthermore, the mutation operation can employ random mutation to obtain a mutated offspring chromosome, which can then replace the current chromosomes.

[0058] It should be noted that if no mutation operation is performed, the other chromosomes are retained. In addition, the determination of whether to perform mutation operation on other chromosomes is repeatedly made based on the preset mutation probability until the mutation operation determination of all other chromosomes is completed, thereby updating the other chromosomes in the current population, filtering out the chromosome with the worst fitness, and combining the remaining chromosomes in the population with the chromosome with the highest fitness to update the chromosome population.

[0059] In this embodiment, the roulette wheel selection mechanism is represented as follows:

[0060]

[0061] Where n represents the number of chromosomes in the updated chromosome population, f i P represents the fitness of the i-th chromosome in the updated chromosome population. i This represents the probability that individual i is selected.

[0062] Step S15: Perform energy management on the electric agricultural machinery according to each preset test condition and its corresponding optimal fuzzy control parameters.

[0063] It should be noted that after obtaining the optimal fuzzy control parameters for all preset test conditions, the obtained optimal fuzzy control parameters for all preset test conditions are input into the controller of the electric agricultural machinery, so as to perform energy management of the electric agricultural machinery based on the current operating conditions and their corresponding optimal fuzzy control parameters.

[0064] In one optional embodiment, the energy management of the hybrid power supply for electric agricultural machinery was performed using a logic threshold strategy, the unoptimized fuzzy control strategy, and the fuzzy control strategy optimized by the improved genetic algorithm in this application, and compared with the single power supply case. The results are shown in the table below:

[0065]

[0066] Therefore, the optimized fuzzy control strategy is superior to the logic threshold strategy. The fuzzy control strategy of this application, which determines the optimal fuzzy control parameters by improving the genetic algorithm, has smaller changes in the maximum peak current and SOC of the battery, which is better than the logic threshold strategy and the fuzzy control strategy before optimization. Moreover, compared with the fuzzy control strategy before optimization, the maximum peak current of the battery of this application is reduced by 36.4%.

[0067] In summary, this invention, based on an improved genetic algorithm, iteratively optimizes fuzzy control rules under different operating conditions of electric agricultural machinery. The optimized fuzzy control strategy is then used for energy management of the electric agricultural machinery, thereby reducing the dependence of the fuzzy control strategy on prior experience and enabling rapid matching of optimal fuzzy control parameters under different operating conditions. Furthermore, the genetic algorithm used in the optimization incorporates an elite retention strategy, ensuring global convergence and thus obtaining the globally optimal solution. Using battery SOC and maximum peak current as economic evaluation indicators, fuzzy control parameters are obtained that fully utilize supercapacitors to reduce battery peak current, decrease the number of high-current discharges, and extend battery life.

[0068] The energy optimization management device for electric agricultural machinery composite power supply provided by the present invention is described below. The energy optimization management device for electric agricultural machinery composite power supply described below can be referred to in correspondence with the energy optimization management method for electric agricultural machinery composite power supply described above.

[0069] Figure 6 A schematic diagram of an energy optimization management device for a hybrid power supply in electric agricultural machinery is shown. The device includes:

[0070] Population generation module 61 generates a chromosome population, which includes multiple chromosomes. A chromosome is an encoded string that encodes a single individual in the chromosome population.

[0071] Decoding module 62 decodes each chromosome in the chromosome population to obtain the fuzzy control parameters for each chromosome.

[0072] The fitness acquisition module 63 obtains the fitness of each chromosome corresponding to each preset test condition based on the fuzzy control parameters and various preset test conditions and vehicle control models.

[0073] The convergence judgment module 64 determines whether the chromosome population corresponding to each preset test condition has converged, and based on the convergence, selects the fuzzy control parameter corresponding to the chromosome with the highest fitness as the optimal fuzzy control parameter.

[0074] The energy management module 65 manages the energy of the electric agricultural machinery based on each preset test condition and its corresponding optimal fuzzy control parameters.

[0075] In this embodiment, the population generation module 61 includes: a setting unit for initially setting fuzzy control parameters and membership functions; an encoding unit for encoding the initially set fuzzy control parameters to obtain chromosomes corresponding to each fuzzy control parameter; and arranging the chromosomes according to a preset arrangement order to obtain a chromosome population.

[0076] In an optional embodiment, the encoding unit includes an encoding subunit that encodes the fuzzy control parameters using binary encoding to improve encoding accuracy and search range.

[0077] In an optional embodiment, the device further includes a screening module, which, after generating the chromosome population, removes chromosomes from the chromosome population in ascending order of fitness according to a preset removal quantity. For example, if there are N chromosomes in the generated chromosome population and the preset removal quantity is M, then the M chromosomes with the lowest fitness among the N chromosomes are removed, leaving the remaining (NM) chromosomes as the chromosome population.

[0078] The fitness acquisition module 63 includes: a model running unit that inputs the fuzzy control parameters corresponding to each chromosome into the vehicle control model and runs the vehicle control model based on preset test conditions; a data acquisition unit that acquires the SOC and maximum peak current of the battery based on the running vehicle control model; and a fitness acquisition unit that obtains the fitness corresponding to each chromosome based on the SOC and maximum peak current of the battery.

[0079] In an optional embodiment, the data acquisition unit is further configured to acquire the vehicle power demand and the SOC of the supercapacitor corresponding to each preset test condition. Correspondingly, the fitness acquisition module 63 further includes a power proportion acquisition unit, which uses the vehicle power demand, battery SOC, and supercapacitor SOC corresponding to each preset test condition as inputs to the fuzzy controller, and obtains the power proportion of the supercapacitor in the composite power supply for each test condition through a fuzzy control inference engine. It should be noted that the fuzzy control parameters are optimized using an improved genetic algorithm to optimize the fuzzy controller, and the optimized fuzzy controller is used to obtain the power proportion of the supercapacitor in the composite power supply corresponding to each preset test condition, thereby facilitating energy control of the composite power supply based on the power proportion. Furthermore, the composite power supply includes a supercapacitor and a battery.

[0080] The convergence judgment module 64 includes: a convergence judgment unit, which judges whether the chromosome population corresponding to each preset test condition has converged; and an optimal parameter acquisition unit, which selects the fuzzy control parameter corresponding to the chromosome with the highest fitness as the optimal fuzzy control parameter based on convergence.

[0081] Specifically, the convergence judgment unit includes: a first convergence judgment subunit, which determines convergence based on the highest fitness meeting the preset optimization range; and / or a second convergence judgment subunit, which determines convergence based on the number of times the chromosome population corresponding to each preset test condition has converged reaching the preset number of iterations.

[0082] In an optional embodiment, the convergence judgment module 64 further includes: a population update unit, which updates the chromosome population based on non-convergence to obtain an updated chromosome population; decodes the updated chromosome population again using the decoding module 62 to obtain the updated fuzzy control parameters of each chromosome in the corresponding updated chromosome population; re-acquires the fitness of each chromosome in the updated chromosome population corresponding to each preset test condition based on the updated fuzzy control parameters and multiple preset test conditions and the vehicle control model using the fitness acquisition module 63; re-determines whether the updated chromosome population has converged using the convergence judgment module 64, and based on convergence, re-selects the updated fuzzy control parameter corresponding to the chromosome with the highest fitness in the updated chromosome population as the optimal fuzzy control parameter; and re-manages the energy of the electric agricultural machinery using the capacity management module 65 based on each preset test condition and its corresponding re-selected optimal fuzzy control parameter.

[0083] Furthermore, the population renewal unit includes: an elite retention subunit, which retains the chromosome with the highest fitness in the chromosome population; a pairing subunit, which randomly pairs all chromosomes in the chromosome population except the chromosome with the highest fitness to obtain paired chromosome pairs; a crossover operation update subunit, which determines whether to perform crossover operation on each chromosome pair according to a preset crossover probability and updates the chromosome pairs according to the determination result; a mutation operation update subunit, which determines whether to perform mutation operation on each other chromosome according to a preset mutation probability and updates the corresponding other chromosomes according to the determination result; a population renewal subunit, which obtains the first population based on the chromosome with the highest fitness, the updated chromosome pairs, and the updated other chromosomes; and a population selection subunit, which uses a roulette wheel selection mechanism to select chromosomes in the first population to obtain the updated chromosome population.

[0084] Furthermore, the crossover operation update subunit includes: a crossover operation judgment subunit, which determines whether to perform crossover operation on each chromosome pair based on a preset crossover probability; and a crossover execution subunit, which updates the corresponding other chromosomes based on the judgment result.

[0085] Specifically, the crossover operation to determine the grandchild unit includes: a first random great-grandchild unit, which randomly generates a first random number within a first preset interval; and a first great-grandchild unit, which performs a crossover operation if the first random number is less than a preset crossover probability.

[0086] In addition, the mutation operation update subunit includes: a mutation operation judgment subunit, which determines whether to perform mutation operations on other chromosomes based on a preset mutation probability; and a mutation execution subunit, which updates the corresponding other chromosomes based on the judgment result.

[0087] Specifically, the mutation operation judgment unit includes: a second random great-grandson unit, which randomly generates a second random number in a second preset interval; and a second judgment great-grandson unit, which performs a mutation operation if the second random number is less than a preset mutation probability.

[0088] In summary, this invention improves the genetic algorithm based on a population generation module, a decoding module, a fitness acquisition module, and a convergence judgment module. It iteratively optimizes the fuzzy control rules under different operating conditions of electric agricultural machinery. Then, the energy management module utilizes the optimized fuzzy control strategy to manage the energy of the electric agricultural machinery, thereby reducing the dependence of the fuzzy control strategy on prior experience and enabling rapid matching of optimal fuzzy control parameters under different operating conditions. Furthermore, the optimized genetic algorithm incorporates an elite retention strategy, ensuring global convergence and thus obtaining the globally optimal solution. Using battery SOC and maximum peak current as economic evaluation indicators, fuzzy control parameters are obtained that fully utilize supercapacitors to reduce battery peak current, decrease the number of high-current discharges, and extend battery life.

[0089] Figure 7 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 7 As shown, the electronic device may include: a processor 71, a communication interface 72, a memory 73, and a communication bus 74. The processor 71, communication interface 72, and memory 73 communicate with each other via the communication bus 74. The processor 71 can call logical instructions in the memory 73 to execute an energy optimization management method for the electric agricultural machinery's composite power supply. This method includes: generating a chromosome population, which comprises multiple chromosomes, each chromosome being an encoded string of a single individual within the chromosome population; decoding each chromosome in the chromosome population to obtain fuzzy control parameters corresponding to each chromosome; obtaining the fitness of each chromosome corresponding to each preset test condition based on the fuzzy control parameters and various preset test conditions and a vehicle control model; determining whether the chromosome population corresponding to each preset test condition has converged, and based on convergence, selecting the fuzzy control parameters corresponding to the chromosome with the highest fitness as the optimal fuzzy control parameters; and managing the energy of the electric agricultural machinery according to each preset test condition and its corresponding optimal fuzzy control parameters.

[0090] Furthermore, the logical instructions in the aforementioned memory 73 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0091] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the electric agricultural machinery composite power supply energy optimization management method provided by the above methods. The method includes: generating a chromosome population, the chromosome population including multiple chromosomes, where a chromosome is an encoded string after encoding a single individual in the chromosome population; decoding each chromosome in the chromosome population to obtain fuzzy control parameters corresponding to each chromosome; obtaining the fitness of each chromosome corresponding to each preset test condition based on the fuzzy control parameters and based on multiple preset test conditions and a vehicle control model; determining whether the chromosome population corresponding to each preset test condition has converged, and based on convergence, selecting the fuzzy control parameters corresponding to the chromosome with the highest fitness as the optimal fuzzy control parameters; and performing energy management on the electric agricultural machinery according to each preset test condition and its corresponding optimal fuzzy control parameters.

[0092] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the energy optimization management method for the combined power supply of electric agricultural machinery provided by the above methods. The method includes: generating a chromosome population, the chromosome population including multiple chromosomes, each chromosome being an encoded string after encoding a single individual in the chromosome population; decoding each chromosome in the chromosome population to obtain fuzzy control parameters corresponding to each chromosome; obtaining the fitness of each chromosome corresponding to each preset test condition based on the fuzzy control parameters and based on multiple preset test conditions and a vehicle control model; determining whether the chromosome population corresponding to each preset test condition has converged, and based on convergence, selecting the fuzzy control parameters corresponding to the chromosome with the highest fitness as the optimal fuzzy control parameters; and performing energy management on the electric agricultural machinery according to each preset test condition and its corresponding optimal fuzzy control parameters.

[0093] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0094] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing energy management of a composite power supply for electric agricultural machinery, characterized in that, include: Generate a chromosome population, wherein the chromosome population comprises multiple chromosomes, and each chromosome is an encoded string that encodes a single individual in the chromosome population; Each chromosome in the chromosome population is decoded to obtain the fuzzy control parameters corresponding to each chromosome; Based on the fuzzy control parameters and various preset test conditions and vehicle control models, the fitness of each chromosome corresponding to each preset test condition is obtained. Determine whether the chromosome population corresponding to each preset test condition has converged, and based on convergence, select the fuzzy control parameter corresponding to the chromosome with the highest fitness as the optimal fuzzy control parameter. Energy management of electric agricultural machinery is carried out based on each preset test condition and its corresponding optimal fuzzy control parameters. The process of obtaining the fitness of each chromosome corresponding to each preset test condition includes: The fuzzy control parameters corresponding to each chromosome are input into the vehicle control model, and the vehicle control model is run based on the preset test conditions. Based on the running vehicle control model, obtain the battery's SOC and maximum peak current; The fitness of each chromosome is obtained based on the SOC and maximum peak current of the battery. The fitness of each chromosome is expressed as follows: ； in, , Indicates the weighting coefficient. This indicates the remaining SOC value of the battery when the composite power supply stops working. This indicates the maximum peak current of the battery.

2. The method for optimizing energy management of electric agricultural machinery composite power supply according to claim 1, characterized in that, After determining whether the chromosome population corresponding to each of the preset test conditions has converged, the method further includes: Based on the lack of convergence, the chromosome population is updated; The updated chromosome population is decoded to obtain the update fuzzy control parameters for each chromosome in the updated chromosome population. Based on the updated fuzzy control parameters, and based on multiple preset test conditions and vehicle control models, the fitness of each chromosome in the updated chromosome population corresponding to each preset test condition is re-acquired. Re-evaluate whether the updated chromosome population has converged, and based on convergence, re-select the updated fuzzy control parameter corresponding to the chromosome with the highest fitness in the updated chromosome population as the optimal fuzzy control parameter. Energy management of electric agricultural machinery is performed again based on the preset test conditions and the corresponding reselected optimal fuzzy control parameters.

3. The method for optimizing energy management of electric agricultural machinery composite power supply according to claim 2, characterized in that, The update of the chromosome population based on non-convergence includes: The chromosome with the highest fitness in the chromosome population is retained; The chromosomes in the chromosome population other than the chromosome with the highest fitness are randomly paired to obtain paired chromosome pairs. Whether to perform a crossover operation on each chromosome pair is determined based on a preset crossover probability, and the chromosome pair is updated based on the determination result; Based on the preset mutation probability, determine whether to perform mutation operations on each of the other chromosomes, and update the corresponding other chromosomes based on the determination result; The first population is obtained based on the chromosome with the highest fitness, the updated chromosome pair, and the other updated chromosomes; Using a roulette wheel selection mechanism, chromosomes in the first population are selected to obtain an updated chromosome population.

4. The method for optimizing energy management of electric agricultural machinery composite power supply according to claim 3, characterized in that, The step of determining whether to perform a crossover operation on each chromosome pair based on a preset crossover probability includes: A first random number is randomly generated within a first preset interval; If the first random number is less than the preset crossover probability, then a crossover operation is performed; The step of determining whether to perform mutation operations on each of the other chromosomes based on a preset mutation probability includes: A second random number is randomly generated within a second preset interval; If the second random number is less than the preset mutation probability, then a mutation operation is performed.

5. The method for optimizing energy management of electric agricultural machinery composite power supply according to claim 1, characterized in that, The determination of whether the chromosome population corresponding to each of the preset test conditions has converged includes: If the highest fitness value meets the preset optimization range, then convergence occurs; and / or, If the number of times the chromosome population corresponding to each preset test condition has converged reaches a preset number of iterations, then it is determined that the population has converged.

6. The method for optimizing energy management of electric agricultural machinery composite power supply according to claim 1, characterized in that, After the chromosome population is generated, it includes: Based on a preset number of chromosomes to be removed, chromosomes in the chromosome population are removed in order of fitness from low to high.

7. An energy optimization management device for a composite power supply of electric agricultural machinery, characterized in that, include: A population generation module generates a chromosome population, which includes multiple chromosomes. Each chromosome is an encoded string that encodes a single individual in the chromosome population. The decoding module decodes each chromosome in the chromosome population to obtain the fuzzy control parameters corresponding to each chromosome. The fitness acquisition module obtains the fitness of each chromosome corresponding to each preset test condition based on the fuzzy control parameters and various preset test conditions and vehicle control models. The convergence judgment module determines whether the chromosome population corresponding to each preset test condition has converged, and based on the convergence, selects the fuzzy control parameter corresponding to the chromosome with the highest fitness as the optimal fuzzy control parameter. The energy management module manages the energy of electric agricultural machinery based on each preset test condition and its corresponding optimal fuzzy control parameters. The fitness acquisition module includes: The model running unit inputs the fuzzy control parameters corresponding to each chromosome into the vehicle control model, and runs the vehicle control model based on preset test conditions; The data acquisition unit acquires the battery's SOC and maximum peak current based on the running vehicle control model. The fitness acquisition unit obtains the fitness of each chromosome based on the SOC and maximum peak current of the battery. The fitness of each chromosome is expressed as follows: ； in, , Indicates the weighting coefficient. This indicates the remaining SOC value of the battery when the composite power supply stops working. This indicates the maximum peak current of the battery.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the electric agricultural machinery composite power supply energy optimization management method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the electric agricultural machinery composite power supply energy optimization management method as described in any one of claims 1 to 6.

Images