Diesel engine intelligent design method and system based on combined intelligent algorithm

Abstract

The invention provides a diesel engine intelligent design method and system based on a combined intelligent algorithm, and the method comprises the steps: constructing an ellipsoid unit neural network model, taking structural design parameters and operation parameters as the input, taking the fuel consumption rate and NOx / soot emission as the output, training the ellipsoid unit neural network model through a data set, and calculating the design parameters of the ellipsoid unit neural network model; obtaining a diesel engine matching design model; based on a particle swarm algorithm principle, combining capture in the eagle algorithm with alpha wolf in the grey wolf algorithm to perform local optimization, and combining migration in the eagle algorithm with beta wolf in the eagle algorithm to jump out of local optimum when falling into local optimum so as to obtain a eagle fusion algorithm; and optimizing the obtained diesel engine matching design model by using the eagle fusion algorithm to obtain a Pareto solution, and determining a diesel engine design scheme based on design optimization requirements, so that the fuel consumption rate and emission of the diesel engine can be balanced, and proper diesel engine design parameters can be selected according to design requirements.

Description

Technical Field

[0001] The present invention belongs to the technical field of engine intelligent design, and in particular relates to a diesel engine intelligent design method and system based on a combined intelligent algorithm. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Large-bore high-speed diesel engines have the characteristics of high power density, good reliability, and low overall cost. Large-bore means larger piston area and longer stroke, which can inhale and compress more air in each working cycle, thereby burning more fuel and generating more power. This makes large-bore diesel engines very suitable for applications that require high power output, and are widely used in large agricultural machinery (such as tractors, etc.), ship power, construction machinery, mining machinery, power locomotives and other high-power power machinery.

[0004] While large-bore diesel engines bring convenience, their economy and emissions are often contradictory under the premise of ensuring power. Diesel engines are relatively economical under high-temperature and high-pressure combustion conditions but are prone to produce emissions such as nitrogen oxides and carbon soot, which pollute the environment. How to balance economy and emissions has become a difficult problem in diesel engine optimization design. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a diesel engine intelligent design method and system based on a combined intelligent algorithm. The present invention constructs an ellipsoid unit neural network model for diesel engine design matching, inputs relevant parameters, and adopts an ellipsoid unit neural network for training to obtain an intelligent design model; improves the Black Hawk algorithm, and based on the principle of a particle swarm algorithm, combines the α wolf in the Grey Wolf algorithm with the capture in the Black Hawk algorithm for optimization, and combines the β wolf in the Grey Wolf algorithm with the migration step in the Black Hawk algorithm to prevent falling into a local optimal solution, thereby obtaining a Black Hawk fusion algorithm; uses the Black Hawk fusion algorithm to optimize the intelligent design model to obtain a Pareto solution, and obtains a diesel engine intelligent design scheme; the fuel consumption rate and emission issues of the diesel engine can be balanced, and appropriate diesel engine design parameters can be selected.

[0006] According to some embodiments, the present invention adopts the following technical solutions:

[0007] A diesel engine intelligent design method based on a combined intelligent algorithm comprises the following steps:

[0008] Obtain the diesel engine structural design parameters and operating parameters, calculate the fuel consumption rate, NO x / Carbon smoke emission data, build a data set;

[0009] The ellipsoid unit neural network model is constructed, and the structural design parameters and operating parameters are used as inputs, and the fuel consumption rate and NO x / carbon smoke emission is taken as output, and the ellipsoid unit neural network model is trained using the data set to obtain a diesel engine matching design model;

[0010] Based on the principle of particle swarm algorithm, the capture in the black hawk algorithm is combined with the α wolf in the gray wolf algorithm to perform local optimization. When trapped in the local optimum, the migration in the black hawk algorithm is combined with the β wolf to jump out of the local optimum, thus obtaining the black hawk fusion algorithm.

[0011] The Black Hawk fusion algorithm is used to optimize the obtained diesel engine matching design model to obtain a Pareto solution, and the diesel engine design scheme is determined based on the design optimization requirements.

[0012] As an optional implementation, the operating parameters include speed and torque, and the structural design parameters include intake swirl, combustion chamber diameter and injection pressure. According to different operating parameters and structural design parameters, the fuel consumption rate and NO in this case are obtained through simulation design. x / smoke emissions, thereby constructing a data set.

[0013] As an optional implementation, the process of combining the capture in the Black Hawk algorithm with the α wolf in the Gray Wolf algorithm includes: firstly, the Black Hawk algorithm is used to search for the best position, and the optimal position is obtained. Then, based on the particle swarm algorithm principle, the α wolf in the gray wolf algorithm is combined with the capture process in the black hawk algorithm to find the best position. Each loop gets two values, and the better position is selected by comparing the two.

[0014] As an optional implementation, the α wolf in the gray wolf algorithm is combined with the capture process in the black hawk algorithm, specifically:

[0015]

[0016] in, is the alpha wolf updating agent position, It is the black hawk position obtained by combining the capture process in the black hawk algorithm and the gray wolf algorithm. is the current best position, D1 and D2 are position adjustment factors, represents the process variable, s0 is a column vector of dimension d, whose elements are between (0.5,1), Represents the position of the i-th black hawk at the t-th update.

[0017] As an optional implementation method, based on the principle of particle swarm algorithm, the formula after the fusion of Black Hawk Gray Wolf algorithm is combined with particle swarm to obtain the following formula:

[0018]

[0019] in, is the position of the combined algorithm at the ith update t+1, ω is the weight; k is the current iteration number; c1 and c2 are learning factors; rand is a random number between [0,1], This is the best value for this update. is the best value obtained by the tth Black Hawk algorithm optimization;

[0020] Compare and Find the best value judge Whether the consecutive times that the value is less than the set value exceeds the predetermined times, if so, it falls into the local optimum, if not, it returns to the optimization process until it falls into the local optimum.

[0021] As an optional implementation method, when the optimization process falls into a local optimum, the migration in the Black Hawk algorithm is combined with the β wolf to jump out of the local optimum. The process is: the β wolf in the gray wolf algorithm is integrated into the migration step in the Black Hawk algorithm to obtain the migration fusion formula:

[0022]

[0023] Where z(f) is the migration function, is the beta wolf updating agent position, is the position obtained after migration, and the migration fusion formula is obtained. s1 is a column vector with dimension d, whose elements are between -1 and 1, and t2 is a random number from 0.4 to 1 formed by tent mixing mapping;

[0024] This results in the Black Hawk fusion algorithm.

[0025] As an optional implementation method, the obtained Black Hawk fusion algorithm is used to optimize the constructed diesel engine matching design model to obtain a Pareto solution; and a design solution is given according to the different requirements of the diesel engine designer for economy or emission.

[0026] A diesel engine intelligent design system based on combined intelligent algorithm, comprising:

[0027] The data set construction module is configured to obtain the diesel engine structural design parameters and operating parameters, calculate the fuel consumption rate, NO x / Carbon smoke emission data, build a data set;

[0028] The model building module is configured to build an ellipsoid unit neural network model, taking the structural design parameters and operating parameters as input, fuel consumption rate and NO x / carbon smoke emission is taken as output, and the ellipsoid unit neural network model is trained using the data set to obtain a diesel engine matching design model;

[0029] The algorithm fusion module is configured to combine the capture in the black hawk algorithm with the α wolf in the gray wolf algorithm based on the particle swarm algorithm principle to perform local optimization. When trapped in the local optimum, the migration in the black hawk algorithm is combined with the β wolf to jump out of the local optimum and obtain the black hawk fusion algorithm.

[0030] The optimization calculation module is configured to use the Black Hawk fusion algorithm to optimize the obtained diesel engine matching design model to obtain a Pareto solution, and determine the diesel engine design solution based on the design optimization requirements.

[0031] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the steps in the above method are completed.

[0032] An electronic device comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps in the above method are completed.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The present invention is based on the principle of particle swarm algorithm, and integrates the capture and migration methods of the Black Hawk algorithm with the Gray Wolf algorithm, which can improve the global and local search capabilities, prevent falling into the local optimum, jump out of the local optimal solution, and is more likely to find the global optimal solution. It effectively balances the search capabilities of the algorithm at different stages, enhances the ability of local development, and makes it possible to find the target solution more quickly in the middle and late stages of the algorithm iteration. It can promote the smooth transition of the algorithm's global and local searches, improve the algorithm's optimization performance and stability, and ensure the timeliness and accuracy of the calculation.

[0035] The present invention comprehensively considers the balance of diesel engine economy, fuel consumption and emissions, monitors changes in various performances, and selects appropriate diesel engine design parameters, which has a great positive effect on reducing pollutant emissions, protecting the environment, and improving economic benefits.

[0036] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0038] Figure 1The present invention is a schematic diagram of a method flow of an embodiment. DETAILED DESCRIPTION

[0039] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0040] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0041] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0042] In the absence of conflict, the embodiments in this application and the features in the embodiments may be combined with each other.

[0043] Embodiment 1

[0044] A diesel engine intelligent design method based on combined intelligent algorithm, such as Figure 1 As shown, the following steps are included:

[0045] Obtain the diesel engine structural design parameters and operating parameters, calculate the fuel consumption rate, NO x / Carbon smoke emission data, build a data set;

[0046] The ellipsoid unit neural network model is constructed, and the structural design parameters and operating parameters are used as inputs, and the fuel consumption rate and NO x / carbon smoke emission is taken as output, and the ellipsoid unit neural network model is trained using the data set to obtain a diesel engine matching design model;

[0047] Based on the principle of particle swarm algorithm, the capture in the black hawk algorithm is combined with the α wolf in the gray wolf algorithm to perform local optimization. When trapped in the local optimum, the migration in the black hawk algorithm is combined with the β wolf to jump out of the local optimum, thus obtaining the black hawk fusion algorithm.

[0048] The Black Hawk fusion algorithm is used to optimize the obtained diesel engine matching design model to obtain a Pareto solution, and the diesel engine design scheme is determined based on the design optimization requirements.

[0049] The key points in the above process are:

[0050] Based on the principle of particle swarm algorithm, the capture and migration methods of the Black Hawk algorithm are integrated with the Gray Wolf algorithm to obtain the Black Hawk fusion algorithm. According to the Black Hawk fusion algorithm, appropriate parameters are selected, specifically speed, torque, intake swirl, combustion chamber diameter and injection pressure, to obtain the corresponding Pareto solution and select the appropriate solution.

[0051] The Black Hawk algorithm process mainly includes searching, capturing and migrating;

[0052] The Black Hawk search formula in the Black Hawk algorithm is:

[0053]

[0054]

[0055] Where: X r t is a random position in the search space updated at the tth time, X i t is the tth update of the position of a random black hawk, X t best is the best position at the moment. t and i are in D-dimensional space, t is the number of cycles, i is the number of black hawks, and D is X t best The farthest distance to the search boundary, r1 is a random number from 0 to 1, t1 is a random number from 0 to 1 formed by tent mapping, ub and lb are the upper and lower limits of the search space respectively. They are all intermediate variables, and minimizefitness is to minimize the fitness;

[0056] The Black Hawk capture formula in the Black Hawk algorithm is:

[0057]

[0058] Where: D1 is the position adjustment factor 1; D2 is the position adjustment factor 2, X i * Represents the position after the first adjustment, s0 is a column vector of dimension d, and its elements are between (0.5,1).

[0059] The black hawk migration formula in the black hawk algorithm is:

[0060]

[0061] in, f bestis the current best fitness value, f(j) is the fitness value of the jth individual, s1 is a column vector of dimension d, whose elements are between -1 and 1, and t2 is a random number from 0.4 to 1 formed by the tent mixing map.

[0062] At the same time, the original Black Hawk algorithm is used to find the best position Based on the principle of particle swarm algorithm, the α wolf in the gray wolf algorithm is combined with the capture process in the black hawk algorithm to find the best position. Each loop gets two values, and the better position is selected by comparing the two, specifically:

[0063] Combining the α wolf with the black hawk algorithm capture process, the formula is as follows:

[0064]

[0065] in is the alpha wolf updating agent position, It is the black hawk position obtained by combining the capture process in the black hawk algorithm and the gray wolf algorithm.

[0066] Then, based on the principle of particle swarm algorithm, the formula after the fusion of Black Hawk Gray Wolf algorithm is combined with particle swarm to obtain the following formula:

[0067]

[0068] in, is the position of the combined algorithm at the ith update t+1, ω is the weight; k is the current iteration number; c1 and c2 are learning factors, also called acceleration constants, usually c1=c2=2; rand is a random number between [0,1], It is the best value obtained by fusion algorithm based on the principle of particle swarm algorithm. It is the best value obtained by the tth Black Hawk algorithm optimization.

[0069] Compare and Find the best value

[0070] Choose the best value of the two judge Whether the consecutive times exceed the first set value, i.e., NP times, and the value of NP can be determined according to the demand;

[0071] If not, it returns to the optimization process of calculating the capture link according to the Black Hawk algorithm and the Black Hawk fusion algorithm until The number of consecutive times > NP, at this time the algorithm falls into a local optimum, and the Gray Wolf Algorithm is integrated into the migration step of the Black Hawk Algorithm.

[0072] In order to prevent falling into the local optimal solution, the Gray Wolf Algorithm is now integrated into the migration step of the Black Hawk Algorithm to obtain the migration fusion formula:

[0073] Bring in the beta wolf position:

[0074]

[0075] Where z(f) is the migration function, is the beta wolf updating agent position, The migration fusion formula is obtained by deriving the position after migration, and t2 is a random number from 0.4 to 1.

[0076] It is manifested as updating the individual positions of black hawks according to the black hawk algorithm, updating the individual positions of β wolves according to the gray wolf algorithm, and bringing the β wolf individuals into the black hawk migration formula to perform migration operations.

[0077] The strategy is executed NF times until NF> the second set value, i.e., Tt, at which time the optimal value is found, thereby obtaining the Black Hawk fusion algorithm.

[0078] The obtained Black Hawk fusion algorithm is used to optimize the constructed diesel engine design matching model, thereby obtaining the Pareto solution. Based on the Pareto solution, the required diesel engine design scheme is obtained from the perspective of economy or emission.

[0079] Embodiment 2

[0080] A diesel engine intelligent design system based on combined intelligent algorithm, comprising:

[0081] The data set construction module is configured to obtain the diesel engine structural design parameters and operating parameters, calculate the fuel consumption rate, NO x / Carbon smoke emission data, build a data set;

[0082] The model building module is configured to build an ellipsoid unit neural network model, taking the structural design parameters and operating parameters as input, fuel consumption rate and NO x / carbon smoke emission is taken as output, and the ellipsoid unit neural network model is trained using the data set to obtain a diesel engine matching design model;

[0083] The algorithm fusion module is configured to combine the capture in the black hawk algorithm with the α wolf in the gray wolf algorithm based on the particle swarm algorithm principle to perform local optimization. When trapped in the local optimum, the migration in the black hawk algorithm is combined with the β wolf to jump out of the local optimum and obtain the black hawk fusion algorithm.

[0084] The optimization calculation module is configured to use the Black Hawk fusion algorithm to optimize the obtained diesel engine matching design model to obtain a Pareto solution, and determine the diesel engine design solution based on the design optimization requirements.

[0085] Embodiment 3

[0086] Embodiment 3 of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, the steps of a diesel engine intelligent design method based on a combined intelligent algorithm as described in Embodiment 1 of the present invention are implemented.

[0087] Embodiment 4

[0088] Embodiment 4 of the present invention provides an electronic device, including a memory and a processor, and computer instructions stored in the memory and running on the processor, wherein the computer instructions, when executed by the processor, implement the steps of a diesel engine intelligent design method based on a combined intelligent algorithm as described in Embodiment 1 of the present invention.

[0089] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0090] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0091] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0092] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0093] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principle of the present invention without creative labor shall be included in the protection scope of the present invention.

Claims

1. A diesel engine intelligent design method based on a combined intelligent algorithm, characterized in that: The following steps are involved: Obtain the diesel engine structural design parameters and operating parameters, calculate the fuel consumption rate, NO x / Carbon smoke emission data, build a data set; The ellipsoid unit neural network model is constructed, and the structural design parameters and operating parameters are used as inputs, and the fuel consumption rate and NO x / carbon smoke emission is taken as output, and the ellipsoid unit neural network model is trained using the data set to obtain a diesel engine matching design model; Based on the principle of particle swarm algorithm, the capture in the black hawk algorithm is combined with the α wolf in the gray wolf algorithm to perform local optimization. When trapped in the local optimum, the migration in the black hawk algorithm is combined with the β wolf to jump out of the local optimum, thus obtaining the black hawk fusion algorithm. The Black Hawk fusion algorithm is used to optimize the obtained diesel engine matching design model to obtain a Pareto solution, and the diesel engine design scheme is determined based on the design optimization requirements.

2. A diesel engine intelligent design method based on a combined intelligent algorithm as claimed in claim 1, characterized in that: The operating parameters include speed and torque, and the structural design parameters include intake swirl, combustion chamber diameter and injection pressure. According to different operating parameters and structural design parameters, the fuel consumption rate and NO in this case are obtained through simulation design. x / smoke emissions, thereby constructing a data set.

3. A diesel engine intelligent design method based on a combined intelligent algorithm as claimed in claim 1, characterized in that: The process of combining the capture in the black hawk algorithm with the alpha wolf in the gray wolf algorithm includes: firstly, using the black hawk algorithm to search for the best position Then, based on the particle swarm algorithm principle, the α wolf in the gray wolf algorithm is combined with the capture process in the black hawk algorithm to find the best position. Each loop gets two values, and the better position is selected by comparing the two.

4. A diesel engine intelligent design method based on a combined intelligent algorithm as claimed in claim 3, characterized in that: Combine the α wolf in the gray wolf algorithm with the capture process in the black hawk algorithm, specifically: in, is the alpha wolf updating agent position, It is the black hawk position obtained by combining the capture process in the black hawk algorithm and the gray wolf algorithm. is the current best position, D1 and D2 are position adjustment factors, represents the process variable, s0 is a column vector of dimension d, whose elements are between (0.5,1), Represents the position of the i-th black hawk at the t-th update.

5. A diesel engine intelligent design method based on a combined intelligent algorithm as claimed in claim 4, characterized in that: Based on the principle of particle swarm algorithm, the formula after the fusion of Black Hawk Gray Wolf algorithm is combined with particle swarm to obtain the following formula: in, is the position of the combined algorithm at the ith update t+1, ω is the weight; k is the current iteration number; c1 and c2 are learning factors; rand is a random number between [0,1], This is the best value for this update. is the best value obtained by the tth Black Hawk algorithm optimization; Compare and Find the best value judge Whether the consecutive times that the value is less than the set value exceeds the predetermined times, if so, it falls into the local optimum, if not, it returns to the optimization process until it falls into the local optimum.

6. A diesel engine intelligent design method based on a combined intelligent algorithm as claimed in claim 5, characterized in that: When the optimization process falls into a local optimum, the migration in the Black Hawk algorithm is combined with the β wolf to jump out of the local optimum. The process is: Integrate the β wolf in the Gray Wolf algorithm into the migration step in the Black Hawk algorithm, and obtain the migration fusion formula: Where z(f) is the migration function, is the beta wolf updating agent position, is the position obtained after migration, and the migration fusion formula is obtained. s1 is a column vector with dimension d, whose elements are between -1 and 1, and t2 is a random number from 0.4 to 1 formed by tent mixing mapping; Update the individual positions of black hawks according to the black hawk algorithm, update the individual positions of β wolves according to the gray wolf algorithm, bring the β wolves into the black hawk migration formula, and perform migration operations; This results in the Black Hawk fusion algorithm.

7. A diesel engine intelligent design method based on a combined intelligent algorithm as claimed in claim 1, characterized in that: The obtained Black Hawk fusion algorithm is used to optimize the constructed diesel engine matching design model and obtain the Pareto solution; Design solutions are provided based on the different requirements of diesel engine designers for economy or emissions.

8. A diesel engine intelligent design system based on a combined intelligent algorithm, characterized in that: include: The data set construction module is configured to obtain the diesel engine structural design parameters and operating parameters, calculate the fuel consumption rate, NO x / Carbon smoke emission data, build a data set; The model building module is configured to build an ellipsoid unit neural network model, taking the structural design parameters and operating parameters as input, fuel consumption rate and NO x / carbon smoke emission is taken as output, and the ellipsoid unit neural network model is trained using the data set to obtain a diesel engine matching design model; The algorithm fusion module is configured to combine the capture in the black hawk algorithm with the α wolf in the gray wolf algorithm based on the particle swarm algorithm principle to perform local optimization. When trapped in the local optimum, the migration in the black hawk algorithm is combined with the β wolf to jump out of the local optimum and obtain the black hawk fusion algorithm. The optimization calculation module is configured to use the Black Hawk fusion algorithm to optimize the obtained diesel engine matching design model to obtain a Pareto solution, and determine the diesel engine design solution based on the design optimization requirements.

9. A computer-readable storage medium, characterized in that: Used to store computer instructions, which, when executed by a processor, complete the steps of the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the steps in the method according to any one of claims 1 to 7 are completed.

Images