A method and system for manufacturing and detecting oil filters based on particle swarm algorithm

Abstract

The present invention provides a method and system for manufacturing and detecting an oil filter based on a particle swarm algorithm, comprising: obtaining historical manufacturing characteristic parameters of equipment corresponding to each manufacturing process of the oil filter, performing characteristic classification according to parameter types, and obtaining historical manufacturing characteristic parameters; constructing particle multidimensional position characteristic parameters of the oil filter manufacturing process corresponding to the historical manufacturing characteristic parameters according to the particle swarm algorithm according to the corresponding historical detection characteristic parameters, configuring an initialization speed value for each multidimensional position characteristic parameter, constructing a fitness function of the particle swarm algorithm according to the corresponding historical detection characteristic parameters, wherein the fitness function of the particle swarm algorithm adopts a minimization constraint calculation of a mean square error value of an objective function; dynamically updating the multidimensional position characteristics and corresponding speed characteristics of each particle in the particle swarm algorithm according to the fitness function of the particle swarm algorithm, and obtaining a local optimal solution or a global optimal solution of the manufacturing parameters corresponding to the oil filter manufacturing process.

Description

Technical Field

[0001] The invention relates to an oil filter processing method and system, and in particular to an oil filter manufacturing detection method and system based on a particle swarm algorithm. Background Art

[0002] At present, the existing oil filter manufacturing and testing are generally implemented separately. The oil filter manufacturing part is carried out according to the traditional manufacturing process, including the selection of oil filter materials, the processing and manufacturing of filter elements, the sealing process of filter elements, and the automated assembly of filter elements and other components. The above-mentioned traditional oil filter manufacturing method often relies on manual experience to adjust the relevant manufacturing parameters of the automated manufacturing process. However, there are many manufacturing parameters in the actual production process, and manual experience is often difficult to accurately control all manufacturing parameters, especially the manufacturing parameters that need to be adjusted in conjunction with some technical goals. The oil filter detection method is used to determine whether the corresponding production and manufacturing process of the oil filter meets the corresponding technical goals. The oil filter detection method includes oil filter filtration efficiency detection, pressure resistance performance detection, and temperature resistance performance detection. The above corresponding detection methods constitute the detection of the manufacturing process of the oil filter itself. The feedback method of the oil filter manufacturing and detection process in the prior art requires a large amount of manual feedback, which increases the manufacturing cost and the uncertainty of the manufacturing results. Summary of the invention

[0003] One of the inventive purposes of the present invention is to provide an oil filter manufacturing detection method and system based on a particle swarm algorithm. The method and system use the manufacturing parameters in the oil filter manufacturing process and the detection parameters in the detection process to solve the particle swarm algorithm, and use the historical manufacturing feature parameters and historical detection parameters of the oil filter as a sample set to solve the particle swarm algorithm. The particle swarm algorithm is used in the present invention to combine the manufacturing parameters in the oil filter manufacturing process and the detection parameters in the detection process. Therefore, the present invention can effectively reduce the cost of manual feedback in the oil filter manufacturing process and improve the efficient self-adjustment of manufacturing parameters.

[0004] Another inventive object of the present invention is to provide an oil filter manufacturing detection method and system based on a particle swarm algorithm, wherein the method and system classify the historical manufacturing characteristic parameters of the oil filter, construct manufacturing parameter types of different dimensions, and use the data of different manufacturing parameter types as elements in the sample. In the present invention, the sample elements of the different manufacturing parameter types are used to construct the particles in the particle swarm algorithm, and the detection data of the oil filter and the target detection data are used to construct the fitness parameters of the particle swarm algorithm. The particle swarm is iteratively optimized through the fitness parameters, thereby effectively improving the effect of the multi-dimensional manufacturing parameter feedback of the oil filter.

[0005] Another inventive object of the present invention is to provide an oil filter manufacturing detection method and system based on a particle swarm algorithm, wherein the method and system construct multi-dimensional position data of the particles based on different types of manufacturing parameters in the oil filter manufacturing process, and obtain local optimal solutions and global optimal solutions based on the fitness function related to the detection data of the particle swarm algorithm; the preset particle movement speed and learning factor construct the corresponding particle position update strategy, wherein the learning factor and particle movement speed can be dynamically updated according to the iterative process, thereby realizing efficient self-correction of oil filter manufacturing.

[0006] In order to achieve at least one of the above-mentioned invention objects, the present invention further provides an oil filter manufacturing detection method based on a particle swarm algorithm, the method comprising:

[0007] Obtaining historical manufacturing characteristic parameters of equipment corresponding to each manufacturing process of the oil filter, and classifying the historical manufacturing characteristic parameters according to their own parameter types to obtain historical manufacturing characteristic parameters of different types of the oil filter;

[0008] Obtaining corresponding historical detection characteristic parameters according to different types of historical manufacturing characteristic parameters of the oil filter, constructing particle multidimensional position characteristic parameters corresponding to the historical manufacturing characteristic parameters of the oil filter manufacturing process according to the particle swarm algorithm, and configuring an initialization speed value for each multidimensional position characteristic parameter to generate an initialization particle feature corresponding to the complete manufacturing process;

[0009] Constructing a fitness function of the particle swarm algorithm according to the historical detection characteristic parameters corresponding to the historical manufacturing characteristic parameters, wherein the fitness function of the particle swarm algorithm is calculated by minimizing the mean square error value of the objective function;

[0010] The multi-dimensional position characteristics and corresponding speed characteristics of each particle in the particle swarm algorithm are dynamically updated according to the fitness function of the particle swarm algorithm to obtain a local optimal solution or a global optimal solution of the manufacturing parameters corresponding to the manufacturing process of the oil filter.

[0011] According to one of the preferred embodiments of the present invention, a feature classification method for historical manufacturing characteristic parameters of equipment corresponding to each manufacturing process of the oil filter includes: dividing the historical manufacturing characteristic parameters of the oil filter into: physical parameters of oil filter material selection, processing and molding parameters of the selected materials, filter element structure parameters, filter element adhesion parameters, filter element welding parameters and assembly parameters; performing data preprocessing on different types of historical manufacturing characteristic parameters of the oil filter to obtain historical manufacturing characteristic parameters of the oil filter of corresponding types of standardization.

[0012] According to another preferred embodiment of the present invention, the data preprocessing method of the historical manufacturing characteristic parameters of different types of oil filters includes: using the Z-score algorithm to standardize the historical manufacturing characteristic parameters of different types of oil filters, and the specific steps include: calculating the average value μ of each type of historical manufacturing characteristic parameter of the oil filter n , and according to the average value μ n The standard deviation σ of each type of historical manufacturing characteristic parameters of computer oil filters n , the standardized historical manufacturing characteristic parameters of different types of oil filters are calculated according to the following formula: , where the subscript n represents the type identification of the corresponding historical manufacturing characteristic parameter, x represents the corresponding manufacturing parameter value, and the superscript ^ represents the standardized value of the corresponding type of manufacturing parameter, where the average value μ of each type of historical manufacturing characteristic parameter of the oil filter is n , standard deviation σ n Are different.

[0013] According to another preferred embodiment of the present invention, the method for constructing the particle multidimensional position feature comprises: after each oil filter is manufactured, obtaining the standardized historical manufacturing feature parameters of different types of oil filters for each oil filter As each sample element, the combined data of each sample element is taken as a particle, and the corresponding type historical manufacturing feature parameter The numerical value is used as the position characteristic parameter of one dimension of the particle to construct a multidimensional particle position characteristic matrix, and the initialization speed value of the position characteristic of each dimension of the multidimensional particle position characteristic matrix is ​​configured to construct an initialized particle feature including the multidimensional particle position characteristic matrix and the initialization speed value of the corresponding dimensional position characteristic.

[0014] According to another preferred embodiment of the present invention, the characteristics of the initialized particles are dynamically updated according to the particle swarm algorithm, and the dynamic update method includes multi-dimensional position speed update of the corresponding initialized particles and corresponding dimensional position update, wherein the multi-dimensional position speed update method of the initialized particles is executed using the following formula:

[0015] ,in represents the velocity value v of the particle feature i at the n-th dimension position after the t-th iteration, t+1 represents the t+1-th iteration, w represents the inertia weight of the particle, and k 1,n and k 2,n Respectively represent different learning factors at the n-th dimension position, r 1,n and r 2,n are different random numbers, used for random search of particle update; pb irepresents the local optimal solution, and gb represents the global optimal solution.

[0016] According to another preferred embodiment of the present invention, a method for updating the corresponding dimensional position of the initialized particle features according to the particle swarm algorithm includes: ,in represents the characteristic value of the n-th dimension position of particle i in t iterations, and the number of iterations of the particle swarm algorithm is preset to be t s , when the particle satisfies the number of iterations t s Then extract all dimensional position features of the particle i: X = [ , , , .... ], wherein X is the extracted multidimensional feature of the particle, which is used for automatic configuration of different types of manufacturing parameters of the oil filter.

[0017] According to another preferred embodiment of the present invention, the fitness function of the particle swarm algorithm includes: obtaining the detection characteristic parameter h after each oil filter manufacturing i，m , where the subscripts i and m represent the particles corresponding to the manufacturing parameters of the oil filter, respectively, and m represents the detection feature type corresponding to particle i. The target function F(i, m) of each detection feature type is preset. According to the target function F(i, m) and the detection feature parameter h i，m The mean square error is used as the fitness function to constrain the iteration of the particle i.

[0018] According to another preferred embodiment of the present invention, the objective function mean square error value minimization constraint method includes: when the corresponding particle i completes the tth iteration, calculating the detection characteristic parameter h of the particle i at the tth iteration i，m , and obtain the target function F(i, m) of the m detection feature types corresponding to particle i, and calculate its mean square error G t = , and obtain the minimum mean square error G obtained by the previous iteration s , if G t <G s , the eigenvalue of the n-dimensional position obtained after the current t-th iteration is taken as the local optimal solution of the oil filter manufacturing parameters.

[0019] In order to achieve at least one of the above-mentioned invention purposes, the present invention further provides an oil filter manufacturing detection system based on a particle swarm algorithm, and the system executes the above-mentioned oil filter manufacturing detection method based on a particle swarm algorithm.

[0020] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the oil filter manufacturing and detection method based on a particle swarm algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 Shown is a schematic flow chart of the oil filter manufacturing and testing method based on the particle swarm algorithm of the present invention. DETAILED DESCRIPTION

[0022] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0023] It is understood that the term "a" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple, and the term "a" should not be understood as a limitation on the number. Figure 1 The present invention discloses a method for manufacturing and detecting an oil filter based on a particle swarm algorithm, wherein the method comprises the following steps: firstly, it is necessary to obtain historical manufacturing characteristic parameters in the manufacturing process of the oil filter and historical detection characteristic parameters corresponding to the historical manufacturing characteristic parameters of each oil filter, and combine the historical detection characteristic parameters corresponding to the historical manufacturing characteristic parameters of the oil filter through a particle swarm algorithm to discover the relationship between the historical detection characteristic parameters corresponding to the historical manufacturing characteristic parameters of the oil filter, thereby improving the automatic selection effect of the manufacturing parameters of the oil filter.

[0024] The historical manufacturing characteristic parameters may include but are not limited to the type parameters of material selection and the structural parameters of material selection; include but are not limited to the manufacturing temperature, folding method, pasting position, pasting pressure of the filter element; and the assembly pressure between the filter element, base and shell of the oil filter, welding temperature, etc. The above-mentioned different types of manufacturing parameters can be obtained by sensors of relevant manufacturing processes, or the type or state data of materials can be obtained by manual preset or machine recognition. The present invention further obtains the historical detection characteristic parameters corresponding to each historical manufacturing characteristic parameter of the oil filter. It should be noted that since the above-mentioned different manufacturing characteristic parameters often affect the overall performance of the oil filter in an unknown way, a single factor or a combination of factors. Therefore, the present invention uses a particle swarm algorithm and a corresponding fitness function between the historical detection characteristic parameters corresponding to each historical manufacturing characteristic parameter of the oil filter to describe the hidden multi-type unknown influencing factors. Compared with the traditional manual processing method, the learning cost of manufacturing parameter modulation is greatly reduced, which is conducive to the rapid realization of the automation process.

[0025] Since the performance of the oil filter needs to be verified, the oil filter needs to be simulated and tested, wherein the contents of the simulation test include but are not limited to the filtering efficiency of the oil filter, the flow resistance test of the oil filter, the pressure resistance test of the oil filter, the high temperature resistance test of the oil filter, and the vibration fatigue test of the oil filter, etc. And different test results need to meet certain standards, so the present invention sets the corresponding test objective function according to different test types, which is used to judge whether the corresponding type of test meets the target requirements.

[0026] The present invention further configures a particle swarm algorithm fitness function related to the historical detection characteristic parameters of the oil filter. The fitness function is obtained by calculating the historical detection characteristic parameters or actual detection characteristic parameters corresponding to the historical manufacturing parameters of a complete oil filter process, and the constraints of the difference between the corresponding target detection characteristic parameters. That is to say, when the difference between the historical detection characteristic parameters or actual detection characteristic parameters and the corresponding target detection characteristic parameters is smaller, it is more in line with the manufacturing target, otherwise it deviates from the manufacturing target.

[0027] Specifically, since the conditions for achieving the target of different detection characteristic parameters of the oil filter are different, the target characteristic function of the detection can be set according to the type of detection characteristic parameter. For example, for pressure resistance performance, its actual detection characteristic is close to a certain standard pressure, then the target function F (i, m) corresponding to the pressure resistance performance can be set to F (i, m) = i + λm, where i represents the corresponding particle, m represents the corresponding detection characteristic category, and λ represents the corresponding adjustment coefficient. When the pressure resistance performance requirement is improved, it is necessary to increase the adjustment coefficient λ. The above formula setting can effectively associate the corresponding particles in the particle group with the detection characteristic type, effectively improving the compatibility of the parameter design of the model itself. Of course, in some other features, they can be set according to their characteristic types, and the present invention will not go into details.

[0028] Furthermore, after obtaining the historical manufacturing characteristic parameters of the oil filter, the present invention needs to perform data preprocessing on the historical manufacturing characteristic parameters of the oil filter, wherein the data preprocessing method includes: using a Z-score algorithm to perform standardization processing on different types of historical manufacturing characteristic parameters of the oil filter, and the specific method includes:

[0029] Define the historical manufacturing characteristic parameter type of the oil filter as n. After obtaining the historical manufacturing characteristic parameters of the oil filter, calculate the average value μ of each type of historical manufacturing characteristic parameters of the oil filter. n , and according to the average value μ n The standard deviation σ of each type of historical manufacturing characteristic parameters of computer oil filters n， The standard deviation σ n Generate feature parameters x by corresponding type history n and the average value μ of the corresponding historical manufacturing characteristic parameter itself n The square root of the mean square error is calculated; for example, the historical test data of the pressure resistance of the computer oil filter is x 1 , and the average value of the historical test data of compressive performance is μ 1 , it is necessary to calculate the historical detection characteristic data x of the compressive performance 1 and the average value μ of the historical test characteristic data of compressive performance 1 The standard deviation between 1 , where the historical detection characteristic data of compressive performance x 1 Generally, there are multiple historical manufacturing characteristic parameters of different types of standardized oil filters. , where the subscript n represents the type identification of the corresponding historical manufacturing characteristic parameter, x represents the corresponding manufacturing parameter value, and the superscript ^ represents the standardized value of the corresponding type of manufacturing parameter, where the average value μ of each type of historical manufacturing characteristic parameter of the oil filter is n, standard deviation σ n Are different.

[0030] The present invention needs to construct the multi-dimensional particle position feature of the particle swarm algorithm according to the standardized historical manufacturing feature parameters x^ of different types of oil filters. The method for constructing the particle multi-dimensional position feature includes: after each oil filter is manufactured, obtaining the standardized historical manufacturing feature parameters of different types of oil filters of each oil filter As each sample element, the combined data of each sample element is taken as a particle, and the corresponding type historical manufacturing feature parameter The value of is used as the position characteristic parameter of one dimension of the particle to construct a multi-dimensional particle position characteristic matrix, wherein the multi-dimensional particle position characteristic matrix can be constructed as [ , , , .... ], and configure the initialization speed value v of each dimension position feature of the multi-dimensional particle position feature matrix 0,n , where n corresponds to the manufacturing parameter feature dimension, and n can include but is not limited to the type parameters of material selection, the structural parameters of material selection, the filter element manufacturing temperature, folding method, pasting position, pasting pressure; and the assembly pressure between the filter element, base and shell of the oil filter, and the welding temperature. The initialization particle features including the multi-dimensional particle position feature matrix and the initialization speed value of the corresponding dimensional position feature are constructed. The above manufacturing feature parameters of different dimensions construct the position parameters defined by the particle swarm algorithm.

[0031] Furthermore, the present invention also dynamically updates the characteristics of the initialized particles according to the particle swarm algorithm, and the dynamic update method includes multi-dimensional position speed update of the corresponding initialized particles and corresponding dimensional position update, wherein the multi-dimensional position speed update method of the initialized particles is executed using the following formula:

[0032] ,in represents the velocity value v of the particle feature i at the n-th dimension position after the t-th iteration, t+1 represents the t+1-th iteration, w represents the inertia weight of the particle, and k 1,n and k 2,n Respectively represent different learning factors at the n-th dimension position, r 1,n and r 2,n are different random numbers, used for random search of particle update; pb i represents the local optimal solution, and gb represents the global optimal solution.

[0033] The method for updating the corresponding dimensional position of the initialized particle feature according to the particle swarm algorithm includes: ,in represents the characteristic value of the n-th dimension position of particle i in t iterations, and the number of iterations of the particle swarm algorithm is preset to be t s , when the particle satisfies the number of iterations t s Then extract all dimensional position features of the particle i: X = [ , , , .... ], wherein X is the extracted multidimensional feature of the particle, which is used for automatic configuration of different types of manufacturing parameters of the oil filter.

[0034] In order to better illustrate the technical solution of the present invention, the present invention adopts the following method to calculate the fitness function of the particle swarm algorithm and provide constraints: The fitness function of the particle swarm algorithm includes: obtaining the detection characteristic parameter h after each oil filter manufacturing i，m , where the subscripts i and m represent the particles corresponding to the manufacturing parameters of the oil filter, respectively, and m represents the detection feature type corresponding to particle i. The target function F(i, m) of each detection feature type is preset. According to the target function F(i, m) and the detection feature parameter h i，m The mean square error is used as the fitness function to constrain the iteration of the particle i.

[0035] In one of the preferred embodiments of the present invention, the present invention preferably adopts a constraint method of minimizing the mean square error to perform particle iterative calculation. The constraint method of minimizing the mean square error value of the objective function includes: when the corresponding particle i completes the tth iteration, calculating the detection characteristic parameter h of the tth iteration of the particle i i，m , and obtain the target function F(i, m) of the m detection feature types corresponding to particle i, and calculate its mean square error G t = , and obtain the minimum mean square error G obtained by the previous iteration s , if G t <G s , the eigenvalue of the n-dimensional position obtained after the current t-th iteration is taken as the local optimal solution of the oil filter manufacturing parameters.

[0036] The embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the functions defined in the method of the present application are executed. It should be noted that the computer-readable medium described in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of an electrical, magnetic, optical, electromagnetic, infrared segment, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wire segments, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may be of various types, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless segments, wire segments, optical cables, RF, etc., or any suitable combination thereof.

[0037] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0038] Those skilled in the art should understand that the embodiments of the present invention described and shown in the drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be deformed or modified in any way.

Claims

1. A method for manufacturing and detecting an oil filter based on a particle swarm algorithm, characterized in that: The method comprises: Obtaining historical manufacturing characteristic parameters of equipment corresponding to each manufacturing process of the oil filter, and classifying the historical manufacturing characteristic parameters according to their own parameter types to obtain historical manufacturing characteristic parameters of different types of the oil filter; Obtaining corresponding historical detection characteristic parameters according to different types of historical manufacturing characteristic parameters of the oil filter, constructing particle multidimensional position characteristic parameters corresponding to the historical manufacturing characteristic parameters of the oil filter manufacturing process according to the particle swarm algorithm, and configuring an initialization speed value for each multidimensional position characteristic parameter to generate an initialization particle feature corresponding to the complete manufacturing process; Constructing a fitness function of the particle swarm algorithm according to the historical detection characteristic parameters corresponding to the historical manufacturing characteristic parameters, wherein the fitness function of the particle swarm algorithm is calculated by minimizing the mean square error value of the objective function; Dynamically updating the multidimensional position characteristics and corresponding speed characteristics of each particle in the particle swarm algorithm according to the fitness function of the particle swarm algorithm, so as to obtain a local optimal solution or a global optimal solution of the manufacturing parameters corresponding to the manufacturing process of the oil filter; The method for constructing the particle multi-dimensional position characteristic parameters comprises: after each oil filter is manufactured, obtaining the standardized historical manufacturing characteristic parameters of different types of oil filters for each oil filter As each sample element, the combined data of each sample element is taken as a particle, and the corresponding type historical manufacturing feature parameter As the position characteristic parameter of one dimension of the particle, a multi-dimensional particle position characteristic matrix is ​​constructed, and the initialization speed value of the position characteristic of each dimension of the multi-dimensional particle position characteristic matrix is ​​configured to construct an initialization particle feature including the multi-dimensional particle position characteristic matrix and the initialization speed value of the position characteristic of the corresponding dimension; The characteristics of the initialized particles are dynamically updated according to the particle swarm algorithm, and the dynamic update method includes a multi-dimensional position speed update of the corresponding initialized particles and a corresponding dimensional position update, wherein the multi-dimensional position speed update method of the initialized particles is executed using the following formula: ,in represents the velocity value v of the particle feature i at the n-th dimension position after the t-th iteration, t+1 represents the t+1-th iteration, w represents the inertia weight of the particle, k 1,n and k 2,n Respectively represent different learning factors at the n-th dimension position, r 1,n and r 2,n They are different random numbers, used for random search of particle updates; pb i represents the local optimal solution, gb represents the global optimal solution; The method for updating the corresponding dimensional position of the initialized particle feature according to the particle swarm algorithm includes: ,in represents the characteristic value of the n-th dimension position of particle i in t iterations, and the number of iterations of the particle swarm algorithm is preset to be t s , when the particle satisfies the number of iterations t s Then extract all dimensional position features of the particle i: X = [ , , , .... ], wherein X is the extracted multi-dimensional position feature of the particle, which is used for automatic configuration of different types of manufacturing parameters of the oil filter.

2. The oil filter manufacturing and detection method based on particle swarm algorithm according to claim 1, characterized in that: The feature classification method of the historical manufacturing characteristic parameters of the equipment corresponding to each manufacturing process of the oil filter includes: dividing the historical manufacturing characteristic parameters of the oil filter into: physical parameters of the oil filter material selection, processing and molding parameters of the selected materials, filter element structure parameters, filter element adhesion parameters, filter element welding parameters and assembly parameters; performing data preprocessing on the historical manufacturing characteristic parameters of different types of the oil filter to obtain the historical manufacturing characteristic parameters of the oil filter of the corresponding type standardization.

3. The oil filter manufacturing and testing method based on particle swarm algorithm according to claim 2 is characterized in that: The data preprocessing method of the historical manufacturing characteristic parameters of different types of oil filters includes: using a Z-score algorithm to standardize the historical manufacturing characteristic parameters of different types of oil filters, and the specific steps include: calculating the average value μ of each type of historical manufacturing characteristic parameter of the oil filter n , and according to the average value μ n The standard deviation σ of each type of historical manufacturing characteristic parameters of computer oil filters n , the standardized historical manufacturing characteristic parameters of different types of oil filters are calculated according to the following formula: , where the subscript n represents the type identification of the corresponding historical manufacturing characteristic parameter, x represents the corresponding manufacturing parameter value, and the superscript ^ represents the standardized value of the corresponding type of manufacturing parameter, where the average value μ of each type of historical manufacturing characteristic parameter of the oil filter is n , standard deviation σ n Are different.

4. The oil filter manufacturing and testing method based on particle swarm algorithm according to claim 1, characterized in that: The fitness function of the particle swarm algorithm includes: obtaining the detection characteristic parameter h after each oil filter manufacturing i，m , where the subscripts i and m represent the particles corresponding to the manufacturing parameters of the oil filter, respectively, and m represents the detection feature type corresponding to particle i. The target function F(i, m) of each detection feature type is preset. According to the target function F(i, m) and the detection feature parameter h i，m The mean square error is used as the fitness function to constrain the iteration of the particle i.

5. The oil filter manufacturing and testing method based on particle swarm algorithm according to claim 4 is characterized in that: The objective function mean square error value minimization constraint method includes: when the corresponding particle i completes the tth iteration, calculating the detection characteristic parameter h of the particle i at the tth iteration i，m , and obtain the objective function F(i, m) of the m detection feature types corresponding to particle i, and calculate its mean square error G t = , and obtain the minimum mean square error G obtained by the previous iteration s , if G t <G s , the eigenvalue of the n-dimensional position obtained after the current t-th iteration is taken as the local optimal solution of the oil filter manufacturing parameters.

6. An oil filter manufacturing and detection system based on particle swarm algorithm, characterized in that: The system executes the oil filter manufacturing detection method based on particle swarm algorithm as described in any one of claims 1-5.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the oil filter manufacturing and detection method based on a particle swarm algorithm as described in any one of claims 1-5.

Images