CN113691238A

CN113691238A - Filter matching method and system based on genetic algorithm

Info

Publication number: CN113691238A
Application number: CN202111235263.7A
Authority: CN
Inventors: 邵淋锋
Original assignee: Nantong Haimei Electronic Co ltd
Current assignee: Nantong Haimei Electronic Co ltd
Priority date: 2021-10-22
Filing date: 2021-10-22
Publication date: 2021-11-23
Anticipated expiration: 2041-10-22
Also published as: CN113691238B

Abstract

The invention discloses a filter matching method and a filter matching system based on a genetic algorithm, which relate to the technical field of data analysis, wherein M filter coefficients are randomly obtained from a filter parameter value threshold, and the M filter coefficients are calculated according to the genetic algorithm to obtain M prediction curves; obtaining an ideal curve; comparing the M prediction curves with the ideal curve to obtain filtering parameters; judging whether the similarity between the prediction curve corresponding to the filtering parameter and the ideal curve meets the similarity requirement or not; and when the similarity does not meet the requirement, repeatedly and randomly acquiring M filter coefficients from the filter parameter value threshold until the similarity requirement is met. The technical problems that the matching degree of a filter and an application scene is not high, the filtering effect is poor and the matching process is not intelligent in the prior art are solved. The matching process utilizes the characteristic of continuous optimization of the genetic algorithm, and the method has the technical effects of improving the matching efficiency and accuracy and having high intelligent degree.

Description

Filter matching method and system based on genetic algorithm

Technical Field

The invention relates to the technical field of data analysis, in particular to a filter matching method and system based on a genetic algorithm.

Background

The filter is a filter circuit consisting of a capacitor, an inductor and a resistor. The filter can effectively filter the frequency point of the specific frequency in the power line or the frequencies except the frequency point to obtain a power signal of the specific frequency or eliminate the power signal of the specific frequency. The parameter information of the filter required to be selected for different application scenes is different, different parameter information corresponds to different filtering effects, and how to select the filter parameter with high matching degree with the application scenes is a problem in the prior art.

In the process of implementing the technical scheme of the invention in the embodiment of the present application, the inventor of the present application finds that the above-mentioned technology has at least the following technical problems:

the technical problems of low matching degree of a filter and an application scene, poor filtering effect and unintelligent matching process exist in the prior art.

Disclosure of Invention

The invention aims to solve the technical defects, and provides a filter matching method and system based on a genetic algorithm to solve the technical problems of low matching degree of a filter and an application scene, poor filtering effect and unintelligent matching process in the prior art.

To this end, a first object of the present invention is to provide a filter matching method based on genetic algorithm, the method comprising: obtaining a filtering parameter value threshold; randomly obtaining M filter coefficients from the filter parameter value threshold, wherein M is a positive integer; calculating the M filtering coefficients according to a genetic algorithm to obtain M prediction curves, wherein the M prediction curves correspond to the M filtering coefficients one by one; obtaining an ideal curve; comparing the M prediction curves with the ideal curve to obtain a filtering parameter, wherein the filtering parameter is a filtering coefficient with the maximum similarity between the corresponding prediction curve and the ideal curve; judging whether the similarity between the prediction curve corresponding to the filtering parameter and the ideal curve meets the similarity requirement or not; when the similarity does not meet the requirement, repeatedly obtaining M filter coefficients randomly from the filter parameter value threshold until the similarity meets the requirement; and obtaining filter information according to the filtering parameters.

Preferably, the obtaining of the ideal curve includes: obtaining a first connection element; obtaining a first element parameter according to the first connecting element; obtaining a first circuit; obtaining a first parameter connection network according to the first circuit; obtaining a signal input threshold value according to the first parameter connection network and the first element parameter; and obtaining the ideal curve according to the signal input threshold.

Preferably, the method comprises: obtaining a matching parameter set according to the signal input threshold and the filtering parameter value threshold; inputting the matching parameters in the matching parameter set and the first parameter connecting network into a prediction curve model in sequence to obtain a prediction curve set; obtaining a curve deviation value according to the prediction curve set; obtaining a first weight according to the curve deviation value; obtaining a second weight according to the matching parameter set; and obtaining the ideal curve according to the first weight and the second weight.

Preferably, the method is applied to a filter evaluation system, the system comprises a filtering monitoring device, the filtering monitoring device comprises a signal acquisition device, and the method comprises the following steps: acquiring a first signal through the signal acquisition equipment, wherein the first signal is an input end signal; obtaining a first signal separation result according to the first signal; acquiring a second signal through the signal acquisition equipment, wherein the second signal is an output end signal; obtaining a second signal separation result according to the second signal; obtaining first filtering information according to the first signal separation result and the second signal separation result; obtaining first interference according to the first filtering information and the first connecting element; determining the filter information when the first interference satisfies a first predetermined condition.

Preferably, the method comprises: when the first interference does not meet the first predetermined condition, obtaining a connection parameter; judging whether the connection parameters meet a second preset condition or not; and when the connection parameter is not satisfied, obtaining adjustment information, wherein the adjustment information is used for adjusting the connection parameter.

Preferably, after determining whether the connection parameter satisfies a second predetermined condition, the method includes: when the first filtering parameter is satisfied, obtaining a first filtering parameter according to the first filtering information; and obtaining filter adjustment information according to the first filtering parameter, wherein the filter adjustment information is used for adjusting the wave recorder according to the first filtering parameter.

Preferably, the calculating the M filtering coefficients according to a genetic algorithm to obtain M prediction curves includes: respectively obtaining wave frequency feature map sets of each filter coefficient in M filter coefficients, wherein the wave frequency feature map sets are M and are in one-to-one correspondence with the M filter coefficients; respectively carrying out fitness calculation on all the wave frequency characteristic graphs in the M wave frequency characteristic graph sets to obtain a fitness set, wherein the fitness set is sorted from small to large according to the fitness; based on the fitness, selecting M matching feature sets; and performing feature intersection and variation on the M matching feature sets to obtain M prediction curves, wherein the M prediction curves are in one-to-one correspondence with the M filter coefficients.

A second object of the present invention is to provide a filter matching system based on a genetic algorithm, the system comprising:

the first obtaining unit is used for obtaining a filtering parameter value threshold;

a second obtaining unit, configured to randomly obtain M filter coefficients from the filter parameter value threshold, where M is a positive integer;

a third obtaining unit, configured to calculate the M filter coefficients according to a genetic algorithm to obtain M prediction curves, where the M prediction curves are in one-to-one correspondence with the M filter coefficients;

a fourth obtaining unit configured to obtain an ideal curve;

a fifth obtaining unit, configured to compare the M prediction curves with the ideal curve to obtain a filtering parameter, where the filtering parameter is a filtering coefficient with a maximum similarity between a corresponding prediction curve and the ideal curve;

the first judging unit is used for judging whether the similarity between the prediction curve corresponding to the filtering parameter and the ideal curve meets the similarity requirement or not;

a sixth obtaining unit, configured to, when the similarity requirement is not met, repeatedly obtain M filter coefficients randomly from the filter parameter value threshold until the similarity requirement is met;

a seventh obtaining unit, configured to obtain filter information according to the filtering parameter.

A third object of the present invention is to provide a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above method when executing the computer program.

One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

1. according to the filter matching method and system based on the genetic algorithm, provided by the embodiment of the invention, the value threshold of the filtering parameter is obtained; randomly obtaining M filter coefficients from the filter parameter value threshold, wherein M is a positive integer; calculating the M filtering coefficients according to a genetic algorithm to obtain M prediction curves, wherein the M prediction curves correspond to the M filtering coefficients one by one; obtaining an ideal curve; comparing the M prediction curves with the ideal curve to obtain a filtering parameter, wherein the filtering parameter is a filtering coefficient with the maximum similarity between the corresponding prediction curve and the ideal curve; judging whether the similarity between the prediction curve corresponding to the filtering parameter and the ideal curve meets the similarity requirement or not; when the similarity does not meet the requirement, repeatedly obtaining M filter coefficients randomly from the filter parameter value threshold until the similarity meets the requirement; and obtaining filter information according to the filtering parameters. The technical problems that the matching degree of a filter and an application scene is not high, the filtering effect is poor and the matching process is not intelligent in the prior art are solved.

2. According to the filter matching method and system based on the genetic algorithm, provided by the embodiment of the invention, a first connecting element is obtained; obtaining a first element parameter according to the first connecting element; obtaining a first circuit; obtaining a first parameter connection network according to the first circuit; obtaining a signal input threshold value according to the first parameter connection network and the first element parameter; and obtaining the ideal curve according to the signal input threshold. The technical effects that the working signals are analyzed in a targeted mode according to the circuit connection characteristics and the parameter requirements of the filtering object, namely the first connecting element, the matching of the filtering processing requirements is carried out according to the working signals, the filtering requirements are better fitted, and the matching performance of the filter is improved are achieved.

3. According to the filter matching method and system based on the genetic algorithm, when the first interference does not meet the first preset condition, connection parameters are obtained; judging whether the connection parameters meet a second preset condition or not; when the matching degree of the filter and the application scene is not high, the filtering effect is poor, and the technical problems that the matching process is not intelligent in the prior art are further solved.

The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.

Drawings

FIG. 1 is a schematic flow chart of a filter matching method based on a genetic algorithm according to an embodiment of the present application;

FIG. 2 is a schematic flow chart of the ideal curve obtained according to the signal input threshold in the filter matching method based on the genetic algorithm according to the embodiment of the present application;

FIG. 3 is a schematic flow chart of obtaining the ideal curve according to weight in a filter matching method based on a genetic algorithm according to an embodiment of the present application;

FIG. 4 is a schematic diagram illustrating a process for determining filter information in a genetic algorithm-based filter matching method according to an embodiment of the present disclosure;

fig. 5 is a schematic flowchart illustrating a process of determining whether the connection parameter satisfies a second predetermined condition in a filter matching method based on a genetic algorithm according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a filter matching system based on a genetic algorithm according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.

Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a fourth obtaining unit 14, a fifth obtaining unit 15, a first judging unit 16, a sixth obtaining unit 17, a seventh obtaining unit 18, an electronic device 300, a memory 301, a processor 302, a communication interface 303, and a bus architecture 304.

Detailed Description

Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention. On the contrary, the embodiments of the invention include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.

In the description of the present invention, it should be noted that any process or method descriptions in flowcharts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and that the scope of the preferred embodiments of the present invention includes additional implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present invention.

A genetic algorithm-based filter matching method according to an embodiment of the present invention is described below with reference to the accompanying drawings.

The technical scheme of the application is as follows: obtaining a filtering parameter value threshold; randomly obtaining M filter coefficients from the filter parameter value threshold, wherein M is a positive integer; calculating the M filtering coefficients according to a genetic algorithm to obtain M prediction curves, wherein the M prediction curves correspond to the M filtering coefficients one by one; obtaining an ideal curve; comparing the M prediction curves with the ideal curve to obtain a filtering parameter, wherein the filtering parameter is a filtering coefficient with the maximum similarity between the corresponding prediction curve and the ideal curve; judging whether the similarity between the prediction curve corresponding to the filtering parameter and the ideal curve meets the similarity requirement or not; when the similarity does not meet the requirement, repeatedly obtaining M filter coefficients randomly from the filter parameter value threshold until the similarity meets the requirement; and obtaining filter information according to the filtering parameters. The technical problems that the matching degree of a filter and an application scene is not high, the filtering effect is poor and the matching process is not intelligent in the prior art are solved.

Example one

As shown in fig. 1, an embodiment of the present application provides a genetic algorithm-based filter matching method, which includes:

step S100, obtaining a filtering parameter value threshold;

specifically, the filtering parameter value threshold is a filtering parameter selectable range of the filtering performance of the filter, in order to adapt to different use environments, use positions and filtering requirements, the filter is divided into various parameters such as industrial use, military use and the like, the performance requirements are different, and meanwhile, for different filtering requirements, the filter is divided into a low-pass filter, a high-pass filter, a band-stop filter, an all-pass filter and the like according to the frequency band of a passing signal. Wherein the low-pass filter: it allows low frequency or direct current components in the signal to pass through, and suppresses high frequency components or interference and noise; a high-pass filter: it allows high frequency components in the signal to pass through, suppressing low frequency or direct current components; band-pass filter: the device allows signals in a certain frequency band to pass through, and inhibits signals, interference and noise below or above the frequency band; band elimination filter: it suppresses signals in a certain frequency band and allows signals outside the frequency band to pass through, also known as notch filters; an all-pass filter: the all-pass filter means that the amplitude of a signal does not change in the full frequency band, that is, the gain of the amplitude is constantly equal to 1 in the full frequency band. Generally, an all-pass filter is used to shift the phase, i.e. to change the phase of the input signal, ideally the phase shift is proportional to the frequency, corresponding to a time delay system. For different filtering frequency band divisions, different parameter ranges and corresponding filtering effects are corresponded, filtering parameters corresponding to all filters or a plurality of given filters on the market at present are comprehensively analyzed, and a range interval which can be selected by the filtering parameters is determined as a filtering parameter value threshold.

Step S200, randomly obtaining M filter coefficients from the filter parameter value threshold, wherein M is a positive integer;

specifically, because various parameter selections exist in the filtering parameter value threshold, namely, the filtering parameters correspond to various filtering coefficients, how to select the filtering coefficient most fit with the filtering use requirement from the filtering coefficients, the embodiment of the application adopts a genetic algorithm, continuously and randomly searches in a solution space based on the genetic algorithm, continuously optimizes and finds the characteristics of a better solution in the searching process, and the characteristics are fit with the filter matching process, and firstly, random M filtering coefficients are randomly extracted from the filtering parameter value threshold to be used as the parameters selected preliminarily to perform the solving process, namely, the process of selecting operation in the genetic algorithm is corresponded.

Step S300, calculating the M filter coefficients according to a genetic algorithm to obtain M prediction curves, wherein the M prediction curves correspond to the M filter coefficients one by one;

further, the step S300 of calculating the M filtering coefficients according to a genetic algorithm to obtain M prediction curves includes:

step S310, respectively obtaining wave frequency feature map sets of each filter coefficient in M filter coefficients, wherein the wave frequency feature map sets are M and are in one-to-one correspondence with the M filter coefficients;

step S320, respectively carrying out fitness calculation on all the wave frequency characteristic diagrams in the M wave frequency characteristic diagram sets to obtain a fitness set, wherein the fitness set is sorted from small to large according to the fitness;

step S330, based on the fitness, selecting M matching feature sets;

step S340 performs feature intersection and variation on the M matching feature sets to obtain M prediction curves, where the M prediction curves are in one-to-one correspondence with the M filter coefficients.

Specifically, a genetic algorithm is used for calculating a filter effect prediction curve for each filter coefficient in the M filter coefficients to obtain a prediction curve corresponding to each filter coefficient, so that the M corresponding prediction curves are obtained, and the prediction curves are wave frequency change curves obtained after filter prediction and filtering processing corresponding to the filter coefficients. Specifically, a wave frequency characteristic diagram set corresponding to each of the M filtering coefficients is calculated and analyzed, the wave frequency characteristic diagram set includes a plurality of filtering wave frequency trend curves, because different use environments can affect the filtering effect, the wave frequency characteristic diagram most conforming to the filtering coefficient is selected from the wave frequency characteristic diagram to realize curve prediction of the filtering coefficient, and the individual fitness of each wave frequency characteristic diagram is calculated, wherein the fitness represents the adaptability of a certain individual to the environment and also represents the ability of the individual to reproduce offspring. The fitness function of the genetic algorithm is also called an evaluation function, is an index for judging the degree of goodness of individuals in a population, and is evaluated according to an objective function of a problem to be solved. Sorting the calculated individual fitness from small to large, selecting a wave frequency characteristic diagram with high fitness for characteristic analysis to obtain characteristic information meeting the requirements of filter coefficients, continuing heredity, then performing cross operation and mutation operation on the characteristics obtained by the part of the wave frequency characteristic diagram, wherein the cross operation is to select one part of characteristics from different wave frequency characteristic diagrams according to the heredity characteristics and select other characteristics from other wave frequency characteristic diagrams for cross heredity, performing cross and mutation optimization on the heredity characteristics meeting the requirements so as to finally determine a filter effect curve which best meets the requirements of the filter coefficients as a prediction curve, and sequentially obtain prediction curves of each filter coefficient, namely M prediction curves which are in one-to-one correspondence with the M filter coefficients, and directly operating a structural object by a genetic algorithm when in use, the method has the advantages that derivation and function continuity limitation do not exist, the method has inherent implicit parallelism and better global optimization capability, a probabilistic optimization method is adopted, the optimized search space can be automatically obtained and guided without determining rules, the search direction is adaptively adjusted, the prediction accuracy and the calculation efficiency are improved through the prediction of a genetic algorithm on the wave frequency change process, new solutions are continuously generated in the calculation process, the algorithm of more optimal solutions is reserved, the realization difficulty is low, and the technical effect of obtaining more satisfactory results in a short time is achieved.

Step S400, obtaining an ideal curve;

further, referring to fig. 2, the step S400 of obtaining the ideal curve includes:

step S410 obtains a first connection element;

step S420, obtaining a first element parameter according to the first connecting element;

step S430 obtains a first circuit;

step S440, obtaining a first parameter connection network according to the first circuit;

step S450, obtaining a signal input threshold value according to the first parameter connection network and the first element parameter;

step S460 obtains the ideal curve according to the signal input threshold.

Specifically, the ideal curve is the wave frequency trend requirement required to be met by the filter using object, namely, which wave frequency curves need to be filtered, so that the waveform reaches the ideal curve can improve the performance and the working efficiency of the element. Since the ideal curve is to satisfy the filtering requirement of the object used by the filter, it is necessary to combine the structural characteristics, the using environment and the parameter requirement of the object used, i.e. the first connecting element, and the first element parameter is a description of the performance of the first connecting element, such as the specification parameter: nominal values, allowed deviation values, precision grade rating values, limit values, etc., quality parameters: the temperature coefficient, the high-frequency characteristic, the reliability and the like, the power size and the like, different element parameters have different requirements on the filtering effect, if the deviation allowance of some elements is small, the requirement on the filtering effect is high, the first circuit is the circuit connection relation related to the first connecting element, and the signal condition and the parameter information of other electronic products related to the first connecting element can be mastered through the first circuit. The parameter relations of all the connecting elements in the first circuit are connected to form a parameter connecting network of an electronic element, namely a first parameter connecting network, the influence degree and relation among the parameters in the circuit are analyzed through the parameter connecting network, different element parameters correspondingly generate different wave frequency interferences in the circuit and influence the use environment of the first connecting element, how to realize the ideal curve of the first connecting element needs to be comprehensively determined by combining the parameters of other elements in the first circuit, the influence of the parameters on the input signal of the first connecting element can be obtained through the first parameter connecting network, the influence relation between the signal influence and the first connecting element can be determined through a circuit connecting mode, for example, the parallel relation, when the connecting distance is 2 m, the influence of a first resistor in the circuit on the signal of the first connecting element is different from the influence of a first resistor in the series relation when the connecting distance is 1 m on the signal of the first connecting element, the method comprises the steps of carrying out image analysis on signal influence of each element through a parameter connection network, obtaining a signal input threshold value of the first connection element by combining parameter requirements of the first connection element, wherein the signal input threshold value is used for reflecting an optimal signal range which is required to be input when the first connection element reaches corresponding parameter requirements in a first circuit, and finally determining an ideal curve for ensuring the working performance of the first connection element based on the signal input threshold value, so that the performance requirements of the first connection element can be still ensured under the condition that influence of other elements is ensured in the whole circuit.

Step S500, comparing the M prediction curves with the ideal curve to obtain a filtering parameter, wherein the filtering parameter is a filtering coefficient with the maximum similarity between the corresponding prediction curve and the ideal curve;

step S600, judging whether the similarity between the prediction curve corresponding to the filtering parameter and the ideal curve meets the similarity requirement or not;

step S700, when the similarity does not meet the requirement, repeating the step of randomly obtaining M filter coefficients from the filter parameter value threshold until the similarity requirement is met;

step S800 obtains filter information according to the filtering parameter.

Specifically, the prediction curves corresponding to M filter coefficients are respectively compared with the ideal curve to obtain a prediction curve with the most fit to the ideal curve, that is, the maximum similarity, and the filter coefficient corresponding to the prediction curve is selected as a filter parameter, since the filter coefficient is the most fit to the rational curve among the M randomly selected filter coefficients, whether the filter coefficient is the best answer or not needs to be judged, the similarity requirement can be set according to the use requirement, the setting value is usually 80-95% or higher depending on the used elements and environment of the filter, if the prediction curve corresponding to the filter parameter meets the similarity requirement of the ideal curve, the filter coefficient is determined as the filter parameter, and if the filter coefficient does not meet the similarity requirement, the M filter coefficients are repeatedly obtained from the value threshold of the filter parameter, the steps S300-S600 are repeatedly executed until the similarity between the prediction curve of the filter coefficient and the ideal curve is found to meet the similarity requirement, the filter coefficient is used as a filter parameter to select the filter, the determined filter information is most suitable for the use requirement, the signal input after the filtering processing can be matched with the signal input requirement of the first connecting element, the corresponding performance of the filter processing is ensured, the working effect is prevented from being influenced by the interference wave frequency, the matching process utilizes the continuous optimization seeking characteristic of the genetic algorithm, the technical effects of improving the matching efficiency and accuracy and having high intelligent degree are achieved, and the technical problems that the matching degree of the filter and the application scene is not high, the filtering effect is poor and the matching process is not intelligent in the prior art are solved.

Further, as shown in fig. 3, the method includes:

step S910, obtaining a matching parameter set according to the signal input threshold and the filtering parameter value threshold;

step S920, inputting the matching parameters in the matching parameter set and the first parameter connecting network into a prediction curve model in sequence to obtain a prediction curve set;

step S930, obtaining a curve deviation value according to the prediction curve set;

step S940, a first weight is obtained according to the curve deviation value;

step S950, obtaining a second weight according to the matching parameter set;

step S960 obtains the ideal curve according to the first weight and the second weight.

Further, the step S920 of sequentially inputting the matching parameters in the matching parameter set and the first parameter connection network into a prediction curve model to obtain a prediction curve set includes:

step S921 sequentially inputs the matching parameters in the matching parameter set and the first parameter connection network into the prediction curve model, where the prediction curve model is obtained by performing training convergence on a plurality of sets of training data, and each set of training data includes the matching parameters, the first parameter connection network, and identification information identifying the prediction curve;

step S922 obtains an output result of the prediction curve model, where the output result includes a prediction curve, and the prediction curve is used to represent prediction curve information corresponding to the input matching parameter and the first parameter connection network, and the prediction curve set is obtained based on all the obtained prediction curves.

Specifically, in order to further optimize an ideal curve, the embodiment of the present application performs filter matching parameter screening through a signal input threshold and a filter parameter value threshold, and may also combine the use environments such as industry, military, and the like in the screening process, so as to effectively narrow the range, and because the signal input threshold has a range interval, how to find an ideal signal input within the range interval, for example, a minimum parameter meeting the threshold may be selected within the range of the signal input threshold, or a larger parameter may be selected, which is better in filtering effect and accuracy for the larger parameter, but the corresponding cost is also high, in order to obtain the most fit ideal curve, the matching parameters in the matching parameter set and the first parameter connection network are used to predict the filtering effect, and the predicted filtering effect and the matching parameters are used to perform effect analysis, if the deviation of the filtering effect is not large, it indicates that large parameters do not have a good filtering effect, and by using the filtering curve, i.e. the first weight, which is the magnitude weight of the deviation value of the filtering effect, and the weight between the matching parameter difference, namely the second weight, is calculated to obtain the most fit ideal curve, namely, the filtering effect meets the requirement of the threshold value of the input signal, and the filtering parameters are not too large to cause resource waste, in order to ensure the accuracy of the prediction curve, the embodiment of the application adds a Neural network model, the prediction curve model is a Neural network model in machine learning, and a Neural Network (NN) is a complex Neural network system formed by widely interconnecting a large number of simple processing units (called neurons), reflects many basic characteristics of human brain functions, and is a highly complex nonlinear dynamical learning system. Neural network models are described based on mathematical models of neurons. Artificial Neural Networks (ANN), is a description of the first-order properties of the human brain system. Briefly, it is a mathematical model. And (3) through training of a large amount of training data, inputting the matching parameters and the first parameter connecting network into a neural network model, and outputting a prediction curve.

Furthermore, the training process is essentially a supervised learning process, each group of supervised data comprises matching parameters, a first parameter connection network and identification information for identifying a prediction curve, the matching parameters and the first parameters are connected and input into a neural network model, the neural network model is continuously self-corrected and adjusted according to the identification information for identifying the prediction curve, and the group of supervised learning is ended and the next group of data supervised learning is carried out until the obtained output result is consistent with the identification information; and when the output information of the neural network model reaches the preset accuracy rate/reaches the convergence state, finishing the supervised learning process. Through the supervised learning of the neural network model, the neural network model can process the input information more accurately, the output prediction curve is more reasonable and accurate, the technical effects of improving the accuracy of the prediction curve and improving the operation efficiency are achieved, and a foundation is laid for the subsequent accurate matching and tamping of filter parameters.

Further, as shown in fig. 4, the method is applied to a filter evaluation system, the system includes a filtering monitoring device, the filtering monitoring device includes a signal acquisition device, and the method includes:

step S1010, obtaining a first signal through the signal acquisition equipment, wherein the first signal is an input end signal;

step S1020 obtains a first signal separation result according to the first signal;

step S1030 of obtaining a second signal through the signal acquisition device, where the second signal is an output end signal;

step S1040 obtains a second signal separation result according to the second signal;

step S1050 obtains first filtering information according to the first signal separation result and the second signal separation result;

step S1060 obtains a first interference according to the first filtering information and the first connection element;

step S1070 determines the filter information when the first interference satisfies a first predetermined condition.

Specifically, a signal acquisition device in the filtering monitoring device is used to acquire information at an input end, i.e. a signal input end of a filter, a first signal is a signal acquired at the input end, wherein the first signal is an original signal which is not subjected to filtering processing, so that an interference signal and a transmission signal exist, all signal wave frequencies existing in the first signal are obtained by performing wave frequency separation on the first signal, for example, signals with different wave frequencies in the first signal are separated by methods such as EMD and wavelet decomposition, the first signal separation result is a separated signal set, meanwhile, signal acquisition is performed at an output end of the filter to obtain a second signal, and the second signal is separated to obtain a second signal separation result, the second signal separation result is used for reflecting wave frequency information left after filtering, and the first signal separation result is compared with the second signal separation result, the filtered wave frequency information is obtained as first filtering information, different interference wave frequencies exist for different electronic elements, if some elements have large interference to high frequencies, some elements have large interference to low frequencies, if the filtered first filtering information has interference to the first connecting element, the filter effect of the filter is achieved, and if the first filtering information does not filter the wave frequency which has interference to the first connecting element, the selected filter does not meet the use requirement of the first connecting element and needs to be adjusted. The technical effects of further ensuring the matching performance of the filter by utilizing the separation and analysis of the filtering signals are achieved. Meanwhile, the interference performance analysis can be carried out by utilizing the second signal separation result and the first connecting element to obtain whether the wave frequency causing interference to the first connecting element still exists or not, if the wave frequency still exists, the filter is also indicated to be not in line with the filtering requirement of the first connecting element, the interference signal of the first filtering information and the interference signal of the second signal separation result are utilized to carry out calculation to obtain the filtering efficiency of the filter, if the filtering effect reaches the preset filtering effect, the filter is determined to be in line with the requirement, if the filtering effect is low, namely, a larger interference signal still exists after filtering, the filter is not in line with the requirement of the first connecting element, the evaluation of the signal filtering effect in multiple directions and multiple angles is realized, and the technical effect of further analyzing the matching performance of the filter is further realized.

Further, as shown in fig. 5, the method includes:

step S1110, when the first interference does not satisfy the first predetermined condition, obtaining a connection parameter;

step S1120 determines whether the connection parameter satisfies a second predetermined condition;

and step S1130, when the connection parameter is not satisfied, obtaining adjustment information, wherein the adjustment information is used for adjusting the connection parameter.

Further, after determining whether the connection parameter satisfies a second predetermined condition, the method includes:

step S1140, when the first filtering parameter is satisfied, obtaining a first filtering parameter according to the first filtering information;

step S1150 obtains filter adjustment information according to the first filtering parameter, where the filter adjustment information is used to adjust the wave recorder according to the first filtering parameter.

Specifically, the connection parameter is information such as parameter information of an element connected to the filter, a length of an input line, and a connection method, and when the first interference does not satisfy the first predetermined condition, the cause of the first interference not satisfying the first predetermined condition is further analyzed. For example, the installation position of the filter is far away from the inlet of the power line, so that the lead is too long, the electromagnetic disturbance generated by the equipment is coupled to the power line again through capacitive or inductive coupling, and the higher the frequency of the disturbance signal is, the stronger the coupling is, so that the experiment is failed; cables in the chassis are bound together, but distributed capacitance exists between transmission lines, which results in great degradation of the performance of the filter. The second predetermined condition means that the connection parameters do not interfere with the filter and do not affect the performance of the filter. And judging the connection parameters and a second preset condition, if the connection parameters do not meet the second preset condition, indicating that factors influencing the filtering effect exist in the connection parameters, adjusting the connection parameters, and obtaining corresponding adjusting information through specific unsatisfied reasons to adjust the connection parameters, so that the interference caused by the installation mode is reduced, and the filtering effect is exerted to a greater extent. If the second predetermined condition is met, it is indicated that the connection parameters all meet the requirements, and there is no poor filtering effect caused by the influence of the connection parameters, and at this time, the filtering effect needs to be changed by adjusting the filter. The method and the device have the advantages that the connection parameters are utilized to analyze the matching performance of the filter, the technical effects that the filter effect is influenced by factors outside the filter, the filter is changed blindly, so that resource waste is caused, or the filtering effect cannot be realized are avoided, and the technical problems that the matching degree of the filter and an application scene is not high, the filtering effect is poor, and the matching process is not intelligent in the prior art are further solved.

Example two

Based on the same inventive concept as the genetic algorithm-based filter matching method in the foregoing embodiment, the present invention further provides a genetic algorithm-based filter matching system, as shown in fig. 6, the system comprising:

a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain a filtering parameter value threshold;

a second obtaining unit 12, where the second obtaining unit 12 is configured to randomly obtain M filter coefficients from the filter parameter value threshold, where M is a positive integer;

a third obtaining unit 13, where the third obtaining unit 13 is configured to calculate the M filter coefficients according to a genetic algorithm to obtain M prediction curves, where the M prediction curves are in one-to-one correspondence with the M filter coefficients;

a fourth obtaining unit 14, wherein the fourth obtaining unit 14 is used for obtaining an ideal curve;

a fifth obtaining unit 15, where the fifth obtaining unit 15 is configured to compare the M prediction curves with the ideal curve to obtain a filtering parameter, where the filtering parameter is a filtering coefficient with the largest similarity between the corresponding prediction curve and the ideal curve;

a first judging unit 16, where the first judging unit 16 is configured to judge whether a similarity between a prediction curve corresponding to the filtering parameter and the ideal curve meets a similarity requirement;

a sixth obtaining unit 17, where the sixth obtaining unit 17 is configured to, when the similarity is not satisfied, repeatedly obtain M filter coefficients from the filter parameter value threshold at random until the similarity requirement is satisfied;

a seventh obtaining unit 18, where the seventh obtaining unit 18 is configured to obtain filter information according to the filtering parameter.

Further, the system further comprises:

an eighth obtaining unit for obtaining a first connection element;

a ninth obtaining unit configured to obtain a first element parameter from the first connection element;

a tenth obtaining unit for obtaining the first circuit;

an eleventh obtaining unit, configured to obtain a first parameter connection net according to the first circuit;

a twelfth obtaining unit, configured to obtain a signal input threshold according to the first parameter connection network and the first element parameter;

a thirteenth obtaining unit configured to obtain the ideal curve according to the signal input threshold.

Further, the system further comprises:

a fourteenth obtaining unit, configured to obtain a matching parameter set according to the signal input threshold and the filtering parameter value threshold;

a fifteenth obtaining unit, configured to sequentially input the matching parameters in the matching parameter set and the first parameter connection network into a prediction curve model, so as to obtain a prediction curve set;

a sixteenth obtaining unit, configured to obtain a curve deviation value according to the prediction curve set;

a seventeenth obtaining unit, configured to obtain a first weight according to the curve deviation value;

an eighteenth obtaining unit, configured to obtain a second weight according to the matching parameter set;

a nineteenth obtaining unit, configured to obtain the ideal curve according to the first weight and the second weight.

Further, the system further comprises:

a twentieth obtaining unit, configured to obtain a first signal by the signal acquisition device, where the first signal is an input end signal;

a twenty-first obtaining unit, configured to obtain a first signal separation result according to the first signal;

a twenty-second obtaining unit, configured to obtain a second signal through the signal acquisition device, where the second signal is an output-end signal;

a twenty-third obtaining unit configured to obtain a second signal separation result from the second signal;

a twenty-fourth obtaining unit, configured to obtain first filtering information according to the first signal separation result and the second signal separation result;

a twenty-fifth obtaining unit, configured to obtain a first interference according to the first filtering information and the first connection element;

a first determination unit to determine the filter information when the first interference satisfies a first predetermined condition.

Further, the system further comprises:

a twenty-sixth obtaining unit, configured to obtain a connection parameter when the first interference does not satisfy the first predetermined condition;

a second judging unit, configured to judge whether the connection parameter satisfies a second predetermined condition;

a twenty-seventh obtaining unit configured to, when not satisfied, obtain adjustment information, the adjustment information being used to adjust the connection parameter.

Further, the system further comprises:

a twenty-eighth obtaining unit, configured to, when satisfied, obtain a first filtering parameter according to the first filtering information;

a twenty-ninth obtaining unit, configured to obtain filter adjustment information according to the first filtering parameter, where the filter adjustment information is used to adjust the filter according to the first filtering parameter.

Further, the system further comprises:

a thirtieth obtaining unit, configured to obtain a wave-frequency feature map set of each filter coefficient in M filter coefficients, where the wave-frequency feature map sets are M and correspond to the M filter coefficients one to one;

a thirty-first obtaining unit, configured to perform fitness calculation on all the wave frequency feature maps in the M wave frequency feature map sets respectively to obtain a fitness set, where the fitness set is sorted from small to large according to the fitness;

the first selection unit is used for selecting M matching feature sets based on the fitness;

a thirty-second obtaining unit, configured to perform feature intersection and variation on the M matching feature sets to obtain M prediction curves, where the M prediction curves are in one-to-one correspondence with the M filter coefficients.

Various variations and specific examples of a genetic algorithm based filter matching method in the first embodiment of fig. 1 are also applicable to a genetic algorithm based filter matching system in this embodiment, and a method for implementing a genetic algorithm based filter matching system in this embodiment is clearly known to those skilled in the art from the foregoing detailed description of a genetic algorithm based filter matching method, so for the brevity of the description, detailed description is omitted here.

The electronic apparatus of the embodiment of the present application is described below with reference to fig. 7.

Fig. 7 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.

Based on the inventive concept of a genetic algorithm based filter matching method as in the previous embodiment, the present invention further provides a computer device having a computer program stored thereon, which when executed by a processor, performs the steps of any one of the methods of the genetic algorithm based filter matching method as described above.

Where in fig. 7 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other systems over a transmission medium.

The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.

according to the filter matching method and system based on the genetic algorithm, provided by the embodiment of the invention, the value threshold of the filtering parameter is obtained; randomly obtaining M filter coefficients from the filter parameter value threshold, wherein M is a positive integer; calculating the M filtering coefficients according to a genetic algorithm to obtain M prediction curves, wherein the M prediction curves correspond to the M filtering coefficients one by one; obtaining an ideal curve; comparing the M prediction curves with the ideal curve to obtain a filtering parameter, wherein the filtering parameter is a filtering coefficient with the maximum similarity between the corresponding prediction curve and the ideal curve; judging whether the similarity between the prediction curve corresponding to the filtering parameter and the ideal curve meets the similarity requirement or not; when the similarity does not meet the requirement, repeatedly obtaining M filter coefficients randomly from the filter parameter value threshold until the similarity meets the requirement; the filter coefficient is used as a filter parameter to select a filter, the determined filter information is most suitable for the use requirement, the signal input after the filtering processing can be matched with the signal input requirement of a filtering use object, namely an ideal curve, the corresponding performance of the filter processing is ensured, the influence of interference wave frequency on the working effect is avoided, the continuous optimization characteristic of a genetic algorithm is utilized in the matching process, the technical effects of improving the matching efficiency and accuracy and being high in intelligent degree are achieved, and the technical problems that the matching degree of the filter and an application scene is not high, the filtering effect is poor and the matching process is not intelligent in the prior art are solved.

Those of ordinary skill in the art will understand that: the various numbers of the first, second, etc. mentioned in this application are only used for the convenience of description and are not used to limit the scope of the embodiments of this application, nor to indicate the order of precedence. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one" means one or more. At least two means two or more. "at least one," "any," or similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one (one ) of a, b, or c, may represent: a, b, c, ab, ac, b c, or a b c, wherein a, b, c may be single or multiple.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer finger

The instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire or wirelessly. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device including one or more available media integrated servers, data centers, and the like. The usable medium may be a magnetic medium, an optical medium, a semiconductor medium, or the like.

The various illustrative logical units and circuits described in this application may be implemented or operated upon by design of a general purpose processor, a digital signal processor, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.

The steps of a method or algorithm described in the embodiments herein may be embodied directly in hardware, in a software element executed by a processor, or in a combination of the two. The software cells may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD ROM, or any other form of storage medium known in the art. For example, a storage medium may be coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC, which may be disposed in a terminal. In the alternative, the processor and the storage medium may reside in different components within the terminal. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

Although the present application has been described in conjunction with specific features and embodiments thereof, it will be evident that various modifications and combinations can be made thereto without departing from the spirit and scope of the application.

Accordingly, the specification and figures are merely exemplary of the present application as defined in the appended claims and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations.

Claims

1. A genetic algorithm based filter matching method, wherein the method comprises:

obtaining a filter coefficient value threshold;

randomly obtaining M filter coefficients from the filter coefficient value threshold, wherein M is a positive integer;

calculating the M filter coefficients according to a genetic algorithm to obtain M prediction curves, wherein the M prediction curves correspond to the M filter coefficients one by one;

obtaining an ideal curve, wherein the ideal curve meets the filtering requirement of a filter using object;

comparing the M prediction curves with the ideal curve to obtain a filtering parameter, wherein the filtering parameter is a filtering coefficient with the maximum similarity between the corresponding prediction curve and the ideal curve;

judging whether the similarity between the prediction curve corresponding to the filtering parameter and the ideal curve meets the similarity requirement or not;

when the similarity does not meet the requirement, repeatedly obtaining M filter coefficients randomly from the filter coefficient value threshold until the similarity meets the requirement;

obtaining filter information according to the filtering parameters;

wherein the obtaining an ideal curve comprises:

obtaining a first connection element;

obtaining a first element parameter according to the first connecting element;

acquiring a first circuit, wherein the first circuit is a circuit connection relation related to a first connecting element, and the signal condition and parameter information of other electronic products related to the first connecting element can be mastered through the first circuit;

obtaining a first parameter connection network according to the first circuit, wherein the first parameter connection network is a parameter connection network of the electronic element formed by connecting parameter relations of all connection elements in the first circuit;

acquiring a signal input threshold according to the first parameter connection network and the first element parameters, specifically, performing image analysis on signal influence of each element through the first parameter connection network, and acquiring the signal input threshold of the first connection element by combining with the parameter requirements of the first connection element;

obtaining the ideal curve according to the signal input threshold;

wherein obtaining the ideal curve according to the signal input threshold comprises:

obtaining a matching parameter set according to the signal input threshold and the filter coefficient value threshold;

inputting matching parameters in the matching parameter set and the first parameter connecting network into a prediction curve model in sequence to obtain a prediction curve set, wherein the prediction curve model is obtained by training a plurality of groups of training data, and each group of training data comprises the matching parameters, the first parameter connecting network and identification information for identifying the prediction curve;

obtaining a curve deviation value according to the prediction curve set;

obtaining a first weight according to the curve deviation value;

obtaining a second weight according to the matching parameter set;

and obtaining the ideal curve according to the first weight and the second weight.

2. The method of claim 1, wherein the method is applied to a filter evaluation system, the system comprising a filter monitoring device comprising a signal acquisition device, the method comprising:

acquiring a first signal through the signal acquisition equipment, wherein the first signal is an input end signal;

obtaining a first signal separation result according to the first signal;

acquiring a second signal through the signal acquisition equipment, wherein the second signal is an output end signal;

obtaining a second signal separation result according to the second signal;

obtaining first filtering information according to the first signal separation result and the second signal separation result;

obtaining first interference according to the first filtering information and the first connecting element;

determining the filter information when the first interference satisfies a first predetermined condition.

3. The method of claim 2, wherein the method comprises:

when the first interference does not meet the first predetermined condition, obtaining a connection parameter;

judging whether the connection parameters meet a second preset condition or not;

and when the connection parameter is not satisfied, obtaining adjustment information, wherein the adjustment information is used for adjusting the connection parameter.

4. The method of claim 3, wherein said determining whether the connection parameter satisfies a second predetermined condition comprises:

when the first filtering parameter is satisfied, obtaining a first filtering parameter according to the first filtering information;

and obtaining filter adjustment information according to the first filtering parameter, wherein the filter adjustment information is used for adjusting the filter according to the first filtering parameter.

5. The method of claim 2, wherein said computing said M filter coefficients according to a genetic algorithm to obtain M prediction curves comprises:

respectively obtaining wave frequency characteristic diagram sets of each filter coefficient in M filter coefficients, wherein the wave frequency characteristic diagram sets are M and correspond to the M filter coefficients one by one;

respectively carrying out fitness calculation on all the wave frequency characteristic graphs in the M wave frequency characteristic graph sets to obtain a fitness set, wherein the fitness set is sorted from small to large according to the fitness;

based on the fitness, selecting M matching feature sets;

and performing feature intersection and variation on the M matching feature sets to obtain M prediction curves, wherein the M prediction curves are in one-to-one correspondence with the M filter coefficients.

6. A genetic algorithm based filter matching system for use in the method of any one of claims 1 to 5, the system comprising:

the first obtaining unit is used for obtaining a filter coefficient value threshold;

a second obtaining unit, configured to randomly obtain M filter coefficients from the filter coefficient value threshold, where M is a positive integer;

a fourth obtaining unit configured to obtain an ideal curve that satisfies a filtering requirement of a filter-using object;

a sixth obtaining unit, configured to, when the similarity requirement is not met, repeatedly obtain M filter coefficients randomly from the filter coefficient value threshold until the similarity requirement is met;

a seventh obtaining unit, configured to obtain filter information according to the filtering parameter;

an eighth obtaining unit for obtaining a first connection element;

a tenth obtaining unit, configured to obtain a first circuit, where the first circuit is a circuit connection relationship related to the first connection element, and the first circuit can grasp signal conditions and parameter information of other electronic products related to the first connection element;

an eleventh obtaining unit, configured to obtain a first parameter connection network according to the first circuit, where the first parameter connection network is a parameter connection network of electronic components formed by connecting parameter relationships of all connection components in the first circuit;

a twelfth obtaining unit, configured to obtain a signal input threshold according to the first parameter connection network and the first element parameter, specifically, perform an image analysis on signal influence of each element through the first parameter connection network, and obtain the signal input threshold of the first connection element by combining with a parameter requirement of the first connection element;

a thirteenth obtaining unit, configured to obtain the ideal curve according to the signal input threshold, including:

a fourteenth obtaining unit, configured to obtain a matching parameter set according to the signal input threshold and the filter coefficient value threshold;

a fifteenth obtaining unit, configured to sequentially input the matching parameters in the matching parameter set and the first parameter connection network into a prediction curve model to obtain a prediction curve set, where the prediction curve model is obtained by training multiple sets of training data, and each set of training data includes the matching parameters, the first parameter connection network, and identification information identifying the prediction curve;

7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of the preceding claims 1-5 when executing the computer program.