Intelligent filtering method and system based on deep learning

Abstract

The invention discloses an intelligent filtering method and system based on deep learning, and relates to the technical field of data filtering. The technical problem that when an intelligent optimization algorithm is used for filter parameter optimization, optimization performance and calculation efficiency conflict with each other is solved. Obtaining interference control instruction data; extracting individuals passed by each piece of data in the later stage of optimization; after the data are classified, optimizing later-stage individuals corresponding to the same type of data are combined to obtain various types of sub-search spaces; and after the filtering control instruction data is classified, the sub-search spaces are called to carry out filter parameter optimization. The method comprises the following steps of: extracting partial filtering parameters of which the filtering effect of an individual focusing on interference control instruction data is close to the optimal in the later stage of optimization; the individuals in the later stage of optimization are combined to obtain the sub-search spaces independently belonging to various types of data, and when the to-be-filtered control instruction data is processed, only the corresponding sub-search spaces are searched, so that the search range is reduced, and the search performance is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data filtering, and in particular to an intelligent filtering method and system based on deep learning. Background Art

[0002] In the actual operation process, unmanned systems will inevitably be interfered by various internal and external factors such as sensor noise, electromagnetic interference or environmental disturbance, which will affect the transmission and execution of control instructions. In order to ensure that the unmanned system can be accurately controlled as expected, the control instructions need to be filtered to suppress noise and interference, so as to achieve effective extraction of control instruction information.

[0003] In the process of filtering control instructions, it is often necessary to set the parameters in the filtering algorithm. In order to solve the problem of difficulty in adapting due to the traditional artificial preset filter parameters, researchers use intelligent optimization algorithms to adaptively find a set of filter parameters that significantly improve the filtering effect. In the process of intelligent optimization of filter parameters, a search space containing a large number of candidate filter parameters is first defined. Each individual in the search space represents a set of possible filter parameters; then the intelligent optimization algorithm simulates a certain phenomenon in nature (bird foraging or ant foraging) to allow each individual to move in the search space, and updates the individual's position and speed according to the fitness function, and approaches the optimal filter parameters through continuous iteration and update of the position and speed.

[0004] However, when filtering each new control instruction data to be processed, the intelligent optimization algorithm needs to perform extensive parameter searches and multiple rounds of calculations in the entire search space, which will cause computing resource consumption and time delays, prolonging the response time of the unmanned system, and thus affecting its real-time decision-making ability and stability. Summary of the invention

[0005] Based on this, in order to solve the technical problem in the prior art that optimization performance and computational efficiency conflict with each other when using intelligent optimization algorithms to optimize filter parameters, the present invention provides an intelligent filtering method and system based on deep learning.

[0006] The present invention provides an intelligent filtering method based on deep learning, comprising: Adding noise signals of different types and intensities to the collected real control instruction data respectively to obtain a plurality of interference control instruction data; A global search space of filter parameters containing several individuals is constructed, where each individual represents a set of filter parameters, and the optimization goal is to minimize the gap between the denoised interference control command data obtained after the filter filters the interference control command data and the real control command data: ; in, It is interference control instruction data; Interference control command data De-noising interference control instruction data obtained after filtering; is the filter, are the filter parameters; is the global search space; Indicates that in the global search space Find a set of optimal filter parameters in , making the gap between the denoised interference control command data and the real control command data Minimum; By adaptively adjusting the inertia weight used to control the particle search range in the original particle swarm optimization algorithm, the individual fluctuations of the original particle swarm optimization algorithm in the later stage of optimization are reduced, and an improved particle swarm optimization algorithm is obtained. The improved particle swarm optimization algorithm specifically includes: I: Initialize the position and velocity of each individual in the particle swarm optimization algorithm; II: is the fitness function, which calculates the fitness value of each individual; III: For each individual, compare its current fitness value with its best historical position The corresponding fitness values ​​are compared. If the current individual's fitness value is high, the current individual position is updated to the historical best position. ; IV: For each individual, compare its current fitness value with the global best position The corresponding fitness values ​​are compared. If the current fitness value is high, the current individual position is updated to the global best position. ; V: Update the speed and position of each individual: ; ; ; in, and In the t Second and t -1 iteration individual i In the d The speed of the dimension; and In the t Second and t -1 iteration individual i In thed The location of the dimension; and They are the first learning factor and the second learning factor used to adjust the maximum learning step size; and are the first random number and the first random number used to increase the randomness of the search, respectively, and All of them are uniformly distributed in the interval [0,1]; It is in t The individual i In the d The optimal position of the dimension; Is an individual i The global optimal position of It is in t Adjust the inertia weight of the search range at the iteration; is the maximum number of iterations; is the adjustment coefficient; The meaning of the above formula is: inertia weight As the number of iterations t The movement speed of the driving individual also decreases with the number of iterations in the later stage of optimization. t , so as to reduce the individual fluctuations experienced by the original particle swarm optimization algorithm in the later stage of optimization; VI: Determine whether the maximum number of iterations has been reached. If so, stop the iteration, otherwise return to II; Extract the individuals that each interference control instruction data passes through in the later stage of optimization, including: Get the t -1 iteration, t The iteration and t +1 iteration fitness value fittness t-1 , fittness t and fittness t+1 ; Calculate the difference in the rate of change of fitness values ​​between adjacent iterations : ; When the difference in the rate of change of fitness values ​​of adjacent iterations When it is less than the set threshold, t The number of iterations is taken as the starting point of the late optimization stage, and the maximum number of iterations is taken as the end point of the late optimization stage, and the individuals from the starting point of the late optimization stage to the end point of the late optimization stage are obtained; According to the similarity of the interference control instruction data, similar interference control instruction data are clustered into one category through a clustering algorithm, several interference control instruction data are divided into different categories, and the individuals corresponding to the interference control instruction data of the same category that have passed through the later stage of optimization are combined to obtain the sub-search space corresponding to each type of interference control instruction data; The control instruction data to be filtered is obtained, the control instruction data to be filtered is classified according to the similarity between the control instruction data to be filtered and various types of interference control instruction data, the sub-search space corresponding to the interference control instruction data is retrieved, and the filter parameter search is performed in the sub-search space using an optimization algorithm.

[0007] The present invention provides an intelligent filtering system based on deep learning, comprising: The data acquisition module is used to add noise signals of different types and intensities to the collected real control instruction data to obtain a plurality of interference control instruction data; The sub-search space individual acquisition module is used to construct a global search space of filter parameters containing several individuals, wherein each individual represents a set of filter parameters, and takes minimizing the gap between the denoised interference control instruction data obtained after the interference control instruction data is filtered by the filter and the real control instruction data as the optimization goal, and uses the optimization algorithm to search for the best in the global search space, and extracts the individuals that each interference control instruction data passes through in the later stage of the search for the best; A sub-search space construction module is used to classify a number of interference control instruction data into different categories according to the similarity of the interference control instruction data, and to combine the individuals corresponding to the interference control instruction data of the same category that have passed through the optimization later stage to obtain sub-search spaces corresponding to each type of interference control instruction data; The filtering module is used to obtain the control instruction data to be filtered, classify the control instruction data to be filtered according to the similarity between the control instruction data to be filtered and various types of interference control instruction data, call the sub-search space corresponding to the interference control instruction data of this type, and use the optimization algorithm to search the filter parameters in the sub-search space.

[0008] At least one of the above technical solutions adopted by the present invention can achieve the following beneficial effects: In the intelligent filtering method based on deep learning provided by the present invention, by extracting the individuals that the optimization algorithm passes through in the later stage of optimization, the focus is on the partial filtering parameters whose filtering effect on the interference control instruction data is gradually close to the optimal one; the later stage individuals corresponding to similar interference control instruction data are combined to obtain a sub-search space unique to each type of interference control instruction data. When processing the filtered control instruction data, only the corresponding sub-search space is used for search, which reduces the search range and increases the probability of obtaining the optimal filtering parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 A schematic diagram of a flow chart of an intelligent filtering method based on deep learning provided by the present invention; Figure 2 A schematic diagram of a process for constructing a global search space for filter parameters provided by the present invention; Figure 3 A schematic diagram of the process flow of the improved particle swarm optimization algorithm provided by the present invention; Figure 4 A schematic diagram of a computer device for implementing an intelligent filtering method based on deep learning provided by the present invention. DETAILED DESCRIPTION

[0010] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in combination with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0011] Unmanned systems are increasingly used, and their autonomy and intelligence levels are constantly improving. Control instructions in unmanned systems are signals or commands used to guide and adjust the behavior and status of unmanned systems. These instructions are usually issued by remote controllers or ground control stations and transmitted to the flight control system or corresponding actuators of the unmanned system through wireless communication links. However, in the actual operation of unmanned systems, they will inevitably be interfered by various internal and external factors such as sensor noise, electromagnetic interference or environmental disturbances, which will affect the transmission and execution of control instructions. To ensure that unmanned systems can be accurately controlled as expected, it is particularly important to filter the control instructions.

[0012] However, when filtering and optimizing based on the intelligent optimization algorithm, when filtering each new control instruction data to be processed, the intelligent optimization algorithm needs to perform extensive parameter searches and multiple rounds of calculations in the entire search space, which will cause computing resource consumption and time delays, prolonging the response time of the unmanned system, and thus affecting its real-time decision-making ability and stability.

[0013] Based on this, the present invention provides an intelligent filtering method based on deep learning. The method obtains the optimal filtering parameter range corresponding to each interference control instruction by extracting the individuals (filtering parameters) passed by the interference control instruction in the later stage of optimization, and combines the individuals passed by similar interference control instructions in the later stage of optimization to obtain a sub-search space of similar interference control instructions. The subspace contains fewer individuals than the global search space, and the individuals contained in the subspace are more suitable for this type of interference control instructions. Searching in the search space can not only improve the quality of the optimal solution obtained, but also significantly reduce the search range and reduce the response time.

[0014] Example 1 Figure 1 The process of the intelligent filtering method based on deep learning in this embodiment is shown. Figure 1 The method is described in detail and specifically comprises the following steps: S1: adding noise signals of different types and intensities to a plurality of collected real control instruction data respectively to obtain a plurality of interference control instruction data.

[0015] S101: Collecting real control instruction data.

[0016] The control command data in the unmanned system usually refers to the control information transmitted from the control end (such as remote control, automatic driving algorithm, ground control station, etc.) to the drone, unmanned vehicle or other unmanned equipment. These control command data may include control commands, status data, sensor input, etc. The control end generates control instructions and encapsulates the control instructions into data packets, and transmits the data packets to the receiving module of the corresponding unmanned equipment through wireless communications such as Wi-Fi, 4G / 5G or LoRa. After the corresponding unmanned equipment receives the data packet, it verifies the data packet. If the data packet verification passes, the drone will parse the control command and perform corresponding actions, such as adjusting the flight altitude or heading. Each data packet contains a timestamp Time, a source address Source, a destination address Desitination, a protocol Protovol, a length Length, and a data packet information Info. Table 1 shows the data packet content corresponding to a set of control instructions for adjusting the flight altitude and heading of the drone sent from the ground control end to the drone. It should be understood that the information in Table 1 is only an example, and the collected relevant data is not limited to Table 1.

[0017] Table 1 Data packet contents corresponding to the control instructions for adjusting the flight altitude and heading of the drone

[0018] S102: Add noise to the real control instruction data to obtain interference control instruction data.

[0019] Add noise to the real control command data in the data transmission process of the unmanned system to simulate the interference of the communication channel. First, select different types and different intensities of noise types, including but not limited to: Gaussian noise, salt and pepper noise, Poisson noise and impulse noise; then add the noise to the real control command collected. Take adding Gaussian noise to as an example: after extracting the data packet list data, set different means and variances of Gaussian noise to simulate noise of different intensities. Based on the set mean and variance of Gaussian noise, use normal distribution to generate Gaussian noise with the same length as the data packet list, add the generated noise to the original control command data, and obtain the interference control command data.

[0020] In step S1, noises of different types and intensities are added to real control instruction data to simulate various real noises, thereby obtaining a plurality of interference control instruction data.

[0021] S2: Construct a global search space for filter parameters containing several individuals, where each individual represents a set of filter parameters. The optimization goal is to minimize the gap between the denoised interference control command data obtained after the interference control command data is filtered by the filter and the real control command data. Use the optimization algorithm to search in the global search space and extract the individuals that each interference control command data passes through in the later stage of optimization.

[0022] Traditional filtering methods often rely on manually preset parameter settings to achieve effective signal filtering. However, this method of relying on manual settings is time-consuming and laborious, and it is difficult to ensure that the parameters are adaptively adjusted to adapt to new situations when the signal characteristics change. In order to solve this problem, researchers began to explore the use of intelligent optimization algorithms such as particle swarm optimization to automatically search and determine filter parameters. As an optimization method based on swarm intelligence, the optimization algorithm converts the search process of filter parameters into an iterative search process in the solution space by simulating a certain phenomenon or process in nature. Each individual in the search space represents a set of possible filter parameters. They move in the solution space according to their position and speed, and update their position and speed according to the fitness function. In the filter parameter optimization problem, researchers first define a search space containing a large number of alternative parameters. Then, an intelligent optimization algorithm is used to conduct a comprehensive search in this space to find the parameter combination that makes the filtering effect optimal. This process is automatic and does not require human intervention, so it can greatly improve the adaptive ability of the filtering method. Through continuous iteration and updating, the intelligent optimization algorithm can gradually approach the optimal solution, thereby obtaining a set of parameters that significantly improve the filtering effect.

[0023] S201: Construct a global search space for filter parameters containing several individuals.

[0024] In the field of signal processing, filters can filter and process signals according to specific frequency characteristics or statistical characteristics. Different filters have their own unique preset parameters, which determine the performance and effect of the filter. The preset parameters of the Gaussian filter include the mean μ and variance σ ², the mean determines the center position of the Gaussian function, while the variance determines the width of the Gaussian function, that is, the degree of smoothness. The preset parameters of the Kalman filter include the process noise covariance Q and the observation noise covariance R. The process noise covariance describes the uncertainty in the process of system state change, while the observation noise covariance describes the uncertainty in the observed data. The preset parameters of the frequency domain filter (including low-pass filter, high-pass filter and band-pass filter) include the cutoff frequency fc and the filter order N. The cutoff frequency determines the frequency range allowed or blocked by the filter. The filter order affects the performance of the filter such as the transition bandwidth and stopband attenuation.

[0025] After clarifying the filter and its corresponding preset parameters, define the value range of each preset parameter. This value range needs to ensure that it can cover most practical application scenarios and filtering requirements. Combining these value ranges defines the search space of the entire parameter of the corresponding filter. Taking the low-pass filter as an example, the process of constructing the global search space of the filter parameters is as follows: Figure 2 As shown, including: S2011: Determine preset parameters of the filter. The preset parameters of the low-pass filter include cutoff frequency fc, filter order N, passband ripple Ripple and stopband attenuation Attenuation.

[0026] S2012: Determine the value range of each preset parameter, set the cutoff frequency fc between 1kHz and 10kHz, the filter order N between 1 and 25, the passband ripple between 0.1dB and 4dB, and the stopband attenuation between 10dB and 100dB.

[0027] S2031: discretize the value range by uniform discretization or logarithmic discretization method. Take uniform discretization as an example: discretize the value range of cutoff frequency fc with a step size of 100 Hz, discretize the value range of filter order N with a step size of 1, discretize the value range of passband ripple Ripple with a step size of 0.1 dB, and discretize the value range of stopband attenuation Attenuation with a step size of 2 dB.

[0028] S2014: Combine the discretized preset parameter values ​​to obtain the global search space. This operation can be implemented through Python's "itertools.product" function. The size of the global search spaceN It is the product of the number of discretization points of all preset parameter value ranges: N=m 1 × ... × m i × ... × m n ; in, n is the number of preset parameters in the filter, m i Indicates that the i-th preset parameter has m i A value.

[0029] S202: Taking minimizing the gap between the denoised interference control instruction data obtained after filtering the interference control instruction data with the filter and the real control instruction data as the optimization goal, an optimization algorithm is used to search for the best in the global search space.

[0030] In order to find the optimal filter configuration in the global search space, the particle swarm optimization algorithm is used to adjust the filter parameters so that the gap between the denoised interference control command data processed by the filter and the real interference-free control command data is minimized, thereby achieving the best filtering effect. The optimization goal constructed is: ; in, It is interference control instruction data; Interference control command data De-noising interference control instruction data obtained after filtering; is the filter, are the filter parameters; is the global search space; Indicates that in the global search space Find a set of optimal filter parameters in , making the gap between the denoised interference control command data and the real control command data Minimum.

[0031] Then, the improved particle swarm optimization algorithm is used to search the global The improved particle swarm optimization algorithm adaptively adjusts the inertia weight used to control the particle search range in the original particle swarm optimization algorithm to reduce the individual fluctuations experienced by the original particle swarm optimization algorithm in the later stage of optimization. The process of the improved particle swarm optimization algorithm is as follows Figure 3 As shown, the specific steps include: I: Initialize the position and velocity of each individual in the particle swarm optimization algorithm.

[0032] II: is the fitness function, and the fitness value of each individual is calculated.

[0033] III: For each individual, compare its current fitness value with its best historical position The corresponding fitness values ​​are compared. If the current individual's fitness value is high, the current individual position is updated to the historical best position. .

[0034] IV: For each individual, compare its current fitness value with the global best position The corresponding fitness values ​​are compared. If the current fitness value is high, the current individual position is updated to the global best position. .

[0035] V: Update the speed and position of each individual: ; ; ; in, and In the t Second and t -1 iteration individual i In the d The speed of the dimension; and In the t Second and t -1 iteration individual i In the d The location of the dimension; and They are the first learning factor and the second learning factor used to adjust the maximum learning step size; and are the first random number and the first random number used to increase the randomness of the search, respectively, and All of them are uniformly distributed in the interval [0,1]; It is in t The individual i In the d The optimal position of the dimension; Is an individual i The global optimal position of It is in t Adjust the inertia weight of the search range at the iteration; is the maximum number of iterations; is the adjustment coefficient; the meaning of the above formula is: inertia weight As the number of iterationst The movement speed of the driving individual also decreases with the number of iterations in the later stage of optimization. t increases with the increase of , so as to reduce the individual fluctuations that the original particle swarm optimization algorithm goes through in the later stage of optimization.

[0036] VI: Determine whether the maximum number of iterations has been reached. If so, stop the iteration; otherwise, return to II.

[0037] S203: extracting the individuals that each interference control instruction data passes through in the later stage of optimization.

[0038] Get the t -1 iteration, t The iteration and t +1 iteration fitness value fittness t-1 , fittness t and fittness t+1 ; Calculate the difference in the rate of change of fitness values ​​between adjacent iterations : .

[0039] When the difference in the rate of change of fitness values ​​of adjacent iterations When it is less than the set threshold, that is, the individual changes of adjacent iterations are relatively stable, so that the corresponding fitness value fluctuation frequency changes are based on the first t The number of iterations is taken as the starting point of the late optimization stage, and the maximum number of iterations is taken as the end point of the late optimization stage. The individual from the starting point of the late optimization stage to the end point of the late optimization stage is obtained, that is, the first t All individual positions at the iteration t+ All individual positions at iteration 1, ..., T The positions of all individuals at iteration .

[0040] Step S2 constructs a global search space for filter parameters, which covers multiple filter parameter combinations with a larger range of values. In order to find the optimal filter parameters in this wide search space, an improved particle swarm algorithm is used for optimization. As the optimization proceeds, the algorithm can gradually focus on a small number of parameter combinations in the later stage of optimization, and these combinations gradually approach the optimal solution in terms of the filtering effect of interference control instruction data. Specifically, the fitness value of the filter parameters tends to the optimal solution, while the corresponding parameter combination range is significantly reduced, which indicates that the convergence of the search process is getting stronger and stronger, and the optimization process gradually focuses on the optimal solution space area.

[0041] S3: Divide a number of interference control instruction data into different categories according to the similarity of the interference control instruction data, combine the individuals corresponding to the same category of interference control instruction data that have passed through in the later stage of optimization, and obtain sub-search spaces corresponding to each category of interference control instruction data.

[0042] S301: Classify a plurality of interference control instruction data into different categories.

[0043] Similar interference control instruction data are automatically grouped into categories through DBSCAN (Density-Based Spatial Clustering of Applications with Noise). DBSCAN can classify similar interference control instruction data into one category without the need for labels, and the differences between interference control instruction data of different categories are as large as possible. The interference control instruction data input into the DBSCAN algorithm is the feature vector obtained after feature extraction by the variational autoencoder (VAE). The variational autoencoder model includes an encoder and a decoder. The encoder maps the input control instruction data to a probability distribution in a latent space, and the decoder maps the samples in the latent space back to the original data space, that is, reconstructing the input data. The loss function in the variational autoencoder training process usually includes two parts: reconstruction loss and KL divergence. The reconstruction loss measures the difference between the reconstructed data and the original data, and the KL divergence measures the difference between the potential representation and the prior distribution. After the model training is completed, the encoder can be used to map the new control instruction data into the latent space to obtain the corresponding feature vector.

[0044] S302: Combining the individuals corresponding to the same type of interference control instruction data that have passed through in the later stage of optimization.

[0045] Since each interference control instruction data corresponds to a filtering parameter optimization process, that is, each interference control instruction data has a "first filter parameter" obtained in step S203. t All individual positions at the iteration t+ All individual positions at iteration 1, ..., T All individual positions at the iteration"; after classifying the interference control instruction data, the corresponding " t All individual positions at the iteration t+ All individual positions at iteration 1, ..., T All individual positions at the iteration also have category attributes. By combining the individuals passed through the later stage of optimization with the same category attributes, the individuals corresponding to this type of noise can be obtained.

[0046] Step S3, in order to improve the efficiency of interference control instruction data processing, by combining the solution space areas corresponding to the interference control instruction data of specific similar properties, a smaller sub-search space is constructed. Compared with the global search space, the scope of this sub-search space is significantly reduced. And because the sub-search space is composed of multiple solution space areas focused on the optimal solution, the probability of obtaining the optimal filter parameters can be greatly improved. Specifically, by focusing on the area most likely to contain the optimal solution, the search range can be more efficiently narrowed, thereby accelerating the search process and improving the quality of the final solution. Compared with the traditional global search method, the construction of the sub-search space significantly improves the convergence speed and performance of the algorithm by reducing redundant calculations and exploring irrelevant solution areas. In addition, the design of the sub-search space not only takes into account the focus of the optimal solution area, but also combines the similarity characteristics of the interference control instruction data, so that the optimization process can better adapt to different types of data distribution, thereby improving the effect of filter parameter optimization.

[0047] S4: Obtain the control instruction data to be filtered, classify the control instruction data to be filtered according to the similarity between the control instruction data to be filtered and various types of interference control instruction data, retrieve the sub-search space corresponding to the interference control instruction data, and use the optimization algorithm to search the filter parameters in the sub-search space.

[0048] First, the control instruction data to be filtered is preprocessed, and after the data preprocessing is completed, the gap or similarity between the control instruction data to be filtered and various types of interference control instruction data is calculated. The gap can be measured by calculating the Euclidean distance or Manhattan distance between the two sets of data. The similarity can be calculated using the similarity measurement method of cosine similarity or Pearson correlation coefficient. After the gap calculation or similarity calculation, a set of values ​​is obtained, which represent the difference or similarity between the data to be filtered and various types of interference control instruction data. By comparing these results, the control instruction data to be filtered will be classified into the category with the smallest gap calculation result or the largest similarity, that is, the data to be filtered will be assigned to the interference data category closest to it. The sub-search space corresponding to this type of interference control instruction data is retrieved, and the filter parameter search is performed in the sub-search space using an optimization algorithm.

[0049] based on Figure 1The deep learning-based intelligent filtering method shown in the figure extracts the individuals that the optimization algorithm passes through in the later stage of optimization, and focuses on the filtering parameters whose filtering effect on the interference control instruction data is gradually approaching the optimal one; the later stage individuals corresponding to similar interference control instruction data are combined to obtain a sub-search space unique to each type of interference control instruction data. When processing the filtered control instruction data, only the corresponding sub-search space is used for searching, which reduces the search range and increases the probability of obtaining the optimal filtering parameters.

[0050] The above is an intelligent filtering method based on deep learning provided by one or more embodiments of the present invention. Based on the same idea, the present invention also provides a corresponding intelligent filtering system based on deep learning, such as Figure 4 As shown, including: The data acquisition module is used to add noise signals of different types and intensities to the acquired real control instruction data to obtain a plurality of interference control instruction data.

[0051] The sub-search space individual acquisition module is used to construct a global search space for filter parameters containing several individuals, where each individual represents a set of filter parameters. The optimization goal is to minimize the gap between the denoised interference control instruction data obtained after the interference control instruction data is filtered by the filter and the real control instruction data. The optimization algorithm is used to search for the best in the global search space to extract the individuals that each interference control instruction data passes through in the later stage of the optimization.

[0052] The sub-search space construction module is used to classify a number of interference control instruction data into different categories according to the similarity of the interference control instruction data, and to combine the individuals corresponding to the same category of interference control instruction data that have passed through the later stage of optimization to obtain the sub-search space corresponding to each category of interference control instruction data.

[0053] The filtering module is used to obtain the control instruction data to be filtered, classify the control instruction data to be filtered according to the similarity between the control instruction data to be filtered and various types of interference control instruction data, call the sub-search space corresponding to the interference control instruction data of this type, and use the optimization algorithm to search the filter parameters in the sub-search space.

[0054] For the specific definition of the intelligent filtering system based on deep learning, please refer to the definition of the intelligent filtering method based on deep learning above, which will not be repeated here. Each module in the above-mentioned intelligent filtering system based on deep learning can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0055] The present invention also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 Provided is an intelligent filtering method based on deep learning.

[0056] The present invention also provides a computer device structure. At the hardware level, the computer device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, it may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 Provided is an intelligent filtering method based on deep learning.

[0057] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0058] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present invention.

Claims

1. An intelligent filtering method based on deep learning, characterized in that: include: Adding noise signals of different types and intensities to the collected real control instruction data respectively to obtain a plurality of interference control instruction data; A global search space of filter parameters containing several individuals is constructed, wherein each individual represents a set of filter parameters. The optimization goal is to minimize the gap between the denoised interference control instruction data obtained after the interference control instruction data is filtered by the filter and the real control instruction data. An optimization algorithm is used to search for the best in the global search space, and the individuals that each interference control instruction data passes through in the later stage of the search are extracted. According to the similarity of the interference control instruction data, a plurality of interference control instruction data are divided into different categories, and the individuals corresponding to the interference control instruction data of the same category that have passed through in the later stage of optimization are combined to obtain the sub-search space corresponding to each type of interference control instruction data; The control instruction data to be filtered is obtained, the control instruction data to be filtered is classified according to the similarity between the control instruction data to be filtered and various types of interference control instruction data, the sub-search space corresponding to the interference control instruction data is retrieved, and the filter parameter search is performed in the sub-search space using an optimization algorithm.

2. The intelligent filtering method based on deep learning according to claim 1, characterized in that: The optimization goal is to minimize the gap between the denoised interference control instruction data obtained after the interference control instruction data is filtered by the filter and the real control instruction data, and to use the optimization algorithm to search for the best in the global search space, specifically including: Build optimization goals: ； in, It is interference control instruction data; Interference control command data De-noising interference control instruction data obtained after filtering; is the filter, are the filter parameters; is the global search space; Indicates that in the global search space Find a set of optimal filter parameters in , making the gap between the denoised interference control command data and the real control command data Minimum; By adaptively adjusting the inertia weight used to control the particle search range in the original particle swarm optimization algorithm, the individual fluctuations of the original particle swarm optimization algorithm in the later stage of optimization are reduced, and an improved particle swarm optimization algorithm is obtained. Optimization is performed in .

3. The intelligent filtering method based on deep learning as claimed in claim 2, characterized in that: The improved particle swarm optimization algorithm specifically includes: I: Initialize the position and velocity of each individual in the particle swarm optimization algorithm; II: is the fitness function, which calculates the fitness value of each individual; III: For each individual, compare its current fitness value with its best historical position The corresponding fitness values ​​are compared. If the current individual's fitness value is high, the current individual position is updated to the historical best position. ; IV: For each individual, compare its current fitness value with the global best position The corresponding fitness values ​​are compared. If the current fitness value is high, the current individual position is updated to the global best position. ; V: Update the speed and position of each individual: ； ； ； in, and In the t Second and t -1 iteration individual i In the d The speed of the dimension; and In the t Second and t -1 iteration individual i In the d The location of the dimension; and They are the first learning factor and the second learning factor used to adjust the maximum learning step size; and are the first random number and the first random number used to increase the randomness of the search, and All of them are uniformly distributed in the interval [0,1]; It is in t The individual i In the d The optimal position of the dimension; Is an individual i The global optimal position of It is in t Adjust the inertia weight of the search range at the iteration; is the maximum number of iterations; is the adjustment coefficient; The meaning of the above formula is: inertia weight As the number of iterations t The movement speed of the driving individual also decreases with the number of iterations in the later stage of optimization. t , so as to reduce the individual fluctuations experienced by the original particle swarm optimization algorithm in the later stage of optimization; VI: Determine whether the maximum number of iterations has been reached. If so, stop the iteration; otherwise, return to II.

4. The intelligent filtering method based on deep learning as claimed in claim 3, characterized in that: The extracting of the individuals that each interference control instruction data passes through in the later stage of optimization specifically includes: Get the t -1 iteration, t The iteration and t +1 iteration fitness value fittness t-1 , fittness t and fittness t+1 ; Calculate the difference in the rate of change of fitness values ​​between adjacent iterations : ； When the difference in the rate of change of fitness values ​​of adjacent iterations When it is less than the set threshold, t The number of iterations is taken as the starting point of the late optimization stage, and the maximum number of iterations is taken as the end point of the late optimization stage, and the individuals passed from the starting point of the late optimization stage to the end point of the late optimization stage are obtained.

5. The intelligent filtering method based on deep learning according to claim 1, characterized in that: The method of classifying a plurality of interference control instruction data into different categories according to the similarity of the interference control instruction data is to cluster similar interference control instruction data into one category through a clustering algorithm.

6. An intelligent filtering system based on deep learning, characterized in that: include: The data acquisition module is used to add noise signals of different types and intensities to the collected real control instruction data to obtain a plurality of interference control instruction data; The sub-search space individual acquisition module is used to construct a global search space of filter parameters containing several individuals, wherein each individual represents a set of filter parameters, and takes minimizing the gap between the denoised interference control instruction data obtained after the interference control instruction data is filtered by the filter and the real control instruction data as the optimization goal, and uses the optimization algorithm to search for the best in the global search space, and extracts the individuals that each interference control instruction data passes through in the later stage of the search for the best; A sub-search space construction module is used to classify a number of interference control instruction data into different categories according to the similarity of the interference control instruction data, and to combine the individuals corresponding to the interference control instruction data of the same category that have passed through the optimization later stage to obtain sub-search spaces corresponding to each type of interference control instruction data; The filtering module is used to obtain the control instruction data to be filtered, classify the control instruction data to be filtered according to the similarity between the control instruction data to be filtered and various types of interference control instruction data, call the sub-search space corresponding to the interference control instruction data of this type, and use the optimization algorithm to search the filter parameters in the sub-search space.

Images