885 results about "Random noise" patented technology

The invention relates to the technical field of vibration monitoring, in particular to a slurry pump motion monitoring management system based on data analysis, which comprises a multi-source acquisition module, a period judgment module, a trend focusing module and a dynamic management and control module. According to the method, vibration data are collected through a three-axis acceleration sensor, a fundamental frequency amplitude is extracted through FFT, time-frequency characteristics and periodic distribution are fused in combination with an extreme value interval sequence, the data representation dimension is enhanced, the rising slope is processed through moving average, the periodic variation is calculated, random noise is restrained, and trend continuity is enhanced. Monotonicity test is combined with dynamic threshold judgment to improve anomaly recognition sensitivity; a sliding window is used for segmenting multi-cycle data; a sudden change interval is positioned based on a pressure amplification rate second derivative; the limitation of a frequency domain on transient feature recognition is broken through, a pressure amplification rate three-dimensional vector is constructed, cosine similarity is calculated, and a working condition difference degree is quantified to dynamically bind a maintenance instruction; and closed-loop feedback is formed to improve the early warning and decision matching degree.

The invention relates to the technical field of cores, and discloses a method and a system for realizing USB flash disk equipment interaction based on a flash memory encryption technology, which comprises the following steps of: dividing an encryptable data block of a flash memory controller, and determining a dynamic entropy weight of the encryptable data block by utilizing an equipment interaction instruction and a random noise characteristic signal; generating a self-adaptive key generation sequence capable of encrypting data blocks through an address allocation mode and a dynamic entropy weight of a flash memory controller; calculating a side channel leakage risk index of the flash memory controller, and setting a security level label of an encryptable data block in combination with a self-adaptive key generation sequence; the method comprises the following steps: setting a differentiated security protection mechanism of an encipherable data block by constructing an access control matrix of the encipherable data block and an encryption risk area of a flash memory controller; and generating a secure interaction scheme of the USB flash disk equipment based on the self-adaptive key generation sequence in combination with the differential security protection mechanism and the access control matrix. According to the invention, the interaction safety and reliability of the USB flash disk equipment can be improved.

The invention discloses a titanium alloy microscopic structure prediction method and system based on a conditional generative adversarial network and a storage medium, and belongs to the following steps: firstly, constructing a process-structure mapping model, and taking the output of the model as a rule constraint condition; inputting the random noise vector and the rule constraint condition into a conditional generative adversarial network to generate a prediction image; according to the generative adversarial network, thermal dynamic constraints based on physical quantities of microscopic structures are introduced in the training process, so that the interpretability of a prediction result is improved. And carrying out quantitative comparison on the predicted image and the real image, verifying the consistency of the statistical characteristics, and if the verification is passed, outputting a prediction result. According to the method, end-to-end prediction from process parameters to microscopic structure images is realized, the limitation that only symbolization or parameterization prediction can be carried out in a traditional method is broken through, and the intuition, the interpretability and the engineering application value of the method are remarkably enhanced.

The invention provides a zero sample time sequence prediction method and system based on an adversarial neural network, and the method comprises the steps: constructing a time sequence generation module, training the generation module to stable convergence through obtained source domain data, and inputting collected random noise to generate a pseudo target sequence; constructing a time sequence prediction module, taking the pseudo sample sequence as a training set of the prediction module, and inputting the pseudo sample sequence into the prediction module for decomposition prediction; comparing the synthetic sequence with the output of the prediction module to obtain a prediction error, and feeding back the prediction error to the generation module to update generator parameters; through multiple rounds of generation-prediction-feedback closed-loop training, the obtained zero-sample linear architecture prediction model can effectively predict a corresponding future time sequence trend based on a synthetic pseudo sample under the condition that a target domain has no historical data completely. According to the method, data can be generated and self-training can be completed under the condition of no real data input, so that the quality of the generated data and the performance of the prediction model are synchronously improved.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for providing differential privacy. One of the methods includes initializing a budget recycling-differential privacy framework; receiving overall privacy parameters for generating random noise values to provide differential privacy to a generated computation result; determining a portion of the overall privacy parameters to allocate to a differential privacy mechanism; determining a recycling probability to allocate to a recycling mechanism; and generating a noisy result for an input computation result according to the allocated portion of the privacy and the recycling probability.

Techniques for executing privacy-preserving aggregation queries on a database table include receiving a query, obtaining the true output, and generating deterministic pseudorandom noise based on the query and current database state. This noise is added to the true output to create a privacy-protected result. For subsequent queries, this process is repeated, potentially with updated state data, ensuring that privacy protection adapts to changes in the underlying data. The approach maintains consistency for repeated queries on unchanged data while providing fresh noise when data changes. It balances privacy protection with data utility, allowing for various query types while guarding against privacy attacks. The techniques include displaying the noisy output to a user interface. The techniques offer adaptive privacy protection, query flexibility, and efficient resource utilization, making them suitable for dynamic data environments requiring both privacy and analytical capabilities.

The invention discloses a combined heat and power generation system control strategy based on an AME-TD3 algorithm, and belongs to the technical field of combined heat and power generation system optimization control. Comprising the following steps: S1, collecting system parameters and initializing a CHP running state; s2, when a target # imgabs0 # value is calculated, an entropy reward mechanism is introduced; s3, realizing exploration and utilization of an adaptive noise adjustment mechanism and a dynamic balance strategy based on Critic network evaluation; and S4, optimizing the control strategy in real time. Aiming at the problem that an existing TD3 algorithm is insufficient in exploratory performance, an entropy correction item is introduced into calculation of a target # imgabs1 # value, structural correction is conducted on a target value function, strategy updating is more efficient, and the effectiveness of overall strategy optimization is improved; aiming at the problem that random noise in a traditional TD3 algorithm cannot adapt to a complex environment, a dynamic self-adjusting noise generation function is added in a strategy updating process, so that the convergence speed is increased, the stability is enhanced, and the self-adaptive adjustment capability of a system to load fluctuation and environmental condition change is enhanced. The method has good expandability.

The invention relates to the technical field of electrical digital data processing, and discloses a lightweight-based multi-modal data enhancement method, which comprises the following steps: acquiring a multi-modal feature tensor; extracting a vector orthogonal projection scalar and determining the novelty; updating the global covariance matrix when the novelty is greater than a redundancy threshold, and maintaining the global covariance matrix in a register state when the novelty is not greater than the redundancy threshold; extracting a main diagonal variance component to determine a differential modulation coefficient; calculating a second-order moment manifold projection operator according to the global covariance matrix, and calibrating the operator by using a differential modulation coefficient; the calibrated operator is used for carrying out orthogonal projection on random noise to generate a structured disturbance vector, the structured disturbance vector is superposed to a multi-modal feature tensor to output enhanced features, a novelty judgment mechanism is used for restraining statistical deviation caused by steady-state redundant data, computing resource occupation is reduced, and it is ensured that semantic alignment between modals is maintained in enhanced feature distribution.

The invention discloses a video generation method, belongs to the technical field of artificial intelligence, particularly relates to the technical fields of computer vision, deep learning, large models and the like, and can be applied to scenes such as digital humans and the like. The method comprises the following steps: extracting a target audio feature of a target audio and a virtual image feature of a virtual image in a reference image; based on an attention mechanism, processing the target audio feature and the initial video feature to obtain a target video feature, the initial video feature being formed by splicing a virtual image feature and random noise; and decoding the target video feature to obtain a target video, the target video comprising a video frame of the virtual image expressed based on the target audio speech. The invention further provides a video generation device, an intelligent agent, electronic equipment and a storage medium.

The invention belongs to the field of data processing, and provides an equipment comfort measurement fault identification method, system and equipment, and the method comprises the steps: obtaining a plurality of modal sequences which are consistent with a sampling signal segment in length and are aligned in bit sequence through variational modal decomposition; traversing each sampling signal segment according to a bit sequence to form a signal segment extended wave; extracting the peak value of the signal segment extended wave and the characteristic of the bit sequence of the peak value to generate an extended wave ratio sequence; the difference between the wave ratio sequence of each sampling signal segment and the original sequence is used as the wave ratio fall; and screening each sampling signal segment according to the wave ratio fall by using the median of the wave ratio fall of all the sampling signal segments, and identifying a signal comfort abnormal segment. The method is not sensitive to amplitude fluctuation of random noise, but is more sensitive to envelope impact and bit sequence displacement of a specific frequency band, can prompt slight problems such as guide shoe clearance, guide rail joint impact and abnormal transmission of a traction machine in the early stage, and is beneficial to preventive maintenance.

The invention discloses a method and a system for capturing an ultra-wideband navigation signal of a low-orbit satellite, which are used for solving the technical problem that the existing method for capturing the ultra-wideband navigation signal of the low-orbit satellite is easy to cause that the signal cannot be locked, and finally the capturing success rate is low. The method comprises the following steps: acquiring ka-band low-orbit satellite signals and low-orbit satellite pseudo-random noise codes corresponding to a plurality of low-orbit satellite ultra-wideband navigation signals; generating a complex signal and an original intermediate-frequency signal according to a preset sampling rate, preset skipping time and the ka-band low-orbit satellite signal; constructing a pseudo-code spectrum library based on the pseudo-random noise codes of the low-orbit satellites, and outputting the pseudo-code spectrum library; determining a discrete frequency search sequence based on known intermediate frequency parameters of the original intermediate frequency signal, performing matrix construction in combination with the complex signal and the pseudo code spectrum library, and outputting a three-dimensional result matrix; and capturing and judging the ultra-wideband navigation signals of the low-orbit satellites by adopting the three-dimensional result matrix, and determining a plurality of successfully captured ultra-wideband navigation signals of the low-orbit satellites.

The invention discloses an airborne laser radar sounding data processing method and system, and relates to the technical field of marine surveying and mapping and earth observation, and the method comprises the following steps: collecting original full-waveform data of an airborne laser radar sounding system, the original full-waveform data comprising infrared laser channel data and blue-green laser multichannel data; joint denoising processing is carried out on the original full-waveform data to obtain denoised waveform data, and the joint denoising processing comprises background noise modeling and removing based on machine learning and random noise filtering based on frequency domain low-pass filtering; a collaborative joint denoising strategy is formed by fusing background noise modeling based on machine learning and frequency domain low-pass filtering based on signal-to-noise ratio optimization. According to the method, complex background noise can be accurately estimated and removed, random noise can be adaptively filtered out, weak underwater echo signals are reserved to the maximum extent, and the problem of water depth information loss caused by excessive smoothness is effectively avoided.

A method is provided for enhancing feature integration in capsule networks using GAN-augmented latent space. The method comprises training an autoencoder to encode input data into a latent space representation that captures essential features; training a generative adversarial network (GAN) to generate synthetic features, wherein the GAN includes (a) a generator configured to produce synthetic features from random noise, and (b) a discriminator configured to evaluate the quality of the synthetic features by comparing them with real features from the latent space representation; combining the latent space representation with the synthetic features to form an augmented latent space; generating routing coefficients for the capsule network based on the augmented latent space; and applying the routing coefficients to modulate dynamic routing between capsule layers in the capsule network.

The invention discloses an electric power system transient stability evaluation sample enhancement method, system and device based on a timing constraint generative adversarial network and a medium, and belongs to the technical field of electric power system safety analysis, and the method comprises the steps: constructing a sample enhancement model, generating transient time sequence data based on random noise and system feature tags by a generator, the discriminator outputs a sample authenticity score and a time sequence consistency score through a time sequence neural network, the physical constraint module calculates physical constraint loss of the generated data, the model is alternately trained in combination with multi-dimensional loss, the trained generator is utilized to synthesize samples, and qualified samples are screened through physical verification. According to the invention, by introducing the LSTM time sequence constraint, the WGAN-GP stable training mechanism and the multi-dimensional physical consistency constraint, three core problems of poor time sequence coherence, modal collapse and physical law violation in the existing sample enhancement method are cooperatively solved, and high-quality transient scarce samples can be generated.

Examples of the disclosure provide for a scatter network device. In some examples, the scatter network device includes a non-transitory memory, at least one processor, and a key exchange application stored in the non-transitory memory. When executed by the at least one processor, the key exchange application generates a key exchange request encrypted according to a public encryption key of a first network endpoint, wherein the encrypted key exchange request is indistinguishable from uniform random noise, and transmits the key exchange request to the first network endpoint via a first communication band, wherein the scatter network device transmits authenticated messages via a second communication band.

The invention discloses a federated learning model compression method based on data-free knowledge distillation and multi-teacher knowledge distillation, and belongs to the technical field of federated learning. According to the technical scheme, a central server is used for pre-training a model to constrain random noise and labels, a loss function is optimized after the model is input into an image generator, and intermediate features are extracted and stored in a feature pool; and after the client uploads the model, sampling from the feature pool to generate a diversified composite image as training data, and training a local aggregation model by combining a pre-training model and a client integrated model as teachers. The beneficial effects are that the FedPET method provided by the invention combines data-free knowledge distillation and integrated knowledge distillation, and innovatively introduces channel feature exchange and multi-teacher model guidance, so that the model compression efficiency, generation diversity, data privacy protection, communication efficiency and accuracy of federal learning are significantly improved; the method has obvious advantages especially in heterogeneous data distribution and resource limited scenes, and an efficient, safe and accurate solution is provided for practical application of federated learning.

The invention discloses a text-guided image style migration method based on a pre-trained diffusion model. The method comprises the following steps: acquiring a diffusion model, acquiring an input content image, and inputting the input content image into an auto-encoder for encoding to obtain a hidden space representation; performing DDIM inversion to obtain noise representation # imgabs0 # of the hidden space and a content characteristic spectrum corresponding to each step of the DDIM inversion; inputting the input style text into a CLIP text encoder, and obtaining a feature word vector of the input style text in a feature space; the method comprises the following steps: initializing random noise, inputting the random noise into a backbone network, performing DDIM reverse diffusion to obtain a style characteristic spectrum, and recording output of the backbone network in each reverse diffusion process; and inputting the noise representation of the hidden space as initial noise into the backbone network, performing DDIM reverse diffusion to obtain the hidden space representation of the stylized image, and inputting the hidden space representation into a decoder to obtain the stylized image. The method is more flexible in an actual application scene, and the limitation of a traditional method can be effectively solved.

The invention discloses a pipeline leakage monitoring method and system, and belongs to the technical field of pipe network leakage monitoring. Based on leakage and non-leakage signal spectrum comparison, a high-difference frequency band far away from low-frequency noise is extracted as a characteristic frequency band, high-frequency effective characteristics are focused, and low-frequency interference is avoided; savitzky-Golay smooth filtering is used to eliminate random noise and maintain spectrum peak shape characteristics at the same time, so that the representativeness of a characteristic curve is improved; amplitude difference caused by environmental factors is eliminated through normalization processing, so that the characteristic curves under different working conditions can be compared; shape and amplitude dual verification is carried out through a Pearson's correlation coefficient PPC and a mean square error RMES, and the misjudgment rate of pipeline leakage is reduced; and through a dynamic threshold setting mechanism, different pipe types and working condition changes are self-adapted, and the problem of sensitivity reduction caused by a fixed threshold is avoided.

The invention provides a distributed coherent communication system synchronization method, and the distributed coherent communication system enables dispersed nodes in a space to cooperate with each other through the construction of a virtual antenna array, so as to form a directional wave beam, thereby achieving the control and enhancement of a signal direction. A distributed Kalman filtering framework is introduced, a frequency and phase joint state space model is constructed, local observation data of nodes and neighbor state information are optimally fused, and dynamic estimation and compensation of frequency offset and phase errors are achieved. An updating strategy is designed in combination with an event triggering mechanism, local Kalman filtering prediction is executed in conventional iteration to suppress random noise and control the communication burden and calculation complexity of a system, meanwhile, the standard deviation of a residual phase error is effectively reduced by one order of magnitude, and the synchronization performance is improved.

The invention relates to the technical field of laser radar wind field inversion, in particular to a coherent Doppler anemometry laser radar-based three-dimensional wind field inversion method, which comprises the following steps of: acquiring original power spectrum data of an anemometry laser radar to be inversed in each direction, and sequentially performing interpolation processing on the original power spectrum data in each direction to obtain an inversion result; obtaining power spectrum data after interpolation in each direction; calculating to obtain a cumulative power spectrum function; and optimizing the obtained vector three-dimensional wind field by using the cumulative power spectrum function so as to calculate the maximum function value of the cumulative power spectrum function, and the three-dimensional wind field corresponding to the maximum function value is the optimal three-dimensional wind field. According to the method, all the power spectrum data after azimuth interpolation are directly processed as a whole, random noise is averaged by using an accumulation process, a real signal is highlighted, and stable and accurate three-dimensional wind field inversion can be realized even when the signal-to-noise ratio is extremely low.

The invention relates to the technical field of bearing monitoring, in particular to a wind generating set bearing monitoring method based on vibration data analysis, and the method comprises the steps: dividing a mixed signal into narrow-band components with independent energy through variational mode decomposition, separating dynamic responses of different frequency bands, weakening the interference effect of random noise, and enhancing the recognizability of a weak characteristic signal; the difference between the inner and outer ring load effects is displayed in a time sequence matrix in an offset trend, quantitative characterization of the energy and offset relation is enhanced, time alignment is carried out on the raceway load and the frequency amplitude by executing dynamic time warping, time sequence offset caused by rotating speed fluctuation is corrected, and the synchronization characteristics of energy and phase in the structure are displayed. Response abnormal characteristics under working condition changes are extracted, and signal de-aliasing, time sequence reconstruction and structure response accurate matching are realized, so that vibration signal identification sensitivity is improved, energy and phase change correlation reliability is enhanced, and abnormal part identification certainty is improved.

The invention discloses a time-space consistency-based video super-resolution method and device for a complex operation scene, and a medium, belongs to the field of image and video processing, and aims at solving the problem that a stable, clear and continuous-structure video sequence is difficult to generate in an existing method, and the time-space consistency-based video super-resolution method for the complex operation scene based on video prior is provided. Comprising the following steps: utilizing submerged space modeling, mapping an input low-resolution video to a submerged space, and obtaining a corresponding submerged variable representation; initializing a random noise tensor with the same size as the latent variable expression as an initial noise state; in each step of sampling, dividing a noise state and latent variable representation into a plurality of blocks according to space and time dimensions; denoising is carried out on each tile block; the initial noise is converted into high-quality latent variable representation; and a high-resolution video is reconstructed. According to the method, the power inspection video with high resolution and high consistency can be generated, the generation stability is kept, and the video texture detail expression capability is improved.

The invention relates to the technical field of inspection robots, and particularly discloses a flexible force feedback sensing system for a substation inspection robot, which comprises a flexible sensor array, a signal processing module, a dynamic compensation mechanism module, a contact force prediction module and a transmission control module. According to the scheme, adaptive Kalman filtering is adopted, force signal dynamic characteristics are modeled through a state equation, sliding window overlapping processing is used, updating delay of the characteristics is effectively reduced, and it is ensured that the system can extract reliable contact force characteristics in a complex inspection environment; dynamic compensation is carried out on inertia force and temperature, random noise in signals is effectively removed, an improved Kalman filtering algorithm is adopted to carry out real-time processing on the signals, and the precision and stability of the contact force signals are further improved; the contact force prediction value is predicted based on the convolutional neural network and the long-short-term memory network, and the active prediction capability of the contact force information is effectively improved.

The invention belongs to the technical field of federated learning, and more specifically relates to a non-data-driven quantum federated learning method based on single communication. The method comprises the following steps: a plurality of clients independently train classical models by depending on respective local data, only perform single communication after training is completed, and upload model representation information to a server; after receiving the model representation information uploaded by each client, the server uniformly fuses the information to construct an integrated teacher model; the server synthesizes a pseudo sample from the random noise by using a pseudo sample generator under the guidance of the integrated teacher model; and migrating the knowledge of the integrated teacher model to the quantum student model through soft label distillation by using the generated pseudo sample, and finally obtaining a unified quantum student model at a server side. The technical problems that in existing quantum federation learning, communication overhead is large, privacy protection and efficiency are difficult to consider, and quantum hardware resources are seriously limited are solved.

The invention belongs to the technical field of physical exploration, and particularly discloses a deep geophysical prospecting weak abnormal signal enhancement method and system, and the method comprises the steps: generating a geostructured prior guide field, carrying out the targeted decomposition of an original geophysical prospecting signal, and synchronously estimating an uncertainty region, thereby achieving the real-time enhancement of a weak abnormal signal while maintaining the fidelity of background information; focusing the enhanced resources in the information fuzzy region; the decomposition signals are input into a dynamic learning model, and random noise and structured interference generated by multiplicity are effectively suppressed through antagonistic learning; the enhanced sub-band signals are fused into reconstructed signals with high geological interpretability by using a deep reconstruction network through a self-attention mechanism and compound loss function optimization; a closed-loop feedback mechanism is established, newly disclosed high-confidence anomaly features are fed back and integrated to a prior field, an iteration guide field is formed to drive multi-round iteration, step-by-step mining and locking of weak anomalies are achieved, and finally a high-reliability result is stably converged.

The invention provides a hybrid filtering denoising method and device based on adaptive parameters, and relates to the technical field of three-dimensional point cloud processing. The method comprises the following steps: acquiring three-dimensional point cloud data of a target object; performing voxel segmentation processing on the three-dimensional point cloud data to obtain a plurality of voxels; according to the segmented three-dimensional point cloud data, combining a plurality of voxels by using a density similarity model to obtain a voxel set with different density distributions; based on the merged voxels, a radius filtering parameter and a statistical filtering parameter of each voxel set are adaptively determined, the radius filtering parameter is used for filtering isolated noise in the three-dimensional point cloud data, and the statistical filtering parameter is used for filtering random noise in the three-dimensional point cloud data; performing random noise removal processing on the three-dimensional point cloud data according to the statistical filtering parameters; and performing isolated noise removal processing on the three-dimensional point cloud data after random noise removal according to the radius filtering parameter.

The invention relates to a method for navigating a vehicle (6) by tracking GNSS signals with spoofing detection by means of a GNSS receiver having a plurality of channels, wherein a first GNSS signal is tracked on a first channel and then checked for plausibility on a second channel, comprising the following steps: a) searching for a second GNSS signal which should contain the identical pseudo random noise code as the first GNSS signal, b) checking the plausibility of the first GNSS signal as an authentic GNSS signal if no second GNSS signal has been found, or carrying out the following sub-steps if a second GNSS signal has been found: i) comparing the first and the second GNSS signal with one another, and ii) checking the plausibility of the first or the second GNSS signal as the authentic GNSS signal on the basis of the comparison result.

The invention discloses a design method of a double-layer metasurface wave absorber, the double-layer metasurface wave absorber comprises a pixelated unit located on the upper layer and a regular topological pattern structure located on the lower layer, and the method comprises the following steps: dispersing a resistive film-air structure of the pattern layer of the pixelated unit into a pixelated structure image, and representing the pixelated structure image by using a 0-1 matrix; generating a plurality of groups of 0-1 matrixes, constructing a pixelated unit, and obtaining a reflection coefficient curve; combining the target reflection coefficient curve and multiple groups of random noise into combined vectors, inputting the combined vectors into a generator, generating multiple target pixelated structure images, and obtaining multiple target pixelated units; determining design parameters of a resonance pattern layer, inputting the target reflection coefficient curve into a DNN neural network, outputting target design parameters, and obtaining a target regular topological pattern structure; and combining the target pixelated unit with the target regular topological pattern structure to obtain the target double-layer metasurface wave absorber. According to the method, rapid design of the double-layer metasurface wave absorber can be completed.

The embodiment of the invention provides a network traffic generation method and device, computer equipment and a readable storage medium. The method comprises the following steps: acquiring random noise data, and inputting the random noise data into a generator of a target model to obtain a corresponding target predicted flow image; performing reverse mapping calculation on the target predicted traffic image to obtain corresponding network traffic; according to the target model, a preset model maximizes the discrimination probability of a discriminator for a sample prediction flow image as an optimization target of a generator, maximizes the discrimination probability of the discriminator for a sample real flow image, and minimizes the discrimination probability of the discriminator for the sample prediction flow image as an optimization target of the discriminator. The sample prediction traffic image is obtained by adversarial training of a generator and a discriminator, the sample prediction traffic image is generated by the generator based on sample random noise, and the sample real traffic image is obtained by forward mapping calculation of sample network traffic updated in real time. Therefore, the authenticity of the generated network flow data can be improved.

The invention provides an in-vehicle acoustic enhancement method and device fusing determinacy-randomness hybrid modeling, and the method comprises the steps: collecting a fitted vehicle acceleration sound sample, extracting audio data, carrying out the analysis, constructing a determinacy component synthesis algorithm, and associating with a vehicle working condition; the method comprises the following steps: constructing a multi-physics-field coupled random noise generation module, wherein the multi-physics-field coupled random noise generation module comprises an aerodynamic noise module for simulating air inlet turbulence, a low-frequency pulse module for representing mechanical shock, a detonation module for simulating combustion uncertainty and a nonlinear distortion module for enhancing exhaust roughness and generating high-order harmonics; each random noise generation module is matched with the deterministic component, and mixing of the deterministic component and the random component is realized through weight adjustment; details are enhanced through dynamic compression, and target sound waves are generated; through collaborative optimization of determinacy-randomness components, the naturalness and brand identification degree of synthetic sound waves are improved, the vehicle working condition and driving information can be converted into perceptible sound effect characteristics, and the problem of information perception simplification in the electric vehicle driving process is solved.