9 results about "Nonlinear transfer function" patented technology

The invention discloses a bogie component vibration fatigue life prediction method considering load periodic evolution, and aims to solve the technical problems that an existing model is coupled in function and low in prediction precision, and a prediction result is a single determined value and cannot meet risk assessment requirements. Comprising the following steps: a) acquiring a historical power spectral density sequence; b) inputting the historical power spectral density sequence into a hybrid degradation prediction model, and predicting axle box vibration power spectral density under any running mileage in the future; c) inputting the axle box vibration power spectral density predicted in the step b) into a nonlinear transfer function model based on artificial intelligence, and calculating the stress power spectral density of the key position of the bogie; d) dynamically determining an optimal calculation mileage step length by the decision-making type artificial intelligence model, and then calculating future prediction fatigue damage; and e) calculating generated actual fatigue damage according to historical monitoring data, and outputting probability distribution of the residual fatigue life of the bogie by integrating future predicted fatigue damage.

The invention discloses an off-line estimation method for an automobile active noise reduction nonlinear transfer function based on RNN (Recurrent Neural Network). Specific used models are LSTM (Long Short Term Memory) and GRU (Generalized Range Unit). For a specific vehicle model, offline acquisition and preprocessing of data, model training and deployment of the model to a specific audio DSP are carried out, a traditional vehicle active noise reduction algorithm (LMS, APA, LS and the like) assumes an acoustic path as a linear system (MA / ARMA model) which cannot adapt to the nonlinear characteristics of an actual acoustic path, and two RNN models of LSTM / GRU are adopted to carry out nonlinear transfer function estimation, so that the nonlinear characteristics of the acoustic path cannot be adapted to the nonlinear characteristics of the actual acoustic path. The nonlinear features of the acoustic path can be accurately represented, the in-vehicle noise suppression effect is effectively improved, and the acoustic experience of a driver and passengers is improved.

A noise reduction system for actively compensating background noise in a passenger transport area of a vehicle. The noise reduction system includes a nonlinearity filter unit having a model of a non-linear transfer function of the sound generator, wherein the nonlinearity filter unit is configured to receive the anti-noise signal and to generate a filtered anti-noise signal by applying a non-linear filter function on the anti-noise signal, which is based on the model of the non-linear transfer function in that the non-linear response of the sound generator is at least partially corrected when driven by the filtered anti-noise signal. Wherein the nonlinearity filter unit is further configured to output the filtered anti-noise signal to a sound generator.

A method for predistorting an input signal with a view to compensating for the effect, on a radiofrequency signal generated from the input signal, of a non-linear transfer function of a power amplifier configured to amplify the radiofrequency signal. The method includes: carrying out a Walsh transform of a series of M terms dependent on temporal samples of the input signal delivering sequential components of a corresponding transformed series; calculating a sum of a plurality of operands resulting from the product between, a piece of data dependent on at least one element of a transformed series and a corresponding predistortion coefficient, delivering a corresponding sequential component of a predistorted transformed input signal: and carrying out an inverse Walsh transform of the sequential components of the predistorted transformed input signal, delivering an output signal for the generation of the radiofrequency signal.

The application provides a liquid tank strong dynamic load pressure field reconstruction and global safety evaluation method, comprising the following steps: S100, establishing a three-dimensional coordinate system of the liquid tank, obtaining actual impact point coordinates and field point position coordinates, and calculating the Euclidean distance of wave front propagation and the deflection angle relative to the ballistic axis; S200, constructing a pressure field model containing anisotropic angle modulation terms and distance attenuation terms, and introducing a fluid-solid coupling phase shift parameter in the anisotropic angle modulation terms; S300, determining the optimal eigenvalue of the fluid-solid coupling phase shift parameter by minimizing the prediction error through an optimization algorithm, so as to represent the wave front lag or distortion effect of the shock wave when propagating in the limited liquid medium; S400, generating a normalization factor based on the nonlinear transfer function solved out of the optimal eigenvalue η , performing cleaning of experimental data; or directly calculating the impact pressure estimation value at the weak point based on the perceived impact point and the preset virtual point coordinates to perform structure safety evaluation.

The invention provides a method for designing a neuromorphic computing chip of a mesoscopic olfactory neural network, which can be used for constructing a multi-channel parallel computing and storage and computing integrated neuromorphic computing chip. The technical problems that in existing software simulation, a neural network describing dynamics through a differential equation is poor in expansibility, low in calculation speed, incapable of conducting real-time processing and the like are solved. The method comprises the following steps: step 1, constructing a digital logic calculation model of a K0 model of a Friemann K series set of an olfactory neural network; 2, constructing a nonlinear transfer function of the K0 model; 3, constructing a main state machine and a sub-state machine of the K0 model; step 4, constructing a KI network and a KII network; and step 5, constructing a KIII network.

The application discloses a UAV position prediction method and system based on a credible UKF-BiLSTM, relates to the technical field of UAV position prediction, and the UAV position prediction method provided by the application utilizes BiLSTM to obtain a nonlinear transfer function when performing prediction, can better describe the nonlinear transfer process of UAV position change, combines UKF to track and predict the UAV position, sets a related loss function according to the credibility, makes the optimization direction of the BiLSTM always consistent with the increasing direction of the credibility, and can reflect the matching of the model in a relatively real-time and observable manner. Compared with traditional UAV prediction algorithms, the application has better precision and interpretability.

The application discloses a kind of radio frequency device digital twin modeling methods based on transfer function. Cubic spline interpolation algorithm is used to obtain the characteristic curve of radio frequency device with continuous change of working frequency of radio frequency signal, and AM-AM curve and AM-PM curve with continuous change of input power of radio frequency signal at each discrete frequency point. Linear transfer function and nonlinear transfer function of radio frequency device are constructed according to the above curves. According to the input signal power of radio frequency device, the working area of radio frequency device is judged, and different transfer functions or fixed parameters are called to obtain intermediate signals. Complex noise is generated, and the same processing method as the input signal of radio frequency device is used for complex noise. Finally, the output signal is obtained. The application realizes the coupling correlation of noise figure and gain compression of radio frequency device.

The invention discloses a radio frequency device digital twin modeling method based on a transfer function. A cubic spline interpolation algorithm is adopted to obtain a characteristic curve of a radio frequency device which continuously changes along with the working frequency of the radio frequency signal, and an AM-AM curve and an AM-PM curve which continuously change along with the input power of the radio frequency signal at each discrete frequency point. And constructing a linear transfer function and a nonlinear transfer function of the radio frequency device according to the curves. Judging a working area of the radio frequency device according to the input signal power of the radio frequency device, and calling different transfer functions or fixed parameters to obtain an intermediate signal; generating complex noise, and processing the complex noise in the same processing mode as the input signal of the radio frequency device; and finally obtaining an output signal. According to the invention, coupling correlation of the noise coefficient and gain compression of the radio frequency device is realized.