41results about How to "Does not increase the amount of calculation" patented technology

The invention provides a power lithium battery thermal runaway fault classification and risk prediction method and system, including: a module-level power battery model fault injection method, a random fault generation and labeling method, and a power lithium-ion battery based on a deep learning method A multi-classification model for faults and a transfer learning method for applying the model to real vehicles. The invention can accurately express the real fault condition of the battery, and migrate to the specific actual vehicle working condition. The trained deep learning algorithm model can be successfully deployed in the real vehicle environment through mathematical processing and code conversion, and can diagnose faults in real time without adding additional calculations to the battery management system, while achieving high estimation accuracy.

The invention provides a water sound frequency hopping communication method for linear modulation signal modulation and demodulation, and relates to a water sound frequency hopping communication. The water sound frequency hopping communication method comprises the following steps: carrying out source encoding on original information so as to obtain compressed digital signals; carrying out channel coding; using data obtained by the channel coding as a linear modulation signal control code; controlling to generate a linear modulation signal according to a frequency hopping sequence as a carrier for modulation, so as to obtain modulation signals; carrying out D / A (Digital / Analogue) conversion and power amplification on the modulation signals; converting the modulated signals into sound waves to spread in an ocean underwater acoustic channel through a transmission energy converter; receiving and converting acoustic signals spreading in the ocean underwater acoustic channel into electric signals through the receiving energy converter; obtaining stimulation signals through front amplification and band-pass filtering; carrying out A / D (Analogue / Digital) conversion on the received stimulation signals; after detecting that the digital signals after the A / D conversion are synchronous, carrying out linear modulation signal demodulation center frequency and demodulation frequency to obtain demodulation data; and carrying out channel decoding on the demodulation data; and carrying out source decoding on the digital signals to obtain information.

The invention proposes a method for compressing and calculating a hologram by using a quantum neural network with optimized initial weight, and belongs to the technical field of compression and transmission of a calculation hologram. On the basis of compressing and transmitting computational holograms in the quantum BP neural network, the method uses the computational hologram training set to pre-train to obtain the optimized initial weight of the quantum BP neural network, and accelerates the convergence process of the pre-trained network by setting the pre-trained parameters to randomly initialize the variance. , and then use the optimized initial weights obtained by pre-training to perform secondary network fine-tuning training for the given holographic compressed data, and at the same time dynamically adjust the network learning rate during the optimization process to accelerate the quantum BP neural network compression transmission process. The present invention can use fewer iterations to complete the training of the compressed transmission network structure without changing the basic structure of the original quantum BP neural network, speed up the compression speed of the quantum BP neural network to calculate the hologram and ensure the reproduction of the hologram image the quality of.

The invention discloses a particle filter tracking method for adaptively adjusting the tracking window size, which mainly solves the problem of real-time adaptive adjustment of the particle filter tracking window. The window adjustment method is: under the particle filter tracking framework, first establish the state transition equation of the moving target, initialize the target state; then use the state transition equation to predict the particle set at the next moment, calculate the particle likelihood function value and update it according to its value The weight of the particle, calculate the average distance d from the particle with a large weight to the center of the particle set; finally let the size of the window change linearly with the value of d, so as to realize the adaptive adjustment of the tracking window. This method realizes the adjustment of the particle filter tracking window with a small amount of calculation. Compared with similar methods, it has the advantages of simple calculation and fast tracking speed.