10 results about "Entropy criterion" patented technology

The invention discloses a sewage treatment plant equipment fault diagnosis method based on multi-scale adaptive feature extraction, and belongs to the technical field of equipment intelligent operation and maintenance. According to the method, after adaptive filtering and quality evaluation are carried out on a vibration signal, an adaptive decomposition strategy fusing VMD and improved EMD is adopted, and a modal number and parameters are optimized according to an information entropy criterion; extracting multi-scale features from three levels of micro-scale (instantaneous characteristics), mesoscale (local statistics) and macro-scale (global energy / entropy), and screening key features through mutual information and a two-layer fusion mechanism; a health index model is constructed, and normal, attention, warning and danger four-level dynamic early warning is achieved; and meanwhile, a self-adaptive fault knowledge base capable of being incrementally updated is established in combination with density clustering and a Markov chain. According to the method, the fault identification accuracy and the system self-adaptive capacity are remarkably improved, and the method is suitable for intelligent diagnosis of sewage treatment key equipment such as a centrifugal pump and a Roots blower.

This invention discloses a fire-fighting pipe fitting leakage risk early warning system based on big data analysis, comprising the following steps: collecting multi-dimensional time-series data such as pressure, flow rate, temperature, and humidity; constructing a data processing and modeling workflow; employing kernel canonical correlation analysis to extract nonlinear correlation features between different monitoring parameters to identify weak correlation changes before leakage; and constructing an anomaly measurement mechanism based on the maximum correlation entropy criterion to quantify the degree of feature shift. By fusing the above correlation features and entropy information, a dynamic risk index is generated and compared with a dynamic threshold to achieve real-time early warning of leakage risk, effectively supporting early fault detection and intelligent assessment of fire-fighting pipe fittings. This invention achieves dynamic perception and intelligent judgment of fire-fighting pipe fitting leakage risk, possessing data-driven early warning capabilities.

The invention relates to a sparse site selection method and device and a storage medium. The method comprises the steps of inputting historical data and a site selection number into a sparse site selection model; the sparse addressing model adopts an error measurement function based on a maximum entropy criterion, a local geometric structure retention item is added, and the sparsity of an addressing matrix and the influence of noise serve as regular items and entropy items corresponding to noise weights; iteratively updating a site selection matrix, a reconstruction matrix and a noise matrix of the sparse site selection model step by step so as to estimate data; and after iteration is carried out until a preset termination condition is met, a final site selection position set, namely a sparse site selection result, is obtained. According to the method, the entropy is used for measuring the similarity between the original data and the estimated data, the noise weight is added into the optimization model for noise indication, the effect of further reducing the noise influence is achieved, and high-precision reconstruction can be achieved through the site selection matrix and the reconstruction matrix in the optimal solution obtained through step-by-step iteration solving of the optimization model.

The invention discloses a robust electromagnetic inverse scattering inversion method based on maximum correlation entropy, and belongs to the technical field of electromagnetic inverse scattering and signal processing. According to the method, a maximum correlation entropy criterion in an information theory is introduced into a contrast source inversion framework, and a novel cost function which is composed of a data fidelity item and a state fidelity item and is based on MCC is constructed; equivalently converting the minimization problem of the non-convex cost function into a series of iterative weighted least square sub-problems by adopting a positive semi-definite optimization technology; in the iteration process, the influence of outliers in the data is dynamically suppressed through a self-adaptive weighting mechanism depending on a previous iteration residual error, and an alternating optimization strategy is adopted to efficiently solve a contrast source and a contrast function. According to the method, the strong outlier in the data can be self-adaptively suppressed, the reconstruction precision and robustness are far better than those of a traditional method in a non-Gaussian noise environment, and meanwhile, the method also shows superior or equivalent performance in a noiseless or Gaussian noise environment, and has extremely high practical value.

The invention belongs to the technical field of communication, and particularly relates to a semantic communication method combining variable length coding and constellation probabilistic shaping, which comprises the following steps of: firstly, constructing a semantic encoder based on a mask auto-encoder framework, and designing a mask rate control function through channel state information and information source characteristics so as to dynamically adjust an information source mask rate; a self-adaptive variable-length coding mechanism is realized; according to the obtained mask rate, sampling a non-masked information source unit by adopting a maximum entropy criterion so as to reserve the information amount of the information source to the maximum extent; the constellation point optimal probability is shaped and approximated to discrete two-dimensional Gaussian distribution, and an end-to-end optimization target is deduced based on variational inference; semantic feature coding distribution is constrained through layer normalization operation to approximate Gaussian prior, so that an objective function is effectively simplified; and finally, designing a quantization modulator of semantic feature-constellation point identical distribution mapping based on finite scalar quantization, and adopting a gradient straight-through estimator to solve the non-differentiable problem of the quantization process, and finally realizing end-to-end joint optimization of the system.

The application provides a time delay-Doppler joint estimation method under polar pulse noise interference. On the basis of the orthogonal matching pursuit algorithm, the maximum correlation entropy criterion and the l1 norm constraint are introduced to enhance the robustness under the pulse noise, and a fast solving algorithm based on a distributed iterative optimization strategy is used to improve the calculation efficiency. Compared with the existing same type estimation method, the method has a wider application range, higher estimation accuracy and stronger robustness.

The invention aims to provide a phase unwrapping method based on extended Kalman filtering. The method comprises the following steps: A, constructing a two-dimensional phase unwrapping program MCC-EKFPU; and B, performing phase unwrapping processing on the interferogram by using a two-dimensional phase unwrapping program MCC-EKFPU to obtain an unwrapped phase of the interferogram. According to the method, the maximum correlation entropy criterion extended Kalman filtering theory is introduced into interferogram wrapping phase unwrapping, and an interferogram phase gradient estimation technology and a robust path tracking strategy are combined, so that the method has higher phase unwrapping precision and better robustness; the method has good application potential in interferogram phase unwrapping application with high accuracy requirements.

The invention provides a UGV anti-interference control method based on disturbance and state collaborative estimation. According to the method, on the basis of establishing a vehicle tracking model containing a lateral error and an orientation error, time-varying disturbance is estimated by using a generalized proportional-integral observer, and a state estimation result based on a maximum correlation entropy criterion is introduced into an updating link of the observer, so that the time-varying disturbance is estimated while the observer keeps the quick response capability to high-order time-varying disturbance. The amplification effect of the high-gain structure on the high-frequency noise of the sensor is effectively reduced; according to the method, disturbance estimation output by the generalized proportional-integral observer serves as prior correction information to be introduced into a state prediction process based on the maximum correlation entropy criterion, prediction error covariance is reduced, unification of disturbance compensation and noise suppression capacity is achieved, and a UGV anti-interference trajectory tracking control law is designed on the basis. A simulation result shows that compared with other methods, the control method has the advantage that the control performance of the lateral deviation and the course error is remarkably improved.

This invention discloses an adaptive MLP pruning method for large-scale vision Transformers, addressing the practical deployment requirements of real-time visual perception, low power consumption, low latency, and high throughput in scenarios such as robots, drones, and mobile terminals. It solves the technical problems of existing large-scale vision Transformers, including redundant parameters, high computational and memory overhead, slow inference speed, and difficulty in edge deployment. The core method first accurately evaluates the importance of hidden neurons in the MLP based on Taylor expansion combined with the information entropy criterion. Then, it adaptively prunes and sorts the neurons according to the redundancy of different MLP modules using a binary search algorithm. Combined with knowledge distillation, it restores the performance of the pruned model, ultimately achieving a reduction of approximately 40% in parameters and computational load, and increasing the inference speed to about 1.5 times the original. This method not only demonstrates near-consistent performance with the original model in multiple benchmark tests such as zero-shot image classification, retrieval, and kNN evaluation, but also slightly surpasses it in some scenarios. Furthermore, it has the advantages of not relying on the original model's loss function and additional modules, and being compatible with word reduction methods. Ultimately, this invention provides a lightweight, high-performance, and easily adaptable practical solution for various application scenarios in the field of computer vision that require efficient model inference, and powerfully promotes the low-cost engineering deployment and commercialization of large-vision Transformer models.

The invention discloses an autonomous underwater vehicle state estimation method based on multiple sensors, and the method comprises the steps: firstly building a target state equation and a multi-sensor measurement model of an AUV, and completing the initialization of model parameters; then linearizing the nonlinear models through an extended Kalman filter, and completing prediction updating of each model; then dynamically determining a mixed coefficient and a measurement covariance matrix, updating the adaptive kernel bandwidth, and designing a Gaussian-Cauchy mixed kernel cost function based on a maximum entropy criterion; and finally, multi-sensor prediction updating results are fused, and an optimal state estimation value is output. According to the method, the underwater non-Gaussian noise interference can be effectively suppressed, the AUV state estimation precision and stability are remarkably improved, reliable technical support is provided for accurate state perception of the underwater autonomous vehicle, and the method can be widely applied to AUV operation scenes such as underwater exploration, resource detection and environment monitoring.