68results about How to "Guaranteed Search Accuracy" patented technology

The embodiment of the invention provides a face search method, device and equipment, and a computer readable storage medium. A mode of directly matching feature information to be searched with featureinformation in a corresponding feature database can be flexibly selected according to the data volume condition of the feature information in a current image feature database to be searched, and / or the feature information to be searched is initially matched with the index corresponding to the feature information in the corresponding feature database, and then the feature information to be searched is finely matched with the feature information corresponding to the index which is successfully matched initially, so that the face search mode is enriched; and meanwhile, as the feature informationto be searched can be initially matched with the feature index with smaller data volume and then finely matched, the number of the feature information needing to be matched one by one can be greatlyreduced, the method can be well suitable for application scenes with large data volume, and the precision of face recognition is ensured.

The invention discloses a ship power grid reconfiguration optimizing method based on a particle swarm algorithm. The ship power grid reconfiguration optimizing method combines the particle swarm algorithm and a small population algorithm. Combinations of all switching-on / off states of circuit breakers between a bus in a ship power grid and each load are used as feasible solutions; each feasible solution is used as a particle, and the set of all the feasible solutions forms a particle swarm; particle swarm algorithm optimization is carried out on the particle swarm; an optimal solution space obtained by carrying out small population algorithm on the particle swarm is used for optimizing; and the ship power grid is reconstructed by using the optimal feasible solution. Compared with the existing methods, the ship power grid reconfiguration optimizing method has the advantages of less occupied machine hours and rapid calculation speed, and the requirement on reconstruction instantaneity of the ship power grid can be met.

The invention discloses a wear prediction method and a state recognition method of a milling cutter. The wear prediction method includes the following steps: firstly, performing wavelet noise reduction processing on the milling vibration data, from three aspects: time domain, frequency domain and time-frequency domain On the one hand, feature extraction is performed on the vibration signal, and after obtaining the initial feature vector set, the correlation coefficient method is used to calculate the correlation between the feature vector and the wear amount, and the optimal feature vector set is obtained by screening; then, the average relative value predicted by the least squares support vector machine is The error is defined as the fitness function of the adaptive step-size cuckoo search algorithm, and the input parameters of the least squares support vector machine are optimized by searching the position of the bird's nest. Finally, the optimal least squares support vector machine is used to predict the amount of wear. The present invention verifies the superiority of the ASCS‑LSSVR algorithm by comparing it with other two hybrid intelligent algorithms.