3results about How to "Improve exploration effect" patented technology

The invention discloses a gearbox fault diagnosis method, system and device and a medium, and the method comprises the steps: firstly obtaining a gearbox vibration signal, and forming a gearbox data set; carrying out denoising processing on a gearbox data set formed by the gearbox vibration signals by adopting a denoising method combining variational mode extraction and a wavelet half-soft-hard threshold value; performing continuous wavelet transform on the denoised gearbox vibration signal to obtain a two-dimensional time-frequency graph as an input sequence of a deep belief network (DBN); performing feature extraction on the input sequence through a DBN, and mining feature information in a two-dimensional time-frequency graph; and inputting the extracted feature information into a Crossform model, carrying out parameter optimization on the Crossform model by adopting an improved jellyfish algorithm, and obtaining a fault diagnosis result of the gearbox through the trained Crossform model. The method is high in diagnosis precision, is high in processing speed, and can effectively carry out the fault diagnosis of the gear box.

The present invention relates to the field of stratum exploration sampling control technology, and specifically to a drilling and sampling integrated device for water conservancy project exploration. The present invention first obtains real-time images and ultrasonic images of the drilled rock during the survey process, and obtains the rock mass smoothness coefficient of each edge line in the real-time image; further divides the real-time image to obtain each layer of rock formation area; further obtains the rock formation fluctuation variation coefficient of the real-time image according to the morphological similarity characteristics and rock mass smoothness coefficient similarity characteristics of all edge lines in each non-innermost rock formation area and the adjacent inner edge lines; further obtains the sampling frequency of the current core drilling according to the grayscale distribution characteristics in the ultrasonic image, the rock formation fluctuation variation coefficient and the preset sampling frequency, and the grayscale similarity characteristics of the ultrasonic images of the current sampling rock formation and the historical adjacent sampling rock formation, effectively improving the accuracy and efficiency of rock formation exploration, optimizing the utilization of sampling resources, and improving the overall effect of water conservancy project exploration.

The application provides a distributed blocking flow shop scheduling optimizer driven by a learning mechanism, and proposes a distributed estimation algorithm applying reverse learning and differential evolution to optimize energy-saving distributed blocking flow shop scheduling. The application fully considers the energy consumption in actual production, and designs an initialization method considering total delay time and total energy consumption; in order to improve the quality of the population, a multi-population collaborative operation guided by reinforcement learning and reverse learning is designed, information interaction is realized through the multi-population collaborative mode, and the search speed is accelerated. Based on the specific characteristics of different populations, adjustable parameter variables meeting the exploration and development capacity are designed. In order to optimize the distributed blocking flow shop scheduling problem with the objective function of reducing total delay time and total energy consumption, acceleration and deceleration operations on different paths are proposed. Through comparison on the 2017 test set and examples composed of different numbers of machines, workpieces and machine arrays, the overall performance of the optimizer is better than that of other optimizers.