5results about How to "Solving Mixing Problems" patented technology

The utility model relates to plant protein technology field especially relates to a kind of concentrated device for extracting composite plant protein, it includes: stirring drum, the inside installation of stirring drum is cleaned ring, multiple cleaning brushes are installed in the circumferential surface of cleaned ring, the circumferential surface of cleaned ring between cleaning brush is equipped with water outlet hole, water outlet hole is connected with the water inlet hole of cleaned ring top by passage, water inlet hole connects the one end of water inlet pipe, the top of cleaned ring is connected with the telescopic end of moving cylinder, the fixed end of moving cylinder is connected with L type support frame horizontal portion, the top of stirring drum is equipped with liquid inlet, the side surface of stirring drum is cleaned by cleaning brush on cleaned ring, and by being provided with water outlet hole, it can be sprayed to outside by water outlet hole in cleaning process, the inner wall of stirring drum in cleaning process can be washed, improve cleaning effect, effectively solve the problem that the tank wall of existing cleaning method is not easy to clean stirring device, influence subsequent plant protein and water mixing.

The present application provides an oxygen system scheduling optimization method based on deep reinforcement learning hybrid action space, comprising the following steps: oxygen system scheduling optimization; drl-based method; results and analysis. The present application is based on deep reinforcement learning, and proposes an HAC algorithm for solving the oxygen system scheduling problem. The proposed algorithm extends the actor network of the AC algorithm, and designs an additional segmented reward function according to the market time-of-use electricity price. The HAC algorithm solves the mixed problem of discrete variables and continuous variables, and realizes energy saving and emission reduction while improving economic benefits. Experimental results show that the HAC algorithm places the scheduling problem in a hybrid action space, avoiding the problem of suboptimal action selection. Compared with the traditional algorithm, the HAC algorithm significantly improves the convergence and accuracy of the algorithm, making the oxygen system have higher oxygen utilization rate and economic benefits.

The present application relates to a kind of material control systems for crystallization kettle, including crystallization kettle, feeding tank and the feeding mechanism being set above crystallization kettle, feeding mechanism includes distribution component a, distribution component b and drive assembly, distribution component a and distribution component b slide in feeding tank, drive assembly drives distribution component a and distribution component b to do reciprocating transverse motion and control the amount of feeding by switching with the connection between feeding pipeline;Cleaning component a and cleaning component b all include water reservoir, distribution component a and distribution component b are cleaned by flushing under the action of water reservoir in its inside;Sliding assembly is arranged between distribution component a and distribution component b, for when distribution component a and distribution component b are not connected with feeding pipeline, material is blocked.The present application overcomes the problem that material can only be quantitatively transported, cannot control the amount of required crystallization, raw material mixing is not uniform and cannot clean the device.