公开(公告)号：US20220326667A1

公开(公告)日：2022-10-13

申请号：US17625690

申请日：2019-07-19

Applicant: Northeastern University

Inventor： Jinliang DING ,  Changxin LIU ,  Depeng XU ,  Tianyou CHAI

IPC: G05B13/04 ,  C01F7/02

Abstract: Provided is an aluminum oxide production operation optimization system and method based on a cloud-edge collaboration, which relates to the technical field of an aluminum oxide production operation optimization. According to the system and method, firstly the whole-flow data in the aluminum oxide production process is acquired, the data is pre-processed, then the pre-processed data is transmitted to a local collaboration production operation optimization unit, the local collaboration production operation optimization unit firstly judges working conditions for the current aluminum oxide production process, an optimization strategy needing to be operated at present is automatically switched according to the working condition, and the local operation optimization strategy obtains the actual setting value of the aluminum oxide production operation indexes.

公开(公告)号：US20210192272A1

公开(公告)日：2021-06-24

申请号：US16955490

申请日：2019-07-17

Applicant: Northeastern University

Inventor： Changxin LIU ,  Depeng XU ,  Jinliang DING ,  Tianyou CHAI

IPC: G06K9/62 ,  G06K9/66 ,  G06N3/04 ,  G06N3/08 ,  G06Q10/06 ,  G06Q50/04 ,  G06Q10/04 ,  C01F7/02 ,  C22B21/00

Abstract: The invention provides a decision-making method of comprehensive alumina production indexes based on a multi-scale deep convolutional network. The method mainly consists of several sub-models: a multi-scale deep splicing convolutional neural network prediction sub-model reflecting the influence of bottom-layer production process indexes on the comprehensive alumina production indexes, a full connecting neural network prediction sub-model reflecting the influence of upper-layer dispatching indexes on the comprehensive alumina production indexes, a full connecting neural network prediction sub-model reflecting the influence of the comprehensive alumina production indexes at a past time on current comprehensive alumina production indexes, and a multi-scale information neural network integrated model for collaborative optimization of sub-model parameters. According to the method, through an integrated prediction model structure, a memory capacity of a superficial-layer network and a feature extraction capacity of a deep-layer network, a precise decision-making for the comprehensive alumina production indexes is realized.