公开(公告)号：US20230205952A1

公开(公告)日：2023-06-29

申请号：US17769002

申请日：2021-12-03

Applicant: Northeastern University

Inventor： Minghan WU ,  Yingwei ZHANG ,  Lin FENG

IPC: G06F30/27 ,  G06V10/56

CPC classification number: G06F30/27 ,  G06V10/56

Abstract: A modeling method for soft measurement of temperature of a blast furnace tuyere raceway includes: collecting picture data of flame combustion at the blast furnace tuyere raceway, physical variable data reflecting operation states of a blast furnace and combustion temperature data of the blast furnace tuyere raceway; extracting characteristics of the picture data of the flame combustion; constructing a multi-kernel least squares support vector regression model based on Pearson correlation coefficient method and least squares support vector regression algorithm as a soft measurement model; optimizing parameters of the soft measurement model by using sine cosine optimization algorithm; and taking optimal kernel function parameters of the picture data, kernel function parameters of the physical variable data and regularization parameters in the multi-kernel least squares support vector regression model as final parameters of the soft measurement model, and achieving prediction and calculation of the combustion temperature of the blast furnace tuyere raceway.

公开(公告)号：US20230348197A1

公开(公告)日：2023-11-02

申请号：US17640035

申请日：2021-07-21

Applicant: Northeastern University

Inventor： Xin SHA ,  Lin FENG ,  Yingwei ZHANG

IPC: B65G43/00 ,  G06F17/11

CPC classification number: B65G43/00 ,  G06F17/11

Abstract: Provided is a sound-based roller fault detecting method by using double-projection neighborhoods preserving embedding, including: acquiring sound data during operation of a roller, performing a wavelet transform energy feature extraction on normal data in the data to obtain wavelet transform energy feature data, then performing double-projection neighborhoods preserving embedding feature extraction on the wavelet energy feature data to obtain an optimal projection matrix of the feature data, establishing a detection model, constructing T2 statistics of a feature space and a residual space of normal sound data, determining detection control limits according to the T2 statistics by a kernel density estimation method, and further judging whether newly acquired data has faults. According to the present method, main features of the data can be extracted under the conditions of non-dimensional reduction and dimensionnal reduction, and thus the present method can achieve the purpose of increasing fault detection accuracy.

公开(公告)号：US20200084845A1

公开(公告)日：2020-03-12

申请号：US16093849

申请日：2018-05-21

Applicant: Northeastern University

Inventor： Yingwei ZHANG ,  Xiaoguang XUE ,  Yongxu LI

IPC: H05B7/20 ,  G01R27/08 ,  G06F17/13

Abstract: The invention provides a calculation method for operating resistance in a dual-electrode DC electric-smelting furnace for magnesium, including the following steps of: calculating a raw material resistance: simplifying a raw material model as an electrode-centered cylindrical model, determining an electric-field strength of each point in an electric field generated by a raw material layer around an electrode in the cylindrical model, calculating a raw material voltage between two electrodes according to the electric-field strength of each point in the electric field, and further obtaining the raw material resistance between the two electrodes; calculating an electric arc-resistance relation model: determining a relation between an actual electric arc length and a distance from the electrode to a surface of a smelting pool, and calculating a relation between an electric arc voltage and the actual electric arc length, namely the electric arc-resistance relation model; and calculating a smelting pool resistance, namely the sum in series of the smelting pool resistance of the two electrodes.

公开(公告)号：US20250103038A1

公开(公告)日：2025-03-27

申请号：US18724548

申请日：2022-01-11

Applicant: Northeastern University

Inventor： Chuan MA ,  Yingwei ZHANG ,  Lin FENG

IPC: G05B23/02 ,  G05B19/418

Abstract: Provided is a method for detecting abnormal working conditions of multi-view data based on feature regression. By the method, data capable of being acquired in a production process is collected together, a big data pool is established, and historical data information is fully utilized; by analyzing the data in the data pool, the method for detecting abnormal working conditions based on the multi-view data is established by a feature regression method, and a general mathematical model is established for preprocessed data acquired by different sensors; left and right projection vectors solved through the model can make similar sample points have better clustering effects in a low dimensional space; and by comparing a correlation between vectors after dimensionality reduction and various category vectors, production working conditions at a current time can be recognized.

公开(公告)号：US20240211662A1

公开(公告)日：2024-06-27

申请号：US18555827

申请日：2021-12-03

Applicant: Northeastern University

Inventor： Peisheng LIU ,  Hao LI ,  Yingwei ZHANG ,  Lin FENG

IPC: G06F30/27 ,  G06F113/08 ,  G06F119/08

CPC classification number: G06F30/27 ,  G06F2113/08 ,  G06F2119/08

Abstract: Provided is a calculating and real-time monitoring method for a boundary of a blast furnace tuyere raceway including: the steps of firstly establishing a depth calculation model for the raceway, and further obtaining a calculation formula for a depth of the raceway so as to obtain a change law of the depth of the raceway; establishing a boundary model for the raceway through the depth calculation model for the raceway, and determining a calculation formula for the boundary of the raceway; obtaining modelling parameters, analyzing an impact of the modelling parameters on the boundary model, and determining main parameters that affect the boundary of the raceway; finally, solving a height of the raceway; and when the height or depth of the raceway exceeds a set range, adjusting a blast wind pressure and a blast wind volume to restore the height or depth of the raceway to a normal range.

公开(公告)号：US20240029000A1

公开(公告)日：2024-01-25

申请号：US17912807

申请日：2021-12-03

Applicant: Northeastern University

Inventor： Hongrui GAO ,  Feng XUE ,  Yingwei ZHANG ,  Lin FENG ,  Shengyang ZHANG ,  Zubian LI

IPC: G06Q10/0637

CPC classification number: G06Q10/06375

Abstract: A second type computer assembly line balancing optimization method based on a migration genetic algorithm, and related to the technical field of assembly line balancing. The method uses assembly experience of similar assembly lines, the feasible solution set of the known assembly lines is transferred to the initial solution set of the assembly line balancing problem to be optimized, due to the migration of high-quality feasible solutions. The method can effectively reduce the sensitivity of the algorithm performance to the initial value and parameters, and improve the lower limit of the local optimal feasible solution of the heuristic algorithm to solve the assembly line balancing problem.

公开(公告)号：US20170146433A1

公开(公告)日：2017-05-25

申请号：US15009241

申请日：2016-01-28

Applicant: Northeastern University

Inventor： Yingwei ZHANG ,  Wenyou DU ,  Yunpeng FAN ,  Qilong JIA ,  Shitao LIU ,  Xu YANG

IPC: G01M99/00

CPC classification number: G05B23/0281

Abstract: Provided is a fault isolation method in industrial process based on regularization framework, including the steps of: collecting and filtering sample data in industrial process to obtain an available sample data set; establishing an objective function for fault isolation in industrial process with local and global regularization items; calculating the optimal solution to the objective function for fault isolation in industrial process by the available sample data set; obtaining a predicted classification label matrix according to the optimal solution to determine the fault information in the process. The method uses the local regularization item to make the nature of the optimal solution ideal, and uses the global regularization item to correct problem of low fault isolation precision caused by the local regularization item. Experiments show that the method is not only feasible but also provides high fault isolation precision and mining the potential information of labeled sample data.