-
公开(公告)号：US20210064988A1
公开(公告)日：2021-03-04
申请号：US16636258
申请日：2019-02-26
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Kuo LIU , Yongqing WANG , Xu LI , Bo QIN , Yongquan GAN , Dawei LI , Haining LIU
IPC: G06N3/08 , G06N3/04 , G06F17/10 , G05B19/4065
Abstract: A method for calculating the reliability of the thermal error model of a machine tool based on deep neural network (DNN) and the Monte Carlo method, which belongs to the field of the thermal error compensation of computer numerical control (CNC) machine tools. Firstly, according to the probability distribution of the thermal parameters and thermal error model, a set of data for training the DNN is generated. Next, the DNN is constructed based on the deep belief networks (DBNs) and trained with the training data. Then, a group of random sampling data is obtained according to the probability distribution of the thermal characteristic parameters of the machine tool, and the group of random sampling is taken as the input and the output is obtained by the trained depth neural network. Finally, the reliability of the thermal error model is calculated based on the Monte Carlo method.
-
公开(公告)号：US20210026319A1
公开(公告)日：2021-01-28
申请号：US16639959
申请日：2019-02-21
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Kuo LIU , Yongqing WANG , Jiakun WU , Haining LIU , Mingrui SHEN , Bo QIN , Haibo LIU
IPC: G05B19/404
Abstract: A self-adaptive compensation method for feed axis thermal error, which belongs to the field of error compensation in NC machine tools. First, based on laser interferometer and temperature sensor, the feed axis thermal error test is carried out; following, the thermal error prediction model, based on the feed axis thermal error mechanism, is established and the thermal characteristic parameters in the model are identified, based on the thermal error test data; next, the parameter identification test is carried out, under the preload state of the nut; next, the adaptive prediction model is established, based on the thermal error prediction model, while the parameters in the measurement model are identified; finally, adaptive compensation of thermal errors is performed, based on the adaptive error prediction model, according to the generated feed axis heat.
-
Patent Agency Ranking
公开(公告)号：US20210364482A1
公开(公告)日：2021-11-25
申请号：US17260156
申请日：2020-03-06
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Yongqing WANG , Bo QIN , Kuo LIU , Mingrui SHEN , Mengmeng NIU , Honghui WANG , Lingsheng HAN
Abstract: A prediction method of part surface roughness and tool wear based on multi-task learning belong to the file of machining technology. Firstly, the vibration signals in the machining process are collected; next, the part surface roughness and tool wear are measured, and the measured results are corresponding to the vibration signals respectively; secondly, the samples are expanded, the features are extracted and normalized; then, a multi-task prediction model based on deep belief networks (DBN) is constructed, and the part surface roughness and tool wear are taken as the output of the model, and the features are extracted as the input to establish the multi-task DBN prediction model; finally, the vibration signals are input into the multi-task prediction model to predict the surface roughness and tool wear.
-
公开(公告)号：US20210287098A1
公开(公告)日：2021-09-16
申请号：US15734940
申请日：2020-02-28
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Kuo LIU , Mingrui SHEN , Bo QIN , Renjie HUANG , Mengmeng NIU , Yongqing WANG
Abstract: An on line prediction method of part surface roughness based on SDAE-DBN algorithm. The tri-axis acceleration sensor is adsorbed on the rear bearing of the machine tool spindle through the magnetic seat to collect the vibration signals of the cutting process, and a microphone is placed in the left front of the processed part to collect the noise signals of the cutting process of the machine tool; the trend term of dynamic signal is eliminated, and the signal is smoothed; a stacked denoising autoencoder is constructed, and the greedy algorithm is used to train the network, and the extracted features are used as the input of deep belief network to train the network; the real-time vibration and noise signals in the machining process are input into the deep network after data processing, and the current surface roughness is set as output by the network.
-
公开(公告)号：US20210178542A1
公开(公告)日：2021-06-17
申请号：US15734912
申请日：2019-09-12
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Yongqing WANG , Lingsheng HAN , Kuo LIU , Haibo LIU , Zaiyou BAN , Bo QIN
Abstract: The invention provides a toolholder matched with the internal jet cooling spindle for cryogenic coolant. The toolholder is mainly composed of a hollow toolholder body, a high-performance thermal insulation structure and a bidirectional sealing structure. They can guide the cryogenic coolant from the spindle to the internal cooling channel of tool and realize the cryogenic thermal insulation and dynamic sealing. The high-performance thermal insulation structure inside the toolholder employs the material with a low thermal conductivity and a low linear expansion coefficient to restrain the low temperature impact of cryogenic coolant on the toolholder and spindle, to ensure the dimensional accuracy and assembly accuracy of the toolholder. The bidirectional sealing structure in the toolholder uses the ultra-low temperature resistant seal rings to prevent the cryogenic coolant from leaking towards the spindle and the tool, to ensure the stability of the coolant transport.
-
公开(公告)号：US20210048793A1
公开(公告)日：2021-02-18
申请号：US16636556
申请日：2019-02-21
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Kuo LIU , Bo QIN , Xu LI , Yongquan GAN , Wei HAN , Renjie HUANG , Yongqing WANG
IPC: G05B19/4155
Abstract: A spindle thermal error compensation method which is insensitive to the disturbance of the cooling system is provided, belonging to the technical field of error compensation in numerical control machine tools. First, the spindle model coefficient identification test, based on multi-state speed variable, is performed; after which, based on the correlation analysis between temperature and thermal error, the temperature measurement point, significantly correlated with the axial thermal error of the spindle, is determined. Next, a spindle thermal error model is established, which is insensitive to the cooling system disturbance. In addition, the coefficients in the model are identified under constraint condition, according to the nonlinear quadratic programming algorithm. Finally, based on the OPC UA communication protocol, the compensation value, as calculated by the model, is input to the numerical control system, in order to realize the compensation of the spindle thermal error.
-
7.发明申请公开(公告)号：US20210197335A1
公开(公告)日：2021-07-01
申请号：US16970301
申请日：2020-02-28
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Yongqing WANG , Mengmeng NIU , Kuo LIU , Bo QIN , Mingrui SHEN , Dawei LI
Abstract: The invention provides a data augmentation method based on generative adversarial networks in tool condition monitoring. Firstly, the sensor acquisition system is used to obtain the vibration signal and noise signal during the cutting process of the tool; second, the noise data subject to the prior distribution is input to the generator to generate data, and the generated data and the collected real sample data are input to the discriminator for identification, the confrontation training between the generator and the discriminator until the training is completed; then, use the trained generator to generate sample data, and determine whether the generated sample data and the actual tool state sample data are similar in distribution; finally, combined with the accuracy of the deep learning network model to predict the state of the tool to verify the availability of the generated data.
-
-
-
-
-
-
Search Results
7
records
(took 0.016 seconds)
