Search

Aimed at the problem that the accuracy of tool remaining life prediction was reduced due to the abnormal monitoring data in machining process, a data anomaly detection method based on self-paced learning was proposed. First, a multi-layer perceptron model was established to correlate the tool processing monitoring data with the tool remaining life. Next, in the process of updating model weight, the model weight parameters were fixed first, and the loss threshold of abnormal samples was obtained by predicting loss fitting Gaussian distribution. Then, the loss function based on the self-paced learning method was constructed to update model parameters iteratively. At the end of the model training, abnormal samples were divided according to the loss threshold. Finally, the actual processing monitoring data of turbine rotor groove were used to verify the proposed method, and compare with the local anomaly factor algorithm, the density-based clustering algorithm, the K-means algorithm, the isolated forest algorithm, and the one-class support vector machines.

Background The measurement of exhaled gas nitric oxide (FeNO) has safe, non-invasive, simple, repetitive characteristics which is widely used in the assessment of airway inflammation in asthmatic patients, but the determination of FeNO is affected by a variety of factors, among which living environment factors exposure may have a close relationship to FeNO level, whereas there are few studies on the impact of exposure of living environment factors on the level of FeNO. Objective To analyze the effect of exposure to living environment factors on the level of exhaled nitric oxide (FeNO) in patients with bronchial asthma in non acute attack period, so as to improve the efficacy of clinicians in using FeNO to manage asthma. Methods A total of 109 patients with bronchial asthma in non acute attack period who visited the Respiratory Department Outpatient of the Second Affiliated Hospital of Guangzhou Medical University from July 2018 to June 2020 were included as the study subjects, the data were collected through a questionnaire survey, and the questionnaire information mainly included general information (gender, age, height, body mass) , living environment factors (including smoking history, whether family members smoked at home, allergy history, location of residence, the distance between the residence and the main road with large traffic volume, whether there were factories around the residence, floors of residential buildings, length of residence building, frequency of washing and drying bed sheets, quilt covers/pillow cases, curtain materials at home, potted plants at home, whether the trash can in the home was cleaned regularly, whether kept pets at home, whether there were cockroaches at home and whether kitchen waste was disposed of the same day, whether there were plush toys at home) and the inspection data of FeNO collected. Patients with bronchial asthma were divided into 3 groups according to FeNO level: there were 47 cases in the FeNO low level group (FeNO50 ppb) . Ordinal multiple classification logistic regression analysis was used to explore the environmental factors affecting the FeNO value level measurement. Results There was no significant difference in gender, age, height and body mass among the three groups (P>0.05) . There was no significant difference among the three groups in floors of residential buildings, length of residence, frequency of washing and drying bed sheets, quilt covers/pillow cases, curtain materials at home, potted plants at home, whether the trash can in the home was cleaned regularly, whether there were cockroaches at home and whether kitchen waste was disposed of the same day, whether there were plush toys at home (P>0.05) ; There were statistically significant differences in smoking history, whether family members smoked at home, allergy history, location of residence, the distance between the residence and the main road with large traffic volume, whether there were factories around the residence, and whether there were pets at home (P

Abstract A twin-screw extruder with an ultra-large length-to-diameter (L/D) ratio of 136 was developed and applied in the gel-spinning process of ultra-high molecular weight polyethylene (UHMWPE). UHMWPE gel fibers with [...]