Research on Feature Extraction and Classification Method of Vibration Signal of Escalator Sprocket Bearing

In order to improve the accuracy of escalator sprocket bearing fault diagnosis,the problem of the feature extraction method of bearing vibration signal is addressed.In this paper,empirical mode is used to decompose the original signal,and the optimal modal component among the multiple modal components is obtained after the optimization decomposition is selected by the envelope spectrum method,and the multi-angle feature measure is introduced to extract the fault characteristic value.According to the vibration characteristics of the bearing vibration signal data,a bearing signal feature group that is more inclined to the fault feature category information is established,which avoids the absolute problem of extracting a single metric feature.The fuzzy C-means clustering algorithm is used to cluster the sample data with similar characteristics into the same cluster area,which effectively solves the problem that a single measurement analysis cannot characterize the complex internal characteristics ofthe bearing vibration signal.

Segmentation and measurement scheme for fish morphological features based on Mask R-CNN

The morphological features of fish,such as the body length,the body width,the caudal peduncle length,the caudal peduncle width,the pupil diameter,and the eye diameter are very important indicators in smart mariculture.Therefore,the accurate measurement of the morphological features is of great significance.However,the existing measurement methods mainly rely on manual measurement,which is operationally complex,low efficiency,and high subjectivity.To address these issues,this paper proposes a scheme for segmenting fish image and measuring fish morphological features indicators based on Mask R-CNN.Firstly,the fish body images are acquired by a home-made image acquisition device.Then,the fish images are preprocessed and labeled,and fed into the Mask R-CNN for training.Finally,the trained model is used to segment fish image,thus the morphological features indicators of the fish can be obtained.The experimental results demonstrate that the proposed scheme can segment the fish body in pure and complex backgrounds with remarkable performance.In pure background,the average relative errors(AREs)of all indicators measured all are less than 2.8%,and the AREs of body length and body width are less than 0.8%.In complex background,the AREs of all indicators are less than 3%,and the AREs of body length and body width is less than 1.8%.2020 China Agricultural University.Production and hosting by Elsevier B.V.on behalf of KeAi.This is an open access article under the CC BY-NC-ND license(http://creativecommons.org/licenses/by-nc-nd/4.0/).1.Introduction With the advancing of its scientific and technological capabilities,China has made great achievements in the mariculture.The production accounts for more than 70%of the world’s overall mariculture output[1].The measurement of body length,body width and other morphological features of fish have wide application prospects in smart mariculture.Due to the difference in the quality and feeding ability of the Juvenile fish,the growth of the fish in the same pond is significantly different after a period of growth.Then,the fish needs to be classified.Grading can make fish grow better and improve feed utilization[2].The fish body length and body width are closely related to the weight of the fish.In the mariculture,the fishermen judge the growth of the fish by collecting the morphological feature of the fish,and use the information as an important reference for feeding,fishing and classification[3].At present,most of the measurement methods of fish body morphological features are manual,the operator usesmeasuring ruler to measure manually.It requires high technical level,and has high labor intensity and low efficiency.Furthermore,https://doi.