A Practical Low-Cost Machine Vision Sensor System for Defect Classification on Air Bearing Surfaces

doi:10.18494/sam.2017.1484

Cited by 4 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extensive inspection measures are usually taken during the production process to determine the quality level of the bearings, such as inspecting the outer surfaces of the bearings before packaging [1]. Compared with defect detection, defect classification [2] can provide original feedback information for ensuring product quality, analyze the root cause of defects, and improve manufacturing processes. Therefore, tiny defect classification of bearings has attracted growing research attention in recent years.…”

Section: Introductionmentioning

confidence: 99%

A novel CNN ensemble framework for bearing surface defects classification based on transfer learning

Ma¹,

Liu²,

Chen³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Bearing surface defect detection and classification methods based on machine vision have been widely used in bearing quality inspection due to their high-speed, high-precision, and non-contact advantages. However, traditional machine vision algorithms have low reusability and their development processes are often expensive and time consuming. Several deep learning-based bearing surface defect detection methods have been proposed. However, these deep learning models often require a large number of datasets, which is often difficult to achieve in the actual industry. Transfer learning provides a promising solution to the small sample difficulties associated with deep learning. However, the complexity of the illumination conditions and the huge differences between bearing dataset and ImageNet dataset make it impossible to use the current single model-based transfer learning for bearing defect detection. In this study, we propose a novel transitive transfer learning convolutional neural network (CNN) ensemble framework for classifying bearing surface defects. Only small-scale datasets are needed in this framework. A transfer path and transfer method selection strategy for transitive transfer learning is then proposed to train the deep learning models, which enhances the feature extraction ability of the CNN models on the basis of multiple illuminations. Ablation experiments are conducted to verify the effectiveness of the proposed method. Experimental results show that the proposed transitive transfer learning CNN ensemble framework has the accuracy rate of 97.51%. The average time for detecting each bearing is 155 ms, which can meet the requirements of industrial online detection.

show abstract

Section: Introductionmentioning

confidence: 99%

A novel CNN ensemble framework for bearing surface defects classification based on transfer learning

Ma¹,

Liu²,

Chen³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…There have been many IoT-based studies in this field, as reviewed in Table 1. (1)(2)(3)(4)(5)(6)(7) In recent years, low-cost IoT systems (8,9) have been used for detection systems including for gas detection and environment monitoring. (10)(11)(12) In addition, the low-cost ESP8266 Wi-Fi module has been used by many researchers in their IoT systems, (13)(14)(15) in which the accuracy and long-term working modes of the sensors and Wi-Fi module have been demonstrated.…”

Section: Introductionmentioning

confidence: 99%

Cost-effective Evaluation, Monitoring, and Warning System for Water Quality based on Internet of Things

Truong¹

2021

Sensors and Materials

View full text Add to dashboard Cite

This paper proposes an evaluating, monitoring, and warning system for water quality for taking care of fish that includes an Arduino Mega2560 board and a sensor system with wireless communication technologies based on IoT technology. Not only the temperature but also the pH and dissolved oxygen (DO) content of water are acquired through the Arduino Mega2560 board. These measurement data are transferred to the server through ESP8266 and SIM800A modules integrated on the board. The stored temperature, pH, and DO values are displayed on a ThingSpeak server. Furthermore, the fault detection of water quality under real working conditions is handled and displayed on the platform or a cellphone-based web service and short messaging service (SMS). The accuracy and reliability of the system for the functions of monitoring, evaluation, and fault detection were demonstrated. Compared with established systems, the proposed system has the advantages of (1) reduced cable use for the monitoring system, (2) a warning system via a cellphone-based SMS cellphone or web service, (3) costeffectiveness, and (4) portability.

show abstract

“…The experimental results show that these methods can be used to successfully inspect the quality of bearings. (8)(9)(10)(11) Sugumaran and Ramachandran solved the problem of detecting vibration signals by applying machine learning. (12) In their study, the support vector machine (SVM) and proximal support vector machine (PSVM) classifiers were used to clarify statistical and histogram features of time domain signals.…”

Section: Introductionmentioning

confidence: 99%

Automatic Optical Apparatus for Inspecting Bearing Assembly Defects

Ye¹,

Hsu²

2018

Sensors and Materials

View full text Add to dashboard Cite

In this study, an inspection apparatus including offline and online inspection systems that are highly efficient is developed for the unidirectional bearing of automobiles. To avoid the influence of outside factors and ambient light, the proposed system, which includes a lighting source, an image capture device, and a sensor, is placed in a dark room as a controlled environment for offline inspection. Furthermore, rule-based algorithms for local mask sensors are developed to overcome the highly reflective characteristic of metallic materials and thus assist online inspection. The inspection process of the system is mainly divided into three parts: central positioning of the device under test (DUT), blob analysis, and identification units of needles. After testing, the correct inspection rates for offline and online inspection systems of the proposed system are 100 and 99.94%, respectively.

show abstract

A Practical Low-Cost Machine Vision Sensor System for Defect Classification on Air Bearing Surfaces

Cited by 4 publications

References 27 publications

A novel CNN ensemble framework for bearing surface defects classification based on transfer learning

A novel CNN ensemble framework for bearing surface defects classification based on transfer learning

Cost-effective Evaluation, Monitoring, and Warning System for Water Quality based on Internet of Things

Automatic Optical Apparatus for Inspecting Bearing Assembly Defects

Contact Info

Product

Resources

About