Although several data-driven soft sensors are available, online reliable prediction of the Mooney viscosity in industrial rubber mixing processes is still a challenging task. A robust semi-supervised soft sensor, called ensemble deep correntropy kernel regression (EDCKR), is proposed. It integrates the ensemble strategy, deep brief network (DBN), and correntropy kernel regression (CKR) into a unified soft sensing framework. The multilevel DBN-based unsupervised learning stage extracts useful information from all secondary variables. Sequentially, a supervised CKR model is built to explore the relationship between the extracted features and the Mooney viscosity values. Without cumbersome preprocessing steps, the negative effects of outliers are reduced using the CKR-based robust nonlinear estimator. With the help of ensemble strategy, more reliable prediction results are further obtained. An industrial case validates the practicality and reliability of EDCKR.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7038447 | PMC |
| http://dx.doi.org/10.3390/s20030695 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Electrically Driven Liquid Crystal Elastomer Self-Oscillators via Rheostat Feedback Mechanism.
Polymers (Basel)
February 2025
School of Mechanical and Electrical Engineering, Anhui Jianzhu University, Hefei 230601, China.
The reliance of feedback mechanisms in conventional light-fueled self-oscillating systems on spatially distributed light and intricately designed structures impedes their application and development in micro-robots, miniature actuators, and other small-scale devices. This paper presents a straightforward rheostat feedback mechanism to create an electrically driven liquid crystal elastomer (LCE) self-oscillator which comprises an LCE fiber, a rheostat, a spring, and a mass. Based on the electrothermally responsive LCE model, we first derive the governing equation for the system's dynamics and subsequently formulate the asymptotic equation.
View Article and Find Full Text PDFBio-Inspired Ionic Sensors: Transforming Natural Mechanisms into Sensory Technologies.
Nanomicro Lett
March 2025
Department of Mechanical Engineering, Kyung Hee University, 1732 Deogyeong-daero, Giheung-gu, Yongin, Gyeonggi-do, 17104, Republic of Korea.
Many natural organisms have evolved unique sensory systems over millions of years that have allowed them to detect various changes in their surrounding environments. Sensory systems feature numerous receptors-such as photoreceptors, mechanoreceptors, and chemoreceptors-that detect various types of external stimuli, including light, pressure, vibration, sound, and chemical substances. These stimuli are converted into electrochemical signals, which are transmitted to the brain to produce the sensations of sight, touch, hearing, taste, and smell.
View Article and Find Full Text PDFProgress in the Development of Flexible Devices Utilizing Protein Nanomaterials.
Nanomaterials (Basel)
February 2025
Key Laboratory of Applied Surface and Colloid Chemistry, Ministry of Education, School of Chemistry and Chemical Engineering, Shaanxi Normal University, Xi'an 710119, China.
Flexible devices are soft, lightweight, and portable, making them suitable for large-area applications. These features significantly expand the scope of electronic devices and demonstrate their unique value in various fields, including smart wearable devices, medical and health monitoring, human-computer interaction, and brain-computer interfaces. Protein materials, due to their unique molecular structure, biological properties, sustainability, self-assembly ability, and good biocompatibility, can be applied in electronic devices to significantly enhance the sensitivity, stability, mechanical strength, energy density, and conductivity of the devices.
View Article and Find Full Text PDFSoft, Stretchable, High-Sensitivity, Multi-Walled Carbon Nanotube-Based Strain Sensor for Joint Healthcare.
Nanomaterials (Basel)
February 2025
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing 100044, China.
Exoskeletons play a crucial role in joint healthcare by providing targeted support and rehabilitation for individuals with musculoskeletal diseases. As an assistive device, the accurate monitoring of the user's joint signals and exoskeleton status using wearable sensors is essential to ensure the efficiency of conducting complex tasks in various scenarios. However, balancing sensitivity and stretchability in wearable devices for exoskeleton applications remains a significant challenge.
View Article and Find Full Text PDFBattery-free head orientation measurement using passive RFID tags.
Wearable Technol
February 2025
Department of Human Centered Design, Cornell University, Ithaca, NY, USA.
Real-time measurement of head rotation, a primary human body movement, offers potential advantages in rehabilitating head or neck motor disorders, promoting seamless human-robot interaction, and tracking the lateral glance of children with autism spectrum disorder for effective intervention. However, existing options such as cameras capturing the entire face or skin-attached sensors have limitations concerning privacy, safety, and/or usability. This research introduces a novel method that employs a battery-free RFID tag-based wearable sensor for monitoring head orientation, as a substitute for the existing options like camera.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!