Fusion Domain-Adaptation CNN Driven by Images and Vibration Signals for Fault Diagnosis of Gearbox Cross-Working Conditions

The vibration signal of gearboxes contains abundant fault information, which can be used for condition monitoring. However, vibration signal is ineffective for some non-structural failures. In order to resolve this dilemma, infrared thermal images are introduced to combine with vibration signals via fusion domain-adaptation convolutional neural network (FDACNN), which can diagnose both structural and non-structural failures under various working conditions. First, the measured raw signals are converted into frequency and squared envelope spectrum to characterize the health states of the gearbox. Second, the sequences of the frequency and squared envelope spectrum are arranged into two-dimensional format, which are combined with infrared thermal images to form fusion data. Finally, the adversarial network is introduced to realize the state recognition of structural and non-structural faults in the unlabeled target domain. An experiment of gearbox test rigs was used for effectiveness validation by measuring both vibration and infrared thermal images. The results suggest that the proposed FDACNN method performs best in cross-domain fault diagnosis of gearboxes via multi-source heterogeneous data compared with the other four methods.

Double Thresholding with Sine Entropy for Thermal Image Segmentation

Traditional thresholding methods are often used for image segmentation of real images. However, due to distinct characteristics of infrared thermal images, it is difficult to ensure an optimal image segmentation using the traditional thresholding algorithms, and therefore, sometimes this can lead to over-segmentation, missing object information, and/or spurious responses in the output. To overcome these issues, we propose a new thresholding technique that makes use of the sine entropy-based criterion. Moreover, we build a double thresholding technique that makes use of two thresholds to get the final image thresholding result. Besides, we introduce the sine entropy concept as a supplement of the Shannon entropy in creating threshold-dependent criterion derived from the grayscale histogram. We found that the sine entropy is more robust in interpreting the strength of the long-range correlation in the gray levels compared to the Shannon entropy. We have experimented with our method on several infrared thermal images collected from standard image databases to describe the performance. On comparing with the state-of-art methods, the qualitative results from the experiments show that the proposed method achieves the best performance with an average sensitivity of 0.98 and an average misclassification error of 0.01, and second-best performance with an average sensitivity of 0.99 and an average specificity of 0.93.

Facial Paralysis Detection in Infrared Thermal Images Using Asymmetry Analysis of Temperature and Texture Features

Facial temperature distribution in healthy people shows contralateral symmetry, which is generally disrupted by facial paralysis. This study aims to develop a quantitative thermal asymmetry analysis method for early diagnosis of facial paralysis in infrared thermal images. First, to improve the reliability of thermal image analysis, the facial regions of interest (ROIs) were segmented using corner and edge detection. A new temperature feature was then defined using the maximum and minimum temperature, and it was combined with the texture feature to represent temperature distribution of facial ROIs. Finally, Minkowski distance was used to measure feature symmetry of bilateral ROIs. The feature symmetry vectors were input into support vector machine to evaluate the degree of facial thermal symmetry. The results showed that there were significant differences in thermal symmetry between patients with facial paralysis and healthy people. The accuracy of the proposed method for early diagnosis of facial paralysis was 0.933, and the area under the ROC curve was 0.947. In conclusion, temperature and texture features can effectively quantify thermal asymmetry caused by facial paralysis, and the application of machine learning in early detection of facial paralysis in thermal images is feasible.

Infrared thermal imaging monitoring on hands when performing repetitive tasks: An experimental study

The monitoring of infrared thermal images is reported to analyze changes in skin temperature in the hand fingers when repetitive work is performed to know which finger has a greater risk of injury, besides, the recovery time is analyzed regarding the initial temperature and its relationship with age, sex, weight, height if practice sports, and Body Mass Index (BMI) per individual. For the above, an experimental test was carried out for 10 minutes on a repetitive operation that takes place in the telecommunications industry and 39 subjects participated in which an infrared thermal image of the dorsal and palmar part of both hands was taken in periods of 5 minutes after the 10-minute test has elapsed. The results show that none of the participants recovered their initial temperature after 10 minutes of the experimental test. In addition, it was found that there is a relationship between skin temperature and sex, and that age influences the recovery of temperature. On the other hand, the thumb, index, and middle fingers have a higher risk of injury in the analyzed task. It is concluded that performing repetitive work with all the fingers of the hand does not show that all they have the same risk of injury, besides that, not all the variables studied affect the recovery of temperature and its behavior.

A novel composite cotton yarn with phase change and electrical conductivity functions

PAN/PEG/CNT/cotton composite yarn (PPCCY) was fabricated by impregnating PEG2000–10000 into CNT/cotton yarn (CCY) and coating electrospun PAN around its surface. The effects of PEG type on the morphology, structure, electrical resistance and phase change behavior of the produced composite yarns were studied thoroughly by scanning electron microscopy (SEM), Fourier transform infrared spectroscopy (FTIR), differential scanning calorimetry (DSC), thermal gravimetric(TG), electrical resistance tester and infrared thermal images. The experimental results indicated that the resulting compound yarn consisted of conductive yarn within which the spacing between cotton fibers was fulfilled by PEG, rendering phase transition enthalpy from 126–150 Jg−1. The composite yarn exhibited adjustable temperature and thermal storage and electrical conductivity abilities. The composite yarn demonstrated good responsive properties to external electrical and thermal stimuli and had reversible heat conversion and storage, which shows a promise for applications in electrical wearable fabrics.

Modified Gaussian convolutional deep belief network and infrared thermal imaging for intelligent fault diagnosis of rotor-bearing system under time-varying speeds

The vast majority of the existing diagnostic studies using deep learning techniques for rotating machinery focus on the vibration analysis under steady rotating speed. Nevertheless, the collected vibration signals are sensitive to time-varying speeds and the vibration sensors may cause structure damage of equipment after long-term close contact. Aiming at these aforementioned problems, a modified Gaussian convolutional deep belief network driven by infrared thermal imaging is proposed to automatically diagnose different faults of rotor-bearing system under time-varying speeds. First, infrared thermal images are measured to characterize the working states of rotor-bearing system to reduce the impact of changeable speeds. Second, Gaussian units are used to construct Gaussian convolutional deep belief network to well deal with infrared thermal images. Finally, trackable learning rate is designed to modify the training algorithm to enhance the performance. The comparison results verify the feasibility of the proposed method, which outperforms the other methods.

Point-of-care infrared thermal imaging for differentiating venomous snakebites from non-venomous and dry bites

Background Local envenomation following snakebites is accompanied by thermal changes, which could be visualized using infrared imaging. We explored whether infrared thermal imaging could be used to differentiate venomous snakebites from non-venomous and dry bites. Methods We prospectively enrolled adult patients with a history of snakebite in the past 24 hours presenting to the emergency of a teaching hospital in southern India. A standardized clinical evaluation for symptoms and signs of envenomation including 20-minute whole-blood clotting test and prothrombin time was performed to assess envenomation status. Infrared thermal imaging was done at enrolment, 6 hours, and 24 hours later using a smartphone-based device under ambient conditions. Processed infrared thermal images were independently interpreted twice by a reference rater and once by three novice raters. Findings We studied 89 patients; 60 (67%) of them were male. Median (IQR) time from bite to enrolment was 11 (6.5–15) hours; 21 (24%) patients were enrolled within 6 hours of snakebite. In all, 48 patients had local envenomation with/without systemic envenomation, and 35 patients were classified as non-venomous/dry bites. Envenomation status was unclear in six patients. At enrolment, area of increased temperature around the bite site (Hot spot) was evident on infrared thermal imaging in 45 of the 48 patients with envenomation, while hot spot was evident in only 6 of the 35 patients without envenomation. Presence of hot spot on baseline infrared thermal images had a sensitivity of 93.7% (95% CI 82.8% to 98.7%) and a specificity of 82.9% (66.3% to 93.4%) to differentiate envenomed patients from those without envenomation. Interrater agreement for identifying hot spots was more than substantial (Kappa statistic >0.85), and intrarater agreement was almost perfect (Kappa = 0.93). Paradoxical thermal changes were observed in 14 patients. Conclusions Point-of-care infrared thermal imaging could be useful in the early identification of non-venomous and dry snakebites.