Infrared Thermography Technology Research Articles

Cd0.9Zn0.1S/NiB Schottky heterojunction for efficient photothermal-assisted photocatalytic hydrogen evolution

Within the theoretical framework of computational prediction, this study introduces a novel tetrapodal Cd0.9Zn0.1S/NiB (CZS/NiB) Schottky heterojunction material, which demonstrates exceptional photothermal effects and remarkable photocatalytic properties. Notably, under visible light irradiation for 3 h, the photocatalytic hydrogen evolution activity of CZS/NiB-3 % surpasses that of pure CZS by a factor of 10.52. This outstanding photocatalytic hydrogen production performance stems from the successful construction of the CZS/NiB-3 % Schottky heterojunction with promoted the separation and transfer of photogenerated charge carriers and excellent photothermal effect. Additionally, the synthesized CZS/NiB exhibits high photostability and cycling stability. The favorable photothermal effect of the synthesized photocatalyst was experimentally validated through infrared thermography technology. Through in-depth computational investigations using density functional theory, the pathways of charge transfer in the Schottky heterojunction are validated. This study provides a feasible strategy for research on photocatalytic water splitting for hydrogen evolution.

Lab-based scale measurements of internal storage of crude oil tank based on non-contact infrared thermography technique

Non-contact sludge measurement methods for storage tanks can address the challenge of measuring the volume of sedimented sludge during long-term storage. While infrared thermography technology can address the issue of liquid level detection, its measurement accuracy for the undulating interface of sludge is insufficient. This study designed and constructed experimental setups for measuring sludge in storage tanks. In this study, infrared images taken by an infrared camera were used to record the temperature distribution of the outer wall of the storage tank. The threshold segmentation method is used to determine the accurate sludge boundary line in image processing. Finally, the Three-Dimensional Tank Residue Recovery Algorithm (3D-TRRA) was applied to fit the 3D distribution of the sludge and calculate accurate sludge volumes. The results indicate that the best segmentation is achieved with a threshold of 170. The measurement error for sludge volume is less than 5%. Accurate visual positioning and recognition of sludge are achieved.

High-resolution monitoring of soil infiltration using distributed fiber optic

Monitoring the infiltration process in soil is of great importance in various fields. However, the majority of existing infiltration monitoring methods have certain limitations that hinder their ability to meet the technical requirements for continuous spatial monitoring of the infiltration process. To address this issue, this study proposes a new method for achieving spatially continuous monitoring of the infiltration process. This method employs the improved Active Heating Fiber Optics (AHFO) technique as the underlying mechanism and utilizes Optical Frequency Domain Reflectometry (OFDR) monitoring technology characterized by exceptionally high spatial resolution and monitoring sensitivity. The proposed method, referred to as Active Heating Optical Frequency Domain Reflectometry (AH-OFDR). The feasibility of AH-OFDR was validated through a set of experimental tests, involving the installation of optical fibers within cylindrical soil samples for infiltration monitoring. A comparison was conducted between the infiltration patterns obtained through AH-OFDR and those acquired using the well-established Distributed Temperature Sensing (DTS) method. Additionally, the temperature distribution within the sample during the infiltration process was monitored by employing infrared thermography technology. The experimental results demonstrated an excellent agreement between the infiltration patterns obtained through AH-OFDR and DTS, reaffirming the viability and accuracy of AH-OFDR for soil infiltration monitoring. However, when compared to DTS, AH-OFDR excels in achieving dynamic monitoring of water content variations at a spatial resolution as fine as the centimeter level, empowering high-resolution and continuous monitoring. The changes in the soil temperature field recorded by the infrared thermography system further confirm the accuracy of the AH-OFDR monitoring results.

Thermal preference prediction through infrared thermography technology: Recognizing adaptive behaviors

The recognition of thermal adaptation behaviors is a crucial and noninvasive method for accurately and swiftly predicting the thermal preferences of occupants. This is instrumental in enhancing the energy efficiency, indoor personnel comfort, and overall productivity of office buildings. This study employed deep-learning models to analyze a thermal adaptive behavior video dataset captured by Infrared thermography (IRT) cameras to predict the thermal preferences of occupants. A large-scale infrared thermography dataset was developed for recognizing thermal adaptive behaviors using 9650 video samples. Two adaptive behavior recognition models for infrared videos were developed by leveraging neural network models: Two-Stream Inflated 3D ConvNet (I3D) and SlowFast (SF) networks. These models achieved the average prediction accuracies of 83.53 % and 88.56 %, respectively. Notably, both models exhibited a recognition time of milliseconds, facilitating the real-time recognition of thermal adaptive behaviors. This study offers vital technical and theoretical underpinnings for developing decision-making solutions for smart buildings based on noninvasive thermal preference prediction.

An advanced heat source localization technology for intelligent warehousing: A multi-source fusion image segmentation approach leveraging infrared and visible light data

Infrared thermography technology, leveraging its unique ability to capture temperature features, has significantly improved the precision of high-temperature target localization. However, infrared imaging technology is limited by issues such as low image contrast, difficulty in distinguishing object categories, and limited image clarity. To enable intelligent detection of high-temperature objects that may cause fires in warehouses, this paper proposes an innovative method that integrates deep learning image segmentation with infrared and visible light image technology. We developed a new image segmentation model based on improved Fully Convolutional Networks and Deconvolutional Networks, introducing a batch normalization layer to accelerate convergence and employing the PReLU activation function to prevent neuron death, thereby enhancing convergence speed and accuracy. Through a feature dynamic image registration method combining a joint model and a cross-modulation strategy, we achieved efficient image fusion. In addition, a game theory-based strategy was adopted to correct localization results, ensuring accuracy. Experimental results demonstrate that the improved model achieves localization accuracy and precision rates of up to 89.30% and 88.00%, respectively, in real-world warehouse heat source scenarios, representing a significant improvement of 9.90% and 2.85% compared to the pre-improvement model, fully validating its advancement and effectiveness.

An approach-based machine learning and automated thermal images to predict the dark-cutting incidence in cattle management of healthcare supply chain

The healthcare supply chain is a network made up of various systems, processes, and elements that function and interact seamlessly to offer healthcare services and products. Food safety is an essential component of the healthcare supply chain. In the cattle industry, the healthcare supply chain contributes positively to the global economy through providing high-quality products such as milk and meat. Stress in cattle is one of main factor that cause low quality meat called “dark meat”. Numerous studies have been conducted on the development of different non-invasive methods based on Infrared Thermography Technology (IRT) to enhance the meat quality by detecting stress in cattle pre-slaughtering. These studies have the following issues: lack of automating in detecting body temperature of cattle and ignoring detecting stress with prediction dark meat incidence. The present study endeavors a new fully automated system for detecting stress, and dark meat incidence, incorporating the following new approaches: Multiview face detecting, Automatic eye localisation for detecting body temperature automatically employing computer vision and image processing, respectively. Furthermore, machine learning algorithms like Support Vector Machine (SVM), Logistic Regression (LR), Naïve Bayes (NB), and Decision Tree (DT) have been developed specifically for stress detection and the prediction of dark meat. To develop automated system, two forms of data were collected: statistical temperature and infrared thermal images. Infrared thermal images are used to develop Multiview face detection and Automatic eye localisation. Temperature data used to develop the machine learning model. Results reveal that Multiview face detection better than the current methods in term of Precision 0.99, Recall 0.91, F-score 0.95 with high True positive rate 0.90 and zero False-positive rate. Automatic eye localisation has high accuracy, with the following values: sensitivity 0.9780, precision 0.7212, F measure of 0.8024, and misclassification 0.0455. Lastly, results elaborate that the decision tree model can attain a notable level of accuracy in terms of specificity, recall, F-measure, and Area Under the Curve (AUC), all at an optimal rate of 98%.

Photothermal-Enhanced S-Scheme Heterojunction of Hollow Core-Shell FeNi2S4@ZnIn2S4 toward Photocatalytic Hydrogen Evolution.

Herein, guided by the results of density functional theory prediction, the study rationally designs a hollow core-shell FeNi2S4@ZnIn2S4 (FNS@ZIS) Step-scheme (S-scheme) heterojunction for photocatalytic H2 evolution with photothermal-assisted. The hollow FNS spheres offered substrate for coating the ZIS nanosheets, which can inhibit ZIS nanosheets from agglomerating into pellet, enrich the active site, increase specific surfaces, and raise the light absorption. Notably, due to its excellent photothermal properties, FNS core generated heat unceasingly inside under visible-light irradiation and effectively prevent the heat loss of the reaction system, which increased the local temperature of photocatalysts and thus accelerated the charge migration. In addition, the S-scheme heterojunction construction via in situ growth has a tight interface, which can facilitate the separation and transfer of carriers and achieve high redox potential. Owning to the distinctive construction, the hollow core-shell FNS@ZIS S-scheme heterojunction show extraordinary stability and photocatalytic H2 evolution rate with 7.7mmolh-1g-1, which is ≈15.2-fold than pristine ZIS. Based on the double evidence of theoretical predictions and experimental confirmations, the photothermal effect and electron transfer mechanism of this innovative material are investigated in depth by the following infrared thermography technology and deep DFT calculations.

Investigation of the applicability of infrared thermography detection of grouting voids in prestressed tendon ducts under hydration heat excitation

Infrared thermography (IRT) has been successfully utilized to identify void defects in external prestressed tendon ducts (without concrete protective layers) under hydration heat excitation. Nonetheless, applying IRT technology for the inspection of internal prestressed tendon ducts presents challenges due to the presence of the thicker concrete protective layer, which can significantly influence the detection results. Therefore, this paper proposes a method for detecting void defects in internal prestressed tendon ducts using IRT technology under hydration heat excitation. The influence of the depth, length and compactness of the void on the detection ability is investigated and the influencing factors such as duct materials are analyzed. The results show that under the hydration heat excitation of the grouting material, IRT can detect complete void defects with a depth of 110 mm below and a length of 350 mm. In addition, the detection effects of metal ducts, tubeless ducts and plastic ducts decrease in turn. Finally, this paper recommends that the IRT detection time be 0.5–2 h and 13–23 h after grouting, which can reduce the cost of post-maintenance by timely detection and repair.

Global trends and performances of infrared imaging technology studies on acupuncture: a bibliometric analysis.

To summarize development processes and research hotspots of infrared imaging technology research on acupuncture and to provide new insights for researchers in future studies. Publications regarding infrared imaging technology in acupuncture from 2008 to 2023 were downloaded from the Web of Science Core Collection (WoSCC). VOSviewer 1.6.19, CiteSpace 6.2.R4, Scimago Graphica, and Microsoft Excel software were used for bibliometric analyses. The main analyses include collaboration analyses between countries, institutions, authors, and journals, as well as analyses on keywords and references. A total of 346 publications were retrieved from 2008 to 2023. The quantity of yearly publications increased steadily, with some fluctuations over the past 15 years. "Evidence-Based Complementary and Alternative Medicine" and "American Journal of Chinese Medicine" were the top-cited journals in frequency and centrality. China has the largest number of publications, with the Shanghai University of Traditional Chinese Medicine being the most prolific institution. Among authors, Litscher Gerhard from Austria (currently Swiss University of Traditional Chinese Medicine, Switzerland) in Europe, was the most published and most cited author. The article published by Rojas RF was the most discussed among the cited references. Common keywords included "Acupuncture," "Near infrared spectroscopy," and "Temperature," among others. Explore the relationship between acupoints and temperature through infrared thermography technology (IRT), evaluate pain objectively by functional near-infrared spectroscopy (fNIRS), and explore acupuncture for functional connectivity between brain regions were the hotspots and frontier trends in this field. This study is the first to use bibliometric methods to explore the hotspots and cutting-edge issues in the application of infrared imaging technology in the field of acupuncture. It offers a fresh perspective on infrared imaging technology research on acupuncture and gives scholars useful data to determine the field's hotspots, present state of affairs, and frontier trends.

Experimental study on defects detection in GFRP laminates using lock-in infrared thermography technology

To detect the debonding defect of glass fiber reinforced polymer (GFRP) laminate, the lock-in infrared thermography non-destructive testing system is built and the systematic testing research are conducted, and the effect of different geometrical parameters of debonding defects on the testing results are analyzed. Algorithms such as inter frame differential-multi frame cumulative average method, polynomial fitting-correlation coefficient method, and time-difference contrast method are used to process the image sequence, and signal-to-noise ratio and information en-tropy are defined as the parameters for evaluating the performance of algorithms.

Thermal imaging and computer vision technologies for the enhancement of pig husbandry: a review.

Pig farming, a vital industry, necessitates proactive measures for early disease detection and crush symptom monitoring to ensure optimum pig health and safety. This review explores advanced thermal sensing technologies and computer vision-based thermal imaging techniques employed for pig disease and piglet crush symptom monitoring on pig farms. Infrared thermography (IRT) is a non-invasive and efficient technology for measuring pig body temperature, providing advantages such as non-destructive, long-distance, and high-sensitivity measurements. Unlike traditional methods, IRT offers a quick and labor-saving approach to acquiring physiological data impacted by environmental temperature, crucial for understanding pig body physiology and metabolism. IRT aids in early disease detection, respiratory health monitoring, and evaluating vaccination effectiveness. Challenges include body surface emissivity variations affecting measurement accuracy. Thermal imaging and deep learning algorithms are used for pig behavior recognition, with the dorsal plane effective for stress detection. Remote health monitoring through thermal imaging, deep learning, and wearable devices facilitates non-invasive assessment of pig health, minimizing medication use. Integration of advanced sensors, thermal imaging, and deep learning shows potential for disease detection and improvement in pig farming, but challenges and ethical considerations must be addressed for successful implementation. This review summarizes the state-of-the-art technologies used in the pig farming industry, including computer vision algorithms such as object detection, image segmentation, and deep learning techniques. It also discusses the benefits and limitations of IRT technology, providing an overview of the current research field. This study provides valuable insights for researchers and farmers regarding IRT application in pig production, highlighting notable approaches and the latest research findings in this field.

Optimalisasi Citra Termal dalam Pertanian Presisi untuk Deteksi Dini Masalah Kesehatan Bibit Kelapa Sawit

The palm oil industry plays a pivotal role in various sectors, including food and bioenergy. The success of oil palm cultivation relies heavily on the health of the plant's seedlings. Early detection of diseases and stress is crucial to prevent a decline in crop yields and financial losses. Infrared Thermography technology has been widely employed across various fields for non-destructive monitoring, including agriculture. This research focuses on optimizing the use of thermal imaging in precision agriculture to early detect health issues in oil palm seedlings. Thermal imaging enables the precise measurement of plant surface temperatures, facilitating the identification of plant health issues without the need for further visual intervention. This study has the potential to transform approaches to proactively monitoring and managing the health of oil palm plants. Infrared thermography technology is utilized to observe temperature distribution patterns in oil palm seedlings. The objective is to explore the correlation between thermal characteristics and potential health issues or symptoms in these seedlings. Samples used in the research involve Tenera variety oil palm seedlings aged between 5-9 months, a critical growth phase. The study employs the UNI-T UTi120 Mobile thermal camera capable of measuring temperatures ranging from -20°C to 400°C. Subsequently, thermal image processing is conducted to identify thermal characteristics that could serve as indicators of health issues in oil palm seedlings. Statistical analysis is then performed to test significant differences in thermal characteristics between healthy and unhealthy plant samples. The analysis results reveal significant temperature variations between healthy and unhealthy portions of the plant seedlings, with a significance value of 0,025. These findings can serve as a basis for identifying temperature changes as potential early indicators of health issues in oil palm seedlings. This provides a foundation for developing more effective precision agriculture approaches within the palm oil industry.

Pig eye area temperature extraction algorithm based on registered images

The body temperature of pigs is closely related to pig diseases. People have tried various methods to use infrared thermography technology for extracting pig body temperature. However, infrared images may vary with changes in pig body temperature. When the body temperature of pigs is abnormal, these body temperature extraction methods using only infrared images may not be able to locate the target area, thereby failing to complete the body temperature extraction operation. Taking the eye area as the target area, this study proposes apig eye area temperature extraction algorithmbased on registered images. This algorithm first aligns the infrared image with the visible image using registration techniques, then uses an object detection model to locate the pig's eye area on the visible light image, and finally completes the temperature extraction by combining the infrared temperature matrix. This algorithm uses visible images to locate the pig's eye area, fully utilizing the fact that visible images do not change with temperature, which can effectively avoid the problem that the pig's eye area may not be located by using only infrared images when the pig's body temperature is abnormal. To apply the pig eye detection model to pig farms and facilitate deployment on edge devices, this study conducts lightweight modification to the model by introducing the Ghost module to modify the neck and head structures of YOLOv7-tiny. The improved algorithm effectively reduces the number of parameters and computational cost. Compared with the original YOLOv7-tiny model, themean average precisiondecreased by 0.8%, while the number of parameters andcomputational costdecreased by 42.3% and 31.5%, respectively. The detection speed of the improved algorithm on the Jetson Nano (an edge device) increased by 12.8%. The improved algorithm achieves a balance betweendetection accuracyand detection speed, making it more suitable for deployment on edge devices.

Experimental and numerical study on liquid film cooling performance under heated wall condition

Liquid film cooling is broadly applied in the thermal protection of liquid rocket engine. An experimental system of liquid film cooling for a heated curved stainless-steel wall is built in this study to investigate the effects of jet mass flow rate, jet angle, and nozzle diameter on the cooling performance. The temperature distribution of the heated wall is demonstrated with infrared thermography technology and the flow spreading shape of the liquid film is captured with high-speed camera. A numerical liquid film cooling model based on the volume of fluid (VOF) coupled Level-set method is established to calculate the evaporative heat absorption and spreading shape of liquid film. The experimental study indicates that the peak film thickness in the hydraulic jump region increases with the jet mass flow rate, such as the peak film thickness increases from 265.15 to 632.25 μm at Q = 100–600 mL·min−1. Besides, a jet angle of 35 degree can maintain the maximum wall temperature drop of 29.4 °C. In addition, the simulated peak film thickness presents a minimum deviation of 5.2 % from the experimental data. The numerical model provides important reference for the study of liquid film cooling performance of the liquid rocket engine.

Detection of Respiratory Rate of Dairy Cows Based on Infrared Thermography and Deep Learning

The respiratory status of dairy cows can reflect their heat stress and health conditions. It is widely used in the precision farming of dairy cows. To realize intelligent monitoring of cow respiratory status, a system based on infrared thermography was constructed. First, the YOLO v8 model was used to detect and track the nose of cows in thermal images. Three instance segmentation models, Mask2Former, Mask R-CNN and SOLOv2, were used to segment the nostrils from the nose area. Second, the hash algorithm was used to extract the temperature of each pixel in the nostril area of a cow to obtain the temperature change curve. Finally, the sliding window approach was used to detect the peaks of the filtered temperature curve to obtain the respiratory rate of cows. Totally 81 infrared thermography videos were used to test the system, and the results showed that the AP50 of nose detection reached 98.6%, and the AP50 of nostril segmentation reached 75.71%. The accuracy of the respiratory rate was 94.58%, and the correlation coefficient R was 0.95. Combining infrared thermography technology with deep learning models can improve the accuracy and usability of the respiratory monitoring system for dairy cows.

The application of infrared thermography technology in flap: A perspective from bibliometric and visual analysis.

The application of infrared thermography technology (IRT) in flap has become a major focus of research, as it provides a non-invasive, real-time, and quantitative approach for monitoring flap perfusion. In this regard, we conducted a comprehensive visualization and scientometric analysis to systematically summarize and discuss the current state of research in this field. We systematically reviewed publications on the application of IRT in flap procedures from 1999 to 2022, using the Web of Science Core Collection (WoSCC). Through scientometric analysis, we examined annual trends, affiliations, countries, journals, authors, and their relationships, providing insights into current hotspots and future developments in this area. We analysed 522 English studies and found a steady increase in annual publications. The United States and Germany had the highest publication rates, with Beth Israel Deaconess Medical Center and Shanghai Jiaotong University being leading institutions. Notably, Lee BT and Alex Keller emerged as influential authors in this field. Compared to existing techniques, infrared-based technology offers significant advantages for non-invasive monitoring of flap perfusion, including simplicity of operation and objective results. Future trends should focus on interdisciplinary collaborations to develop new infrared devices and achieve intelligent image processing, enabling broader application in various clinical scenarios. This bibliometric study summarizes the progress and landscape of research on 'the Application of infrared thermography technology in flap' over the past two decades, providing valuable insights and serving as a reliable reference to drive further advancements and spark researchers' interest in this field.

Design of Aeroengine Air Leak Automatic Monitoring System Based on Infrared Thermography

The aeroengine often suffers from air leaks during the test, which will affect the performance of the aeroengine, thus affecting the test task and even the test safety. In order to make up for the low efficiency and poor real-time of traditional manual detection methods for aeroengine air leaks, a design scheme for aeroengine leakage real-time automatic detection system is proposed. The system uses infrared thermography technology to collect real-time infrared information on the surface of the aeroengine during the test and then generates thermal images. The image processing technology is used to identify the leakage fault and locate the leakage location. Through the design and analysis of the system architecture, composition unit, operation principle and key technologies of the system implementation, the designed air leak monitoring system has high feasibility. Compared with traditional air leak detection methods, the system has the advantages of real-time, automaticity, remoteness, non-contact, non-destructive, simplicity, and intuitiveness, and can significantly improve the efficiency of aeroengine air leak fault detection.

Use of infrared thermography to detect reactions to stressful events: does animal personality matter?

The study of the relationship between animal stress and personality for free-ranging animals is limited and provides contrasting results. The perception of stressors by an individual may vary due to its personality, and certain personality traits may help individuals to better cope with them. Using non-invasive infrared thermography (IRT), we investigated the link between physiological and behavioral components expressed during an acute stress event by free-ranging Fremont's squirrels (Tamiasciurus fremonti). We expected that, during the acute stress event of being approached by the researcher, individuals that showed a fast pace-of-life syndrome (bolder, more active, and less social/more aggressive) based on an arena test would exhibit stronger sympathetic-adrenal-medullary system reactivity showing a more intense stress-induced hyperthermia (high core body temperature and low peripheral temperature) than individuals with a slow pace of life (shy, less active, and more social). We successfully employed IRT technology to images of Fremont's squirrels with identification of the individuals' body parts (eye, nose, ear, hind foot). However, we found no support for our hypothesis. Squirrels' body surface temperatures told us more about a squirrel's external environment and less about the thermal state of the body in that environment following a stressful event. Further studies need to assess how to make IRT effective and efficient in the field and improve its performance in studying the relationships between physiology and personality in wildlife.

Micro Calcification Detection in Mammogram Images Using Contiguous Convolutional Neural Network Algorithm

The mortality rate decreases as the early detection of Breast Cancer (BC) methods are emerging very fast, and when the starting stage of BC is detected, it is curable. The early detection of the disease depends on the image processing techniques, and it is used to identify the disease easily and accurately, especially the micro calcifications are visible on mammography when they are 0.1 mm or bigger, and cancer cells are about 0.03 mm, which is crucial for identifying in the BC area. To achieve this micro calcification in the BC images, it is necessary to focus on the four main steps presented in this work. There are three significant stages of the process assigned to find the BC using a thermal image; the image processing procedures are described below. In the first stage of the process, the Gaussian filter technique is implemented to magnify the screening image. During the second stage, BC detection is separated from the pre-processed image. The Proposed Versatile K-means clustering (VKC) algorithm with segmentation is used to identify the BC detection form of the screening image. The centroids are then recalculated using proposed VKC, which takes the mean of all data points allocated to that centroid’s cluster, lowering the overall intra-cluster variance in comparison to the prior phase. The “means” in K-means refers to the process of averaging the data and determining a new centroid. This process eliminates unnecessary areas of interest. First, the mammogram screening image information is taken from the patient and begins with the Contiguous Convolutional Neural Network (CCNN) method. The proposed CCNN is used to classify the Micro calcification in the BC spot using the feature values is the fourth stage of the process. The assess the presence of high-definition digital infrared thermography technology and knowledge base and suggests that future diagnostic and treatment services in breast cancer imaging will be developed. The use of sophisticated CCNN techniques in thermography is being developed to attain a greater level of consistency. The implemented (CCNN) technique’s performance is examined with different classification parameters like Recall, Precision, F-measure and accuracy. Finally, the Breast Cancer stages will be classified based on the true positive and true negative values.

CAD system for inter-turn fault diagnosis of offshore wind turbines via multi-CNNs & feature selection

Condition monitoring, fault diagnosis, and scheduled maintenance of wind turbines (WTs) are becoming a necessity to maximize their economic benefits and reduce their downtime. One of the critical faults in WTs is inter-turn short-circuit faults (ITSCF) in their rotating machines. Being dependent on higher wind speeds, offshore wind farms are more efficient than onshore ones, yet at the cost of higher ITSCF, more maintenance requirements, and difficulty in accessibility. Thus, they require an efficient non-contact fault diagnosis technique to enable operators to inspect all WT components with minimal contact. Among existing fault detection technologies, Infrared thermography (IRT) is considered as a non-invasive and non-destructive anomaly detection technique based on capturing thermal images by IR cameras, making it suitable for offshore harsh environments. Meanwhile, deep learning (DL) fault diagnosis approaches have proven to be promising intelligent tools with minimum human labor. This paper proposes an efficient and robust ensemble DL-based diagnosis method for ITSCF detection in induction rotating machines, besides identifying fault locations and short-circuit severity. The proposed technique is quite convenient for early diagnosis of offshore WT generator faults since it depends on IRT technology. Compared to previous studies, the proposed approach outperforms its counterparts since it integrates eight DL models, rather than using a single model, thus merging all their structural benefits altogether. Moreover, a cascaded feature fusion and selection procedure is introduced. First, the deep features extracted from the DL models are fused, then the most influential features are selected using a hybrid feature selection scheme. Thus, the classification accuracy is enhanced to reach 100% and meanwhile, the input features’ size to the classifier is reduced, decreasing classification complexity and training time. Finally, no clustering or segmentation phases are required in the proposed technique, resulting in a further decrease in the diagnosis time and computation burden.