Gearbox faults can lead to significant damage and downtime in industrial machinery, resulting in substantial losses for manufacturers. Detection of faults in gears in the incipient state is essential to ensure safe and reliable operation of industrial machineries. In recent years, there has been an increasing interest in using machine learning algorithms to automate gearbox fault detection. This paper proposes a machine learning approach for identifying different categories of faults in a gearbox based on vibration signals. The proposed method was evaluated on a dataset of vibration signals collected from a two-stage gearbox under different operational conditions. The research is focused on developing a sequential neural network-based method for detecting multiple gear faults simultaneously. The results showed that the developed method achieved high training and validation accuracies and relatively low training and validation losses, indicating the model's ability to accurately detect and classify faults in gearboxes. The testing accuracies were also high, demonstrating the model's ability to generalize well to new data. The practical implications of the research are significant for improving the reliability and maintenance of gearboxes in various industrial applications. The developed method has the potential to reduce downtime, maintenance costs, and improve safety and efficiency.

Wheelsets form an indispensable part of the railway rolling stock and need to be periodically inspected to ensure stable, safe, reliable, and sustainable rail operation. Wheel profiles are usually inspected and measured in a workshop environment using handheld equipment or by utilizing wayside measuring equipment. A common practice for both methods is to measure the wheel profile at one position along the circumference of the wheel, resulting in a one-slice measurement strategy, based on the assumption that the wheel profile has the same shape independent of the measurement position along the wheel. In this article, the representability of a one-slice measurement strategy with respect to the wheel profile parameters is investigated using handheld measurement equipment. The calculated range of standard deviation of the parameters estimated such as flange height, flange width, flange slope, and hollow wear from the measurements shows a spread in the parameter value along the circumference of the wheel. As an initial validation of the results, measurements from the wayside monitoring systems were also investigated to see if a similar spread was visible. The spread was significantly higher for flange height, flange width, and flange slope estimated from wayside measurement equipment than for the same parameters estimated using the handheld measurement equipment.

Switches and crossings (S&Cs) are also known as turnouts or railway points. They are important assets in railway infrastructures and a defect in such a critical asset might lead to a long delay for the railway network and decrease the quality of service. A squat is a common rail head defect for S&Cs and needs to be detected and monitored as early as possible to avoid costly emergent maintenance activities and enhance both the reliability and availability of the railway system. Squats on the switchblade could even potentially cause the blade to break and cause a derailment. This study presented a method to collect and process vibration data at the point machine with accelerometers on three axes to extract useful features. The two most important features, the number of peaks and the total power, were found. Three different unsupervised machine learning algorithms were applied to cluster the data. The results showed that the presented method could provide promising features. The k-means and the agglomerative hierarchical clustering methods are suitable for this data set. The density-based spatial clustering of applications with noise (DBSCAN) encounters some challenges.

Railway switch and crossing (S&C) systems have complicated moving structures compared with regular rail. They require multiple components that vary in complexity. The complexity of railway S&C, together with the fact that they are discontinuous points of the system, makes them vulnerable to defects such as squats. A squat on the switching rail could potentially cause rail breakage and lead to catastrophic results, such as derailment. In this study, a method based on anomaly scoring was investigated to estimate the status of an S&C system with respect to squat defects. The proposed method was tested in a real environment under controlled measurement sequences. The results show that the methods can differ between an S&C with squats and another one without them.

Railway switches and crossings (S&Cs) are critical, high-value assets in railway networks. A single failure of such an asset could result in severe network disturbance and considerable economical losses. Squats are common rail surface defects of S&Cs and need to be detected and estimated at an early stage to minimise maintenance costs and increase the reliability of S&Cs. For practicality, installation of wired or wireless sensors along the S&C may not be reliable due to the risk of damages of power and signal cables or sensors. To cope with these issues, this study presents a method for collecting and processing vibration data from an accelerometer installed at the point machine to extract features related to the squat defects of the S&C. An unsupervised anomaly-detection method using the isolation forest algorithm is applied to generate anomaly scores from the features. Important features are ranked and selected. This paper describes the procedure of parameter tuning and presents the achieved anomaly scores. The results show that the proposed method is effective and that the generated anomaly scores indicate the health status of an S&C regarding squat defects.

Rail transportation is a sustainable mode of transportation and is a key enabler of the socio-economic development of modern society through passenger and freight services. Growth in overall transport demand has led to railways experiencing higher demand on operational capacity, service quality, and safety. However, an increase in traffic and load can lead to an increase in degradation of the components and thus cause a reduction in the infrastructure quality. Such degradation leads to failures of components, consequently resulting in a higher frequency of interventions for maintenance and renewal activities. The downtime arising from such maintenance and renewal of networks is a significant contributor to the delays incurred to the passengers. A plausible solution to attain higher operational capacity and quality of service with the existing infrastructure and minimise delays due to failure would be to inspect the track and its components frequently using in-service trains, operating in regular traffic. 

One of the crucial components in rail tracks is the rail fastening system, which acts as a means to fix the rails onto the sleeper, upholding the track stability and track gauge.  Failures of fasteners can increase wheel flange wear, reduce the safety of train operations, and may lead to derailment due to gage widening or wheel climb. In Sweden, the inspection of track fasteners is mainly carried out either manually by trained inspectors or by using measurement cars. Manual inspections are slow, cost-intensive, labour-intensive, pose safety issues for maintenance personal involved, and are prone to human errors. Inspections based on measurement cars are cost intensive and requires track possession and thus cannot be utilised frequently without compromising the operational capacity. Further, the adverse weather condition, especially in the north of Sweden for the majority of the year, limit regular fastener inspection that depends on such traditional inspection methods. The research presented in this thesis has aimed to find an automated method for fastener inspection that can be carried out using vehicle-mounted measuring equipment operating in regular traffic. 

Firstly, a study was carried out to determine the effectiveness of automated visual-based solutions for fastener state detection. An anomaly detection model combining image processing techniques and deep learning algorithms was developed to detect the fastener state from rail images captured during the vision-based inspection. The model had a high capability of detecting the fastener state from the rail images. However, the model had difficulties detecting the fastener when there were instances of occlusions of fasteners due to the presence of snow and ballast stones and when the image brightness was low. In Sweden, specifically the northern part of it, the fastening systems are covered under snow for up to six months and thus can inhibit regular fastener inspections that rely on such automated visual inspection methods. 

To overcome the challenges associated with automated visual inspection systems for fastener state detection, an alternative inspection method using a differential eddy current measurement system was investigated. Controlled field measurements were carried out along a heavy haul railway line in the north of Sweden to determine the effectiveness of the proposed measurement system. An anomaly detection model based on a supervised machine learning algorithm was developed to detect the fastener state from the controlled eddy current measurements. Further, to test the effectiveness of the eddy current sensor during real-time measurements, the proposed sensor system was mounted on an in-service freight train, and measurements were carried out along the iron ore line of Sweden. An anomaly detection model using unsupervised machine learning algorithms was developed to facilitate fastener state detection and detect other anomalies from the real-time measurement data.

The rail fastening system plays a crucial role in railway tracks as it ensures operational safety by fixing the rail on to the sleeper. Early detection of rail fastener system defects is crucial to ensure track safety and to enable maintenance optimization. Fastener inspections are normally conducted either manually by trained maintenance personnel or by using automated 2-D visual inspection methods. Such methods have drawbacks when visibility is limited, and they are also found to be expensive in terms of system maintenance cost and track possession time. In a previous study, the authors proposed a train-based differential eddy current sensor system based on the principle of electromagnetic induction for fastener inspection that could overcome the challenges mentioned above. The detection in the previous study was carried out with the aid of a supervised machine learning algorithm. This study reports the finding of a case study, along a heavy haul line in the north of Sweden, using the same eddy current sensor system mounted on an in-service freight train. In this study, unsupervised machine learning models for detecting and analyzing missing clamps in a fastener system were developed. The differential eddy current measurement system was set to use a driving field frequency of 27 kHz. An anomaly detection model combining isolation forest (IF) and connectivity-based outlier factor (COF) was implemented to detect anomalies from fastener inspection measurements. To group the anomalies into meaningful clusters and to detect missing clamps within the fastening system, an unsupervised clustering based on the DBSCAN algorithm was also implemented. The models were verified by measuring a section of the track for which the track conditions were known. The proposed anomaly detection model had a detection accuracy of 96.79% and also exhibited a high score of sensitivity and specificity. The DBSCAN model was successful in clustering missing clamps, both one and two missing clamps, from a fastening system separately.

The rail fastening system forms an indispensable part of the rail tracks and needs to be periodically inspected to ensure safe, reliable and sustainable rail operations. Automated visual inspection has gained significant importance for fastener inspection in recent years. Position accuracy, robustness, and practical limitations due to the complex environment are some of the major concerns associated with this method. This study investigates the combined use of image processing and deep learning algorithms for detecting missing clamps within a rail fastening system. The images used for this study was acquired during field inspections carried out along the Borlänge-Avesta line in Sweden. The image processing techniques proposed in this study enabled the improvement of the fastener position and removal of redundant information from the fastener images. In addition, image augmentation was carried out to enhance the data set, ensure experimental reliability and replicate practical challenges associated with such visual inspection. Convolutional neural network and ResNet-50 algorithms are used for classification purposes, and both the algorithms achieved over 98% accuracy during training and validation and over 94% accuracy during the test stage. Both the algorithms also maintained a good balance between the precision and recall scores during the test stage. CNN and ResNet-50 algorithms were also tested to analyse their performances when the clamp areas were covered. CNN was able to accurately predict the fastener state up to 70% of clamp area occlusion, and ResNet-50 was able to achieve accurate predictions up to 75% of clamp area occlusion.

The rail fastening system forms an integral part of rail tracks, as it maintains the rail in a fixed position, upholding the track stability and track gauge. Hence, it becomes necessary to monitor their conditions periodically to ensure safe and reliable operation of the railway. Inspection is normally carried out manually by trained operators or by employing 2-D visual inspection methods. However, these methods have drawbacks when visibility is minimal and are found to be expensive and time consuming. In the previous study, the authors proposed a train-based differential eddy current sensor system that uses the principle of electromagnetic induction for inspecting the railway fastening system that can overcome the above-mentioned challenges. The sensor system includes two individual differential eddy current sensors with a driving field frequency of 18 kHz and 27 kHz respectively. This study analyses the performance of a machine learning algorithm for detecting and analysing missing clamps within the fastening system, measured using a train-based differential eddy current sensor. The data required for the study was collected from field measurements carried out along a heavy haul railway line in the north of Sweden, using the train-based differential eddy current sensor system. Six classification algorithms are tested in this study and the best performing model achieved a precision and recall of 96.64% and 95.52% respectively. The results from the study shows that the performance of the machine learning algorithms improved when features from both the driving channels were used simultaneously to represent the fasteners. The best performing algorithm also maintained a good balance between the precision and recall scores during the test stage.

One of the crucial components in rail tracks is the rail fastening system, which acts as a means of fixing rails to the sleepers to maintain the track gauge and stability. Manual inspection and 2D visual inspection of fastening systems have predominated over the past two decades. However, both methods have drawbacks when visibility is obscured and are found to be relatively expensive in terms of cost and track possession. The present article presents the concept of a train-based differential eddy current (EC) sensor system for fastener detection. The sensor uses the principle of electromagnetic induction, where an alternating-current-carrying coil is used to create an EC on the rail and other electrically conductive material in the vicinity and a pick-up coil is used to measure the returning field. This paper gives an insight into the theoretical background and application of the proposed differential EC sensor system for the condition monitoring system of rail fasteners and shows experimental results from both laboratory and field measurements. The field measurements were carried out along a heavy-haul railway line in the north of Sweden. Results obtained from both the field measurements and from the lab tests reveal that that the proposed method was able to detect an individual fastening system from a height of 65 mm above the rail. Furthermore, missing clamps within a fastening system are detected by analysing a time domain feature of the measurement signal.