Search results

The presence of ferrous wear debris in lubricating oil may cause progressive damage in the internal combustion engines. Online monitoring of the size and concentration of these particles in the oil is a way to optimize the engine performance and its life cycle.

In this study, an online sensor was designed and fabricated to identify ferrous wear particles in the engine oil based on the induction method. The diameter of the sensor outlet duct was designed as small as possible to generate a high-intensity magnetic induction and achieve a proper sensitivity in the sensor. The experiments were designed and performed in offline mode. Furthermore, to evaluate the actual performance of the sensor in presence of iron particles in the oil, online tests were performed at different sizes and concentrations.

It was concluded from offline tests that the highest sensitivity of the sensor occurs at the frequency and voltage of 2.5 kHz and 120 V, respectively. According to the results of the online tests, the larger the particle size, the higher the peaks at the sensor output. Also, a high density of the peaks was observed in the sensor output graphs as the concentration of particles was increased.

The proposed sensor was able to identify ferrous wear particles larger than 125 µm separately, which is the failure limit in the internal combustion engines.

The involvement of wear, friction and lubrication in engineering systems and industrial applications makes it imperative to study the various aspects of tribology in relation with advanced technologies and concepts. The concept of Industry 4.0 and its implementation further faces a lot of barriers, particularly in developing economies. Real-time and reliable data is an important enabler for the implementation of the concept of Industry 4.0. For availability of reliable and real-time data about various tribological systems is crucial in applying the various concepts of Industry 4.0. This paper aims to attempt to highlight the role of sensors related to friction, wear and lubrication in implementing Industry 4.0 in various tribology-related industries and equipment.

A through literature review has been done to study the interrelationships between the availability of tribology-related data and implementation of Industry 4.0 are also discussed. Relevant and recent research papers from prominent databases have been included. A detailed overview about the various types of sensors used in generating tribological data is also presented. Some studies related to the application of machine learning and artificial intelligence (AI) are also included in the paper. A discussion on fault diagnosis and cyber physical systems in connection with tribology has also been included.

Industry 4.0 and tribology are interconnected through various means and the various pillars of Industry 4.0 such as big data, AI can effectively be implemented in various tribological systems. Data is an important parameter in the effective application of concepts of Industry 4.0 in the tribological environment. Sensors have a vital role to play in the implementation of Industry 4.0 in tribological systems. Determining the machine health, carrying out maintenance in off-shore and remote mechanical systems is possible by applying online-real-time data acquisition.

The paper tries to relate the pillars of Industry 4.0 with various aspects of tribology. The paper is a first of its kind wherein the interdisciplinary field of tribology has been linked with Industry 4.0. The paper also highlights the role of sensors in generating tribological data related to the critical parameters, such as wear rate, coefficient of friction, surface roughness which is critical in implementing the various pillars of Industry 4.0.

Engine oil degrades in quality during its use and after certain period of time the oil needs to be changed depending upon its condition. The purpose of this paper is to design and develop an online condition monitoring device for engine oil.

Based on the previous works in this line and some testing of used oils in the laboratory, the correlation of change in colour with other properties were identified. An optical colour sensor was then designed and developed which can transform the darkness of oil colour into electrical resistance. A series of tests were undertaken to calibrate the system for its correctness.

This type of sensor provides the information about the condition of the oil and also can inform about the probable time for drain‐off of the oil.

Engine oil changes are normally done by schedules which are highly conservative and cost the user as the oil is changed when it could be still used for some time. Use of an online sensor will minimize the cost on lubricants to some extent.

The device is of great value to the users of IC engines as it not only reduces the cost on lubricants but also informs the user about the present condition of the oil.

This paper aims to discuss an online sensor-based support system which is believed to be useful for persons with a cognitive impairment, such as those with Alzheimer’s disease, suffering from deficiencies in cognitive skills which reduce their independence. Such patients can benefit from the provision of further assistance such as reminders for carrying out instrumental activities of daily living (iADLs).

The system proposed processes data from a network of sensors that have the capability of sensing user interactions and ongoing iADLs in the living environment itself. A probabilistic learning model is built that computes joint probability distributions over different activities representing users’ behavioural patterns in performing activities. This probability model can underpin an intervention framework that prompts the user with the next step in the iADL when inactivity is being observed. This prompt for the next step is inferred from the conditional probability, taking into consideration the iADL steps that have already been completed, in addition to contextual information relating to the time of day and the amount of time already spent on the activity. The originality of the work lies in combining partially observed sensor sequences and duration data associated with the iADLs. The prediction of the next step is then adjusted as further steps are completed and more time is spent towards the completion of the activity; thus, updating the confidence that the prediction is correct. A reminder is only issued when there has been sufficient inactivity on the part of the patient and the confidence is high that the prediction is correct.

The results verify that by including duration information, the prediction accuracy of the model is increased, and the confidence level for the next step in the iADL is also increased. As such, there is approximately a 10 per cent rise in the prediction performance in the case of single-sensor activation in comparison to an alternative approach which did not consider activity durations. Thus, it is concluded that incorporating progressive duration information into partially observed sensor sequences of iADLs has the potential to increase performance of a reminder system for patients with a cognitive impairment, such as Alzheimer’s disease.

Activity duration information can be a potential feature in measuring the performance of a user and distinguishing different activities. The results verify that by including duration information, the prediction accuracy of the model is increased, and the confidence level for the next step in the activity is also increased. The use of duration information in online prediction of activities can also be associated to monitoring the deterioration in cognitive abilities and in making a decision about the level of assistance required. Such improvements have significance in building more accurate reminder systems that precisely predict activities and assist its users, thus, improving the overall support provided for living independently.

The purpose of this paper is to discuss an online sensor-based support system which the authors believe can be useful in such scenarios. Persons with a cognitive impairment, such as those with Alzheimer’s disease, suffer from deficiencies in cognitive skills which reduce their independence; such patients can benefit from the provision of further assistance such as reminders for carrying out instrumental activities of daily living (IADLs).

The system proposed processes data from a network of sensors that have the capability of sensing user interactions and on-going IADLs in the living environment itself. A probabilistic learning model is built that computes joint probability distributions over different activities representing users’ behavioural patterns in performing activities. This probability model can underpin an intervention framework that prompts the user with the next step in the IADL when inactivity is being observed. This prompt for the next step is inferred from the conditional probability taken into consideration the IADL steps that have already been completed, in addition to contextual information relating to the time of day and the amount of time already spent on the activity. The originality of the work lies in combining partially observed sensor sequences and duration data associated with the IADLs. The prediction of the next step is then adjusted as further steps are completed and more time is spent towards the completion of the activity, thus updating the confidence that the prediction is correct. A reminder is only issued when there has been sufficient inactivity on the part of the patient and the confidence is high that the prediction is correct.

The results of this study verify that by including duration information the prediction accuracy of the model is increased and the confidence level for the next step in the IADL is also increased. As such, there is approximately a 10 per cent rise in the prediction performance in the case of single sensor activation in comparison to an alternative approach which did not consider activity durations.

Duration information to a certain extent has been widely ignored by activity recognition researchers and has received a very limited application within smart environments.

This study concludes that incorporating progressive duration information into partially observed sensor sequences of IADLs has the potential to increase performance of a reminder system for patients with a cognitive impairment, such as Alzheimer’s disease.

The purpose of this paper is to develop a maintenance decision support system (DSS) framework using in-service lubricant data for fault diagnosis. The DSS reveals embedded patterns in the data (knowledge discovery) and automatically quantifies the influence of lubricant parameters on the unhealthy state of the machine using alternative classifiers. The classifiers are compared for robustness from which decision-makers select an appropriate classifier given a specific lubricant data set.

The DSS embeds a framework integrating cluster and principal component analysis, for feature extraction, and eight classifiers among them extreme gradient boosting (XGB), random forest (RF), decision trees (DT) and logistic regression (LR). A qualitative and quantitative criterion is developed in conjunction with practitioners for comparing the classifier models.

The results show the importance of embedded knowledge, explored via a knowledge discovery approach. Moreover, the efficacy of the embedded knowledge on maintenance DSS is emphasized. Importantly, the proposed framework is demonstrated as plausible for decision support due to its high accuracy and consideration of practitioners needs.

The proposed framework will potentially assist maintenance managers in accurately exploiting lubricant data for maintenance DSS, while offering insights with reduced time and errors.

Advances in lubricant-based intelligent approach for fault diagnosis is seldom utilized in practice, however, may be incorporated in the information management systems offering high predictive accuracy. The classification models' comparison approach, will inevitably assist the industry in selecting amongst divergent models' for DSS.

This paper aims to investigate the effect of misalignment on wear of spur gears and on oil degradation using online sensors.

The misalignment effect on gears is created through a self-alignment bearing, and is measured using laser alignment system. Several online sensors such as Fe-concentration sensor, moisture sensor, oil condition sensor, oil temperature sensor and metallic particle sensor are installed in the gear test rig to monitor lubricant quality and wear debris in real time to assess gearbox failure.

Offset and angular misalignments are detected in both vertical and horizontal planes. The failure of misaligned gear is observed at both the ends and on both the surfaces of the gear teeth. Larger-size ferrous and non-ferrous particles are traced by metallic particle sensor due to gear and seal wear caused by misalignment. Scanning electron microscope (SEM) images examine chuck, spherical and flat platelet particles, and confirm the presence of fatigue (pitting) and adhesion (scuffing) wear mechanism. Energy-dispersive X-ray spectroscopy analysis of SEM particles traces carbon (C) and iron (Fe) elements due to gear failure.

Gear misalignment is one of the major causes of gearbox failure and the lubricant analysis is as important as wear debris analysis. A reliable online gearbox condition monitoring system is developed by integrating wear and oil analyses for misaligned spur gear pair in contact.

Advancements in real-time water monitoring technologies permit rapid detection of water quality, and threats from waste loads. Water Framework Directive mandating the establishment of Member States’ water resources monitoring, presence of hazardous contaminants in effluents, and perception of vulnerability of water distribution system to attacks, have spurred technical and economic interests. The paper aims to discuss these issues.

As alternative to traditional analyzers, chemosensors, operate according to physical principles, without sample collection (online), and are capable of supplying parameter values continuously and in real-time. Their low selectivity and stability issues have been overcome by technological developments. This review paper contains a comprehensive survey of existing and expected online monitoring technologies for measurement/detection of pollutants in water.

The state-of-the-art in online water monitoring is presented. Application examples are reported. Monitoring costs will become a lesser part of a water utility budget due to the fact that automation and technological simplification will abate human cost factors, and reduce the complexity of laboratory procedures.

An overview of applicable instrumentation, and forthcoming developments, is given. Technological development in this field is very rapid, and astonishing advances are anticipated in several areas (fingerprinting, optochemical sensors, biosensors, molecular techniques). Online monitoring is becoming an ever-important tool not only for compliance control or plant management purposes, but also as a useful approach to pollution control and reduction, minimizing the environmental impact of discharges.

Minimizing the energy consumption in a wireless sensor node is important for lengthening the lifetime of a battery. Radio transmission is the most energy-consuming task in a wireless sensor node, and by compressing the sensor data in the online mode, it is possible to reduce the number of transmission periods. This study aims to demonstrate that temporal compression methods present an effective method for lengthening the lifetime of a battery-powered wireless sensor node.

In this study, the energy consumption of LoRa-based sensor node was evaluated and measured. The experiments were conducted with different LoRaWAN data rate parameters, with and without compression algorithms implemented to compress sensor data in the online mode. The effect of temporal compression algorithms on the overall energy consumption was measured.

Energy consumption was measured with different LoRaWAN spreading factors. The LoRaWAN transmission energy consumption significantly depends on the spreading factor used. The other significant factors affecting the LoRa-based sensor node energy consumption are the measurement interval and sleep mode current consumption. The results show that temporal compression algorithms are an effective method for reducing the energy consumption of a LoRa sensor node by reducing the number of LoRa transmission periods.

This paper presents with a practical case that it is possible to reduce the overall energy consumption of a wireless sensor node by compressing sensor data in online mode with simple temporal compression algorithms.

The mechanical facilities of large-scale buildings have many complexities, so facility management (FM) encounters a massive amount of information during the operation, and inspection is not implemented efficiently. This study aims to integrate building information modeling (BIM), augmented reality (AR) and sensors to mitigate the operation and maintenance (O&M) problems of mechanical facilities by establishing intelligent management.

The component-level data of an under-construction commercial complex were implemented in a 3D model in Autodesk Revit and Navisworks. Then, sensors were installed in mechanical facilities to provide vital online information for the model. Moreover, Unity was used on Vuforia for the AR visualization of the devices.

It was found that FM not only could obtain building information but can also visualize the functioning of mechanical facilities online through a 3D model in BIM. Thus, in the case of a failure, the AR platform is used on tablets, smartphones and smart glasses to show the technician how mechanical facilities can be repaired and maintained.

Previous studies focused on some factors and processes to improve mechanical FM and did not cover the entire aspect. However, this method reduces the average maintenance time, extends the lives of mechanical devices and prevents unpredicted failures.