Continuous Condition Monitoring Research Articles

A predictive maintenance approach based on real-time internal parameter monitoring

Since continuous real-time components or equipment condition monitoring is not available for injection molding machines, we propose a predictive maintenance approach that uses injection molding process parameters instead of machine components to evaluate the condition of equipment. In the proposed approach, maintenance decisions are made based on the statistical process control technique with real-time data monitoring of injection molding process parameters. First, machine components or equipment of injection molding machines, which require maintenance, is identified and then injection molding process parameters, which may be affected by malfunctioning of the previously identified components, are identified. Second, regression analysis is performed to select the process parameters that significantly affect the quality of the lens and require a high degree of attention. By analyzing the patterns of real-time monitored data series of process parameters, we can diagnose the status of the components or equipment because the process parameters are affected by machine components or equipment. Third, statistical predictive models for the selected process parameters are developed to apply statistical analysis techniques to the monitored data series of parameters, in order to identify abnormal trends. Fourth, when abnormal trends or patterns are found based on statistical process control techniques, maintenance information for related components or equipment is notified to maintenance workers. Finally, a prototype system is developed to show feasibility in a LabVIEW® environment and an experiment is performed to validate the proposed approach.

Approach towards sensor placement, selection and fusion for real-time condition monitoring of precision machines

Moving mechanical parts in a machine will inevitably generate vibration profiles reflecting its operating conditions. Vibration profile analysis is a useful tool for real-time condition monitoring to avoid loss of performance and unwanted machine downtime. In this paper, we propose and validate an approach for sensor placement, selection and fusion for continuous machine condition monitoring. The main idea is to use a minimal series of sensors mounted at key locations of a machine to measure and infer the actual vibration spectrum at a critical point where it is not suitable to mount a sensor. The locations for sensors’ mountings which are subsequently used for vibration inference are identified based on sensitivity calibration at these locations moderated with normalized Fisher Information (NFI) associated with the measurement quality of the sensor at that location. Each of the identified sensor placement location is associated with one or more sensitive frequencies for which it ranks top in terms of the moderated sensitivities calibrated. A set of Radial Basis Function (RBF), each of them associated with a range of sensitive frequencies, is used to infer the vibration at the critical point for that frequency. The overall vibration spectrum of the critical point is then fused from these components. A comprehensive set of experimental results for validation of the proposed approach is provided in the paper.

Condition monitoring of railway axles based on low frequency vibrations

Railway axles are safety–critical components and their structural integrity needs to be properly monitored against potentially catastrophic failures. This paper proposes a method for the continuous condition monitoring of railway axles by measuring the axle in-service bending vibration and diagnosing the presence of a fatigue crack based on the examination of harmonic components with periodicity corresponding to an integer sub-multiple of the axle revolution period (nxRev).To analyse the feasibility of the proposed method, full-scale measurements were performed on cracked and non-cracked railway axles undergoing fatigue tests and a mathematical Finite Element (FE) model of a cracked railway axle was defined and used to reproduce the laboratory experiments and also to analyse the case of a railway wheelset with cracked axle rolling on a railway track.The results of both experimental and numerical investigations show that the 1xRev, 2xRev and 3xRev components of axle bending vibration can be used to detect the presence of cracks in axles, provided the crack area is in the range of 16% of axle cross section or larger. Hence, the proposed method cannot replace periodical non-destructive inspections, but may serve as an additional safety measure detecting cracked axles in an advanced stage of the damage process but still on time to avoid in-service failures.

Chromatic acoustic condition monitoring of transformers

Purpose – The purpose of this paper is to present an approach for continuous acoustic condition monitoring of transformers based on chromatic principles for abstracting information on individual acoustic events as well as secondary trends in the behaviour of the events. Design/methodology/approach – The potential benefits of condition monitoring of high-value transformer equipment are explored, and an approach based on chromatic information abstraction is illustrated and discussed. Findings – Tracking of large numbers of complex and variable individual acoustic events over time using a chromatic approach appears to offer a means for remote operators to evaluate mechanical transformer tap changer condition in a traceable manner. Originality/value – The condition monitoring is retrofittable and non-intrusive, and the approach may be applied generically for combining condition indicators for overall health-checking. A complex system behaviour may be operationally simplified without discarding the complexity.

Multisensor Wireless System for Eccentricity and Bearing Fault Detection in Induction Motors

This paper presents a stand-alone multisensor wireless system for continuous condition monitoring of induction motors. The proposed wireless system provides a low-cost alternative to expensive condition monitoring technology available through dedicated current signature analysis or vibration monitoring equipment. The system employs multiple sensors (acoustic, vibration, and current) mounted on a common wireless platform. The faults of interest are static and dynamic air-gap eccentricity, bearing damage, and their combinations. The Hilbert-Huang transform of vibration data and power spectral density of current and acoustic signals are used as the features in a hierarchical classifier. The proposed wireless system can distinguish a faulty motor from a healthy motor with a probability of 99.9% of correct detection and less than 0.1% likelihood of false alarm. It can also discriminate between different fault categories and severity with an average accuracy of 95%.

Increased safety and improved operation of pipelines with integrated condition sensing in flexible risers and flowlines

Continuous condition monitoring of offshore production installations is a vital part of integrity management to ensure safe operation of the asset at its optimum level for the maximum period of time. The recent implementation of fiber-optic condition monitoring embedded into the structures of flexible risers and flowlines is an important step towards turning flexible pipelines into inspectable structures. Embedded sensors enable a suite of monitoring options for both real-time response and long-term changes, which can provide a highly accurate picture of a pipeline’s condition during operation. In this paper the author reports the results from extensive full-scale testing on flexible pipes instrumented with sensors, conducted in cooperation with a major operator. The testing includes detection of a breach of the outer sheath with ingress of seawater into the annulus, remote monitoring of the location of accessories mounted on the pipe—such as buoyancy modules—monitoring of the temperature at a buried section of a pipe in the seabed, identification of hotspots, detection of breaks of tensile armor wires, and monitoring of accumulated fatigue damage in tensile armor wires during operation. Reported failure modes from flexible pipes in operation are briefly discussed to show that the major failure modes reported across all operators through the years are covered by the NOV integrated sensing systems. The detection of structural and temperature issues with integrated condition sensing in flexible pipelines will allow operators to satisfy requirements for periodic inspection, which for rigid steel pipes is performed with intelligent pigging.

Использование мониторинговых технологий в процессе разработки стратегии развития рынка гостиничных услуг (на примере Московского региона)

The necessity for continuous market condition monitoring, which is called forth by the intensive external environment dynamics, makes monitoring technologies a priority in terms of industry research. Unlike conventional marketing analysis, monitoring affords the opportunity to collect and store information over a relatively extended period of time, which provides a solid ground for and benefits the quality of managerial decision making.
 The article aims at identifying the special aspects of pre- and in-monitoring with the hotel industry targeted, and presents the monitoring procedure worked out and applied by the authors (case study: the Moscow region hotel service sector).

Air-Core Sensors Operation Modes for Partial Discharge Detection and On-line Diagnostics in Medium Voltage Networks

Abstract In this paper, sensors for the application of high voltage networks insulation diagnostics are focused on. For detection and localization of the components with insulation deterioration, observing the partial discharge transients is one of the main methods. However, as the partial discharge traces are transients of extremely short duration, monitoring of such transients is also a challenging task. This paper presents the inductive sensors that would be suitable for the on-line partial discharge monitoring and the selection of operating mode and characteristics are discussed. The issues of resonance and signal processing are analyzed for the targets of reaching highest accuracy of the measurements. Operation criteria and performance limits such as sensitivity and upper bandwidth are particularly discussed. It is presented that in order to reach highest accuracy and sensitivity the sensor should be used in damped mode. Applying the accurate air-core inductive sensors would allow the condition monitoring systems to be cheaper and thus mounted for permanent and continuous condition monitoring in various locations in the power distribution networks.

Online fault diagnosis method based on Incremental Support Vector Data Description and Extreme Learning Machine with incremental output structure

Online fault diagnosis system should be able to detect faults, recognize fault types and update the discriminating ability and knowledge of itself automatically in real time. But the class number in fault diagnosis is not constant and it is in a dynamic state with new members enrolled. The traditional recognition algorithms are not able to update diagnosis system efficiently when the class number of failure modes is increasing. To solve the problem, an online fault diagnosis method based on Incremental Support Vector Data Description (ISVDD) and Extreme Learning Machine with incremental output structure (IOELM) is proposed. ISVDD is used to find a new failure mode quickly in the continuous condition monitoring of the equipments. The fixed structure of Extreme Learning Machine is changed into an elastic structure whose output nodes could be added incrementally to recognize the new fault mode efficiently. Recognition experiments on the diesel engine under eleven different conditions show that the online fault diagnosis method based on ISVDD and IOELM works well, and the method is also feasible in fault diagnosis of other mechanical equipments.

Release of maintenance jobs in a decentralized multi-stage production/maintenance system with continuous condition monitoring

Condition-based maintenance is analyzed for multi-stage production with a separate maintenance department. It is assumed that the conditions of the machines deteriorate as a function of multiple production parameters and that the task of maintenance is to keep up predefined operational availabilities of the individual machines. In this context the problem of determining the optimal machine condition that triggers the release of a preventive maintenance job and the problem of scheduling maintenance jobs at the maintenance department arise. Existing approaches to solve these problems either assume a monolithic production/maintenance system or concentrate on a decentralized system in which the information flow and resource transfer do not cause delays. With our paper we aim at (1) deriving a triggering mechanism that is able to cope with relaxed assumptions and at (2) developing specific priority rules for scheduling maintenance jobs. Therefore, in this paper a specific continuous condition monitoring and a suitable information exchange protocol are developed, factors determining the release situation are operationalized, impacts of choosing the triggering conditions are identified and the components of specific priority rules for scheduling maintenance jobs are clearly elaborated. Finally the performance of the resulting solution approach is analyzed by simulations. Thereby, relevant characteristics of the production/maintenance system, the maintenance task and relevant priority rules are varied systematically. This research contributes answers to the questions on how the exchange of local information can be structured, the parameters of condition-based maintenance can be set and on what maintenance-specific priority rules can be applied in case of incomplete information about deterioration in a decentralized multistage production/maintenance system.

Analysis of electrical power data for condition monitoring of a small wind turbine

Certain parts of a wind turbine, for example, the gearbox require significant time and heavy lifting equipment in the event of catastrophic failure necessitating replacement. Continuous condition monitoring has the potential to catch problems early, enable scheduled preventative maintenance and thereby reduce turbine downtime, reduce the number of site visits and prevent secondary damage. Accelerometers applied to mechanical components of the drive train are traditionally used for condition monitoring, but require their own data acquisition system and analysis software. In contrast, the electrical current and voltage are continuously measured and could also be used for condition monitoring more cheaply. An experimental data acquisition system has been installed on a small (25 kW) onshore turbine in Leicestershire, UK to compare three-phase currents and voltages on the stator windings with six accelerometer signals. Data have been recorded before and after a gearbox failure and replacement. Data were analysed using both Fourier transform and Morlet continuous wavelet transform methods. Results show that the stator voltages show the same radial and axial mode vibration frequencies as the accelerometers, and could therefore be used for condition monitoring. Furthermore, the stator currents show torsional modes of vibration not picked up by the accelerometers.

Wind turbine fault detection using multiwavelet denoising with the data-driven block threshold

Rapid expansion of wind turbines has drawn attention to reduce the operation and maintenance costs. Continuous condition monitoring of wind turbines allows for early detection of the generator faults, facilitating a proactive response, minimizing downtime and maximizing productivity. However, the weak features of incipient faults in wind turbines are always immersed in noises of the equipment and the environment. Wavelet denoising is a useful tool for incipient fault detection and its effect mainly depends on the feature separation and the noise elimination. Multiwavelets have two or more multiscaling functions and multiwavelet functions. They possess the properties of orthogonality, symmetry, compact support and high vanishing moments simultaneously. The data-driven block threshold selected the optimal block length and threshold at different decomposition levels by using the minimum Stein’s unbiased risk estimate. A multiwavelet denoising technique with the data-driven block threshold was proposed in this paper. The simulation experiment and the feature detection of a rolling bearing with a slight inner race defect indicated that the proposed method successfully detected the weak features of incipient faults.

Online Particle Counter for Continuous Fluid Condition Monitoring

Online Particle Counter for Continuous Fluid Condition Monitoring

Analysis of the possibility of applying a condition-based maintenance model on an example of tank weapons

For any modern army it is very important to continuously maintain a high degree of operational (combat) readiness (availability) in order to maximize the effectiveness of the use of technical systems. Since determination and prediction of technical states and failures of technical systems in engineering, especially in armament, are difficult due to the impossibility of continuous condition monitoring with appropriate measuring equipment there is a need for a maintenance model that would be most helpful in taking timely action maintenance. In this paper, the subject of research is a model of maintenance of the M-84 tank weapoons systems. Introduction. The M-84 tank is one of the most promising technical systems in the Serbian Army. Its use and modifications are foreseen in the next ten years. The M-84 is characterized by good tactical and technical characteristics. It has a powerful 125 mm cannon, coupled 7.62 mm machine gun and 12.7 mm anti-aircraft machine gun. The M-84 tank has an automatic battery charger and a fire control system. The fire control system enables fast target tracking and stabilization of the cannon barrel, which is a prerequisite for timely and favorable effect on the target. There are certain ambiguities in the existing model of maintenance of tank weapons.

A Physically Segmented Hidden Markov Model Approach for Continuous Tool Condition Monitoring: Diagnostics and Prognostics

In this paper, a temporal probabilistic approach based on the hidden Markov model (HMM), named physically segmented HMM with continuous output, is introduced for continuous tool condition monitoring in machinery systems. The proposed approach has the advantage of providing an explicit relationship between the actual health states and the hidden state values. The provided relationship is further exploited for formulation and parameter estimation in the proposed approach. The introduced approach is tested for continuous tool wear prediction in a computer numerical control milling machine and compared with two well-established neural network (NN) approaches, namely, multilayer perceptron and Elman network. In the experimental study, the prediction results are provided and compared after adopting appropriate hyper-parameter values for all the approaches by cross-validation. Based on the experimental results, physically segmented HMM approach outperforms the NN approaches. Moreover, the prognosis ability of the proposed approach is studied.

Diagnosis of MV Power Cables for Nuclear Power Plants

The diagnosis of MV (Medium Voltage) cable used in NPPs (Nuclear Power Plants) has become one of the most urgent issues. In accordance with PSR (Periodic Safety Review) results, continuous condition monitoring of cables is also continuously required. In this paper, HFPD (High Frequency Partial Discharge) measurement and an infrared imaging thermography test were performed to check the status of 13.8 and 4.16 kV MV cables installed in the domestic power plant. The diagnosis was found to be good for the target cable. The on-line diagnostic technology to assess the condition of MV cables during the operation of a power plant will contribute to enhance the safety of NPPs. In the future, these latest technologies will be applied to perform condition monitoring of HV (High Voltage) cables in NPPs.

Importance of lubricant analysis

Monitoring the performance of lubricants in practical application has multiple significance for both the consumer and the lubricant manufacturer. The primary significance for the consumer is extended life and timely change of lubricants, which keeps the costs of maintenance down. The lubricant manufacturer gains by creating a partner relationship with the consumer, as well as creating the possibility of gathering information about the performance of his product which will serve as the foundation for its further improvement and development. If we wish to maintain technical systems so that they have minimum halts and costs caused by halt removal or system failures, we must monitor data indicating equipment condition throughout the system operation. It is especially difficult to obtain data on equipment condition for parts which cannot be observed due to their position. In such cases, the oil analysis enables a continuous equipment condition monitoring and timely response in order to prevent undesirable prolonged halts.

Monitoring lubricant performances in field application

The need for more effective maintenance and possibility of continuous exploitation of equipment has developed numerous strategies and methods for machinery maintenance. The maintenance strategy by condition, that requires continuous monitoring and equipment overlook, has initiated the development and use of lubricant analysis. Monitoring the performance of lubricants in practical application has multiple significance for both the consumer and the lubricant manufacturer. The primary significance for the consumer is extended life and timely change of lubricants, which keeps the costs of maintenance down. The lubricant manufacturer gains by creating a partner relationship with the consumer, as well as creating the possibility of gathering information about the performance of his product which will serve as a foundation for the further improvement and development of his product. If we wish to maintain technical systems so that they have as little halts and costs caused by halt removal or system failure as possible, we must monitor data indicating equipment condition throughout the system operation. It is especially difficult to obtain data on equipment condition for parts which cannot be observed due to their position. In such cases, oil analysis enables a continuous equipment condition monitoring and timely response in order to prevent undesirable prolonged halts.

Predictive maintenance techniques

This article discusses the importance of PdM for industrial process applications and investigates a number of emerging technologies that enable this approach, including online energy-efficiency evaluation and continuous condition monitoring. The article gives an overview of existing and future technologies that can be used in these areas. Two methods for bearing fault detection and energy-efficiency estimation are discussed. The article concludes with focus on one pilot installation at Weyerhaeuser's Containerboard Packaging Plant in Manitowoc, Wisconsin, USA, monitoring three critical induction motors: a 75-hrho blower motor, a 50-hrho hydraulic pump motor, and a 200-hp compressor motor. Finally, the field experience gained in this plant is presented as two case studies.

Determining moisture levels in straw bale construction

The use of straw bales for the construction of buildings in the UK has to date generally been limited to the self-build fringe sector. In order to bring this form of construction into the mainstream sector, to benefit from its inherent low carbon and high insulation characteristics, it is necessary to guarantee the long-term durability of the straw. Maintaining low moisture levels is critical to the long-term resistance of straw to biological decomposition. This paper presents results from a study on moisture monitoring in straw bale construction, and includes the development of an empirical equation which relates straw moisture content to surrounding microclimate relative humidity and temperature. This knowledge allows continuous non-invasive condition monitoring of the straw in on-going research work and potentially as part of future managed maintenance of straw bale buildings.