Predictive Maintenance Activities Research Articles

Thermal transfer analysis of machines used for the treatment of textile materials

The present paper aims to introduce a comprehensive thermal analysis of the sizing-finishing machine (Squeezing Pader Machine) to identify the overheating areas to organise maintenance activities. As there is no universal application for checking the condition of a machine, specific methods must be used depending on the characteristics of the machines being monitored, as machine condition monitoring is very important in terms of productivity, economic benefits and maintenance. The thermal analysis of the equipment in this work paper, has an important role (for planning maintenance activities), because this machine ensures optimal loading with different material treatment solutions, intended for mattresses, according to customer requirements. In the present paper, the authors conducted research on the whole technological flow to plan predictive maintenance activities using online monitoring methods. The mathematical modelling of the data obtained from the thermal analysis of the engines carried out based on the polynomial regression is used to predict the evolution of the temperatures along the analysed lines outside the measurement interval for each engine analysed. In this sense, the authors propose online monitoring of the motors that have the role of stretching and transporting the material, which is not included in the real-time temperature monitoring in the machine software, as the rest of the motors are monitored. Regular monitoring of motors with the help of thermography can help identify potential problems before they become serious, allowing preventive maintenance to improve the equipment’s reliability and efficiency.

Determining a Reliability Centered Maintenance (RCM) analysis model for large diameter prestressed concrete water pipelines

Which maintenance task to perform on an asset is generally known but the schedule of when to perform the task may not be well defined. If the task is performed early, while it may benefit the asset, it may also be expending resources that could be better used elsewhere. If the task is not performed soon enough, the asset may fail, or the asset may require more extensive maintenance be performed. Reliability Centered Maintenance (RCM) is an analysis process used to determine the most effective maintenance strategies. RCM analysis can help an agency establish the most cost effective maintenance strategies for an asset and help establish the best schedule for implementing those strategies. The ultimate goal of an RCM is to determine the required function of an asset with the required reliability at the lowest operation and maintenance costs by identifying revealing indicators of potential failures to establish a condition based strategy; essentially, predicting failures and identifying procedures to minimize the risk of the failure. This paper reviews potential models for predicting the progression of distress of prestressed concrete pipe segments for use in an RCM analysis and proposes a regression model operators can use to forecast when to perform maintenance activities. The paper further considers the condition of the drinking water infrastructure in the United States, developing the case for evaluating predictive models to forecast when a pipeline may reach a specified limit state. The results of this study suggest that RCM analyses for large diameter water pipelines can improve reliability, reduce maintenance costs, and extend the useful life of a pipeline regardless of age or material. Further, using a regression style model with gathered data can be used to forecast when specific maintenance thresholds may be reached, prompting predictive maintenance actions.

Microwave Structural Health Monitoring of the Grouted Connection of a Monopile-Based Offshore Wind Turbine: Fatigue Testing Using a Scaled Laboratory Demonstrator

Offshore wind turbines play a significant role in the expansion of clean and renewable energy. However, their exposure to harsh marine environments and dynamic loading conditions poses significant challenges to their structural integrity. In particular, the grouted connection, serving as the crucial interface between the monopile and the transition piece, is susceptible to cracking and particle washout that can lead to destabilizing grout erosion over time. In this paper, we propose a microwave structural health monitoring (SHM) approach for damage detection in grouted connections based on a stepped-frequency continuous wave radar. The methodology exploits ultra-wideband (UWB) electromagnetic wave propagation in the frequency range from 100 MHz to 2 GHz, where the microwaves propagate along the concrete-type dielectric material guided by the surrounding steel cylinders. For the proof of concept, a scaled laboratory demonstrator was built that realistically models the dynamic loading experienced by a full-scale monopile. The structure was equipped with an UWB radar system using two transmitting and three receiving antennas directly coupled to the grout. For validation, a large number of other sensors, i.e., accelerometers, strain gauges, and acoustic emission sensors have also been installed and measured synchronously during the fatigue test. It is demonstrated here that the proposed SHM methodology offers a nondestructive and real-time method for assessing the structural integrity of the grouted connection directly, actively, and automatically. This has the potential to support predictive maintenance activities in the future.

Implementation of a reliability cell in a natural gas treatment unit

Maintenance management in large companies is essential to ensure the continuous, safe and efficient operation of their complex systems and assets. The implementation of reliability cells plays a crucial role in this context. These cells are multidisciplinary teams dedicated to improving equipment reliability through data analysis, performance monitoring, predictive maintenance, and preventive actions. By adopting this approach, companies can proactively identify potential failures, minimize unplanned downtime, and extend asset life. Furthermore, reliability cells contribute to worker safety, reduced operating costs and increased market competitiveness, making them a crucial tool in the management of large companies. In this context, the implementation of the security cell aims to improve and solve problems in a simplified way, through strategic planning. Through data validation, performance, and disclosure with their pre-determined deadlines for each subsystem of the unit, corrective maintenance was minimized, and preventive and predictive maintenance were improved, generating maximum equipment availability.

LIGHTING MAINTENANCE MANAGEMENT THROUGH IOT-BASED AUTOMATED FAULT DIAGNOSTICS

Monitoring building assets is fundamental for preventing failures during building utilization. This practice is performed in predictive maintenance activities, which are based on asset monitoring using sensors to predict and avoid failures. Even if it has been demonstrated how asset monitoring can save costs, time and reduce breakdowns, it is still rarely used in common practice by facility managers. This paper proposes a framework for monitoring lighting systems to predict failures and intervene before their occurrence. The monitoring system is composed of sensors that capture temperature, voltage, electrical power and current data from lighting systems. The system can compare the data gathered with the expected value and, if anomalies are detected, it sends a maintenance request or, in case of an emergency, can actuate the shutdown of the device and schedule emergency maintenance. Furthermore, a fault detection diagram is illustrated based on the more common failures detected in lighting systems. The proposed framework provides the theoretical foundation for the development of a system for laboratory experiments.

Proposal of a predictive and preventive maintenance plan in electrical substations through the use of thermography

The objective of this study was to make a proposal for a predictive and preventive maintenance plan in the electrical substations La Propicia, Las Palmas, and La Pradera belonging to CNEL-EP Esmeraldas Business Unit through the use of thermography. The methodology was of a qualitative approach, under the type of documentary-bibliographical research. The search for information was carried out online in scientific and academic databases. It was found that the information on the maintenance plans in the subtransmission system of CNEL EP Esmeraldas Business Unit, is meager, preventive and predictive maintenance actions are carried out such as revision, washing, readjustment and replacement of elements in poor condition, but no information was found on the analysis technique used leading to the maintenance activities of electrical equipment and installations. The results of the consulted investigations agree that the thermographic technique and its tools such as drones, infrared cameras and software programs are very useful for the diagnosis, collection and processing of data in electrical systems to determine maintenance requirements. Finally, the investigation yielded substantial information that allowed the preparation of a maintenance plan for the aforementioned La Propicia, Las Palmas and La Pradera electrical substations of CNEL-EP Esmeraldas Business Unit through the use of infrared thermography, to assist in their better operation. and performance by allowing the evaluation of the state of the equipment that makes up the electrical system of the aforementioned substations.

Decision Support System for Predictive Maintenance

Predictive maintenance (PdM) is having vital importance in achieving optimum business objectives in industrial processes. Adapting to appropriate maintenance system is the necessity of today’s corporate world in view of cutthroat competitions for maximizing profits. A decision support system (DSS) added with PdM activities helps achieve organizational goals in structured manner. Bayesian Networks (BN) and Influence Diagrams (ID) have got unique features to be used in DSS. The present work uses these tools to develop a DSS for PdM of industrial equipment.

A Predictive Maintenance System Design and Implementation for Intelligent Manufacturing

The importance of predictive maintenance (PdM) programs has been recognized across many industries. Seamless integration of the PdM program into today’s manufacturing execution systems requires a scalable and generic system design and a set of key performance indicators (KPIs) to make condition monitoring and PdM activities more effective. In this study, a new PdM system and its implementation are presented. KPIs and metrics are proposed and implemented during the design to enhance the system and the PdM performance monitoring needs. The proposed system has been tested in two independent use cases (autonomous transfer vehicle and electric motor) for condition monitoring applications to detect incipient equipment faults or operational anomalies. Machine learning-based data augmentation tools and models are introduced and automated with state-of-the-art AutoML and workflow automation technologies to increase the system’s data collection and data-driven fault classification performance.

Feature extraction and health status prediction in PV systems

Diagnosis aims at predicting the health status of components and systems. In photovoltaic systems, it is vital to guarantee energy production and extend the useful life of photovoltaic power plants. Multiple prediction and classification algorithms have been proposed for this purpose in the literature. The accuracy of these algorithms depends directly on the quality of the data and the features with which they are tuned or trained. In this paper, an innovative approach for predicting the health status of photovoltaic systems is proposed, which includes a feature selection stage. This approach first discriminates severely affected photovoltaic panels using basic electrical features. In a second step, it discriminates the other faulty panels using more elaborated time–frequency features and selecting the most relevant features through correlation and variance analysis. Finally, the approach predicts the health status of photovoltaic panels using a nonlinear regression method named partial least squares. This later is then combined with linear discriminant analysis and compared. The approach is validated with real current data from a photovoltaic plant composed of twelve photovoltaic panels with power between 205 and 240 Wp in three health states, namely broken glass, healthy, and big snail trails. The results obtained show that the proposed approach efficiently predicts the three health states. It determines the level of degradation of the panels, which indicates priorities to corrective and predictive maintenance actions. Furthermore, it is cost-effective since it uses only electrical measurements that are already available in standard photovoltaic data acquisition systems. Above all, the approach is generic and it can be easily extrapolated to other diagnosis problems in other domains.

An approach for joint scheduling of production and predictive maintenance activities

The Industry 4.0 paradigm, thanks to the deployment of cutting-edge technologies enabling the deployment of new services, contributes to improve the agility of productive organizations. Among these services, the Prognostic and Health Management (PHM) contributes to the health assessment of the manufacturing resources and to prognose their future conditions by providing decision supports for production and predictive maintenance management. However, the future conditions of technical production resources depend on the productive tasks they will have to carry out. If their future conditions will not satisfy production criteria, maintenance tasks will have to be planned and productive tasks will be delayed or assigned to other resources for which their future conditions considering these new tasks must be assessed. In this context, a multi-agent system SCEMP (Supervisor, Customers, Environment, Maintainers and Producers) is here proposed in which production scheduling and predictive maintenance planning collaborate and exploit decision supports provided by PHM modules. The proposed multi-agent system provides a framework in which production and the predictive maintenance activities can be scheduled simultaneously by compromising on their objectives. During the scheduling process, SCEMP enables to identify the needed predictive maintenance from the assignments of production tasks to machines, the machine component prognoses and machine models. It schedules production tasks and predictive maintenance activities according to the number, competencies and availabilities of production and maintenance resources. The SCEMP framework is described and presented in the tough job shop context. For this context, case studies have been generated and scheduled within acceptable computation times. To illustrate the SCEMP functioning, some case studies are detailed with the obtained performances. It is flexible and can be adapted to various manufacturing situations. It can also be used to assess the interest of implementing prognostic functions for machine components.

Automatic grouping of production data in Industry 4.0: The use case of internal logistics systems based on Automated Guided Vehicles

Automated Guided Vehicles (AGVs) have become an indispensable component of Flexible Manufacturing Systems. AGVs are also a huge source of information that can be utilised by the data mining algorithms that support the new generation of manufacturing. This paper focuses on data preprocessing, aggregation, and clustering in the new generation of manufacturing systems that use the agile manufacturing paradigm and utilise AGVs. This paper presents a method by which it is possible to automatically detect the types of work performed by an AGV based on streaming information. The paper presents a comparison of results obtained with two different classical clustering algorithms: K-Means and DBScan. As the results show, using at least one of the proposed algorithms, it is possible to automatically detect the types of work performed by AGVs and to detect new, previously unknown types. Additionally, to a limited extent, it is possible to identify anomalies using this method. The proposed methodology can be used as the initial step for production optimisation, predictive maintenance activities, production technology verification, or as a source of models for the simulation tools that are used in virtual factories. This is an extended version of the ‘Data preprocessing, aggregation and clustering for agile manufacturing based on Automated Guided Vehicles’ paper [43].

Assessing the Performance of Multi-Resolution Satellite SAR Images for Post-Earthquake Damage Detection and Mapping Aimed at Emergency Response Management

The increasing availability of satellite Synthetic Aperture Radar (SAR) images is opening new opportunities for operational support to predictive maintenance and emergency actions. With the purpose of investigating the performances of SAR images characterized by different geometric resolutions for post-earthquake damage detection and mapping, we analyzed three SAR image datasets (Sentinel-1, COSMO-SkyMed Spotlight, and COSMO-SkyMed StripMap) available in Norcia (Central Italy) that were severely affected by a strong seismic sequence in 2016. By applying the amplitude and the coherent change detection processing tools, we compared pairs of images with equivalent features collected before and after the main shock on 30 October 2016 (at 06:40, UTC). Results were compared against each other and then measured against the findings of post-earthquake field surveys for damage assessment, performed by the Italian National Fire and Rescue Service (Corpo Nazionale dei Vigili del Fuoco—CNVVF). Thanks to the interesting and very rare opportunity to have pre-event COSMO-SkyMed Spotlight images, we determined that 1 × 1-m nominal geometric resolutions can provide very detailed single-building damage mapping, while COSMO-SkyMed StripMap HIMAGE images at 3 × 3-m resolutions return relatively good detections of damaged buildings; and, the Sentinel-1 images did not allow acquiring information on single buildings—they simply provided approximate identifications of the most severely damaged sectors. The main outcomes of the performance investigation we carried out in this work can be exploited considering the exponentially growing satellite market in terms of revisit time and image resolution.

Predicting remaining useful life of turbofan engines using degradation signal based echo state network

Abstract The field of Prognostics and Health Management (PHM) in industries is gaining greater popularity to achieve high reliability by shifting the preventive maintenance to predictive maintenance. Estimation of Remaining Useful Life (RUL) is an effective prognostic measure that forecasts the health state of machine based on degradation modelling and condition monitoring. This article proposes a novel and robust methodology that uses Reduced Affinity Propagation (RAP) clustering technique that extracts representatives from the temporal signals measured through various heterogeneous sensors to predict the RUL using Echo State Network (ESN) with dynamic lateral inhibiting connections. The main advantage of the proposed model is that it does not overlook the features from the degradation signals and also learns the natural mapping among the representative points from the integrated sensor value. This approach is verified using CMAPPS dataset to show hopeful results in predicting the RUL of aircraft turbo fan engine. Also, this methodology can be a deployed as a tool in real time industrial applications to schedule predictive maintenance activities.

ANALISIS KINERJA PMS REL 2 BAY TRAFO 6 MENGGUNAKAN THERMOVISION METHODE DI GARDU INDUK SUNYARAGI

In an effort to provide reliable and efficient electrical energy, substations have an important role in regulating the demand for electric power loads and as a center for securing electrical power system components in a certain area. Frequent disturbances become a benchmark for an electric power system whether or not it is good or not in an effort to provide reliable and efficient energy. One of the maintenance measures is temperature measurement using thermal imagers, which is commonly referred to as thermovision measurement.Thermal imager is a tool that can be used for predictive maintenance activities to monitor the condition and performance of an equipment so that the possibility of equipment failure can be minimized. In October 2020, after thermovisiting transformer bay 6 at the Sunyaragi substation, it was discovered that there was a hotspot on the T-phase separation blade, causing heating of the blade, the above conditions can result in a decrease in PMS performance, with the worst condition if left alone can result in damage to the PMS blade and can also melt when the peak load is on the transformer 6. Under these conditions, maintenance is carried out by maintaining contact resistance, insulation resistance, and grounding resistance. The results of the analysis of contact resistance after maintenance show that the equipment is in good condition and still suitable for use, with a value of 7μΩ for the R phase, 6.5μΩ for the S phase, and 6.7μΩ for the T phase.

Maintenance Plan Based on TPM for Turbine Recovery Machinery

The maintenance and repair of the components of hydroelectric turbines require the use of specialized equipment. To keep these teams operational, it is proposed to design a master plan in order to develop a TPM philosophy for a vertical turning lathe. This project develops five of the twelve steps established by JIPM for the TPM implementation. This paper also provides the necessary documentation for 5S and autonomous maintenance applications. Also, some safety, health and environmental suggestions are provided. PM activities are chosen based on RCM techniques like CA and FMEA. And predictive maintenance activities are established following ISO 3655, 2006. All these activities including automotive maintenance ones are organized and scheduled. Finally, OEE rate is applied to the lathe to identify the principal losses on the machine. After applying this proposal there is an increase of 27.84% and 39.71% in availability and performance respectively. The OEE calculation has increased by 29.97%, thereby motivating readers to implement this methodology in other industries.

High Temperature VLRA Lead Acid Battery SOH Characterization Based on the Evolution of Open Circuit Voltage at Different States of Charge

This work presents the results of experimental analysis of the correlation between open-circuit voltage at 0% and the state of charge of a set (3 × 6) of high-temperature valve-regulated lead acid batteries, which provides a valuable health diagnosis tool when performing predictive maintenance actions. The proposed test could be executed after any emergency event in the battery system. It offers an alternative to the integration ampere hours, simplifying the diagnostic system, and can be used in many applications where the diagnosis can be made by monitoring the discharge voltage to a defined controlled value. By testing three different sealed, high-temperature lead acid battery models, it has been proved that open-circuit-voltage measurement at 0% state of charge is valid to evaluate health status and is applicable to different manufactures. In addition, the first derivative value calculation of the relaxation voltage over time provides accurate correlation with the state of health of the battery. The method proposed minimizes diagnosis times providing an easier way to implement the method in real systems.

Bayesian Monte Carlo approach for developing stochastic railway track degradation model using expert-based priors

In the present paper, a novel method is proposed to consider the inherent uncertainties in railway track degradation model using data from eliciting expert prior beliefs in the Bayesian framework. This leads the infrastructure manager to more integrated and updatable maintenance decisions. Despite the extensive observation of this phenomenon in the literature, there are still growing appeals to consider the effect of several variables on the degradation model. Moreover, implementing prior experience and data in maintenance decisions have rarely been studied directly. To illuminate this uncharted area, Bayesian approach with informative priors is put forward. Since experts are thoroughly conversant with the actual behaviour of the system, systematic questionnaires were designed to elicit their experience comprehensively and to construct informative priors. Subsequently, by collecting further inspection data from the network, posterior distributions for the parameters have been estimated. Accordingly, the probability that a track section hits the threshold values in a specific time is calculated using Monte Carlo simulations. To show the feasibility, comprehensive case studies were presented, and the potential impacts of this methodology in outsourcing maintenance contracts are highlighted. The results have significant implications on the allocation of limited budget and resources for scheduling predictive maintenance actions.

Adaptive and noncyclic preventive maintenance to augment production activities

PurposeProduction schedules, if not met as per timelines may result in heavy losses to a company in terms of its standing and the overall profit. Production scheduling is generally planned by not taking preventive maintenance schedules into consideration. Most of the plants allocate discrete hours/time for preventive maintenance activities. These hours allocated for preventive maintenance will be in addition to the hours which would be lost during breakdown maintenance. These lost hours may be reduced if production scheduling and preventive maintenance activities are integrated. This advocates that we need to devise a methodology which can take care of lost hours.Design/methodology/approachAdaptive and noncyclic maintenance strategy describes the modification of existing maintenance practices, policies and procedures to meet new dynamic tasks/opportunities. It demands a high degree of flexibility and mental agility from maintenance staff members. The maintenance team has to be on a lookout for an opportunity message received from the central server and has to act promptly. The moment an opportunity arises, a message is forwarded to a central maintenance server (opportunity is captured). The central server then assigns individuals/team, based on their expertise and the maintenance task due on that machine/equipment. This action is completely automated and implemented without delay.FindingsThe total man-hours saved by executing adaptive and noncyclic preventive maintenance methodology comes to 705 h during 15 days on 30 machines installed in three different sections. There was a contribution of 71 innovative ideas from the repair teams. Out of these 71 innovative ideas, 16 were found suitable for execution. A quantum jump in the morale and motivation of the maintenance team was noticed from the feedback forms. Mutual understanding and respect for each other among employees has been enhanced. The optimization of resources and infrastructure including tools, gauges, testing equipment, etc. could truly be attained.Practical implicationsThe developed adaptive and noncyclic preventive maintenance model assists in capturing lost hours and make the system proactive and lean. The suggested model optimizes the preventive and predictive maintenance activities and results in substantial saving of efforts, manpower, resources and allocated budget.Originality/valueThe adaptive and noncyclic preventive maintenance model discussed in the article is a novel approach for the optimization of resources. The technique assists in capturing lost hours and utilization of these hours for preventive maintenance tasks. The model will also encourage creative and innovative ideas from employees and take the organization toward Continual Maintenance Optimization.

A Rolling-Horizon Approach for Predictive Maintenance Planning to Reduce the Risk of Rail Service Disruptions

This article proposes a model for the risk-based scheduling of predictive maintenance activities on a railway line to intervene when a track segment has reached a certain state of degradation, thus preventing faults and possible failures. With the aim of taking into account the stochastic nature of real environments, the rail-track degradation process is represented as a stochastic process, and the failure probability is evaluated as the probability of reaching a degradation threshold. Moreover, a rolling-horizon framework is introduced to manage newly available real-time information and unpredicted faults or maintenance activity delays. Whereas the traditional scheduling models are offline models that cover the long-term horizon but neglect operational disturbances, the presented model allows for dynamic day-to-day planning and adaptation of the maintenance plan to real-time information, thereby responding to the increasing understanding of real-world processes. The optimization problem on maintenance scheduling is formulated as a mixed-integer linear programming problem based on risk minimization, in adherence to ISO 55 000 guidelines. Finally, the application of the approach to a real rail network is reported and discussed, with a focus on the planning of tamping activities at the operational level.

Channel Coordination under Predictive and Corrective Maintenance Outsourcing

With respect to Industry 4.0, predictive maintenance plays an important role in production systems. A better predictive maintenance strategy is absolutely essential to an efficient, reliable and safe production process. This study considers a supply chain that consists of a manufacturer and an external contractor wherein the manufacturer is willing to outsource the predictive maintenance activities provided by the contractor. In order to achieve channel coordination, we introduce three incentive contracts: 1) maintenance cost subsidisation contract; 2) uptime target and bonus contract; 3) uptime reward contract, which enhance the cooperation willingness of the contractor and increases profit for both parties, thereby leading to a win-win situation. We also discuss the feasibility of the contracts given improvements in the failure rate and maintenance capability. Theoretical results show that the uptime target and bonus and uptime reward contracts can achieve channel coordination under specific conditions given increases in the failures rate and maintenance capacity. Numerical results are further presented to reveal the managerial insights.