A Review of Sustainable Maintenance Strategies for Single Component and Multicomponent Equipment

A total productive maintenance & reliability framework for an active pharmaceutical ingredient plant utilising design for Lean Six Sigma

This research investigates the requirement for and relationship and implementation of a total productive maintenance (TPM) and Reliability Centred Maintenance (RCM) strategy within an Active Pharmaceutical Ingredient (API) Plant. This research aimed to study the tools and techniques of TPM and Reliability Engineering and then deploy a designed model to an API plant. A case study involving Design for Lean Six Sigma phases of Define, Measure, Analyse, Design, and Verify was utilised to build an API site TPM pilot program. Data was collected using interviews across Company 'X's local and Global Engineering teams. Process runtime, downtime and plant availability metrics were compiled and a new design for Total Productive Maintenance and Reliability was proposed and verified. A maintenance framework was designed to optimally incorporate Total Productive Maintenance, Reliability and Operational Excellence with an emphasis on Overall Equipment Efficiency (OEE) realizing a 33 % reduction in planned maintenance activities, a 70 % reduction in Corrective Maintenance, Cleaning for Maintenance was reduced by 50 %, the pilot maintenance area of the centrifuge has its OEE increased by 20 % and plant availability increased by two hundred and 6 h. This research highlights the importance of Total Productive Maintenance as a key component of an effective maintenance strategy and its potential to transform maintenance practices. Based on this research and results, TPM is recommended to be applied to any API manufacturing organization. A limitation of the study is that it is a single-site case study. The novelty of this research is based upon the emphasis on Reliability Engineering to remove non-value add Maintenance time from the manufacturing schedule. The Total Productive Maintenance & Reliability model designed and implemented in this research is unique in the literature and can be leveraged by engineering professionals and academics to understand the benefits of TPM.

Towards partial autonomy of operation and maintenance of unreliable equipment

This study considers the case of unreliable equipment subjected to random failures that induce high maintenance and environmental costs. We consider situations where the equipment is located in remote areas, which are difficult to access, and situations where there could be confinement linked to a pandemic, making it impossible to perform the replacement of the failed equipment. In such situations, the objective is to explore the possibility of providing a system with self-maintenance capabilities to a certain extent by adding redundant (stand-by) identical modules. Both the designs (with and without passive redundancy) are considered. A mathematical cost model is developed for each alternative to help decide whether to adopt redundancy and determine the optimal number of redundant modules, which minimises the total expected cost. The latter includes the costs related to the acquisition, maintenance, and recycling of failed modules. A numerical example is presented, and a sensitivity study is performed to investigate the effect of variations in relevant input parameters on the optimal design.

Exploring the Efficiencies of Spectral Isolation for Intelligent Wear Monitoring of Micro Drill Bit Automatic Regrinding In-Line Systems

Despite the increasing digitalization of equipment diagnostic/condition monitoring systems, it remains a challenge to accurately harness discriminant information from multiple sensors with unique spectral (and transient) behaviors. High-precision systems such as the automatic regrinding in-line equipment provide intelligent regrinding of micro drill bits; however, immediate monitoring of the grinder during the grinding process has become necessary because ignoring it directly affects the drill bit’s life and the equipment’s overall utility. Vibration signals from the frame and the high-speed grinding wheels reflect the different health stages of the grinding wheel and can be exploited for intelligent condition monitoring. The spectral isolation technique as a preprocessing tool ensures that only the critical spectral segments of the inputs are retained for improved diagnostic accuracy at reduced computational costs. This study explores artificial intelligence-based models for learning the discriminant spectral information stored in the vibration signals and considers the accuracy and cost implications of spectral isolation of the critical spectral segments of the signals for accurate equipment monitoring. Results from one-dimensional convolutional neural networks (1D-CNN) and multi-layer perceptron (MLP) neural networks, respectively, reveal that spectral isolation offers a higher condition monitoring accuracy at reduced computational costs. Experimental results using different 1D-CNN and MLP architectures reveal 4.6% and 7.5% improved diagnostic accuracy by the 1D-CNNs and MLPs, respectively, at about 1.3% and 5.71% reduced computational costs, respectively.

Modeling and Fault Detection of Brushless Direct Current Motor by Deep Learning Sensor Data Fusion

Only with new sensor concepts in a network, which go far beyond what the current state-of-the-art can offer, can current and future requirements for flexibility, safety, and security be met. The combination of data from many sensors allows a richer representation of the observed phenomenon, e.g., system degradation, which can facilitate analysis and decision-making processes. This work addresses the topic of predictive maintenance by exploiting sensor data fusion and artificial intelligence-based analysis. With a dataset such as vibration and sound from sensors, we focus on studying paradigms that orchestrate the most optimal combination of sensors with deep learning sensor fusion algorithms to enable predictive maintenance. In our experimental setup, we used raw data obtained from two sensors, a microphone, and an accelerometer installed on a brushless direct current (BLDC) motor. The data from each sensor were processed individually and, in a second step, merged to create a solid base for analysis. To diagnose BLDC motor faults, this work proposes to use data-level sensor fusion with deep learning methods such as deep convolutional neural networks (DCNNs) for their ability to automatically extract relevant information from the input data, the long short-term memory method (LSTM), and convolutional long short-term memory (CNN-LSTM), a combination of the two previous methods. The results show that in our setup, sound signals outperform vibrations when used individually for training. However, without any feature selection/extraction step, the accuracy of the models improves with data fusion and reaches 98.8%, 93.5%, and 73.6% for the DCNN, CNN-LSTM, and LSTM methods, respectively, 98.8% being a performance that, according to our reading, has never been reached in the analysis of the faults of a BLDC motor without first going through the extraction of the characteristics and their fusion by traditional methods. These results show that it is possible to work with raw data from multiple sensors and achieve good results using deep learning methods without spending time and resources on selecting appropriate features to extract and methods to use for feature extraction and data fusion.