Project – Predictive Maintenance and Operational Efficiency of Industrial Equipment in Selected Manufacturing Industries in Lagos

CHAPTER ONE

INTRODUCTION

1.1 Background to the Study

Manufacturing industries depend heavily on the availability, reliability and functional condition of industrial equipment to sustain continuous production, maintain product quality and achieve operational targets. Machines such as production lines, motors, pumps, compressors, generators, conveyors, boilers, packaging machines and processing equipment are exposed to wear, vibration, heat, corrosion, overload and other forms of deterioration during operation. When equipment fails unexpectedly, production may be interrupted, materials may be wasted, delivery schedules may be affected and maintenance costs may increase. Maintenance management has therefore become an important component of industrial operations because the effectiveness of maintenance directly influences equipment availability, reliability, productivity and operational performance. Mobley (2002) explains that effective maintenance management seeks to maximize equipment availability and reliability while controlling maintenance-related costs. In the Nigerian manufacturing environment, the importance of maintenance is even greater because operational constraints and infrastructural challenges can intensify the consequences of equipment downtime.

Traditional maintenance practices have generally included corrective maintenance, preventive maintenance and routine inspection. Corrective maintenance involves repairing equipment after a fault or breakdown has occurred, while preventive maintenance involves carrying out maintenance activities according to predetermined schedules or operating intervals. Although preventive maintenance can reduce unexpected failures, fixed maintenance intervals may sometimes result in unnecessary replacement of components that still have useful life or may fail to identify abnormal conditions occurring between scheduled inspections. Eti, Ogaji and Probert (2004) found that Nigerian manufacturing industries could achieve improvements through total productive maintenance and greater attention to systematic maintenance practices. Similarly, Eti, Ogaji and Probert (2006) demonstrated the value of proactive maintenance approaches in Nigerian industries, noting that higher plant reliability can reduce equipment failure, production losses and resource wastage. These limitations and opportunities have contributed to the growing interest in predictive maintenance as a more condition-oriented approach.

Predictive maintenance represents a shift from maintenance based primarily on fixed schedules or breakdown responses towards maintenance decisions based on the actual condition and predicted future behaviour of equipment. It involves continuously or periodically collecting information about equipment conditions and using such information to identify abnormalities and predict potential failures before they occur. Parameters such as vibration, temperature, pressure, acoustic emissions, electrical current, lubrication condition and operating speed can be monitored through sensors and other diagnostic technologies. Zonta et al. (2020), in their systematic review of predictive maintenance in Industry 4.0, explained that the ability to predict when an asset will require maintenance is increasingly important and that predictive maintenance can contribute to improvements in downtime, maintenance cost, control and production quality. Likewise, Carvalho et al. (2019) identified machine-learning techniques as increasingly important tools for predictive maintenance because large volumes of equipment and production data can be analysed to identify patterns associated with impending equipment failures.

The emergence of Industry 4.0 has further expanded the possibilities for predictive maintenance in manufacturing industries. Technologies such as the Internet of Things (IoT), industrial sensors, cloud computing, artificial intelligence, machine learning, big-data analytics, cyber-physical systems and digital twins provide opportunities for manufacturing firms to collect and analyse equipment-condition data in real time. Such technologies allow maintenance personnel to move beyond simply identifying that a machine has failed to estimating when failure may occur and determining what maintenance action is most appropriate. Silvestri et al. (2020) observed that Industry 4.0 is transforming maintenance through technologies that facilitate remote monitoring, intelligent decision-making and more advanced maintenance strategies. Esteban et al. (2022) similarly explained that data mining and artificial intelligence are increasingly being used in predictive maintenance to optimise the timing and type of maintenance activities, maximize equipment availability and minimize maintenance resources.

Operational efficiency is an important outcome associated with effective equipment maintenance because manufacturing firms require equipment to operate at appropriate levels of availability, speed, quality and reliability. Frequent machine breakdowns can cause unplanned downtime, production interruptions, reduced capacity utilization, overtime costs, defective products and delayed delivery. Predictive maintenance can potentially improve operational efficiency by identifying deteriorating equipment conditions before breakdown occurs, thereby allowing maintenance activities to be scheduled during appropriate production intervals. Zonta et al. (2022) demonstrated that predictive maintenance information can also be incorporated into production scheduling, thereby allowing maintenance requirements and production decisions to be coordinated. Similarly, Jun (2022) identified advanced maintenance approaches, including predictive maintenance and prognostics and health management, as important components of efforts to achieve efficient and reliable manufacturing systems.

The relevance of predictive maintenance is particularly important in Nigeria, where manufacturing industries face several operational challenges that can affect equipment reliability and production continuity. Nigerian manufacturers may operate equipment under demanding conditions, while limitations in infrastructure, spare-parts availability, technical skills, maintenance planning and investment capacity can make equipment failures more difficult and expensive to manage. Okokpujie, Tartibu and Omietimi (2023) reported that Nigerian manufacturing industries face significant maintainability and reliability challenges and noted that industries may operate equipment extensively without conducting sufficient maintenance and reliability checks. Earlier research by Eti et al. (2006) also found that reactive maintenance practices remained prevalent in Nigerian industries and advocated a movement towards more proactive maintenance approaches. These findings indicate the importance of investigating whether predictive maintenance can provide a more effective mechanism for improving the reliability and operational performance of industrial equipment in the Nigerian manufacturing environment.

There is also growing evidence from Nigerian industrial research that data-driven and predictive approaches can support better equipment-maintenance decisions. Onawumi et al. (2021) developed a strategic maintenance prediction model for critical equipment in a manufacturing company and found predictive maintenance to be an effective strategy when compared with existing maintenance approaches in the case examined. The model incorporated equipment criticality assessment and decision-support techniques to determine appropriate maintenance strategies. More recently, Otuagoma et al. (2025) demonstrated the practical application of telemetry-based predictive maintenance in a Nigerian brewery environment by integrating vibration, speed, temperature and electrical-current sensors with industrial control and real-time visualization technologies. These studies indicate that predictive maintenance is not merely a theoretical Industry 4.0 concept but has potential for practical application within Nigerian manufacturing operations.

Lagos State provides a particularly relevant setting for examining predictive maintenance because it is one of Nigeria’s major industrial and commercial centres and contains manufacturing activities across several sectors. Manufacturing firms in Lagos operate different categories of production equipment whose availability and reliability are essential for maintaining production output. Previous studies on industrial maintenance in Lagos have shown the relationship between maintenance strategies and the condition and performance of industrial facilities. Oseghale (2014), for example, examined maintenance strategies in selected industrial estates in Lagos State and identified maintenance practices as an important consideration in determining the condition of industrial facilities and equipment. Onawumi et al. (2015) similarly assessed maintenance and facility safety in selected Nigerian manufacturing industries and reported variations in equipment maintainability, availability and reliability among the firms studied. These findings provide a basis for examining whether a more technologically advanced maintenance approach, such as predictive maintenance, can improve operational efficiency in selected manufacturing industries in Lagos.

Despite the potential benefits of predictive maintenance, its implementation may involve substantial technological, financial and organisational challenges. Predictive systems require sensors, data infrastructure, analytical software, technical expertise and personnel capable of interpreting equipment-condition information. Manufacturing firms may also encounter challenges relating to the initial cost of implementation, inadequate digital infrastructure, poor historical maintenance data, cybersecurity, employee resistance and difficulty integrating new systems with existing maintenance practices. Zonta et al. (2020) identified integration, data management and multidisciplinary requirements among the important challenges associated with predictive maintenance in Industry 4.0. Okokpujie et al. (2023) similarly highlighted infrastructural and organisational challenges affecting the adoption of advanced maintenance practices in Nigerian manufacturing. Therefore, the effectiveness of predictive maintenance cannot be assumed solely from the availability of the technology; its relationship with operational efficiency must be empirically assessed within the specific industrial context.

Against this background, this study focuses on Predictive Maintenance and Operational Efficiency of Industrial Equipment in Selected Manufacturing Industries in Lagos. The study seeks to examine the extent to which predictive maintenance practices, including condition monitoring, equipment-data analysis, early fault detection and failure prediction, contribute to improved equipment availability, reduced downtime, improved reliability and overall operational efficiency. The study is particularly relevant because the increasing adoption of digital manufacturing technologies creates an opportunity for Nigerian manufacturing industries to move from predominantly reactive maintenance practices towards data-driven and proactive maintenance systems. By examining selected manufacturing industries in Lagos, the study is expected to provide empirical evidence that can assist managers, maintenance professionals and other industrial stakeholders in understanding the potential contribution of predictive maintenance to improved operational efficiency.

1.2 Statement of the Problem

Industrial equipment is central to manufacturing operations, yet equipment breakdown and unplanned downtime remain significant challenges that can disrupt production activities and reduce operational efficiency. When critical machines fail unexpectedly, production may be stopped or slowed, raw materials may remain unused, production targets may not be achieved and maintenance expenditure may increase. In addition, repeated equipment failures may reduce the useful life of machinery and affect product quality. Studies of Nigerian industries have historically identified inadequate maintenance practices and equipment unreliability as important industrial challenges. Eti et al. (2006) reported that reactive maintenance was still prevalent in Nigerian industries and emphasized the need to move towards more proactive approaches capable of reducing equipment failure and production losses.

A related problem is the continued reliance on maintenance approaches that may not provide sufficient information about the actual condition of industrial equipment. Corrective maintenance responds after failure has occurred, while conventional preventive maintenance often relies on predetermined schedules that may not correspond precisely with the actual condition of a machine. Such approaches can result either in unexpected failures between maintenance periods or unnecessary maintenance activities before equipment components have reached the end of their useful life. Carvalho et al. (2019) noted that the availability of increasing quantities of data from industrial equipment creates opportunities to use machine-learning methods for predicting failures before they disrupt production. However, the extent to which manufacturing firms in Lagos have adopted such data-driven approaches and the degree to which they improve operational efficiency remain insufficiently established.

Another problem concerns the limited adoption and effective utilisation of advanced predictive technologies within the Nigerian manufacturing environment. Predictive maintenance requires condition-monitoring devices, sensors, reliable data collection, analytical capabilities, suitable maintenance software and technically competent personnel. Some manufacturing firms may lack the financial resources, technical expertise or digital infrastructure required to deploy and sustain these technologies. Okokpujie et al. (2023) identified inadequate maintenance and reliability checks, infrastructural limitations and other organisational challenges as continuing concerns within Nigerian manufacturing industries. Consequently, there is a need to establish whether the benefits associated with predictive maintenance in advanced industrial environments can also be realised by manufacturing firms operating under Nigerian conditions.

The specific relationship between predictive maintenance and operational efficiency among selected manufacturing industries in Lagos also requires further empirical investigation. Although previous Nigerian studies have examined preventive maintenance, total productive maintenance, equipment availability and industrial maintenance strategies, comparatively less attention has been given to the impact of predictive maintenance technologies on operational efficiency at the firm level. Onawumi et al. (2021) demonstrated the potential of predictive maintenance for critical equipment in a Nigerian manufacturing context, while Otuagoma et al. (2025) provided evidence of telemetry-based predictive monitoring in a Nigerian brewery. Nevertheless, there remains a need to examine whether predictive maintenance practices are associated with measurable improvements in equipment availability, reliability, reduced downtime and production efficiency across selected manufacturing industries in Lagos. This study therefore seeks to address this gap by assessing the relationship between predictive maintenance and operational efficiency of industrial equipment in selected manufacturing industries in Lagos.

1.3 Aim of the Study

The main aim of this study is to examine the relationship between predictive maintenance and operational efficiency of industrial equipment in selected manufacturing industries in Lagos.

1.4 Objectives of the Study

The specific objectives of the study are to:

1. examine the extent of adoption of predictive maintenance practices in selected manufacturing industries in Lagos;
2. determine the effect of condition monitoring and early fault detection on equipment downtime in selected manufacturing industries in Lagos;
3. assess the effect of predictive maintenance on equipment availability and reliability in selected manufacturing industries in Lagos; and
4. examine the challenges affecting the implementation of predictive maintenance practices in selected manufacturing industries in Lagos.

1.5 Research Questions

The study will be guided by the following research questions:

1. What is the extent of adoption of predictive maintenance practices in selected manufacturing industries in Lagos?
2. To what extent do condition monitoring and early fault detection affect equipment downtime in selected manufacturing industries in Lagos?
3. What effect does predictive maintenance have on equipment availability and reliability in selected manufacturing industries in Lagos?
4. What challenges affect the implementation of predictive maintenance practices in selected manufacturing industries in Lagos?

1.6 Research Hypothesis

The following null hypothesis will be tested at 0.05 level of significance:

H₀: Predictive maintenance has no significant effect on the operational efficiency of industrial equipment in selected manufacturing industries in Lagos.

1.7 Significance of the Study

The study will be beneficial to manufacturing industry management because it will provide empirical evidence concerning the contribution of predictive maintenance to equipment performance and operational efficiency. The findings may assist managers in determining whether investments in sensors, monitoring systems, maintenance analytics and predictive technologies are justified by improvements in equipment availability, reliability and production continuity.

The study will also benefit maintenance managers and engineers by providing information about the usefulness of condition monitoring, equipment diagnostics, data analysis and early fault detection. The findings may help maintenance personnel develop maintenance strategies that reduce dependence on emergency repairs and improve the planning of maintenance activities.

The study will be useful to production managers because equipment availability and reliability directly influence production schedules and output. A maintenance system capable of identifying potential equipment problems before catastrophic failure may enable production managers to coordinate maintenance activities with production schedules and reduce unplanned interruptions.

The study will further benefit manufacturing employees and technical personnel by emphasizing the importance of data-driven maintenance and continuous equipment monitoring. Predictive maintenance can provide early indications of abnormal machine conditions, potentially allowing maintenance teams to respond before failures become severe. This may contribute to improved workplace safety and more organised maintenance activities.

The study will also be relevant to technology providers and industrial automation companies because it will provide insight into the technological and organisational factors influencing predictive-maintenance adoption within the Nigerian manufacturing environment. Such information may assist technology providers in developing solutions that are appropriate for local industrial conditions.

Finally, the study will contribute to academic knowledge in maintenance engineering, industrial engineering, manufacturing management, operations management and Industry 4.0 research. It will provide evidence concerning predictive maintenance within the Nigerian manufacturing context and may serve as a reference for future studies on industrial equipment reliability, machine learning, condition monitoring, maintenance optimisation and operational efficiency.

1.8 Scope of the Study

The study focuses on predictive maintenance and operational efficiency of industrial equipment in selected manufacturing industries in Lagos.

The study will examine predictive maintenance through such practices as:

• condition monitoring;
• sensor-based equipment monitoring;
• vibration and temperature monitoring;
• equipment data collection;
• early fault detection;
• failure prediction;
• equipment diagnostics;
• maintenance-data analysis; and
• technology-assisted maintenance decision-making.

Operational efficiency will be considered in terms of:

• equipment availability;
• equipment reliability;
• reduction in unplanned downtime;
• maintenance response;
• production continuity; and
• effective utilisation of industrial equipment.

The study will be geographically limited to selected manufacturing industries in Lagos State, Nigeria. Relevant personnel may include maintenance engineers, maintenance managers, production managers, operations managers, technical officers and other employees directly involved in equipment operation and maintenance.

1.9 Operational Definition of Terms

Predictive Maintenance: A maintenance approach that uses information about the actual condition and performance of equipment, together with analytical techniques, to predict potential failures and determine the appropriate time for maintenance intervention.

Operational Efficiency: The ability of an organisation to achieve its desired production objectives using available resources effectively while minimising downtime, waste, unnecessary costs and operational interruptions.

Industrial Equipment: Machines, mechanical systems, electrical systems and other physical assets used directly or indirectly in manufacturing and production activities.

Condition Monitoring: The continuous or periodic observation and measurement of equipment parameters to determine the operational health and condition of machinery.

Early Fault Detection: The identification of abnormal equipment conditions at an early stage before they develop into major failures or production interruptions.

Equipment Reliability: The probability that a machine or equipment will perform its required function under specified conditions for a specified period without failure.

Equipment Availability: The proportion of time that equipment is operational and available to perform its intended production function.

Unplanned Downtime: The period during which equipment is unavailable for production because of unexpected failure, breakdown or other unforeseen operational problems.

Preventive Maintenance: Maintenance performed at predetermined intervals or according to prescribed criteria to reduce the likelihood of equipment failure.

Corrective Maintenance: Maintenance carried out to restore equipment to a functioning condition after a fault or failure has occurred.

Condition-Based Maintenance: A maintenance strategy in which maintenance decisions are based on measured indicators of the actual condition of equipment.

Machine Learning: A branch of artificial intelligence that enables computer systems to identify patterns in data and use those patterns to make predictions or decisions without being explicitly programmed for every individual situation.

Industrial Internet of Things (IIoT): The application of interconnected sensors, devices, machines and communication technologies to collect and exchange data within industrial environments.

Maintenance Analytics: The systematic analysis of maintenance and equipment data to identify patterns, predict failures, evaluate equipment performance and support maintenance decisions.

Remaining Useful Life (RUL): The estimated amount of operating time remaining before an equipment component or machine is expected to fail or no longer perform satisfactorily.

Manufacturing Industry: An industrial sector involved in transforming raw materials, components or other inputs into finished or semi-finished products through mechanical, chemical, electrical or other production processes.

Project – Predictive Maintenance and Operational Efficiency of Industrial Equipment in Selected Manufacturing Industries in Lagos