Condition-based maintenance (CBM) may be considered an essential part of the Industry 4.0 environment because it can improve production processes through the use of the latest digital technologies, which allows improvements to products, processes, and business models. Nonetheless, despite this importance, there are no models or methodologies in the literature to assist in choosing predictive techniques and the level of complexity to be used in a given organization. This chapter describes a model for choosing the most suitable CBM technique to be introduced in a subsidiary of a petrochemical plant. The predictive techniques of vibration analysis, lubricant analysis, and a combination of the two were considered at three technological levels. The model was built using the measuring attractiveness by a categorical based evaluation technique (MACBETH) approach. The present model could avoid failures in these programmes when making decisions about the techniques and technologies most suited to the characteristics of the industrial plant.
TopIntroduction
Traditional maintenance strategies can reduce the overall productive capacity of a plant by between 5 and 20 percent. Unlike traditional corrective and preventive maintenance, Predictive Maintenance, Condition Based Maintenance (CBM) or Prognostic and Health Management (PHM) (Shin & Jun, 2015) can use the latest digital technology to increase the productivity of industrial plants. CBM is a maintenance technique in which physical parameters of a working machine are monitored, periodically or continuously, from a set of sensors, to analyse and compare data, which then allows decisions to be taken about the working and maintenance of the machine (Carnero, 2009).
Therefore, although CBM is not a new concept, the decrease in cost of digital technologies and the increase in the Digital Supply Network (DSN), have allowed CBM to be set up in a large number of organizations of different sizes and a variety of processes (Coleman, Damodaran, & Chandramouli, 2017).
CBM, therefore, has among its goals the development of diagnostic tools to identify a failing component and its failure mode and, prognosis aimed at predicting the remaining useful life of a component, or estimating the probability that a machine or component can still function before failure occurs (Jardine, Lin, Banjevic, 2006).
In any case, diagnosis is, in practice, used much more widely than prognosis (Heng, Zhang, Tan, & Mathew, 2009). Some of the literature considers CBM as a part of a preventive maintenance policy, since preventive actions are carried out depending of the performance of the parameter monitored.
CBM allows faults to be detected at an early stage, and so corrective action can be planned and programmed as best suited to the organization. Furthermore, diagnostic techniques are applied while the machinery is working, which allows for greater availability of equipment.
Thus, among the benefits of applying CBM in an organization are improvements in availability of facilities and equipment, meeting of delivery deadlines, improvements in quality of manufactured products and parts, improvements in staff and plant safety, reduction in maintenance, inventory and energy costs, availability of tools to check the quality of both internal and outsourced maintenance activity, increasing the useful life of equipment, improving company sustainability, as well as contributing to acquiring and retaining standards ISO 9000, QS 9000, etc, (Ayo-Imoru & Cilliers, 2018; Bari, Deshpande, & Patil, 2015; Carnero, López-Escobar, González-Palma, Mayorga, & Almorza, 2015; Carvalho, Gomes, Schmidt, & Brandão, 2015; Mobley, 2002; Precup, Angelov, Costa, & Sayed-Mouchaweh, 2015).
These benefits are more important in the Industry 4.0 environment, due to the following features (Köhler, 2016):
- 1.
Real-time CBM. Production data from the machines and processes, together with sensor data, is taken in real time, using Industry 4.0 software. The resulting data can be seen by everyone, anywhere, on different devices and in the cloud.
- 2.
Evaluation and flexible analysis. Data can be evaluated using highly customised algorithms, rules, or groups of experts, and the technician can apply expert systems without complicated IT know-how. Therefore, the software is adapted to the CBM necessities of each organization.
- 3.
Targeted notification of experts. As soon as the software identifies the need for maintenance action in a machine, the information is sent automatically to the appropriate team by means of a digital ticket that includes all the relevant information. Once the maintenance task is finished, the ticket can be closed automatically and on line, updating the information related to the failure.