Abstract— Looking forward to integrating practically the industry 4.0 technologies, it is mandatory to deal with information unavailability problems to manage better the mining machines by maintenance KPIs. This close monitoring issue is more present in the maintenance information’s flow through all the organization management level. This research presents the predictive maintenance system PdMSys design using model-based system engineering according to the system life cycle management paradigm. The use of a modeling language such as SysML helped dissect all aspects to meet the mining industry stakeholders' needs and expectations regarding the PdMSys features. PdMSys is a transversal and customized system created for three users’ hierarchical levels. The system sources data from the field sensors, the machine's parameters, and other systems databases to enable first monitoring assets' health state and secondly effectively managing the maintenance KPIs across the ore mine. This paper discusses the ability of PdMSys to transform the company's traditional practices into digital and proactive. Additionally, the financial benefits of implementing PdMSys are also presented. Lastly, the authors address PdMSys resilience to handle scalability and interoperability. Keywords— Predictive maintenance, Industry 4.0, Key performance indicators management, Model based system engineering, System modeling language

Predictive maintenance currently involves digital transformation with all the technologies developed to serve the latter. This maintenance strategy is believed to be an efficient solution to end late/early intervention issues. It is for this reason that machine health state monitoring by Remaining Useful Life prognosis is very crucial. However, in the literature, most studies focus on failure diagnosis more than the system's Remaining Useful Life. In addition, to prepare models to serve the prognosis, the use of actual machinery data is critical to assure the later scalability of the application. The literature about predictive maintenance has often evaluated data-driven approaches with machine learning techniques processing simulated Data rather than real ones. To tackle this problem, the authors propose a continuity of previous work treating a jaw crusher default diagnosis in the context of the ore mining industry. The RUL of the crusher components is estimated upon completion of the fault diagnosis data. Smart sensors Data have been preprocessed to serve the evaluation of four regression machine learning models: Bayesian Linear Regression, Poisson Regression, Neural Network Regression, and Random Forest. Poisson regression and Neural Network required data normalization in this case study to improve their performance. Linear regression methods proved their inability to forecast the machine degradation state, while the bagging ensemble method, Random Forest, was able to track the actual values. This paper aims to enhance the Prognosis and Health Management of the machine while contributing to the literature enhancement on failure prognosis using real industrial data. Keywords— Data-driven approach, Industry 4.0, Machine learning, Predictive Maintenance, RUL prognosis, Smart sensors.

This article deals with a diagnostic approach based on a predictive / conditional maintenance approach of a hydroelectric group. The technique used is based on the spectral analysis of the vibration signals, as well as on the orbital analysis of the bearings displacements. To do this, test protocols in different operating regimes are carried out, based on the collection of data measured according to the multisensor approach, the aim of which is to identify the predominant faults. The positions of the sensors are placed as close as possible to the bearings on the rigid structure of the hydroelectric group in accordance with the recommendations of standard ISO 10816-5. The evaluation approach is based on the analysis of the amplitudes of the vibration speeds, the aim of which is to identify the type of faults, as well as on the bearing displacement indicators in order to classify them in the pre-established zones according to thresholds recommended by the Standard. Therefore, a recommended tuning intervention can be planned in order to restore the unit to its proper operating condition, the aim of which is to increase its service life and improve fuel efficiency. Keywords—Diagnostic, Vibration analysis, Hydroelectric group, Multi-sensor approach, Standard

No abstract

No abstract