We study optimal data pooling for shared learning in two common maintenance operations: condition-based maintenance and spare parts management. We consider a set of systems subject to Poisson input -- the degradation or demand process -- that are coupled through an a-priori unknown rate. Decision problems involving these systems are high-dimensional Markov decision processes (MDPs) and hence notoriously difficult to solve. We present a decomposition result that reduces such an MDP to two-dimensional MDPs, enabling structural analyses and computations. Leveraging this decomposition, we (i) demonstrate that pooling data can lead to significant cost reductions compared to not pooling, and (ii) show that the optimal policy for the condition-based maintenance problem is a control limit policy, while for the spare parts management problem, it is an order-up-to level policy, both dependent on the pooled data.

Diagnosis in PV systems aims to detect, locate and identify faults. Diagnosing these faults is vital to guarantee energy production and extend the useful life of PV power plants. In the literature, multiple machine learning approaches have been proposed for this purpose. However, few of these works have paid special attention to the detection of fine faults and the specialized process of extraction and selection of features for their classification. A fine fault is one whose characteristic signature is difficult to distinguish to that of a healthy panel. As a contribution to the detection of fine faults (especially of the snail trail type), this article proposes an innovative approach based on the Random Forest (RF) algorithm. This approach uses a complex feature extraction and selection method that improves the computational time of fault classification while maintaining high accuracy.

Industry 4.0, also known as the Fourth Industrial Revolution, refers to the current trend of automation and data exchange in manufacturing technologies, including the Internet of Things (IoT), artificial intelligence, and cloud computing. This trend is expected to lead to a more integrated and flexible manufacturing process, as well as increased efficiency and productivity. In terms of maintenance strategy, Industry 4.0 is likely to lead to a shift towards predictive maintenance, in which maintenance is performed based on data and analytics rather than on a fixed schedule. This can involve the use of sensors and IoT devices to monitor the condition of equipment in real-time, and the use of data analysis and machine learning algorithms to predict when maintenance will be needed. Predictive maintenance can help to reduce downtime and improve equipment reliability, as well as potentially reducing maintenance costs.

Predictive Maintenance is one of the big revolutions happening across all major industries right now. Instead of changing parts regularly or even only after they failed it uses Machine Learning methods to predict when a part is going to fail. If you want to get an introduction to this fascinating developing area, read on! Predictive maintenance techniques are designed to help determine the condition of in-service equipment in order to estimate when maintenance should be performed. This approach promises cost savings over routine or time-based preventive maintenance, because tasks are performed only when warranted.

Frequent instances of enterprise downtime can derail the growth trajectory of your organization. To avoid that fate, one of the more effective solutions to prevent downtime involves incorporating AI in the workplace. Downtime of any kind, whether it is driven by cyber-attacks, malfunctioning devices, erratically-working applications or maintenance work, is lossmaking for your organization. Unplanned network outages, device breakdown and other events that cause downtime--a loose term used to denote the cumulative "productive company time" lost during repairs--can incur losses of up to US$5 million for organizations, and that figure excludes legal fees, compensation and penalties of any kind. Let's face it, events such as the ones listed above are inevitable for organizations in any sector.

The amount of data to be stored and processed is increasing day by day. Therefore, today's manufacturing companies need to find new solutions and use cases for this data. Of course, data benefits manufacturing companies as it allows to automate large-scale processes and speed up execution time. Data science is said to have dramatically changed the manufacturing industry. Let's consider a few data science use cases that have become common in manufacturing and benefit manufacturers.

Machines play a huge role in our lives, including the machines we use every day, but without maintenance, every machine will eventually break down. Companies follow various maintenance programs to increase operational reliability and reduce costs. Maintenance is the set of operations necessary to preserve the functionality and efficiency of an asset and can take place in response to a failure or as a previously planned action. According to research conducted by Deloitte, a non-optimized maintenance strategy can reduce the production capacity of an industrial plant by 5 to 20%. Recent studies also show that downtime costs industrial manufacturers about 45 billion euros a year.

AI is being infused into the Internet of Things, setting the stage for significant improvements in manufacturing productivity, improved uptime, and reduced costs -- regardless of market segment. The traditional approach to improving manufacturing equipment reliability and efficiency is regular scheduled maintenance. While that is an improvement over just fixing or replacing equipment when it breaks, it's far from optimal. Even with periodic maintenance, equipment can suddenly break down, idling workers, delaying shipments, and disappointing customers. This is where AI fits in.

This blog post has been written with the collaboration of Juan Olloniego and Germán Hoffman. Even if machines have done a big part of the heavy lifting for us since the industrial revolution, they still depend on us for their maintenance. As they have that annoying tendency to break from time to time, their conservation becomes essential to keep up with our daily activities. Now, with the industry 4.0, the internet of things, and the artificial intelligence advent, we are letting a new kind of machines take care of their older counterparts. We make these new transistor-based machines look after their ancestors.

The manufacturing business faces huge transformations nowadays. Due to rapid development of digital world and broad application of data science, various fields of human activity seek improvement. Modern manufacturing is often referred to as industry 4.0 that is the manufacturing under conditions of the fourth industrial revolution that has brought robotization, automation and broad application of data. The amount of data to be stored and processed is growing every day. Therefore, today's manufacturing companies need to find new solutions and use cases for this data.