Nowadays, competitiveness is a reality in all industrial fields and the plastic injection industry is not an exception. Due to the complex intrinsic changes that the parameters undergo during the injection process, it is essential to monitor the parameters that influence the quality of the final part to guarantee a superior quality of service provided to customers. Quality requirements impose the development of intelligent systems capable to detect defects in the produced parts. This article presents a first step towards building an intelligent system for classifying the quality of produced parts. The basic approach of this work is machine learning methods (Artificial Neural Networks and Support Vector Machines) and techniques that combine the two previous approaches (ensemble method). These are trained as classifiers to detect conformity or even defect types in parts. The data analyzed were collected at a plastic injection company in Portugal. The results show that these techniques are capable of incorporating the non-linear relationships between the process variables, which allows for a good accuracy (≈99%) in the identification of defects. Although these techniques present good accuracy, we show that taking into account the history of the last cycles and the use of combined techniques improves even further the performance. The approach presented in this article has a number of potential advantages for online predicting of parts quality in injection molding processes.

As the access to consumption data available in household smart meters is now very common in several developed countries, this kind of information is assuming a providential role for different players in the energy sector. The proposed study was applied to data available from the Smart Meter Energy Consumption Data in the London Households dataset, provided by UK Power Networks, containing half-hourly readings from an original sample of 5567 households (71 households were hereby carefully selected after a justified filtering process). The main aim is to forecast the day—ahead load profile, based only on previous load values and some auxiliary variables. During this research different forecasting models are applied, tested and compared to allow comprehensive analyses integrating forecasting accuracy, processing times and the interpretation of the most influential features in each case. The selected models are based on Multivariate Adaptive Regression Splines, Random Forests and Artificial Neural Networks, and the accuracies resulted from each model are compared and confronted with a baseline (Naïve model). The different forecasting approaches being evaluated have been revealed to be effective, ensuring a mean reduction of 15% in Mean Absolute Error when compared to the baseline. Artificial Neural Networks proved to be the most accurate model for a major part of the residential consumers.

Nowadays, as more data is now available from an increasing number of installed sensors, load forecasting applied to buildings is being increasingly explored. The amount and quality of resulting information can provide inputs for smarter decisions when managing and operating office buildings. In this article, the authors use two data-driven methods (artificial neural networks and support vector machines) to predict the heating and cooling energy demand in an office building located in Lisbon, Portugal. In the present case-study, these methods prove to be an accurate and appealing alternative to the use of accurate but time-consuming multi-zone dynamic simulation tools, which strongly depend on several parameters to be inserted and user expertise to calibrate the model. Artificial neural networks and support vector machines were developed and parametrized using historical data and different sets of exogenous variables to encounter the best performance combinations for both the heating and cooling periods of a year. In the case of support vector regression, a variation introduced simulated annealing to guide the search for different combinations of hyperparameters. After a feature selection stage for each individual method, the results for the different methods were compared, based on error metrics and distributions. The outputs of the study include the most suitable methodology for each season, and also the features (historical load records, but also exogenous features such as outdoor temperature, relative humidity or occupancy profile) that led to the most accurate models. Results clearly show there is a potential for faster, yet accurate machine-learning based forecasting methods to replace well-established, very accurate but time-consuming multi-zone dynamic simulation tools to forecast building energy consumption.

Nowadays, companies must embrace the concept of Digitalization and Industry 4.0 to remain competitive in the market. The reality is that most of them do not have their industrial devices prepared to access their data on a real-time basis. As most companies do not have the possibility to renew all their legacy devices and because these devices are still very productive, a retrofit solution is of high interest. In this work, we propose an affordable procedure that allows data collection and monitoring of older injection machines, as a contribution towards legacy devices integration. The developed system neither requires additional proprietary modules, nor contractual annual fees for different devices, sharing the same interface across different machine manufacturers and also contributing to uniform data collection. Evaluation was carried out in a real shop floor, monitoring the injection parameters for different machine models, validating the effectiveness of the developed system.