A common source of defects in manufacturing miniature Printed Circuits Boards (PCB) is the attachment of silicon die or other wire bondable components on a Liq- uid Crystal Polymer (LCP) substrate. Typically, a conductive glue is dispensed prior to attachment with defects caused either by insufficient or excessive glue. The current prac- tice in electronics industry is to examine the deposited glue by a human operator a process that is both time consuming and inefficient especially in preproduction runs where the error rate is high. In this paper we propose a system that automates fault diagnosis by accurately estimating the vol- ume of glue deposits before and even after die attachment. To this end a modular scanning system is deployed that produces high resolution point clouds whereas the actual estimation of glue volume is performed by (R)egression- Net (RNet), a 3D Convolutional Neural Network (3DCNN). RNet outperforms other deep architectures and is able to estimate the volume either directly from the point cloud of a glue deposit or more interestingly after die attachment when only a small part of glue is visible around each die. The entire methodology is evaluated under operational conditions where the proposed system achieves accurate results without delaying the manufacturing process.

In manufacturing environments, monitoring of the Overall Equipment Effectiveness (OEE) via soft sensors plays a pivotal role in enhancing productivity and efficiently planning maintenance schedules. However, the accurate forecasting of the OEE presents considerable challenges due to the complexity of manufacturing data and equipment interdependence across stages. To this end, advanced time series forecasting methods based on Deep Learning (DL) pose a promising avenue in tackling these challenges. In this study, we present a taxonomy of DL forecasting architectures, consisting of Multi-Layer Perceptrons (MLPs), Recurrent models, Transformer-based models, and Temporal Convolutional Networks (TCNs), and we perform a comparative study of the state-of-the-art approaches. Additionally, a lightweight late fusion Linear architecture is proposed, incorporating Patching, Moving Average Decomposition, and Fourier Transform Decomposition (PDFLinear) and an Exponentially Weighted Averaging (EWA) module responsible for late fusion. Representative state-of-the-art models of each taxonomy class are benchmarked using a real-world antenna assembly line use case and compared against our proposed method. The experimental results show that our proposed model consistently matches or outperforms the state-of-the-art models in terms of forecasting efficacy for all forecast horizons, whilst requiring a fraction of the computational resources.

Deep Learning (DL) has certainly improved industrial inspection while significant progress has been also achieved in metrology with impressive results reached through their combination. However, it is not easy to deploy metrology sensors in a factory, as they are expensive, and require special acquisition conditions. In this paper, we propose a methodology to replace a high-end sensor with a low-cost one introducing a data-driven Soft Sensor (SS) model. Concretely, a residual architecture (R $^{2}$ esNet) is proposed for quality inspection, along with an error-correction scheme to lessen noise impact. Our method is validated in PCB manufacturing, through the identification of defects related to glue dispensing before the attachment of silicon dies. Finally, a detection system is developed to localize PCB regions of interest, thus offering flexibility during data acquisition. Our methodology is evaluated under operational conditions achieving promising results, whereas PCB inspection takes a fraction of the time needed by other methods.

A common problem for machine vision applications is uncontrolled illumination conditions that cause undesired artifacts on sensorial data. For instance, quality inspection using color cameras, while having wide industrial application, requires manual illumination adjustment and is severely affected by external lighting sources and the physical properties of the inspected object. To overcome this problem, we propose an autonomous illumination solution, that adjusts illumination via a Deep Reinforcement Learning (DRL) agent following a goal-oriented reward that takes into account image entropy and specularity. The system is validated in a challenging vehicle documentation use case where vehicle images are captured under various lighting conditions using a camera and an in-house built illumination system. The DRL agent learns to control illumination levels directly from high-dimensional visual inputs by mapping the interactions from the environment to the reward-driven control actions of the illumination system, targeting an optimal illumination zone even under the appearance of abrupt illumination changes in the environment.