With the rise of Machine Learning (ML) and Artificial Intelligence (AI), the semiconductor industry is undergoing a revolution in how it approaches manufacturing. The SMART-IC project (DATE'24 MPP category: initial stage) works in this direction, by proposing an AI-enabled framework to support the smart monitoring and optimization of the semiconductor manufacturing process. An AI-powered engine examines sensor data recording physical parameters during production (like gas flow, temperature, voltage, etc.) as well as test data, with different goals: (1) the identification of anomalies in the production chain, either offline from collected data-traces or online from a continuous stream of sensed data; (2) the forecasting of new data of the future production; and (3) the automatic generation of synthetic traces, to strengthen the data-based algorithms. All such tasks provide valuable information to an advanced Manufacturing Execution System (MES), which reacts by optimizing the production process and management of the equipment maintenance policies. SMART-IC is a 300k€ academic project funded by the Italian Ministry of University and supported by STMicroelectronics and Technoprobe with industrial expertise and real-world applications. This paper shares the view of SMART-IC on the future of semiconductor manufacturing, the preliminary efforts, and the future results that will be reached by the end of the project, in 2025.

In this paper, we present the project “VIR2EM: VIrtualization and Remotization for Resilient and Efficient Manufacturing” by providing details on its research themes and its scientific and technological output. The project, centered on virtualization and remotization in the industrial sector, was promoted by Regione Veneto in Italy, and it has seen the participation and collaboration of 3 universities, 1 public research entity, and 10 companies composed of end users of digital solutions and high knowledge-intensive service providers. The project aims to develop and use tools for the virtualization of processes, systems, resources, and remoting of operations in order to: (1) maximize the efficiency of manufacturing systems under normal operating conditions; (2) maintain operations in case of emergency situations; (3) facilitate the restart of operations downstream of emergency situations by ensuring flexibility and predictive capability. Each theoretical proposal has been validated in distinct industrial facilities by constructing ten different prototypes.

Continual Learning aims to learn from a stream of tasks, being able to remember at the same time both new and old tasks. We propose a scenario that holds immense appeal for various real-world applications, where a model adapts to handle a stream of machines with distribution shifts Tests on real packaging data proved the feasibility of Continual Learning for addressing such problems. Our study uncovers the limitations of previous algorithms in the Domain Incremental Learning. Our research presents a novel approach for tackling multi-label tasks in Continual Learning, achieving superior performance compared to existing approaches found in the literature. Our method not only achieves optimal performance but also has logarithmic complexity, significantly reducing computation times.

An increasing number of vehicles today are equipped with advanced driver-assistance systems that provide humans involved in the driving tasks with continuous and active support. State-of-the-art implementations of these systems frequently rely on an underlying vehicle controller based on the model-predictive control strategy. In this article, we propose a nonlinear model-predictive contouring controller for a driving assistance system in high-performance scenarios. The design follows specific features to ensure the effectiveness of the interaction, namely, adaptability with respect to the current vehicle state, high-performance driving capabilities, and tunability of the assistance system. First, the control algorithm performance is evaluated offline and compared with a commercial lap-time minimizer, then experimental implementation of the assistance system with the human driver (HD) in the loop has been accomplished on a professional dynamic driving simulator, where an evaluation of the specific features has been performed: 1) a gg-bound is exploited to adapt the controller’s behavior to different driver abilities; 2) the controller’s adaptability to unexpected HD behavior is tested; and 3) the controller’s ability to handle the vehicle at the limit of maneuverability is established. The obtained strategy, then, demonstrates to be suitable as an underlying vehicle controller for a driver-assistance system on a racing track.

In manufacturing industries, it is of fundamental importance to detect anomalies in production in order to meet the required quality goals and to limit the number of defective products that are accidentally delivered to the customers. Nevertheless, monitoring systems currently employed in production are typically very simple and rely on a set of univariate control charts that fail to capture the multivariate and complex nature of real-world industrial systems. In such context, Machine Learning (ML)-based approaches for Anomaly Detection (AD) have proven to be extremely effective in increasing anomalies detectability and, in general, in enhancing monitoring procedures. However, industrial data are typically very complex and not suitable to be fed directly to classical ML-based AD tools making feature extraction procedures a necessary step that unfortunately may lead to information loss and low scalability. Deep Learning, has proven very effective at learning useful representations of complex data in an automatic way. In this paper, we propose an AD pipeline that makes use of convolutional autoencoders to extract useful features from two-dimensional, non-image, data. We test our approach on real world Optical Emission Spectroscopy data that are typical of semiconductor manufacturing and we achieve improved performance over classical monitoring methods.Note to Practitioners—Advanced monitoring is one of the most important task in the context of Industry 4.0. Some of the main issues in developing Machine Learning-based solutions in industrial environment are: (i) the lack of reliable tagged data; (ii) the complexity of data structures present in real-world scenarios. In this paper we investigate unsupervised anomaly detection for 2-dimensional data in manufacturing environment: we provide an approach that exploit Deep Learning-based architecture for handling the data at hand. We show the effectiveness of the proposed approach in a real world case study related to optical emission spectroscopy data in semiconductor manufacturing process providing satisfactory classification accuracy.

Predictive Maintenance technologies are particularly appealing for Industrial Equipment producers, as they pave the way to the selling of high added-value services and customized maintenance plans. However, standard Predictive Maintenance approaches assume the availability of sensor measurements, and the costs associated with adding sensors or remotely accessing sensor readings may discourage the development of such technologies. In this context, Alarm Forecasting can be very useful as it represents a low-cost alternative or helpful support to sensor-based Predictive Maintenance. In this work, we propose a new formulation for the Alarm Forecasting problem, framed as a multi-label classification task. We present a novel deep learning-based approach called FORMULA (alarm FORecasting in MUlti-LAbel setting). FORMULA leverages Transformer, a popular Neural Network architecture in the field of Natural Language Processing. To cope with alarm imbalance, we draw inspiration from Segmentation and Object Detection. Thus, FORMULA is trained by minimizing the Weighted Focal Loss, which turns out to be very effective in predicting rare alarms. These alarms, even if they are difficult to predict by nature, often are business-critical. We assess the proposed approach on a representative real-world problem from the packaging industry. In particular, we show that it outperforms not only classic multilabel techniques but also models based on recurrent neural networks. As regards the latter, the proposed approach also exhibits a lower computational burden, both in terms of training time and model size. To foster research in the field and reproducibility, we also publicly share the alarm logs dataset and the code used to perform the experiments.Note to Practitioners—This paper was motivated by the problem of monitoring equipment in the scenario of dairy products packaging, under the mild assumption that logs of the alarm generated by the packaging machines are available. This paper proposes an alarm forecasting algorithm. Its goal is to predict if any alarm will occur in the future, based only on past alarm logs. The limits of the considered future window can be defined arbitrarily, so there is enough time to perform corrective actions. Thus, the proposed approach aims to prevent unexpected downtime that would not only hinder productivity but also imply significant material waste. The proposed approach leverages methodologies from Natural Language Processing and Object Detection to deal with rare alarms that are often very informative in the industrial scenario. Besides, both the code and the real-world industrial datasets used to evaluate the methodology are available publicly. Currently, the proposed approach only uses alarm logs. Especially in the context of Industry 4.0, where many sensory data may be available, this is a limitation. Thus, the described approach might be extended by integrating alarm logs with sensory data. This integration is expected to improve the estimation of equipment health state. The results described in this paper may find application not only in the manufacturing sector but also in different areas such as Cyber Security, where log files keep activity records of each process performed.

In modern manufacturing scenarios, detecting anomalies in production systems is pivotal to keep high-quality standards and reduce costs. Even in the Industry 4.0 context, real-world monitoring systems are often simple and based on the use of multiple univariate control charts. Data-driven technologies offer a whole range of tools to perform multivariate data analysis that allow to implement more effective monitoring procedures. However, when dealing with complex data, common data-driven methods cannot be directly used, and a feature extraction phase must be employed. Feature extraction is a particularly critical operation, especially in anomaly detection tasks, and it is generally associated with information loss and low scalability. In this paper we consider the task of Anomaly Detection with two-dimensional, image-like input data, by adopting a Deep Learning-based monitoring procedure, that makes use of convolutional autoencoders. The procedure is tested on real Optical Emission Spectroscopy data, typical of semiconductor manufacturing. The results show that the proposed approach outperforms classical feature extraction procedures.

In the past recent years, Machine Learning methodologies have been applied in countless application areas. In particular, they play a key role in enabling Industry 4.0. However, one of the main obstacles to the diffusion of Machine Learning-based applications is related to the lack of interpretability of most of these methods. In this work, we propose an approach for defining a `feature importance' in Anomaly Detection problems. Anomaly Detection is an important Machine Learning task that has an enormous applicability in industrial scenarios. Indeed, it is extremely relevant for the purpose of quality monitoring. Moreover, it is often the first step towards the design of a Machine Learning-based smart monitoring solution because Anomaly Detection can be implemented without the need of labelled data. The proposed feature importance evaluation approach is designed for Isolation Forest, one of the most commonly used algorithm for Anomaly Detection. The efficacy of the proposed method is tested on synthetic and real industrial datasets.

Water chillers play a crucial role in HVAC systems. Faulty operations of chillers can lead to energy wastage, system unreliability and shorter equipment life. Due to the intrinsic complexity of these systems, which are nonlinear with interrelated parameters, and since data regarding unforeseen phenomena and abnormalities are not usually available for air-conditioning installations, the development of fault detection algorithms is a burdensome task. In this paper, a data-driven approach is used in order to develop a fault detection methodology that makes no use of a priori knowledge about abnormal phenomena. In particular, we exploit a local Principal Component Analysis to handle nonlinear cases and to accent novelties with respect to non-faulty operations variability. The performance of the proposed approach is assessed by using a synthetic dataset which is related to an air-condensed water chiller in both fault-free and faulty conditions.

Driving simulators are nowadays a widely used tool in the automotive industry. In particular, the need for safe and repeatable conditions in automated driving testing is now defining a new challenge: to extend the use of the tool to nonprofessional drivers. Quality of the motion control strategies in generating both realistic and feasible inputs to the driver is therefore, more than ever, a crucial aspect. The motion strategies are implemented in the so-called motion cueing algorithms (MCAs). A recently proposed effective approach to MCA is based on model predictive control (MPC), as it is well suited to solve constrained optimal control problems and to take advantage of models of the human sensing system. However, the predictive aspect of the algorithm has not been exploited yet, due to the hard real-time requirement when using long prediction windows. In this paper, a real-time implementation of an MPC-based MCA with predictive feature is presented, endowed with an on-line switching policy to a nonpredictive algorithm when the expected driver behavior is considered unreliable. The motion action based on the actual driver behavior and the expected one are considered in the same procedure, thus fully exploiting the availability of a perceptive model. An optimal tuning procedure is also proposed, based on a multiobjective optimization, where both performance improvement due to the prediction exploitation, and robustness to varying driver behaviour are considered. Finally, a characterization of the driver skill level is proposed and validated in an experimental environment for the specific case of the vertical DOF.

In this paper an approach to deal with Predictive Maintenance (PdM) problems with time-series data is discussed. PdM is a important approach to tackle maintenance and it is gaining an increasing attention in advanced manufacturing to minimize scrap materials, downtime, and associated costs. PdM approaches are generally based on Machine Learning tools that require the availability of historical process and maintenance data. Given the exponential growth in data logging in modern equipment, time series dataset are increasingly available in PdM applications. To exploit time series data for PdM, a functional learning methodology, namely Supervised Aggregative Feature Extraction (SAFE), is here employed on a semiconductor manufacturing maintenance problem.

In this paper, a multiple classifier machine learning (ML) methodology for predictive maintenance (PdM) is presented. PdM is a prominent strategy for dealing with maintenance issues given the increasing need to minimize downtime and associated costs. One of the challenges with PdM is generating the so-called “health factors,” or quantitative indicators, of the status of a system associated with a given maintenance issue, and determining their relationship to operating costs and failure risk. The proposed PdM methodology allows dynamical decision rules to be adopted for maintenance management, and can be used with high-dimensional and censored data problems. This is achieved by training multiple classification modules with different prediction horizons to provide different performance tradeoffs in terms of frequency of unexpected breaks and unexploited lifetime, and then employing this information in an operating cost-based maintenance decision system to minimize expected costs. The effectiveness of the methodology is demonstrated using a simulated example and a benchmark semiconductor manufacturing maintenance problem.

Cyber-physical systems (CPS) refer to novel hardware and software compositions creating smart, autonomously acting devices, enabling efficient end-to-end workflows and new forms of user-machine interaction, in a wide range of application fields. Given their heterogeneous nature, CPS are naturally designed in the so-called simulation-centric process, where physical equipment design are translated into behavioral simulation models. Although many tools exist to ease the design phase in the different disciplines, their full integration is still an open problem. This fact holds particularly true in a control design perspective, given that in a CPS the "plant" has a heterogeneous nature, and the design of model-based, advanced control techniques would strongly benefit from the availability of a common modeling environment. In this paper, we try to enhance this simulation-centric process by introducing a pure simulation kind of prototype, based on the co-simulation of the firmware and of the multi-physical controlled system. We introduce some innovative tools, implemented in μLab/CfL [1], and discuss upon their impact towards a better collaborative design and integration during the design of CPS. An example is given, taken from the HVAC (Heating, Ventilation, and Air Conditioning) field.

Smart management of maintenances has become fundamental in manufacturing environments in order to decrease downtime and costs associated with failures. Predictive Maintenance (PdM) systems based on Machine Learning (ML) techniques have the possibility with low added costs of drastically decrease failures-related expenses; given the increase of availability of data and capabilities of ML tools, PdM systems are becoming really popular, especially in semiconductor manufacturing. A PdM module based on Classification methods is presented here for the prediction of integral type faults that are related to machine usage and stress of equipment parts. The module has been applied to an important class of semiconductor processes, ion-implantation, for the prediction of ion-source tungsten filament breaks. The PdM has been tested on a real production dataset.

Dynamic driving simulators are seeing an increasing interest in the automotive community, both in the research and industrial fields. Different aspects are involved, from virtual prototyping to rehab: racing applications are of particular interest, where simulators are exploited to improve the driver's capabilities and test different vehicle set-ups avoiding the costs of testing on real tracks. The ability of the platform to reproduce as faithfully as possible the driving feelings is crucial in such context: this is the task of Motion Cueing Algorithms. Recently, innovative, MPC-based approaches have been proposed which improve the performance with respect to the classical, filtering-based procedures. The criticality in such approaches is the prediction phase, both for the derivation of reliable reference signals and the computational burden associated with the solution of the optimal problem. In this paper, a first strategy is proposed to derive an affordable reference by exploiting the repetitive pattern typical of the racing context, while a move-blocking approach is integrated to assure real-time capabilities.

In semiconductor manufacturing plants, monitoring of all wafers is fundamental in order to maintain good yield and high quality standards. However, this is a costly approach and in practice only few wafers in a lot are actually monitored. With a Virtual Metrology (VM) system it is possible to partly overcome the lack of physical metrology. In a VM scheme, tool data are used to predict, for every wafer, metrology measurements. In this paper, we present a VM system for a Chemical Vapor Deposition (CVD) process. Various data mining techniques are proposed. Due to the huge fragmentation of data derived from CVD's mixed production, several kind of data clustering have been adopted. The proposed models have been tested on real productive industrial data sets.

Given a Markov process x(k) defined over a finite interval I=[0,N], I/spl sub/Z we construct a process x*(k) with the same initial density as x, but a different end-point density, which minimizes the relative entropy of x and x*. It is shown that x* is a Markov process in the same reciprocal class as x. In the Gaussian case, the minimum relative entropy problem is related to a minimum energy LQG optimal control problem.