FUDIPO is a project funded by the European Commission under H2020 programme, SPIRE-02-2016: "Plant-wide monitoring and control of data-intensive processes", which started on October 1st, 2016 and ends on 30th September 2020. Mälardalen University coordinates the project, and the consortium is composed of energy experts, applied mathematicians, and software engineering experts to face the SPIRE topic. The goal with FUDIPO project is to introduce AI systems into process industries. The special demands for industry are to have very robust functions and a good possibility to keep control of all functions to avoid causing new problems! This demands a structured work, but still utilising the most advanced functions to benefit from this new world, and see that European industry really stay in the forefront of production development.

This paper presents a new approach to classification of high dimensional spectroscopy data and demonstrates that it outperforms other current state-of-the art approaches. The specific task we consider is identifying whether samples contain chlorinated solvents or not, based on their Raman spectra. We also examine robustness to classification of outlier samples that are not represented in the training set (negative outliers). A novel application of a locally-connected neural network (NN) for the binary classification of spectroscopy data is proposed and demonstrated to yield improved accuracy over traditionally popular algorithms. Additionally, we present the ability to further increase the accuracy of the locally-connected NN algorithm through the use of synthetic training spectra and we investigate the use of autoencoder based one-class classifiers and outlier detectors. Finally, a two-step classification process is presented as an alternative to the binary and one-class classification paradigms. This process combines the locally-connected NN classifier, the use of synthetic training data, and an autoencoder based outlier detector to produce a model which is shown to both produce high classification accuracy, and be robust to the presence of negative outliers.

Designing functional molecules and advanced materials requires complex interdependent design choices: tuning continuous process parameters such as temperatures or flow rates, while simultaneously selecting categorical variables like catalysts or solvents. To date, the development of data-driven experiment planning strategies for autonomous experimentation has largely focused on continuous process parameters despite the urge to devise efficient strategies for the selection of categorical variables to substantially accelerate scientific discovery. We introduce Gryffin, as a general purpose optimization framework for the autonomous selection of categorical variables driven by expert knowledge. Gryffin augments Bayesian optimization with kernel density estimation using smooth approximations to categorical distributions. Leveraging domain knowledge from physicochemical descriptors to characterize categorical options, Gryffin can significantly accelerate the search for promising molecules and materials. Gryffin can further highlight relevant correlations between the provided descriptors to inspire physical insights and foster scientific intuition. In addition to comprehensive benchmarks, we demonstrate the capabilities and performance of Gryffin on three examples in materials science and chemistry: (i) the discovery of non-fullerene acceptors for organic solar cells, (ii) the design of hybrid organic-inorganic perovskites for light-harvesting, and (iii) the identification of ligands and process parameters for Suzuki-Miyaura reactions. Our observations suggest that Gryffin, in its simplest form without descriptors, constitutes a competitive categorical optimizer compared to state-of-the-art approaches. However, when leveraging domain knowledge provided via descriptors, Gryffin can optimize at considerable higher rates and refine this domain knowledge to spark scientific understanding.

In process mining, process models are extracted from event logs using process discovery algorithms and are commonly assessed using multiple quality dimensions. While the metrics that measure the relationship of an extracted process model to its event log are well-studied, quantifying the level by which a process model can describe the unobserved behavior of its underlying system falls short in the literature. In this paper, a novel deep learning-based methodology called Adversarial System Variant Approximation (AVATAR) is proposed to overcome this issue. Sequence Generative Adversarial Networks are trained on the variants contained in an event log with the intention to approximate the underlying variant distribution of the system behavior. Unobserved realistic variants are sampled either directly from the Sequence Generative Adversarial Network or by leveraging the Metropolis-Hastings algorithm. The degree by which a process model relates to its underlying unknown system behavior is then quantified based on the realistic observed and estimated unobserved variants using established process model quality metrics. Significant performance improvements in revealing realistic unobserved variants are demonstrated in a controlled experiment on 15 ground truth systems. Additionally, the proposed methodology is experimentally tested and evaluated to quantify the generalization of 60 discovered process models with respect to their systems.

It's already possible to take "snapshots" of the BIM as it evolves over time, using digital authoring software. When viewed as stand-alone files, these snapshots may not provide much information about workflow. However, when the files are compared automatically and continuously over time, they increase a project manager's understanding of the workflow involved, thus adding value. Kouhestani and Nik-Bakht saw an opportunity to improve BIM capability by automating an archiving and analyzing process. "We created an algorithm to make'event logs' that track changes in consecutive files," says Kouhestani. "Once we created the event logs, we used them as input for process mining."

The researchers used a neural algorithm based on our brain's olfactory circuits to train the Loihi research chip to sniff out the scents of 10 hazardous chemicals, including ammonia and methane. In order to do so, the team fed Loihi a dataset consisting of the activity of 72 chemical sensors in response to these smells and configured the circuit diagram of biological olfaction on Loihi, according to a news release. The chip quickly learnt the neural representation of each smell and recognized each odour, even in the presence of significant background interference. The findings were published recently in the journal Nature Machine Intelligence. Such neuromorphic chips could be used to build intelligent "electronic nose systems" that could then be used in robots to detect hazardous materials or even for environmental monitoring.

A common pitfall a lot of machine learning (ML) companies run into is mistaking data as knowledge. Several enterprises think that having a lot of data makes them ripe for harvesting insights instantly through AI and ML techniques. It is not entirely true. Data is not equal to knowledge, or more precisely, not the knowledge you think it equals. Ernesto Miguel, 47 is a plant operator in a leading cement company.

Computer chips using AI might put sniffer dogs out of work -- at least in the area of smelling dangerous chemicals in drugs, explosives, and other substances -- according to a new study published in the journal Nature. Researchers for Cornell University and Intel produced a "neuromorphic" chip called Loihi that reportedly makes computers think like biological brains, according to Daily Mail. The researchers created the circuit on the chip, mirroring organic circuits found in the olfactory bulbs of a dog's brain, which is how they process their sense of smell. The Loihi chip can identify a specific odor on the first try and even differentiate other, background smells, said Intel, according to Daily Mail. The chip can even detect smells humans emit when sick with a disease -- which varies depending on the illness -- and smells linked to environmental gases and drugs.

Of all the senses, scent is a particularly difficult one to teach AI, but that doesn't stop researchers from trying. Most recently, researchers from Intel and Cornell University trained a neuromorphic chip to learn and recognize the scents of 10 hazardous chemicals. In the future, the tech might enable "electronic noses" and robots to detect weapons, explosives, narcotics and even diseases. Using Intel's Loihi, a neuromorphic chip, the team designed an algorithm based on the brain's olfactory circuit. When you take a whiff of something, molecules stimulate olfactory cells in your nose.

In the architecture and construction industries, structural design for large buildings has always been laborious, time-consuming, and difficult to optimize. It is an iterative process that involves two steps: analyzing the current structural design by a slow and computationally expensive simulation, and then manually revising the design based on professional experience and rules. In this work, we propose an end-to-end learning pipeline to solve the size design optimization problem, which is to design the optimal cross-sections for columns and beams, given the design objectives and building code as constraints. We pre-train a graph neural network as a surrogate model to not only replace the structural simulation for speed but also use its differentiable nature to provide gradient signals to the other graph neural network for size optimization. Our results show that the pre-trained surrogate model can predict simulation results accurately, and the trained optimization model demonstrates the capability of designing convincing cross-section designs for buildings under various scenarios.