Search

Artificial intelligence is more present than ever, both in our society in general and in science. At the center of this development has been the concept of deep learning, the use of artificial neural networks that are many layers deep and can often reproduce human‐like behavior much better than other machine‐learning techniques. The articles in this collection are some recent examples of its application for X‐ray photon science and crystallography that have been published in Journal of Applied Crystallography. [ABSTRACT FROM AUTHOR]

Because of the recent declining demand for gasoline, the key to making refineries competitive is to maximize the yields of propylene and aromatics by converting heavier feedstock into basic petrochemicals through the residue fluid catalytic cracking (RFCC) process. This study presents an artificial intelligence (AI) hybrid reaction model to optimize the catalyst make‐up rate and maximize the product yield in a real‐time operation by (1) developing a catalyst activity evaluation method, (2) integrating the catalyst to oil (Cat/Oil) ratio to evaluate the reaction performance, and (3) incorporating the yield prediction model into the latest digital technologies. To this end, the catalyst deactivation function, which uses a deep neural network of the basic machine learning method, was added to the past RFCC reaction model. Under actual operational conditions, this study shows that the AI hybrid reaction model using the catalyst deactivation function can minimize catalyst loss and produce an accurate yield prediction as a production planning support tool. [ABSTRACT FROM AUTHOR]

Current algorithms for the real‐time prediction of the Kp index use a combination of models empirically driven by solar wind measurements at the L1 Lagrange point and historical values of the index. In this study, we explore the limitations of this approach, examining the forecast for short and long lead times using measurements at L1 and Kp time series as input to artificial neural networks. We explore the relative efficiency of the solar wind‐based predictions, predictions based on recurrence, and predictions based on persistence. Our modeling results show that for short‐term forecasts of approximately half a day, the addition of the historical values of Kp to the measured solar wind values provides a barely noticeable improvement. For a longer‐term forecast of more than 2 days, predictions can be made using recurrence only, while solar wind measurements provide very little improvement for a forecast with long horizon times. We also examine predictions for disturbed and quiet geomagnetic activity conditions. Our results show that the paucity of historical measurements of the solar wind for high Kp results in a lower accuracy of predictions during disturbed conditions. Rebalancing of input data can help tailor the predictions for more disturbed conditions. Key Points: Short‐term predictions should be made with solar wind data and long‐term predictions with recurrence forecastThe accuracy of predictions is much lower during disturbed geomagnetic conditionsRebalancing allows us to improve the accuracy of predictions during disturbed geomagnetic conditions [ABSTRACT FROM AUTHOR]

The article discusses the presence and potential of Artificial Intelligence in Chemical Engineering and discusses its background. Topics include the Phases of Artificial Intelligence in Chemical Engineering, Architecture of a feedforward neural network and also the Deep learning and the data science era.

AI trained neural network model is used to generate compensated image to correct the display panel nonuniformity, with camera captured input images of display panel as the inputs for model training. Usage cases are illustrated with simulated 2D BLU for LCD and MiniLED tiled displays. [ABSTRACT FROM AUTHOR]

We developed a method for automated evaluation of display luminance non‐uniformity using an auto‐encoder. Usually, a reconstruction loss of auto‐encoder is used for abnormality detection. In our method, we used reconstruction loss as the main indicator and cosine similarity as a secondary indicator. Our method succeeded in the non‐uniformity evaluation. [ABSTRACT FROM AUTHOR]