Application of machine learning to predict the thermal power plant process condition

This paper deals with the development of an algorithm for predicting thermal power plant process variables. The input data are described, and the data cleaning algorithm is presented along with the Python frameworks used. The employed machine learning model is discussed, and the results are presented.

Overview of Arabidopsis as a Genetics Model System and Its Limitation, Leading to the Development of Emerging Plant Model Systems

Model plant systems make it easier to perform experiments with them. They help to understand and expand our knowledge about the genetic basis behind different plant process. Also, it is easier to design and perform genetic and genomic experiments using a model plant system. A. thaliana was initially chosen as the model plant system, and remains to this date, one of the most widely studied plant. With the advent of better molecular biology and sequencing tools and to understand the genetic basis for the unique processes in different plant species, there is emergence of several new model systems.

Application of PCA and Classification for Fault Diagnosis of MAB Installed in Petrochemical Plant Process Facilities

In large systems, such as power plants or petrochemical plants, various equipment (e.g., compressors, pumps, turbines, etc.) are typically deployed. Each piece of equipment operates under generally harsh operating conditions, depending on its purpose, and operates with a probability of failure. Therefore, several sensors are attached to monitor the status of each piece of equipment to observe its conditions; however, there are many limitations in monitoring equipment using thresholds such as maximum and minimum values of data. Therefore, this study introduces a technology that can diagnose fault conditions by analyzing several sensor data obtained from plant operation information systems. The equipment for the case study was a main air blower (MAB), an important cooling equipment in the plant process. The driving sensor data were analyzed for approximately three years, measured at the plant. The fault history of the actual process was also analyzed. Due to the large number of sensors installed in the MAB system, a dimension reduction method was applied with the principal component analysis (PCA) method when analyzing collected sensor data. For application to PCA, the collected sensor data were analyzed according to the statistical analysis method and data features were extracted. Then, the features were labeled and classified according to normal and fault operating conditions. The analyzed features were converted with a diagnosis model, by dimensional reduction, applying the PCA method and a classification algorithm. Finally, to validate the diagnosis model, the actual failure signal that occurred in the plant was applied to the suggested method. As a result, the results from diagnosing signs of failure were confirmed even before the failure occurred. This paper explains the case study of fault diagnosis for MAB equipment with the suggested method and its results.

Capturing and Selecting Senescence Variation in Wheat

Senescence is a highly quantitative trait, but in wheat the genetics underpinning senescence regulation remain relatively unknown. To select senescence variation and ultimately identify novel genetic regulators, accurate characterization of senescence phenotypes is essential. When investigating senescence, phenotyping efforts often focus on, or are limited to, the visual assessment of flag leaves. However, senescence is a whole-plant process, involving remobilization and translocation of resources into the developing grain. Furthermore, the temporal progression of senescence poses challenges regarding trait quantification and description, whereupon the different models and approaches applied result in varying definitions of apparently similar metrics. To gain a holistic understanding of senescence, we phenotyped flag leaf and peduncle senescence progression, alongside grain maturation. Reviewing the literature, we identified techniques commonly applied in quantification of senescence variation and developed simple methods to calculate descriptive and discriminatory metrics. To capture senescence dynamism, we developed the idea of calculating thermal time to different flag leaf senescence scores, for which between-year Spearman’s rank correlations of r ≥ 0.59, P < 4.7 × 10–5 (TT70), identify as an accurate phenotyping method. Following our experience of senescence trait genetic mapping, we recognized the need for singular metrics capable of discriminating senescence variation, identifying thermal time to flag leaf senescence score of 70 (TT70) and mean peduncle senescence (MeanPed) scores as most informative. Moreover, grain maturity assessments confirmed a previous association between our staygreen traits and grain fill extension, illustrating trait functionality. Here we review different senescence phenotyping approaches and share our experiences of phenotyping two independent recombinant inbred line (RIL) populations segregating for staygreen traits. Together, we direct readers toward senescence phenotyping methods we found most effective, encouraging their use when investigating and discriminating senescence variation of differing genetic bases, and aid trait selection and weighting in breeding and research programs alike.

Supporting Student Visualization of Molecular Processes Through Diagram Drawing

Historically, scientists and researchers have accompanied their observations with drawings, indicating that visual models are an effective way of communicating science. Studies have shown that students should draw images that are either interpretational or transformative, and artistic ability is irrelevant as they still help improve learning. However, many educators do not utilize this practice in their courses. In this study, we investigated if practising making simple and schematic drawings can help students understand complex molecular processes, and to use that tool to contextualize complex plant biology processes in an undergraduate plant biology course. When students were introduced to a complex plant process, the instructor accompanied their explanation with a simple schematic drawing. Students were told by the instructor that 1-2 drawing questions would appear on the midterm. For the final exam, no questions explicitly asked students to include a schematic drawing. Students who drew often scored higher on questions related to the topics where drawings were introduced in the course and the lab. Students who drew on the final exam did 12.3% better on the exam than those who didn’t draw. Students who had continuous exposure to drawing style questions during the midterms, did 6% better in the course compared to students who did not write the midterms. Students also gave an overwhelmingly positive response towards drawing, and 94% of the surveyors believed that making simple drawings helped with their learning of complex molecular processes. This could indicate that exposure to drawing style questions helped reinforce the learning of complex molecular processes.