Innovative Approach to Build a Scalable Hybrid Model for Prescriptive Maintenance

Objective and Scope Analysis of operational plant data needs experts in order to interpret detected anomalies which are defined as unusual operation points. The next step on the digital transformation journey is to provide actionable insights into the data. Prescriptive Maintenance defines in advance which kind of detailed maintenance and spare parts will be required. This paper details requirements to improve these predictions for rotating equipment and show potential to integrate the outcome into an operational workflow. Methods, Procedures, Process First principle or physics-based modelling provides additional insights into the data, since the results are directly interpretable. However, such approaches are typically assumed to be expensive to build and not scalable. Identification of and focus on the relevant equipment to be modeled in a hybrid model using a combination of first principle physics and machine learning is a successful strategy. The model is trained using a machine learning approach with historic or current real plant data, to predict conditions which have not occurred before. The better the Artificial Intelligence is trained, the better the prediction will be. Results, Observations, Conclusions The general aim when operating a plant is the actual usage of operational data for process and maintenance optimization by advanced analytics. Typically a data-driven central oversight function supports operations and maintenance staff. A major lesson-learned is that the results of a rather simple statistical approach to detect anomalies fall behind the expectations and are too labor intensive. It is a widely spread misinterpretation that being able to deal with big data is sufficient to come up with good prediction quality for Prescriptive Maintenance. What big data companies are normally missing is domain knowledge, especially on plant critical rotating equipment. Without having domain knowledge the relevant input into the model will have shortcomings and hence the same will apply to its predictions. This paper gives an example of a refinery where the described hybrid model has been used. Novel and Additive Information First principle models are typically expensive to build and not scalable. This hybrid model approach, combining first principle physics based models with artificial intelligence and integration into an operational workflow shows a new way forward.

270 Evaluation of Steer Implant Strategies for Long-season Grazing of Cool-season Annuals

The objective of this study was to determine the relative effects of stocker-phase implant strategies on growth and carcass characteristics of beef steers. In each of 2 locations (OK and MS), steers were grazed on cool-season annual pastures in fall 2018 through spring 2019. Steers (n = 300 in MS, n = 240 in OK) were randomly assigned to one of three implant treatments, 1) a single Synovex® One Grass implant at d 0, 2) a single Component® TE-G with Tylan implant at d 0, or 3) a reimplant treatment receiving Component® TE-G with Tylan at d 0 and again at d 82 (OK) or 85 (MS). Steers from each treatment were commingled in 2 (OK) or 3 (MS) pastures for 159 (OK) or 161 d (MS). Following grazing, steers were shipped to a commercial feedyard for finishing, sorted into 3 pens based on BW with each treatment equally represented in each pen, and were managed according to that site’s BMPs. Steers from all treatments were implanted identically in the feedyard. Steers were slaughtered when the pen was visually estimated to be at 1 cm backfat. Carcass data of individuals were collected by camera grading equipment in the packing plant. Data were analyzed as a completely random design with animal as the experimental unit, treatment as a fixed effect, and pasture within location as a random effect. Marbling score tended to be greater in the single Component® TE-G with Tylan (treatment 2) vs. the other 2 treatments (425 vs 408 and 410, P = 0.07). No other production variables, including stocker-phase ADG, approached a significant difference (P > 0.39). No evidence was found to recommend stocker-phase reimplanting even in relatively long stocker phases with high ADG, and producers should consider selecting the most cost-effective implant at grazing initiation.

Towards zero carbon dioxide concentration in sweet natural gas product from amine sweetening plant

This work presents a two-step method to reduce CO2 concentration of sweet natural gas product from amine sweetening plant via amine blending (Step 1) followed by minor process modification (Step 2). In Step 1, an industrial natural gas sweetening plant was simulated using Aspen HYSYS and the simulation results were validated against the plant data. Afterwards, different blends of methyl diethanolamine and monoethanolamine (MDEA-MEA) and methyl diethanolamine and diethanolamine (MDEA-DEA) were investigated. Then the optimum amine blend of 28 wt.% MDEA and 10 wt.% MEA was reported. The optimum amine blend achieved a significant reduction in CO2 concentration of sweet natural gas of 99.9% compared to the base case (plant data). In Step 2, two types of amine stream splits, i.e., lean amine stream split and semi-lean amine stream split were studied. The study covered split stream amount, absorber recycle stage, and regenerator stage withdrawal. Both types of stream splits attained a significant reduction in CO2 concentration of sweet natural gas product and amine circulation rate compared to Step 1. However, the semi-lean amine stream split was superior to lean amine split with 69.1% and 63.6% reduction in CO2 concentration of sweet natural gas and lean amine circulation rate, respectively.

Ethnoveterinary study of medicinal plants used for cattle treatment in Bojonegoro District, East Java, Indonesia

Pratama AM, Herawati O, Nabila AN, Belinda TA, Wijayanti AD. 2021. Ethnoveterinary study of medicinal plants used for cattle treatment in Bojonegoro District, East Java, Indonesia. Biodiversitas 22: 4236-4245. Bojonegoro is a rural district in Indonesia's East Java Province where farming and cattle rearing are the main economic activities. The Bojonegoro District's cattle producers employ some medicinal plants specifically for the treatment of bovine illnesses. However, no data has been reported thus far. The goal of this research was to find and document ethnoveterinary medicinal herbs for cattle cures in the Bojonegoro District. A total of 41 cattle breeders were interviewed for the study. To collect demographic and ethnoveterinary medicinal plant data, each informant was interviewed using a semi-structured questionnaire in the native language of each informant. The stastitical analysis in this study include informant consensus (Fic), Fidelity Level (FL), and Plant Part Frequency (PPF). Approximately 78.00% of the respondents are between the ages of 30 and 50, with 36.59% having only graduated from senior high school. The Peranakan Ongole (PO) is the most common breed preserved by cattle breeders. In the study area, 41 ethnoveterinary medicinal plants were mentioned by male respondents to cure cattle health problems. Digestive illnesses are the most frequent ailments in cattle treated with medicinal plants. Curcuma longa L. was the most commonly mentioned medicinal plant. A majority of the source ethnoveterinary medicinal plants were cultivated on-site and the leaves of these plants were most often used.

Segmentation and quantification of solar PV losses using data-driven algorithms to help better design and operational monitoring

<div>In the current scenario of increasing demand for solar Photo-voltaic (PV) systems, the need to predict their feasibility and monitor performance is more than ever. Although PV systems are known for their reliability, they are not above the damaging effects of their surroundings. Various lossy phenomena affect overall plant performance. In this paper, several of such losses, namely thermal, soiling, module degradation and inverter clipping, are discussed. Algorithms to evaluate these losses are proposed which are data-driven and empirical in nature. This is done as an effort to leverage the analytical capabilities provided by the plant data. The paper also compares the estimated losses with those obtained using the PVsyst simulation. As the latter is an independent industrial standard, it helps in understanding the ground reality of PV performance and insights for better operational monitoring. These insights are of immense business value and are aimed at optimizing performance and thereby revenue. As part of our asset management, all the solar PV plant components have sensors whose measurements are sent to the servers on a real-time basis. This is incorporated into our analytics portal which is used for operations and monitoring. The data used for this study is time-series in nature with a temporal least count of 5 minutes (instantaneous values spaced every 5min throughout the period of data capture). The actual data and its list of parameters is dependent on solar plant capacity and design site. For the reference dataset, a grid-connected solar rooftop PV plant in India was studied and its loss parameters were estimated. The plant components are discussed in the prologue of the results section. Solar PV is such a technology which has been enjoying increasing demand and this market scenario is quite favourable for innovation in energy research. This paper hopes to not only introduce the context of PV losses but also tries to engage the motivation to adopt data-driven and empirical methodologies to understand modern systems. This approach is better in the sense that it only gets better at prediction as time goes by and there is more data. Industrial research such as the above work in critical analysis of PV systems not only helps identify possible limitations but also suggest room for improvement. Since energy generation and project cost are key towards maximizing revenue, these estimation models aimed at predicting PV losses are to be deemed indispensable. As with any estimation, there is no one unique way of hitting the bull’s eye that is to know the exact value. The algorithms proposed above are very much dependent on the quality and quantity of data. However, the comparison between losses estimated using plant data and standard simulation using energy modelling can act as feedback towards improving the design and maintenance of such PV systems.</div>

Studies on Mealybug Species (Hemiptera: Coccomorpha: Pseudococcidae) with Description of Two New Species and Three Newly Recorded Species from Indonesia

Mealybugs (Hemiptera: Coccomorpha: Pseudococcidae) include economically important insect pests worldwide. However, little is known about mealybug species in Indonesia. Scale insects were collected and identified from natural and cultivated plants in several regions of southern Sumatra, Indonesia between 2018 and 2019. In total, 16 species of Pseudococcidae in 7 genera were found, including two new species and three new records for the Indonesian mealybug fauna. Dysmicoccus sosromarsonae Zarkani & Kaydan sp. n., and Dysmicoccus zeynepae Zarkani & Kaydan sp. n. are described and illustrated as new species for science-based on the adult female. Furthermore, Dysmicoccus arachidis Williams and Dysmicoccus carens Williams and Pseudococcus leptotrichotus Williams were found as new records for the country. New locality and host plant data are given for all species. Additionally, an identification key to mealybug genera occurring in Indonesia is also provided.