| 1. |
- Blackburn, Landen D., et al.
(author)
-
Development of novel dynamic machine learning-based optimization of a coal-fired power plant
- 2022
-
In: Computers and Chemical Engineering. - : Elsevier BV. - 0098-1354. ; 163
-
Journal article (peer-reviewed)abstract
- The increasing fraction of intermittent renewable energy in the electrical grid is resulting in coal-fired boilers now routinely ramp up and down. The current state-of-the-art operation for such boilers is to apply steady-state, neural network-based optimization to make control decisions in real-time, and this work demonstrates the feasibility of extending this to dynamic, neural network-based optimization using a long short-term memory neural network. A simplified numerical simulation of a t-fired coal boiler and supporting equipment is used to represent a real plant subjected to both steady-state, neural network-based optimization and dynamic, neural network-based optimization. Using the same intervals and a particle swarm optimization algorithm, the dynamic optimization outperforms the steady-state optimization and realizes up to 4.58% improvement in thermal efficiency. Dynamic optimization with a long short-term memory neural network is shown to both be feasible and beneficial for operation of a coal-fired boiler under changing load.
|
|
| 2. |
- Blackburn, Landen D., et al.
(author)
-
Dynamic machine learning-based optimization algorithm to improve boiler efficiency
- 2022
-
In: Journal of Process Control. - : Elsevier BV. - 0959-1524. ; 120, s. 129-149
-
Research review (peer-reviewed)abstract
- With decreasing computational costs, improvement in algorithms, and the aggregation of large industrial and commercial datasets, machine learning is becoming a ubiquitous tool for process and business innovations. Machine learning is still lacking applications in the field of dynamic optimization for real-time control. This work presents a novel framework for performing constrained dynamic optimization using a recurrent neural network model combined with a metaheuristic optimizer. The framework is designed to augment an existing control system and is purely data-driven, like most industrial Model Predictive Control applications. Several recurrent neural network models are compared as well as several metaheuristic optimizers. Hyperparameters and optimizer parameters are tuned with parameter sweeps, and the resulting values are reported. The best parameters for each optimizer and model combination are demonstrated in closed-loop control of a dynamic simulation, and several recommendations are made for generalizing this framework to other systems. Up to 0.953% improvement is realized over the non-optimized case for a simulated coal-fired boiler. While this is not a large improvement in percentage, the total economic impact is $991,000 per year, and this study builds a foundation for future machine learning with dynamic optimization.
|
|
| 3. |
- Mohammadi, Kasra, et al.
(author)
-
A review on the application of machine learning for combustion in power generation applications
- 2023
-
In: Reviews in Chemical Engineering. - : Walter de Gruyter GmbH. - 2191-0235 .- 0167-8299. ; 39:6, s. 1027-1059
-
Research review (peer-reviewed)abstract
- Although the world is shifting toward using more renewable energy resources, combustion systems will still play an important role in the immediate future of global energy. To follow a sustainable path to the future and reduce global warming impacts, it is important to improve the efficiency and performance of combustion processes and minimize their emissions. Machine learning techniques are a cost-effective solution for improving the sustainability of combustion systems through modeling, prediction, forecasting, optimization, fault detection, and control of processes. The objective of this study is to provide a review and discussion regarding the current state of research on the applications of machine learning techniques in different combustion processes related to power generation. Depending on the type of combustion process, the applications of machine learning techniques are categorized into three main groups: (1) coal and natural gas power plants, (2) biomass combustion, and (3) carbon capture systems. This study discusses the potential benefits and challenges of machine learning in the combustion area and provides some research directions for future studies. Overall, the conducted review demonstrates that machine learning techniques can play a substantial role to shift combustion systems towards lower emission processes with improved operational flexibility and reduced operating cost.
|
|
| 4. |
- Tuttle, Jacob F., et al.
(author)
-
A systematic comparison of machine learning methods for modeling of dynamic processes applied to combustion emission rate modeling
- 2021
-
In: Applied Energy. - : Elsevier BV. - 1872-9118 .- 0306-2619. ; 292
-
Journal article (peer-reviewed)abstract
- Ten established, data-driven dynamic algorithms are surveyed and a practical guide for understanding these methods generated. Existing Python programming packages for implementing each algorithm are acknowledged, and the model equations necessary for prediction are presented. A case study on a coal-fired power plant's NO emission rates is performed, directly comparing each modeling method's performance on a mutual system. Each model is evaluated by its root mean squared error (RMSE) on out-of-sample future horizon predictions. Optimal hyperparameters are identified using either an exhaustive search or genetic algorithm. The top five model structures of each method are used to recursively predict future NO emission rates over a 60-step time horizon. The RMSE at each future timestep is determined, and the recursive output prediction trends compared against measurements in time. The GRU neural network is identified as the best candidate for representing the system, demonstrating accurate and stable predictions across the future horizon by all considered models, while satisfactory performance was observed in several of the ARX/NARX formulations. These efforts have contributed 1) a concise resource of multiple proven dynamic machine learning methods, 2) a practical guide explaining the use of these methods, effectively lowering the “barrier-to-entry” of deploying such models in control systems, 3) a comparison study evaluating each method's performance on a mutual system, 4) demonstration of accurate multi-timestep emissions modeling suitable for systems-level control, and 5) generalizable results demonstrating the suitability of each method for prediction over a multi-step future horizon to other complex dynamic systems.
|
|
| 5. |
- Westberg, Lars, 1973, et al.
(author)
-
Association between a dinucleotide repeat polymorphism of the estrogen receptor alpha gene and personality traits in women.
- 2003
-
In: Molecular psychiatry. - : Springer Science and Business Media LLC. - 1359-4184 .- 1476-5578. ; 8:1, s. 118-22
-
Journal article (peer-reviewed)abstract
- Estrogens are known to play a key role in the regulation of various aspects of behavior. In order to study the potential contribution of genetic variation in the estrogen receptor (ER) alpha to specific personality traits, we investigated a repeat polymorphism in the ER alpha gene in 172 42-year-old women who had been assessed using the Karolinska Scales of Personality (KSP). Based on the hypothesis that there is a relationship between the length of a repeat polymorphism and gene function,(1) the alleles were divided into two groups: short and long. In order to elucidate the possible influence of the ER alpha gene on the different aspects of personality measured by means of the KSP, the possible association between this gene and four different factors ('neuroticism', 'psychoticism', 'non-conformity', and 'extraversion') was analysed. 'Neuroticism', 'psychoticism', and 'non-conformity' all appeared to be associated with the ER alpha gene. After correction for multiple comparisons by means of permutation analysis, the associations with the factor 'non-conformity'--including the subscales 'indirect aggression' and 'irritability'--and the factor 'psychoticism'--including the subscale 'suspicion'--remained significant. The results suggest that the studied dinucleotide repeat polymorphism of the ER alpha gene may contribute to specific components of personality.
|
|
| 6. |
- Xu, Jingjing, et al.
(author)
-
Plasma Concentrations of Short-Chain Fatty Acids in Active and Recovered Anorexia Nervosa.
- 2022
-
In: Nutrients. - : MDPI AG. - 2072-6643. ; 14:24
-
Journal article (peer-reviewed)abstract
- Anorexia nervosa (AN) is one of the most lethal psychiatric disorders. To date, we lack adequate knowledge about the (neuro)biological mechanisms of this disorder to inform evidence-based pharmacological treatment. Gut dysbiosis is a trending topic in mental health, including AN. Communication between the gut microbiota and the brain is partly mediated by metabolites produced by the gut microbiota such as short-chain fatty acids (SCFA). Previous research has suggested a role of SCFA in weight regulation (e.g., correlations between specific SCFA-producing bacteria and BMI have been demonstrated). Moreover, fecal SCFA concentrations are reported to be altered in active AN. However, data concerning SCFA concentrations in individuals who have recovered from AN are limited. In the present study, we analyzed and compared the plasma concentrations of seven SCFA (acetic-, butyric-, formic-, isobutyric-, isovaleric-, propionic-, and succinic acid) in females with active AN (n = 109), recovered from AN (AN-REC, n = 108), and healthy-weight age-matched controls (CTRL, n = 110), and explored correlations between SCFA concentrations and BMI. Significantly lower plasma concentrations of butyric, isobutyric-, and isovaleric acid were detected in AN as well as AN-REC compared with CTRL. We also show significant correlations between plasma concentrations of SCFA and BMI. These results encourage studies evaluating whether interventions directed toward altering gut microbiota and SCFA could support weight restoration in AN.
|
|
