Assessing transformer oil quality using deep convolutional networks
- Alam, Mohammad, Karmakar, Gour, Islam, Syed, Kamruzzaman, Joarder, Chetty, Madhu, Lim, Suryani, Appuhamillage, Gayan, Chattopadhyay, Gopi, Wilcox, Steve, Verheyen, Vincent
- Authors: Alam, Mohammad , Karmakar, Gour , Islam, Syed , Kamruzzaman, Joarder , Chetty, Madhu , Lim, Suryani , Appuhamillage, Gayan , Chattopadhyay, Gopi , Wilcox, Steve , Verheyen, Vincent
- Date: 2019
- Type: Text , Conference proceedings , Conference paper
- Relation: 29th Australasian Universities Power Engineering Conference, AUPEC 2019
- Full Text:
- Reviewed:
- Description: Electrical power grids comprise a significantly large number of transformers that interconnect power generation, transmission and distribution. These transformers having different MVA ratings are critical assets that require proper maintenance to provide long and uninterrupted electrical service. The mineral oil, an essential component of any transformer, not only provides cooling but also acts as an insulating medium within the transformer. The quality and the key dissolved properties of insulating mineral oil for the transformer are critical with its proper and reliable operation. However, traditional chemical diagnostic methods are expensive and time-consuming. A transformer oil image analysis approach, based on the entropy value of oil, which is inexpensive, effective and quick. However, the inability of entropy to estimate the vital transformer oil properties such as equivalent age, Neutralization Number (NN), dissipation factor (tanδ) and power factor (PF); and many intuitively derived constants usage limit its estimation accuracy. To address this issue, in this paper, we introduce an innovative transformer oil analysis using two deep convolutional learning techniques such as Convolutional Neural Network (ConvNet) and Residual Neural Network (ResNet). These two deep neural networks are chosen for this project as they have superior performance in computer vision. After estimating the equivalent aging year of transformer oil from its image by our proposed method, NN, tanδ and PF are computed using that estimated age. Our deep learning based techniques can accurately predict the transformer oil equivalent age, leading to calculate NN, tanδ and PF more accurately. The root means square error of estimated equivalent age produced by entropy, ConvNet and ResNet based methods are 0.718, 0.122 and 0.065, respectively. ConvNet and ResNet based methods have reduced the error of the oil age estimation by 83% and 91%, respectively compared to that of the entropy method. Our proposed oil image analysis can calculate the equivalent age that is very close to the actual age for all images used in the experiment. © 2019 IEEE.
- Description: E1
- Authors: Alam, Mohammad , Karmakar, Gour , Islam, Syed , Kamruzzaman, Joarder , Chetty, Madhu , Lim, Suryani , Appuhamillage, Gayan , Chattopadhyay, Gopi , Wilcox, Steve , Verheyen, Vincent
- Date: 2019
- Type: Text , Conference proceedings , Conference paper
- Relation: 29th Australasian Universities Power Engineering Conference, AUPEC 2019
- Full Text:
- Reviewed:
- Description: Electrical power grids comprise a significantly large number of transformers that interconnect power generation, transmission and distribution. These transformers having different MVA ratings are critical assets that require proper maintenance to provide long and uninterrupted electrical service. The mineral oil, an essential component of any transformer, not only provides cooling but also acts as an insulating medium within the transformer. The quality and the key dissolved properties of insulating mineral oil for the transformer are critical with its proper and reliable operation. However, traditional chemical diagnostic methods are expensive and time-consuming. A transformer oil image analysis approach, based on the entropy value of oil, which is inexpensive, effective and quick. However, the inability of entropy to estimate the vital transformer oil properties such as equivalent age, Neutralization Number (NN), dissipation factor (tanδ) and power factor (PF); and many intuitively derived constants usage limit its estimation accuracy. To address this issue, in this paper, we introduce an innovative transformer oil analysis using two deep convolutional learning techniques such as Convolutional Neural Network (ConvNet) and Residual Neural Network (ResNet). These two deep neural networks are chosen for this project as they have superior performance in computer vision. After estimating the equivalent aging year of transformer oil from its image by our proposed method, NN, tanδ and PF are computed using that estimated age. Our deep learning based techniques can accurately predict the transformer oil equivalent age, leading to calculate NN, tanδ and PF more accurately. The root means square error of estimated equivalent age produced by entropy, ConvNet and ResNet based methods are 0.718, 0.122 and 0.065, respectively. ConvNet and ResNet based methods have reduced the error of the oil age estimation by 83% and 91%, respectively compared to that of the entropy method. Our proposed oil image analysis can calculate the equivalent age that is very close to the actual age for all images used in the experiment. © 2019 IEEE.
- Description: E1
Use of MEA oxidation intermediates to monitor oxidation conditions during post-combustion capture of CO2
- Reynolds, Alicia, Verheyen, Vincent
- Authors: Reynolds, Alicia , Verheyen, Vincent
- Date: 2019
- Type: Text , Conference paper
- Relation: 14th Greenhouse Gas Control Technologies Conference (GHGT-14); Melbourne 21-26 ; October 2018 p.
- Full Text:
- Reviewed:
- Description: Amine oxidation is a serious concern for post-combustion capture (PCC) of CO2 from fossil-fuel fired power stations. Organic acids are important oxidation products and have been measured in different ratios at different pilot plants. The concentrations of acetate, formate, glycolate and oxalate were measured in samples of degraded monoethanolamine from a variety of PCC pilot plants as well as laboratory-scale degradation experiments. The results suggest that the ratios of monoethanolamine oxidation intermediates (particularly glycolate and oxalate) have potential as process monitoring tools. Ultimately, ratios of these oxidation intermediates could be used to proactively manage and minimise oxidation of amine-based PCC absorbents by indicating the need for oxygen-scavenger addition or alerting operators to imminent increases in oxidative degradation rates.
- Authors: Reynolds, Alicia , Verheyen, Vincent
- Date: 2019
- Type: Text , Conference paper
- Relation: 14th Greenhouse Gas Control Technologies Conference (GHGT-14); Melbourne 21-26 ; October 2018 p.
- Full Text:
- Reviewed:
- Description: Amine oxidation is a serious concern for post-combustion capture (PCC) of CO2 from fossil-fuel fired power stations. Organic acids are important oxidation products and have been measured in different ratios at different pilot plants. The concentrations of acetate, formate, glycolate and oxalate were measured in samples of degraded monoethanolamine from a variety of PCC pilot plants as well as laboratory-scale degradation experiments. The results suggest that the ratios of monoethanolamine oxidation intermediates (particularly glycolate and oxalate) have potential as process monitoring tools. Ultimately, ratios of these oxidation intermediates could be used to proactively manage and minimise oxidation of amine-based PCC absorbents by indicating the need for oxygen-scavenger addition or alerting operators to imminent increases in oxidative degradation rates.
Experimental evaluation of methods for reclaiming sulfur loaded amine absorbents
- Garg, Bharti, Pearson, Pauline, Cousins, Ashleigh, Verheyen, Vincent, Puxty, Graeme, Feron, Paul
- Authors: Garg, Bharti , Pearson, Pauline , Cousins, Ashleigh , Verheyen, Vincent , Puxty, Graeme , Feron, Paul
- Date: 2018
- Type: Text , Conference proceedings , Conference paper
- Relation: 14th Greenhouse Gas Control Technologies Conference (GHGT-14); Melbourne, Australia; 21st-26th October 2018 p. 1-8
- Full Text:
- Reviewed:
- Description: Sulfur dioxide (SO2) is a major flue gas contaminant that has a direct effect on the performance of amine-based carbon dioxide capture units operating on power plant flue gases. In many countries, flue gas desulfurisation (FGD) is an essential upstream requirement to CO2 capture systems, thereby increasing the overall operational and capital cost of the capture system. In Australia, the efficacy of CO2 capture may be compromised by the accumulation of SO2 in the absorption solvent. CSIRO’s CS-Cap process is designed to capture of both these acidic gases in one absorption column, thereby eliminating the need for a separate FGD unit which could potentially save millions of dollars. Previous research at CSIRO’s post-combustion capture pilot plant at Loy Yang power station has shown that mono-ethanolamine (MEA) solvent absorbs both CO2 and SO2, resulting in a spent amine absorbent rich in sulfates. Further development of the CS-Cap concept requires a deeper understanding of the properties of the sulfate-rich absorbent and the conditions under which it can be effectively regenerated. In the present study, thermal reclamation and reactive crystallisation processes were investigated, allowing the parameters affecting the regeneration of sulfate-loaded amine to be identified. It was found that amine losses were considerably higher in thermal reclamation than in reactive precipitation. During thermal reclamation, vacuum conditions were more effective than atmospheric, and pH of the initial solution played a significant role in recovery of MEA from the sulfate-rich absorbent. Reactive crystallisation could be effectively accomplished with the addition of KOH. An advantage of this process was that high purity K2SO4 crystals (~99%) were formed, despite the presence of degradation products in the solvent.
- Authors: Garg, Bharti , Pearson, Pauline , Cousins, Ashleigh , Verheyen, Vincent , Puxty, Graeme , Feron, Paul
- Date: 2018
- Type: Text , Conference proceedings , Conference paper
- Relation: 14th Greenhouse Gas Control Technologies Conference (GHGT-14); Melbourne, Australia; 21st-26th October 2018 p. 1-8
- Full Text:
- Reviewed:
- Description: Sulfur dioxide (SO2) is a major flue gas contaminant that has a direct effect on the performance of amine-based carbon dioxide capture units operating on power plant flue gases. In many countries, flue gas desulfurisation (FGD) is an essential upstream requirement to CO2 capture systems, thereby increasing the overall operational and capital cost of the capture system. In Australia, the efficacy of CO2 capture may be compromised by the accumulation of SO2 in the absorption solvent. CSIRO’s CS-Cap process is designed to capture of both these acidic gases in one absorption column, thereby eliminating the need for a separate FGD unit which could potentially save millions of dollars. Previous research at CSIRO’s post-combustion capture pilot plant at Loy Yang power station has shown that mono-ethanolamine (MEA) solvent absorbs both CO2 and SO2, resulting in a spent amine absorbent rich in sulfates. Further development of the CS-Cap concept requires a deeper understanding of the properties of the sulfate-rich absorbent and the conditions under which it can be effectively regenerated. In the present study, thermal reclamation and reactive crystallisation processes were investigated, allowing the parameters affecting the regeneration of sulfate-loaded amine to be identified. It was found that amine losses were considerably higher in thermal reclamation than in reactive precipitation. During thermal reclamation, vacuum conditions were more effective than atmospheric, and pH of the initial solution played a significant role in recovery of MEA from the sulfate-rich absorbent. Reactive crystallisation could be effectively accomplished with the addition of KOH. An advantage of this process was that high purity K2SO4 crystals (~99%) were formed, despite the presence of degradation products in the solvent.
Dynamic operation of post-combustion CO2 capture in Australian coal-fired power plants
- Bui, Mai, Gunawan, Indra, Verheyen, Vincent, Meuleman, Erik, Feron, Paul
- Authors: Bui, Mai , Gunawan, Indra , Verheyen, Vincent , Meuleman, Erik , Feron, Paul
- Date: 2014
- Type: Text , Conference paper
- Relation: 12th International Conference on Greenhouse Gas Control Technologies, GHGT 2014 p. 1368-1375
- Full Text:
- Reviewed:
- Description: Flexible operation of post-combustion CO2 capture (PCC) plants can improve efficiency through coordinating the balance between consumer demands for electricity and CO2 emission reductions. This strategy however, will impose process disturbances and the immediate and long term impact is unclear. There is a justified need for the development of accurate dynamic PCC models, as well as practical experience in dynamic operation of PCC pilot plants. This paper presents CSIRO PCC pilot plant data from the 2012 and 2013 dynamic campaigns using MEA solvent. The step-change approach to dynamic plant operation was implemented and the use of density meters to instantaneously measure CO2 loading instantaneously was investigated.
- Authors: Bui, Mai , Gunawan, Indra , Verheyen, Vincent , Meuleman, Erik , Feron, Paul
- Date: 2014
- Type: Text , Conference paper
- Relation: 12th International Conference on Greenhouse Gas Control Technologies, GHGT 2014 p. 1368-1375
- Full Text:
- Reviewed:
- Description: Flexible operation of post-combustion CO2 capture (PCC) plants can improve efficiency through coordinating the balance between consumer demands for electricity and CO2 emission reductions. This strategy however, will impose process disturbances and the immediate and long term impact is unclear. There is a justified need for the development of accurate dynamic PCC models, as well as practical experience in dynamic operation of PCC pilot plants. This paper presents CSIRO PCC pilot plant data from the 2012 and 2013 dynamic campaigns using MEA solvent. The step-change approach to dynamic plant operation was implemented and the use of density meters to instantaneously measure CO2 loading instantaneously was investigated.
- «
- ‹
- 1
- ›
- »