Volume 4: Controls, Diagnostics, and Instrumentation; Cycle Innovations; Cycle Innovations: Energy Storage; Education; Electric Power最新文献

{"title":"Prediction Enhancement of Machine Learning Using Time Series Modeling in Gas Turbines","authors":"Vipul Goyal, Mengyu Xu, J. Kapat, L. Vesely","doi":"10.1115/gt2021-59082","DOIUrl":"https://doi.org/10.1115/gt2021-59082","url":null,"abstract":"\u0000 Blade-path temperature can serve as a precursor of anomalies in combustion system and/or cooling system. Given observations from blade-path temperature sensors of a power plant, we consider prediction of the temperature for each sensor. The only extraneous predictor is the combustion turbine fuel flow, while measurements of other potential predictors are unavailable. Long-memory behavior and heterogeneous variance are observed from the residuals of the generalized additive model. Autoregressive Fractionally Integrated Moving Average (ARFIMA) and Generalized Autoregressive Conditional Heteroskedasticity (GARCH) models are employed to fit the residual process, which significantly improve the prediction.\u0000 Rolling one-step-ahead forecast is studied for each of the sixteen univariate blade-path temperature sensors. Their conditional variances are also estimated. Numerical experiments are performed with manually generated perturbation to evaluate the specificity and sensitivity of the prediction. Abrupt changes in the temperature are considered in the numerical study with various jump sizes. We also consider slowly increasing trend in the blade-path temperature with different slopes. Our prediction is sensitive given reasonable signal-to-noise ratio. It also has a much lower false positive rate than the generalized additive model prediction from the combustion turbine fuel flow. Difference between the real-time forecast and observation can be deployed to test for anomalies.","PeriodicalId":169840,"journal":{"name":"Volume 4: Controls, Diagnostics, and Instrumentation; Cycle Innovations; Cycle Innovations: Energy Storage; Education; Electric Power","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126080988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Lesson on Operationalizing Machine Learning for Predictive Maintenance of Gas Turbines","authors":"P. Pileggi, E. Lazovik, R. Snijders, L. Axelsson, Sietse Drost, Giulio Martinelli, Max de Grauw, Joris Graff","doi":"10.1115/gt2021-59249","DOIUrl":"https://doi.org/10.1115/gt2021-59249","url":null,"abstract":"\u0000 OEMs, service providers and end-users are moving from preventative to predictive maintenance to minimize the risk of unwanted power plant shut-downs and to maximize profitability. Digital Twin and Machine Learning (ML) are important techniques in this transformation as it complements and improves the traditional expert-based knowledge systems. There is a continued trend to use data-driven, so-called black-box, ML techniques as an improvement over traditional statistical approaches. However, these ML approaches suffer from low interpretability or explainability, making it hard to trust how or why a certain anomaly in the system is detected, limiting the trust in the prediction and making it much less likely to identify the real original cause of the problem. In this paper, we present our lesson learnt from operationalizing ML in a real-world use case that studied data from the 1.85 MWe OPRA OP16 all radial single-shaft gas turbine. We comment on the unforeseen obstacles we uncovered during our ML anomaly detection application and juxtapose them with the high potential value that our novel ML applications and explanation method can provide. ML may be enticing for the predictive maintenance of gas turbines but our lesson makes it clear that operationalizing ML goes beyond merely algorithm specifics. In line with the nature of the Digital Twin, it requires careful consideration of the specialized IT system supporting the algorithm, and the specific process it supports and in which it is deployed.","PeriodicalId":169840,"journal":{"name":"Volume 4: Controls, Diagnostics, and Instrumentation; Cycle Innovations; Cycle Innovations: Energy Storage; Education; Electric Power","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126859600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Anomaly Detection for Large Fleets of Industrial Equipment: Utilizing Machine Learning With Applications to Power Plant Monitoring","authors":"C. Allen, Chad M. Holcomb, M. D. de Oliveira","doi":"10.1115/gt2021-60116","DOIUrl":"https://doi.org/10.1115/gt2021-60116","url":null,"abstract":"\u0000 This paper covers three contemporary topics in the development and deployment of machine learning based diagnostics for large fleets of industrial machines. First, we address the philosophy of monitoring as to whether anomaly detection versus specific failure classification should be pursued, utilizing published statistics of reliability of industrial machines. Second we address the question of unsupervised versus supervised methods using a simulated example of a typical industrial machine fault, where we apply a number of popular unsupervised and supervised algorithms and directly compare their alerting ability. Lastly, model development and deployment at global scale is discussed, with application to a global fleet of gas turbines. The application includes a framework of neural network models that have been trained to find anomalous behavior for a system of the gas turbine package. The remainder of the paper includes a discussion of the results from the fleet application. Specifically, we discuss the fleet training procedure and hardships incurred in moving from proof of concept designs to full deployment on global production asset monitoring. Selected training models that failed to be of production quality are examined and the source of training error is identified. Throughout, the paper provides lessons learned, broad insights gained, and productionization issues that still need improvement as it relates to development and deployment of machine learning models at the scale of global industrial machine monitoring.","PeriodicalId":169840,"journal":{"name":"Volume 4: Controls, Diagnostics, and Instrumentation; Cycle Innovations; Cycle Innovations: Energy Storage; Education; Electric Power","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129629305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GT36 Turbine Development and Full-Scale Validation","authors":"S. Naik, B. Stephan, M. Henze","doi":"10.1115/gt2021-59470","DOIUrl":"https://doi.org/10.1115/gt2021-59470","url":null,"abstract":"\u0000 This paper describes the full-scale turbine section validation of the GT36 heavy duty gas turbine, which was conducted in a test Power Plant in Birr, Switzerland.\u0000 The GT36 Test Power Plant is extensively instrumented with both standard and specialised instrumentation. In the turbine section, specialised instrumentation includes metal and gas thermocouples, thermal paint, pressure sensors, hot gas rakes, strain gauges, five-hole probes, pyrometers and tip timing sensors. Similar specialised instrumentation also exists for the compressor, combustor and the rotor sections. Three major test campaigns were conducted over an extended period, which consisted of both long and short duration tests, including a range of off-design tests.\u0000 Within the turbine section, detailed transient and steady-state measurements were obtained of the stage inlet pressures and temperatures, airfoil surface pressures and metal temperatures. These measurements indicated that both the aerodynamic and cooling performances of the turbine blades and vanes are highly consistent and repeatable over a range of operating conditions. Detailed comparisons of the measured engine pressures and temperatures with predictions also indicated that there was generally a very good match in the Mach numbers and metal temperatures for all the turbine blades and vanes.","PeriodicalId":169840,"journal":{"name":"Volume 4: Controls, Diagnostics, and Instrumentation; Cycle Innovations; Cycle Innovations: Energy Storage; Education; Electric Power","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117350596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Reduced-Order Model for the Preliminary Design of Small-Scale Radial Inflow Turbines","authors":"Marco Manfredi, M. Alberio, M. Astolfi, A. Spinelli","doi":"10.1115/gt2021-59444","DOIUrl":"https://doi.org/10.1115/gt2021-59444","url":null,"abstract":"\u0000 Power production from waste heat recovery represents an attractive and viable solution to contribute to the reduction of pollutant emissions generated by industrial plants and automotive sector. For transport applications, a promising technology can be identified in bottoming mini-organic Rankine cycles (ORCs), devoted to heat recovery from internal combustion engines (ICE). While commercial ORCs exploiting turbo-expanders in the power range of hundreds kW to several MW are a mature technology, well-established design guidelines are not yet available for turbines targeting small power outputs (below 50 kW). The present work develops a reduced-order model for the preliminary design of mini-ORC radial inflow turbines (RITs) for high-pressure ratio applications, suitable to be integrated in a comprehensive cycle optimization. An exhaustive review of existing loss models, whose development pattern is retraced up to the original approaches, is proposed. This investigation is finalized in a loss models effectiveness analysis performed by testing several correlations over six existing geometries. These test case turbines, operating with different fluids and covering a wide range of target expansion ratio, size, and gross power output, are then employed to carry out the validation procedure, whose results prove the robustness and prediction capability of the proposed reduced-order model.","PeriodicalId":169840,"journal":{"name":"Volume 4: Controls, Diagnostics, and Instrumentation; Cycle Innovations; Cycle Innovations: Energy Storage; Education; Electric Power","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133655464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and Validation of a Novel Turbogenerator’s Robotized Inspection System","authors":"Enrico Pignone, A. Pistone, C. Canali, Fabrizio D’Agostino, G. Martorana","doi":"10.1115/gt2021-59546","DOIUrl":"https://doi.org/10.1115/gt2021-59546","url":null,"abstract":"\u0000 The inspection of power generators is a critical activity that will grow in importance during the next decades as operators are seeking solutions to continuously reduce outage duration and improve availability and reliability of the equipment. Automatic and systematic data collection on the status of health of the generator enables the possibility to implement predictive diagnostic/maintenance strategies and reduce the downtime due to repair activities. In this context robotic inspections play a crucial role since they allow a quick and efficient method to acquire data on the status of the generator. This paper describes an innovative robotic system that, thanks to a novel multi-sensor analysis method, is able to inspect and evaluate the overall status of power generators. The detection system, which is located on board a crawler robot, consists of inspection cameras, a micro-hammering system that is able to detect the acoustic response of fixing components of the generator bars and an Electromagnetic Core Imperfection Detection (EL-CID) sensor, which aims to detect insulation failures. Additionally, there is a description of how the robot has been designed to be adaptable to a wide range of different generators, and how it was tested and validated in the field.","PeriodicalId":169840,"journal":{"name":"Volume 4: Controls, Diagnostics, and Instrumentation; Cycle Innovations; Cycle Innovations: Energy Storage; Education; Electric Power","volume":"335 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131655824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Acoustic Pyrometry Robustness to Time of Flight Estimation Errors","authors":"G. Caposciutti, L. Ferrari","doi":"10.1115/gt2021-60266","DOIUrl":"https://doi.org/10.1115/gt2021-60266","url":null,"abstract":"\u0000 Acoustic pyrometry is a widely used technique for contactless temperature measurement. It may be used in several applications, especially when high temperatures and harsh environments are involved. For instance, it has been applied to measure the temperature distribution at gas turbine outlet. This technique is based on the measurement of the time of flight of an acoustic wave through a medium. If multiple emitter-receiver couples are used, by using a computational procedure a reconstruction of a temperature map is possible. On the other hand, a full assessment of the robustness of this technique to potential errors in time of flight estimation is still missing. In this study, the impact of an inaccuracy in time of flight estimation on the reconstruction of a correct temperature map is investigated by means of a statistical approach. As a general result, it was found that when the time of flight was measured without inaccuracies, temperature estimation errors may be lowered by simply increasing the number of cells in which the estimation is performed. However, when the estimation of the time of flight is affected by errors, an optimal configuration exists that minimize the temperature estimation errors.","PeriodicalId":169840,"journal":{"name":"Volume 4: Controls, Diagnostics, and Instrumentation; Cycle Innovations; Cycle Innovations: Energy Storage; Education; Electric Power","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115829595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Effect of Compressibility Factor on Turbine Performance","authors":"D. Baumgärtner, J. Otter, Andrew P. S. Wheeler","doi":"10.1115/gt2021-60241","DOIUrl":"https://doi.org/10.1115/gt2021-60241","url":null,"abstract":"\u0000 The compressibility factor Z is one of the most common properties that describes a fluid diversion from an ideal gas. Still, its effect on turbine performance is not well known. We determine a set of non-dimensional parameters that fix the gas dynamic behaviour, independent of Z, and thus isolate the effect that Z has on turbine performance. The results indicate that, contrary to the common perception, low values of Z and hence a strong diversion from an ideal gas lead to a reduction in loss for supersonic operating conditions, if all other non-dimensionals are accounted for. The aerodynamic mechanisms responsible are due to reductions in shock, boundary layer and trailing edge loss. The results from this paper are relevant for all future turbines operating with non-ideal working fluids.","PeriodicalId":169840,"journal":{"name":"Volume 4: Controls, Diagnostics, and Instrumentation; Cycle Innovations; Cycle Innovations: Energy Storage; Education; Electric Power","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130097163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Off-Design of a Pumped Thermal Energy Storage Based on Closed Brayton Cycles","authors":"G. F. Frate, Luigia Paternostro, L. Ferrari, U. Desideri","doi":"10.1115/gt2021-60185","DOIUrl":"https://doi.org/10.1115/gt2021-60185","url":null,"abstract":"\u0000 The growth of renewable energy source requires reliable, durable and cheap storage technologies. In this field, the Pumped Thermal Energy Storage (PTES), is drawing some interest as it appears not to be affected by geographical limitations and use very cheap materials. PTES is less efficient than pumped hydro and batteries, but it could achieve satisfactory efficiencies, show better economic performance and be characterized by negligible environmental impacts. A PTES stores the electric energy as thermal exergy in solid packed beds, by operating two closed Brayton cycles, one for charging and the other one for discharging. Although PTES thermodynamical behavior is well understood, the interaction between the components is rarely investigated. This study investigates the impact of packed-bed behavior on turbomachines operating conditions. In this way, PTES off-design and part-load performance are estimated. A control strategy especially suited for closed Brayton cycles, i.e. the inventory control, is used to control the system. As it resulted, PTES is characterized by an excellent part-load performance, which might be a significant advantage over the competing technologies. However, the off-design operation induced by the packed-bed thermal behavior might significantly reduce the system performance and, in particular, that of the discharge phase.","PeriodicalId":169840,"journal":{"name":"Volume 4: Controls, Diagnostics, and Instrumentation; Cycle Innovations; Cycle Innovations: Energy Storage; Education; Electric Power","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128781258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of Thermoacoustic Applications Using Waste Heat to Reduce Carbon Footprint","authors":"P. Spoor, D. Prabhudharwadkar, S. Somu, S. Saxena, D. Lacoste, W. Roberts","doi":"10.1115/gt2021-59688","DOIUrl":"https://doi.org/10.1115/gt2021-59688","url":null,"abstract":"\u0000 Thermoacoustics (TA) engines and refrigerators typically run on the Stirling cycle with acoustic networks and resonators replacing the physical pistons. Without moving parts, these TA machines achieve a reasonable fraction of Carnot’s efficiency. They are also scalable, from fractions of a Watt up to kW of cooling. Despite their apparent promise, TA devices are not in widespread use, because outside of a few niche applications, their advantages are not quite compelling enough to dislodge established technology.\u0000 In the present study, the authors have evaluated a selected group of applications that appear suitable for utilization of industrial waste heat using TA devices and have arrived at a ranked order. The principal thought is to appraise whether thermoacoustics can be a viable path, from both an economic and energy standpoint, for carbon mitigation in those applications. The applications considered include cryogenic carbon capture for power plant exhaust gases, waste-heat powered air conditioning/water chilling for factories and office buildings, hydrogen liquefaction, and zero-boiloff liquid hydrogen (LH2) storage. Although the criteria used for evaluating the applications are somewhat subjective, the overall approach has been consistent, with the same set of criteria applied to each of them. Thermoeconomic analysis is performed to evaluate the system viability, together with overall consideration of a thermoacoustic device’s general nature, advantages, and limitations.\u0000 Our study convincingly demonstrates that the most promising application is zero-boiloff liquid hydrogen storage, which is physically well-suited to thermoacoustic refrigeration and requires cooling at a temperature and magnitude not ideal for standard refrigeration methods. Waste-heat powered air conditioning ranks next in its potential to be a viable commercial application. The rest of the applications have been found to have relatively lower potentials to enter the existing commercial space.","PeriodicalId":169840,"journal":{"name":"Volume 4: Controls, Diagnostics, and Instrumentation; Cycle Innovations; Cycle Innovations: Energy Storage; Education; Electric Power","volume":"214 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132342594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}