Optimization Of Operation And Maintenance In Thermal Power Plants Using .
Optimization of Operation andMaintenance in ThermalPower Plants using PI SystemPresented by Hiroshi KuwaharaRyota IsekiUSERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC
Agenda Overview of Kansai Electric Power Challenges in Thermal Power Generation Optimization of Operation and Maintenance in ThermalPower Plants with IoT, Big Data and AI Introduction of PI System to Thermal Power Plants Application Examples Expansion Plan ConclusionUSERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC2
Overview of Kansai Electric PowerKansai RegionTokyoOsaka Established in 1951 Electricity Sales : 127,516 GW Installed Plant Capacity : 46 GWCapacity (2016)Fossil Fuel8%10%19%29%52%Coal PlantGas PlantGTCC PlantOil PlantUSERS CONFERENCE 201761%21%FossilNuclearHydroRenewable energy etc.@ osisoft#OSIsoftUCCoalLNGOil Copyright 2017 OSIsoft, LLC3
Kansai’s Overseas ProjectsNam (Hydro)IndonesiaTanjung Jati B(Thermal)TaiwanKuo Kuang(Thermal)Ming-Jian(Hydro)San Roque(Hydro) Total Output: 2,159 MW- Fossil : 1,788 MW- Hydro : 371 MWUSWest Deptford(Thermal)PhilippineAustraliaEmpire Power StationGTCC, 635 MWRensselaer, NY, USBluewaters(Thermal)USERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC4
Power System Deregulation in JapanBefore 9 Electricity Power Companiesdominated and controlled themarket.After Full liberalization of theelectricity market in 2016 Opening a new market- 200 billion market scaleUSERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC5
Challenges in Thermal Power GenerationOptimization of Operation & MaintenanceMinimizingForced OutageOptimizingMaintenance PlanEnhancingPlant EfficiencyTo address these challenges,Ｗe need to make the best use of enormous amount of plant operating data.USERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC6
Challenges in Thermal Power 644750020設備利用率rate[％] (%)Utilization計画外停止件数 [件]Number of Forced Outage1500H22年度2010H23年度2011USERS CONFERENCE 2017H24年度2012H25年度2013@ osisoftH26年度2014#OSIsoftUC Copyright 2017 OSIsoft, LLC7
Challenges in Thermal Power GenerationCoal Fired Power Plant2010 - 2014100080060%60040%Predictive40020020%Long TailUSERS CONFERENCE 2017@ osisoftその他0%Others湿灰処理設備Ash handlingsystem循環水ポンプCirculationwater pumpボイラケーシングBoiler Casing配管Sub systempiping主要配管Main �ーブHigh voltagemotor080%Cumulative Sum100%PreventiveBoiler TubeDowntime (hours)1200#OSIsoftUC Copyright 2017 OSIsoft, LLC8
Optimization of O & M in Thermal Power Plants with IoT, BD & AIOptimization of Operation & MaintenanceIoT devicesBD Analytics with AIData Management Infrastructure - PI SystemExpertiseUSERS CONFERENCE 2017OperatingDataKnowledge &Experience@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC9
Introduction of PI System to Thermal Power Plants20162015Oil PlantCoal PlantGTCC Plant Build the systemin two months.USERS CONFERENCE 2017 Deployed to 3 Power Plants/ Coal, Oil & GTCC Plants Create 200 surveillance screens@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC10
Introduction of PI System to Thermal Power PlantsExisting SystemDCSPlant APlant BPlant CPI SystemDBServerData TransferProgram was InstalledDataDataOPC, Modbus arenot used for DCSPI UFL Interfacewas InstalledIt took only 2 months to install PI System in our existing plants.USERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC11
Condition MonitoringWe have OSIsoft has Operation Data Knowledge Know-howand etc. PI ng Condition MonitoringUSERS CONFERENCE 2017Ensuring Expertise Transfer@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC12
Example - Condition Monitoring on Heat ExchangersCondensate Water System Surveillance �替弁の状態を確認すること。13USERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC13
Example – Condition Monitoring on Coal MillDisplay for Pre- AlarmsCoal Fired Boiler Surveillance DisplayCoal Mill Setting pre-alarm based on past failure data for earlier anomaly detection. Adding a single pre alarm to existing system costs US 10,000 / in PI System US 0 !USERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC14
Life Estimation of Crucial EquipmentTBM :Maintenance Intervals recommendedby Manufacturers.TBM CBM Now in the process of transition to CBM PastPresent CBM : Optimize Maintenance Management Future Extend equipment lifetime based on real-time conditionTBMmonitoring & inspection records.USERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC15
Example - Life Estimation of Gas Turbine Inlet Air FiltersIntake Air TempIntake Air FiltersGas Turbine OutputUSERS CONFERENCE 2017Filter Differential Press@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC16
Example - Life Estimation on Components of Crucial maining残寿命残寿命Lifetime19% 費率）取替時期 �期ScheduleConsumption earingSolenoid ValveStem NutNumberof ofNumberNumberofopen&&closeOpenCloseopen&close5% h7,2005%3%Jul.20203%17Optimize overhaul schedule of crucial equipment based on monitoringdeteriorating condition of the mechanical weak point of them.USERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC17
Further ProjectsPerformance OptimizationAnomaly Detection ToolsPI System ToolsPI System / Collect・Store・VisualizePlant ComputersProcess InstrumentsUSERS CONFERENCE 2017@ osisoftIoT devices#OSIsoftUC Copyright 2017 OSIsoft, LLC18
Use of high-tech sensor devices- Multi-Point sensor for Boiler Super Heater tubesMulti-PointSensorThermocoupleBoiler tubesUSERS CONFERENCE 2017Thermocouple Single-Point MeasurementMulti-Point sensor Multi-Point Measurement enables- More accurate lifetime estimation- Earlier anomaly detection@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC19
Boiler TubesTemperatureUse of high-tech sensor devices- Multi-Point sensor for Boiler Super Heater tubesBoiler Tube Panel LocationMulti-PointSensorTemperature of Boiler Tube Panel SurfaceUSERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC20
Further ProjectsPerformance OptimizationAnomaly Detection ToolsPI System ToolsPI System / Collect・Store・VisualizePlant ComputersProcess InstrumentsUSERS CONFERENCE 2017@ osisoftIoT devices#OSIsoftUC Copyright 2017 OSIsoft, LLC21
Big Data Analytics for Anomaly DetectionTechniqueSchematic DiagramMethod / TheoryClusteringAdaptive Resonance TheoryClassificationPattern RecognitionDeep -regressionMahalanobis - TaguchiUSERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC22
Big Data AnalyticsGas Heater heating medium tank levelActualActual value deviatefrom predicted valueOperators noticed the anomalyby Level-Low Alarm.Up to 6 days earlierPredictedGas Heater outlet flue gas temp.Anomaly Detectionwith Big Data Analytics toolWith BD analytics tools, the anomaly was detected 6 daysearlier than operators actually had noticed it.USERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC23
Big Data AnalyticsNon-Stationary rsStationary DataShut-downTimeStart-upTimeFurther TrialTo verify whether or not the tools can detect anomaly even whileplant load changes or plant is in start-up & shut-down operation.USERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC24
Further ProjectsPerformance OptimizationAnomaly Detection ToolsPI System ToolsPI System / Collect・Store・VisualizePlant ComputersProcess InstrumentsUSERS CONFERENCE 2017@ osisoftIoT devices#OSIsoftUC Copyright 2017 OSIsoft, LLC25
Plant Operation Optimization SystemParametersOptimal Reduction of excess air rate Combustion optimization withimage recognition technologyO2 Steam temp optimizationNOx Soot blowers optimizationEfficiencyCurrentCOAir fuel ratioEfficiency Improvement 0.1% abs. UPUSERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC26
Expansion Plan - PI System20152016HeadquartersMaizuruSakaikouAkohUSERS CONFERENCE 20172017Himeji No.2Himeji No.1NankoAioiGobo@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC27
SummaryCOMPANY and GOAL1)2)Picture / ImageKansai Electric PowerTo be the foremost Power Company in Japan.Competing successfully in the power market.CHALLENGETo maximize optimization ofO & M at our thermal powerplants. Minimizing forced outages Optimizing maintenance plan andtime, Making plant operations moreefficient.SOLUTIONTo merge our knowledge andexpertise in O & M with recentremarkable developments indigital technology.We confirmed that it is possible toreduce O & M costs by using the PISystem and its high compatibilitywith sensor devices and Big DataAnalytics tools. Strengthening condition monitoring Switching from TBM to CBM Conducted the verification of Multipoint sensor, anomaly detectiontools and operational improvementsoftware. PI System IoT devices Big Data Analytics toolsUSERS CONFERENCE 2017RESULTS@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC
Conclusion Optimize our Operations and Maintenance in an ongoing fashionand stay competitive with PI System. PI System is a crucial “bridge” that links large process data withour expertise, collective knowledge and digital technology.USERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC28
Contact InformationHiroshi Kuwaharakuwahara.hiroshi@c2.kepco.co.jpThermal Power DivisionThe Kansai Electric Power Co.,Inc.Ryota Isekiiseki.ryota@b5.kepco.co.jpThermal Power DivisionThe Kansai Electric Power Co.,Inc.USERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC30
QuestionsPlease wait for themicrophone before askingyour questionsPlease remember to Complete the Online Surveyfor this sessionState yourname & companyhttp://bit.ly/uc2017-appUSERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC31
Thank YouUSERS CONFERENCE 2017@ osisoft#OSIsoftUC Copyright 2017 OSIsoft, LLC
Plant Operation Optimization System Reduction of excess air rate Combustion optimization with image recognition technology Steam temp optimization Soot blowers optimization O 2 NOx CO Efficiency Air fuel ratio Parameters Optimal Current Efficiency Improvement 0.1% abs. UP
Since the eld { also referred to as black-box optimization, gradient-free optimization, optimization without derivatives, simulation-based optimization and zeroth-order optimization { is now far too expansive for a single survey, we focus on methods for local optimization of continuous-valued, single-objective problems.
An approach for the combined topology, shape and sizing optimization of profile cross-sections is the method of Graph and Heuristic Based Topology Optimization (GHT) [4], which separates the optimization problem into an outer optimization loop for the topology modification and an inner optimization loo
Structure topology optimization design is a complex multi-standard, multi-disciplinary optimization theory, which can be divided into three category Sizing optimization, Shape optimization and material selection, Topology optimization according to the structura
2. Robust Optimization Robust optimization is one of the optimization methods used to deal with uncertainty. When the parameter is only known to have a certain interval with a certain level of confidence and the value covers a certain range of variations, then the robust optimization approach can be used. The purpose of robust optimization is .
2. Topology Optimization Method Based on Variable Density 2.1. Basic Theory There are three kinds of structure optimization, they are: size optimization, shape optimization and topology op-timization. Three optimization methods correspond to the three stages of the product design process, namely the
alculus In Motion “Related Rates” * Related Rates MORE” 4.7 Applied Optimization Pg. 262-269 #2-8E, 12, 19 WS –Optimization(LL) NC #45(SM) MMM 19 Optimization MMM 20 Economic Optimization Problems WS – Optimization(KM) Calculus In Motion “Optimization-Applications” TEST: CH
vii. Image optimization . Image search optimization techniques can be viewed as a subset of search engine optimization techniques that focuses on gaining high ranks on image search engine results. 6.2 Off page Optimization[5] Off-Page optimization is the technique to improve th. e search engine rankings for keywords.
Fjalët kyce : Administrim publik, Demokraci, Qeverisje, Burokraci, Korrupsion. 3 Abstract. Public administration, and as a result all the other institutions that are involved in the spectrum of its concept, is a field of study that are mounted on many debates. First, it is not determined whether the public administration ca be called a discipline in itself, because it is still a heated debate .
