Risk-Based Prioritization of Sewer Pipe Inspection from Infrastructure Asset Management Perspective
Abstract
:1. Introduction
1.1. Research Background
1.2. Research Obejctive
2. Literature Review
2.1. Factors Influencing Condition of Sewer Pipes
2.1.1. Physical Factors
2.1.2. Environmental Factors
2.2. Condition Prediction Models for Sewer Pipes
2.3. Criticality of Sewer Pipes
3. Methodology
3.1. Factor Identification
3.2. Data Collection and Preparation
3.2.1. Sewer Pipe Data
3.2.2. Geographic Data
3.2.3. Statistical Data
3.3. Condition Prediction
3.4. Criticality Assessment
3.4.1. Factor Weight Measurement
3.4.2. Factor Scoring
3.5. Prioritization
4. Results
4.1. Condition Prediction Model
4.1.1. Model Development and Test
4.1.2. Model Application
4.2. Criticality Assessment Model
4.2.1. Factor Weight and Score
4.2.2. Criticality Assessment Results
4.3. Prioritization Results
5. Discussion
5.1. Comparing Characteristics of High-Risk Sewer Pipes and Others
5.2. Utility of Proposed Framework for Prioritizion of High-Risk Sewer Pipes
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Appendix A
Age (years) | 0~10 | 10~20 | 20~30 | 30~40 | 40~50 | >50 |
2676 (2.0%) | 24,008 (17.8%) | 28,356 (21.1%) | 31,003 (23.0%) | 11,900 (8.8%) | 36,598 (27.2%) | |
Diameter (mm) | 0~400 | 400~500 | 500~600 | 600~700 | 700~800 | >800 |
6411 (4.8%) | 55,937 (41.6%) | 51,001 (37.9%) | 4135 (3.1%) | 7291 (5.4%) | 9766 (7.3%) | |
Length (m) | 0~10 | 10~20 | 20~30 | 30~40 | 40~50 | >50 |
17,903 (13.3%) | 22,661 (16.8%) | 28,167 (20.9%) | 26,817 (19.9%) | 20,418 (15.2%) | 18,575 (13.8%) | |
Depth (m) | 0~0.5 | 0.5~1 | 1~3 | >3 | ||
18,710 (13.9%) | 74,664 (55.5%) | 40,474 (30.1%) | 693 (0.5%) | |||
Slope (‰) | 0 | 0~5 | 5~10 | 10~30 | 30~50 | >50 |
1929 (1.4%) | 30,954 (23.0%) | 17,224 (12.8%) | 36,120 (26.8%) | 17,247 (12.8%) | 31,067 (23.1%) | |
Lane | 0~1 | 1~2 | 2~3 | 3~4 | 4~5 | >5 |
53,849 (40.0%) | 48,894 (36.3%) | 3420 (2.5%) | 11,734 (8.7%) | 1744 (1.3%) | 14,900 (11.1%) | |
Road Type | Major arterial | Minor arterial | Collector | Alley | No-way | |
5061 (3.8%) | 82,496 (61.3%) | 39,980 (29.7%) | 6646 (4.9%) | 358 (0.3%) | ||
Precipitation (mm) | 0~1200 | 1200~1250 | 1250~1300 | 1300~1350 | 1350~1400 | >1400 |
10,470 (7.8%) | 28,242 (21.0%) | 36,906 (27.4%) | 42,907 (31.9%) | 7580 (5.6%) | 8436 (6.3%) | |
Land Use | Industrial | Commercial | Rural | Residential | Others | |
2568 (1.9%) | 14,596 (10.8%) | 1233 (0.9%) | 56,383 (41.9%) | 59,761 (44.4%) | ||
Population | 0~10,000 | 10,000~20,000 | 20,000~30,000 | 30,000~40,000 | 40,000~50,000 | >50,000 |
5862 (4.4%) | 26,353 (19.6%) | 56,036 (41.6%) | 37,373 (27.8%) | 6993 (5.2%) | 1924 (1.4%) |
Age (years) | 0~10 | 10~20 | 20~30 | 30~40 | 40~50 | >50 |
23,110 (15.6%) | 13,866 (9.4%) | 19,672 (13.3%) | 21,034 (14.2%) | 9791 (6.6%) | 60,404 (40.8%) | |
Diameter (mm) | 0~400 | 400~500 | 500~600 | 600~700 | 700~800 | >800 |
22,746 (15.4%) | 59,578 (40.3%) | 40,792 (27.6%) | 3734 (2.5%) | 8825 (6.0%) | 12,202 (8.3%) | |
Length (m) | 0~10 | 10~20 | 20~30 | 30~40 | 40~50 | >50 |
39,856 (27.0%) | 29,470 (19.9%) | 27,594 (18.7%) | 21,463 (14.5%) | 14,724 (10.0%) | 14,770 (10.0%) | |
Depth (m) | 0~0.5 | 0.5~1 | 1~3 | >3 | ||
20,906 (14.1%) | 73,027 (49.4%) | 51,907 (35.1%) | 2037 (1.4%) | |||
Slope (‰) | 0 | 0~5 | 5~10 | 10~30 | 30~50 | >50 |
2959 (2.0%) | 29,037 (19.6%) | 18,233 (12.3%) | 38,302 (25.9%) | 19,458 (13.2%) | 39,888 (27.0%) | |
Lane | 0~1 | 1~2 | 2~3 | 3~4 | 4~5 | >5 |
71,136 (48.1%) | 49,420 (33.4%) | 3548 (2.4%) | 11,034 (7.5%) | 1911 (1.3%) | 10,828 (7.3%) | |
Road Type | No-way | Alley | Collector | Minor arterial | Major arterial | |
387 (0.3%) | 5730 (3.9%) | 48,779 (33.0%) | 83,144 (56.2%) | 9837 (6.7%) | ||
Precipitation (mm) | 0~1200 | 1200~1250 | 1250~1300 | 1300~1350 | 1350~1400 | >1400 |
11,350 (7.7%) | 28,319 (19.2%) | 43,008 (29.1%) | 40,047 (27.1%) | 10,284 (7.0%) | 14,869 (10.1%) | |
Land Use | Others | Residential | Rural | Commercial | Industrial | |
78,627 (53.2%) | 52,969 (35.8%) | 764 (0.5%) | 12,987 (8.8%) | 2530 (1.7%) | ||
Population | 0~10,000 | 10,000~20,000 | 20,000~30,000 | 30,000~40,000 | 40,000~50,000 | >50,000 |
8785 (5.9%) | 28,209 (19.1%) | 60,974 (41.2%) | 39,605 (26.8%) | 9203 (6.2%) | 1101 (0.7%) |
References
- American Society of Civil Engineers (ASCE). 2021 Infrastructure Report Card; American Society of Civil Engineers: Reston, VA, USA, 2021. [Google Scholar]
- Ariaratnam, S.T.; El-Assaly, A.; Yang, Y. Assessment of infrastructure inspection needs using logistic models. J. Infrastruct. Syst. 2001, 7, 160–165. [Google Scholar] [CrossRef]
- Wirahadikusumah, R.; Abraham, D.; Iseley, T. Challenging issues in modeling deterioration of combined sewers. J. Infrastruct. Syst. 2001, 7, 77–84. [Google Scholar] [CrossRef]
- American Society of Civil Engineers. Failure to Act: Closing the Infrastructure Investment Gap for America’s Economic Future; American Society of Civil Engineers: Reston, VA, USA, 2016. [Google Scholar]
- Ingenium, I. International Infrastructure Management Manual; Association of Local Government Engineering NZ Inc. (INGENIUM); The Institute of Public Works Engineering of Australia (IPWEA): Sydney, Australia, 2011. [Google Scholar]
- Ugarelli, R.; Venkatesh, G.; Brattebø, H.; Di Federico, V.; Sægrov, S. Asset management for urban wastewater pipeline networks. J. Infrastruct. Syst. 2010, 16, 112–121. [Google Scholar] [CrossRef]
- Brunetto, Y.; Xerri, M.; Nelson, S. Building a proactive, engagement culture in asset management organizations. J. Manag. Eng. 2014, 30, 04014014. [Google Scholar] [CrossRef] [Green Version]
- Henderson, K.; Pahlenkemper, G.; Kraska, O. Integrated asset management–an investment in sustainability. Procedia Eng. 2014, 83, 448–454. [Google Scholar] [CrossRef]
- Chae, M.J. Automated Interpretation and Assessment of Sewer Pipeline Infrastructure; Purdue University: West Lafayette, IN, USA, 2001. [Google Scholar]
- Khan, Z.; Zayed, T.; Moselhi, O. Stochastic Analysis of Factors Affecting Sewer Network Operational Condition. In ICPTT 2009: Advances and Experiences with Pipelines and Trenchless Technology for Water, Sewer, Gas, and Oil Applications; Shanghai, China, 2009; pp. 389–400. Available online: https://ascelibrary.org/doi/abs/10.1061/41073(361)41 (accessed on 23 June 2021).
- Baah, K.; Dubey, B.; Harvey, R.; McBean, E. A risk-based approach to sanitary sewer pipe asset management. Sci. Total Environ. 2015, 505, 1011–1017. [Google Scholar] [CrossRef] [PubMed]
- Bădilă, I.N.; Rusu, T.; Gabor, T. Study on the Impact of Sewer Pipes on the Environment. J. Environ. Res. Prot. 2014, 11, 1–10. [Google Scholar]
- Halfawy, M.R.; Dridi, L.; Baker, S. Integrated decision support system for optimal renewal planning of sewer networks. J. Comput. Civ. Eng. 2008, 22, 360–372. [Google Scholar] [CrossRef] [Green Version]
- Ana, E.; Bauwens, W. Modeling the structural deterioration of urban drainage pipes: The state-of-the-art in statistical methods. Urban Water J. 2010, 7, 47–59. [Google Scholar] [CrossRef]
- Kley, G.; Caradot, N. Review of Sewer Deterioration Models; KWB Project SEMA Report; Veolia: Berlin, Germany, 2013. [Google Scholar]
- British Standards Institution. 55-2: Asset Management. In Part 2: Guidelines for the Application of PAS 55-1; British Standards Institution: London, UK, 2008. [Google Scholar]
- Montoya Montoya, A. The Influence of Different Characteristics on the Probabilities of Failure of Sewer Pipes. Master’s Thesis, Delft University of Technology, 2019. Available online: https://repository.tudelft.nl/islandora/object/uuid:62bbc111-402f-4e51-b4b6-bfe979ee691d?collection=education (accessed on 23 June 2021).
- Chughtai, F.; Zayed, T. Infrastructure condition prediction models for sustainable sewer pipelines. J. Perform. Constr. Facil. 2008, 22, 333–341. [Google Scholar] [CrossRef]
- Malek Mohammadi, M.; Najafi, M.; Kermanshachi, S.; Kaushal, V.; Serajiantehrani, R. Factors Influencing the Condition of Sew-er Pipes: State-of-the-Art Review. J. Pipeline Syst. Eng. Pract. 2020, 11, 03120002. [Google Scholar] [CrossRef]
- Kulandaivel, G. Sewer Pipeline Condition Prediction Using Neural Network Models. Master’s Thesis, Michigan State University, 2004. Available online: https://0-www-proquest-com.brum.beds.ac.uk/docview/305157063/previewPDF/2E2FA03FF21D42DDPQ/1?accountid=11933 (accessed on 23 June 2021).
- Malek Mohammadi, M. Development of Condition Prediction Models for Sanitary Sewer Pipes. Ph.D. Thesis, University of Texas at Arlington, 2019. Available online: https://rc.library.uta.edu/uta-ir/handle/10106/28665 (accessed on 23 June 2021).
- Salman, B. Infrastructure Management and Deterioration Risk Assessment of Wastewater Collection Systems. Ph.D. Thesis, University of Cincinnati, 2010. Available online: https://etd.ohiolink.edu/apexprod/rws_olink/r/1501/10?clear=10&p10_accession_num=ucin1282051343 (accessed on 23 June 2021).
- Abraham, D.M.; Wirahadikusumah, R.; Short, T.; Shahbahrami, S. Optimization modeling for sewer network management. J. Constr. Eng. Manag. 1998, 124, 402–410. [Google Scholar] [CrossRef]
- Bakry, I.; Alzraiee, H.; Kaddoura, K.; El Masry, M.; Zayed, T. Condition prediction for chemical grouting rehabilitation of sewer networks. J. Perform. Constr. Facil. 2016, 30, 04016042. [Google Scholar] [CrossRef]
- Jeong, H.S.; Baik, H.-S.; Abraham, D.M. An ordered probit model approach for developing markov chain based deterioration model for wastewater infrastructure systems. In Pipelines 2005: Optimizing Pipeline Design, Operations, and Maintenance in Today’s Economy; 2005; pp. 649–661. Available online: https://ascelibrary.org/doi/abs/10.1061/40800(180)52 (accessed on 23 June 2021).
- Ana, E.; Bauwens, W.; Pessemier, M.; Thoeye, C.; Smolders, S.; Boonen, I.; De Gueldre, G. An investigation of the factors influencing sewer structural deterioration. Urban Water J. 2009, 6, 303–312. [Google Scholar] [CrossRef]
- Salman, B.; Salem, O. Risk assessment of wastewater collection lines using failure models and criticality ratings. J. Pipeline Syst. Eng. Pract. 2012, 3, 68–76. [Google Scholar] [CrossRef]
- Davies, J.; Clarke, B.; Whiter, J.; Cunningham, R. Factors influencing the structural deterioration and collapse of rigid sewer pipes. Urban Water 2001, 3, 73–89. [Google Scholar] [CrossRef]
- Baur, R.; Herz, R. Selective inspection planning with ageing forecast for sewer types. Water Sci. Technol. 2002, 46, 389–396. [Google Scholar] [CrossRef]
- Ribalta, M.; Mateu, C.; Bejar, R.; Rubión, E.; Echeverria, L.; Varela Alegre, F.J.; Corominas, L. Sediment Level Prediction of a Combined Sewer System Using Spatial Features. Sustainability 2021, 13, 4013. [Google Scholar] [CrossRef]
- El-Abbasy, M.S.; Zayed, T.; El Chanati, H.; Mosleh, F.; Senouci, A.; Al-Derham, H. Simulation-based deterioration patterns of water pipelines. Struct. Infrastruct. Eng. 2019, 15, 965–982. [Google Scholar] [CrossRef]
- Salman, B.; Salem, O. Modeling failure of wastewater collection lines using various section-level regression models. J. Infrastruct. Syst. 2012, 18, 146–154. [Google Scholar] [CrossRef]
- Nasrin, T.; Sharma, A.K.; Muttil, N. Impact of short duration intense rainfall events on sanitary sewer network performance. Water 2017, 9, 225. [Google Scholar] [CrossRef] [Green Version]
- Marlow, D.; Heart, S.; Burn, S.; Urquhart, A.; Gould, S.; Anderson, M.; Cook, S.; Ambrose, M.; Madin, B.; Fitzgerald, A. Condition Assessment Strategies and Protocols for Water and Wastewater Utility Assets; CSIRO: Australia, 2007; Available online: http://hdl.handle.net/102.100.100/127479?index=1 (accessed on 23 June 2021).
- Angarita, H.; Niño, P.; Vargas, D.; Hernández, N.; Torres, A. Identifying explanatory variables of structural state for optimum asset management of urban drainage networks: A pilot study for the city of Bogota. Ing. Investig. 2017, 37, 6–16. [Google Scholar] [CrossRef]
- Hawari, A.; Alkadour, F.; Elmasry, M.; Zayed, T. A state of the art review on condition assessment models developed for sewer pipelines. Eng. Appl. Artif. Intell. 2020, 93, 103721. [Google Scholar] [CrossRef]
- Baik, H.-S.; Jeong, H.S.; Abraham, D.M. Estimating transition probabilities in Markov chain-based deterioration models for management of wastewater systems. J. Water Resour. Plan. Manag. 2006, 132, 15–24. [Google Scholar] [CrossRef]
- Kleiner, Y.; Sadiq, R.; Rajani, B. Modeling failure risk in buried pipes using fuzzy Markov deterioration process. In Pipeline Engineering and Construction: What’s on the Horizon? 2004; pp. 1–12. Available online: https://ascelibrary.org/doi/abs/10.1061/40745(146)7 (accessed on 23 June 2021).
- Le Gat, Y. Modelling the deterioration process of drainage pipelines. Urban Water J. 2008, 5, 97–106. [Google Scholar] [CrossRef]
- Tran, D.; Perera, B.; Ng, A. Neural network based prediction models for structural deterioration of urban drainage pipes. In Land, Water and Environmental Management: Integrated Systems for Sustainability, Proceedings, Christchurch; 2007; pp. 2264–2270. Available online: https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.563.9704&rep=rep1&type=pdf (accessed on 23 June 2021).
- Syachrani, S.; Jeong, H.S.D.; Chung, C.S. Decision tree-based deterioration model for buried wastewater pipelines. J. Perform. Constr. Facil. 2013, 27, 633–645. [Google Scholar] [CrossRef]
- Harvey, R.R.; McBean, E.A. Predicting the structural condition of individual sanitary sewer pipes with random forests. Can. J. Civ. Eng. 2014, 41, 294–303. [Google Scholar] [CrossRef]
- Hahn, M.A.; Palmer, R.N.; Merrill, M.S.; Lukas, A.B. Expert system for prioritizing the inspection of sewers: Knowledge base formulation and evaluation. J. Water Resour. Plan. Manag. 2002, 128, 121–129. [Google Scholar] [CrossRef] [Green Version]
- Elsawah, H.; Bakry, I.; Moselhi, O. Decision support model for integrated risk assessment and prioritization of intervention plans of municipal infrastructure. J. Pipeline Syst. Eng. Pract. 2016, 7, 04016010. [Google Scholar] [CrossRef]
- Vladeanu, G.J.; Matthews, J.C. Consequence-of-failure model for risk-based asset management of wastewater pipes using AHP. J. Pipeline Syst. Eng. Pract. 2019, 10, 04019005. [Google Scholar] [CrossRef]
- Anbari, M.J.; Tabesh, M.; Roozbahani, A. Risk assessment model to prioritize sewer pipes inspection in wastewater collection networks. J. Environ. Manag. 2017, 190, 91–101. [Google Scholar] [CrossRef]
- Rossi, R.C., II. Criticality and Risk Assessment for Pipe Rehabilitation in the City of Santa Barbara Sewer System. Master’s Thesis, California Polytechnic State University, 2015. Available online: https://digitalcommons.calpoly.edu/cgi/viewcontent.cgi?referer=https://0-scholar-google-com.brum.beds.ac.uk/&httpsredir=1&article=2553&context=theses (accessed on 23 June 2021).
- Son, J.; Lee, J.; Oh, J. Sewer CCTV Inspection Prioritization Based on Risk Assessment. J. Korean Soc. Civ. Eng. 2017, 37, 585–592. [Google Scholar]
- Kabir, G.; Balek, N.B.C.; Tesfamariam, S. Consequence-based framework for buried infrastructure systems: A Bayesian belief network model. Reliab. Eng. Syst. Saf. 2018, 180, 290–301. [Google Scholar] [CrossRef]
- Singh, A.; Adachi, S. Bathtub curves and pipe prioritization based on failure rate. Built Environ. Proj. Asset Manag. 2013, 3, 105–122. [Google Scholar] [CrossRef]
- Kim, K.; Kim, J.; Kwak, T.-Y.; Chung, C.-K. Logistic regression model for sinkhole susceptibility due to damaged sewer pipes. Nat. Hazards 2018, 93, 765–785. [Google Scholar] [CrossRef]
- Miles, S.W.; Styers, F.C.; Nesbit, C.M. Setting Pipeline Rehabilitation Priorities to Achieve “Best” Results—A Case Study Using Condition and Criticality Criteria. In Pipelines 2007: Advances and Experiences with Trenchless Pipeline Projects; 2007; pp. 1–10. Available online: https://ascelibrary.org/doi/abs/10.1061/40934(252)72 (accessed on 23 June 2021).
- Kaddoura, K.; Zayed, T. Criticality Model to Prioritize Pipeline Rehabilitation Decisions. In Pipelines 2018: Condition Assessment, Construction, and Rehabilitation; American Society of Civil Engineers: Reston, VA, USA, 2018; pp. 75–85. [Google Scholar]
- Şen, Z. Average areal precipitation by percentage weighted polygon method. J. Hydrol. Eng. 1998, 3, 69–72. [Google Scholar] [CrossRef]
- Saaty, T.L. How to make a decision: The analytic hierarchy process. Eur. J. Oper. Res. 1990, 48, 9–26. [Google Scholar] [CrossRef]
Model | Category | Factor | Reference |
---|---|---|---|
Condition Prediction | Physical | Age | [21,28,50] |
Diameter | [2,10,18,24,25,31] | ||
Length | [18,25,26,28,32] | ||
Depth | [10,18,25] | ||
Slope | [18,25,26,29] | ||
Environmental | Number of Lanes | [18,27,31] | |
Road Type | [20,24,46] | ||
Precipitation | [20,33,51] | ||
Land Use | [26,31] | ||
Population | [21,42] | ||
Criticality Assessment | Economic | Diameter | [11,13,46,47,52] |
Length | [45,47,49,53] | ||
Depth | [11,13,27,47,49] | ||
Social | Distance to Medical Facility | [11,45,47] | |
Distance to Educational Facility | [11,45,47] | ||
Number of Lanes | [13,27,45,49] | ||
Distance to Railway | [11,27,46] | ||
Distance to Commercial Area | [45,48] | ||
Distance to Residential Area | [45,46,48] | ||
Environmental | Distance to River | [46,47,48,52] | |
Distance to Forest | [12] | ||
Distance to Farmland | [12] |
Data | # of Data | Year | Type | Source |
---|---|---|---|---|
Medical Facility | 22,586 | 2019 | Point | Healthcare Bigdata Hub |
Educational Facility | 1316 | 2019 | Point | School Information System |
Road | 328,404 | 2014 | Line | Seoul Metropolitan Government |
68,580 | 2018 | Line | National Spatial Data Infrastructure Portal | |
Railway | 58 | 2018 | Line | National Spatial Data Infrastructure Portal |
Land Use | 32,250 | 2018 | Polygon | National Spatial Data Infrastructure Portal |
River | 154 | 2016 | Polygon | National Spatial Data Infrastructure Portal |
Forest | 1153 | 2019 | Polygon | Forest Geographic Information System |
Drainage Sector | 239 | 2014 | Polygon | Seoul Metropolitan Government |
Predicted Bad (Grade A + B) | Predicted Good (Grade C) | |
---|---|---|
Actual Bad (Grade A + B) | True Positive (TP) | False Negative (FN) |
Actual Good (Grade C) | False Positive (FP) | True Negative (TN) |
Indicator | Description | Equation |
---|---|---|
Accuracy | Ratio of data accurately predicted by the model regardless of condition grade | |
Precision | Ratio of actual Grade A + Bs among Grade A + Bs predicted by the model | |
Recall | Ratio of Grade A + Bs predicted by the model among total actual Grade A + Bs |
Category | Factor | Score | ||||
---|---|---|---|---|---|---|
5 | 4 | 3 | 2 | 1 | ||
Economic | Diameter | >900 mm | >650 mm | >450 mm | >350 mm | ≤350 mm |
Length | >50 m | >30 m | >15 m | >5 m | ≤5 m | |
Depth | <1 m | <3 m | <7 m | <10 m | ≥10 m | |
Social | Medical | <20 m | <50 m | <100 m | <150 m | ≥150 m |
Educational | <50 m | <100 m | <150 m | <200 m | ≥200 m | |
Road | >7 lanes | >5 lanes | >3 lanes | >1 lane | ≤1 lane | |
Railway | <70 m | <120 m | <200 m | <400 m | ≥400 m | |
Commercial | <20 m | <50 m | <100 m | <200 m | ≥200 m | |
Residential | <20 m | <50 m | <100 m | <200 m | ≥200 m | |
Environmental | River | <50 m | <150 m | <250 m | <450 m | ≥450 m |
Forest | <50 m | <150 m | <250 m | <450 m | ≥450 m | |
Farmland | <50 m | <150 m | <250 m | <450 m | ≥450 m |
Performance | Method | Mean | Standard Deviation | t-Value | p-Value |
---|---|---|---|---|---|
Accuracy | Random Forest | 0.748 | 0.193 | - | - |
Decision Tree | 0.716 | 0.293 | 109.390 | 0.000 | |
ANN | 0.612 | 0.834 | 166.992 | 0.000 | |
Logistic Reg. | 0.605 | 0.013 | 774.685 | 0.000 | |
Precision | Random Forest | 0.725 | 0.003 | - | - |
Decision Tree | 0.685 | 0.004 | 92.910 | 0.000 | |
ANN | 0.584 | 0.029 | 47.754 | 0.000 | |
Logistic Reg. | 0.578 | 0.000 | 520.173 | 0.000 | |
Recall | Random Forest | 0.691 | 0.003 | - | - |
Decision Tree | 0.660 | 0.007 | 43.992 | 0.000 | |
ANN | 0.464 | 0.129 | 17.588 | 0.000 | |
Logistic Reg. | 0.384 | 0.000 | 913.766 | 0.000 |
Condition Class | Output Range | Frequency | Cumulative Frequency |
---|---|---|---|
Good (Grade C) | 0.0~0.1 | 2842 (1.9%) | 2842 (1.9%) |
0.1~0.2 | 7748 (5.2%) | 10,590 (7.2%) | |
0.2~0.3 | 13,581 (9.2%) | 24,171 (16.3%) | |
0.3~0.4 | 20,299 (13.7%) | 44,470 (30.0%) | |
0.4~0.5 | 25,896 (17.5%) | 70,366 (47.6%) | |
Bad (Grades A and B) | 0.5~0.6 | 27,448 (18.6%) | 97,814 (66.2%) |
0.6~0.7 | 23,728 (16.0%) | 121,542 (82.2%) | |
0.7~0.8 | 15,978 (10.8%) | 137,520 (93.0%) | |
0.8~0.9 | 7816 (5.3%) | 145,336 (98.3%) | |
0.9~1.0 | 2514 (1.7%) | 147,850 (100.0%) |
Category | Factor | Weight | Score | ||||
---|---|---|---|---|---|---|---|
5 | 4 | 3 | 2 | 1 | |||
Economic | Diameter | 0.0398 | 8555 (5.8%) | 16,203 (11.0%) | 42,366 (28.6%) | 59,004 (39.9%) | 21,749 (14.7%) |
Length | 0.0249 | 14,770 (10.0%) | 36,187 (24.5%) | 41,893 (28.3%) | 34,809 (23.5%) | 20,218 (13.7%) | |
Depth | 0.1121 | 93,933 (63.5%) | 51,907 (35.1%) | 1784 (1.2%) | 100 (0.1%) | 153 (0.1%) | |
Social | Medical | 0.0445 | 10,314 (7.0%) | 25,183 (17.0%) | 34,722 (23.5%) | 27,552 (18.6%) | 50,106 (33.9%) |
Educational | 0.0222 | 4388 (3.0%) | 9591 (6.5%) | 13,577 (9.2%) | 15,891 (10.7%) | 104,430 (70.6%) | |
Lanes | 0.2208 | 4204 (2.8%) | 6624 (4.5%) | 12,945 (8.8%) | 52,968 (35.8%) | 71,136 (48.1%) | |
Railway | 0.1908 | 28,734 (19.4%) | 12,798 (8.7%) | 16,464 (11.1%) | 32,285 (21.8%) | 57,596 (38.9%) | |
Commercial | 0.0483 | 25,907 (17.5%) | 11,396 (7.7%) | 17,658 (11.9%) | 30,056 (20.3%) | 62,860 (42.5%) | |
Residential | 0.0955 | 104,000 (70.3%) | 14,529 (9.8%) | 12,713 (8.6%) | 10,400 (7.0%) | 6235 (4.2%) | |
Environmental | River | 0.1181 | 9735 (6.6%) | 16,216 (11.0%) | 14,387 (9.7%) | 26,752 (18.1%) | 80,787 (54.6%) |
Forest | 0.0260 | 19,406 (13.1%) | 14,466 (9.8%) | 13,362 (9.0%) | 25,544 (17.3%) | 75,099 (50.8%) | |
Farmland | 0.0571 | 3208 (2.2%) | 2871 (1.9%) | 2591 (1.8%) | 6180 (4.2%) | 133,027 (90.0%) |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Lee, J.; Park, C.Y.; Baek, S.; Han, S.H.; Yun, S. Risk-Based Prioritization of Sewer Pipe Inspection from Infrastructure Asset Management Perspective. Sustainability 2021, 13, 7213. https://0-doi-org.brum.beds.ac.uk/10.3390/su13137213
Lee J, Park CY, Baek S, Han SH, Yun S. Risk-Based Prioritization of Sewer Pipe Inspection from Infrastructure Asset Management Perspective. Sustainability. 2021; 13(13):7213. https://0-doi-org.brum.beds.ac.uk/10.3390/su13137213
Chicago/Turabian StyleLee, Jeonghun, Chan Young Park, Seungwon Baek, Seung H. Han, and Sungmin Yun. 2021. "Risk-Based Prioritization of Sewer Pipe Inspection from Infrastructure Asset Management Perspective" Sustainability 13, no. 13: 7213. https://0-doi-org.brum.beds.ac.uk/10.3390/su13137213