“…As an alternative, the extreme learning machine (ELM) calculates optimum weights in a single hidden layer feed-forward artificial neural network [5]. Hence, ELM-ANN differs from the traditional FFBP-ANN method, as the optimum weights in the network are calculated analytically, resulting in high performance capacity and fast training for large data sets [6][7][8][9][10][11][12][13][14][15][16][17][18]. However, although having many desirable features, the authors have not identified any application of ELM-ANN to water pipe networks.…”
A novel failure rate prediction model is developed by the extreme learning machine (ELM) to provide key information needed for optimum ongoing maintenance/ rehabilitation of a water network, meaning the estimated times for the next failures of individual pipes within the network. The developed ELM model is trained using more than 9500 instances of pipe failure in the Greater Toronto Area, Canada from 1920 to 2005 with pipe attributes as inputs, including pipe length, diameter, material, and previously recorded failures. The models show recent, extensive usage of pipe coating with cement mortar and cathodic protection has significantly increased their lifespan. The predictive model includes the pipe protection method as pipe attributes and can reflect in its predictions, the effect of different pipe protection methods on the expected time to the next pipe failure. The developed ELM has a superior prediction accuracy relative to other available machine learning algorithms such as feed-forward artificial neural network that is trained by backpropagation, support vector regression, and non-linear regression. The utility of the models provides useful inputs when planning and budgeting for watermain inspection, maintenance, and rehabilitation.
“…As an alternative, the extreme learning machine (ELM) calculates optimum weights in a single hidden layer feed-forward artificial neural network [5]. Hence, ELM-ANN differs from the traditional FFBP-ANN method, as the optimum weights in the network are calculated analytically, resulting in high performance capacity and fast training for large data sets [6][7][8][9][10][11][12][13][14][15][16][17][18]. However, although having many desirable features, the authors have not identified any application of ELM-ANN to water pipe networks.…”
A novel failure rate prediction model is developed by the extreme learning machine (ELM) to provide key information needed for optimum ongoing maintenance/ rehabilitation of a water network, meaning the estimated times for the next failures of individual pipes within the network. The developed ELM model is trained using more than 9500 instances of pipe failure in the Greater Toronto Area, Canada from 1920 to 2005 with pipe attributes as inputs, including pipe length, diameter, material, and previously recorded failures. The models show recent, extensive usage of pipe coating with cement mortar and cathodic protection has significantly increased their lifespan. The predictive model includes the pipe protection method as pipe attributes and can reflect in its predictions, the effect of different pipe protection methods on the expected time to the next pipe failure. The developed ELM has a superior prediction accuracy relative to other available machine learning algorithms such as feed-forward artificial neural network that is trained by backpropagation, support vector regression, and non-linear regression. The utility of the models provides useful inputs when planning and budgeting for watermain inspection, maintenance, and rehabilitation.
“…Therefore, most of the observed failure modes (planer, wedge, toppling) in the field were controlled by discontinuities. In addition to several climatic factors directly and indirectly widely induce road slope instability such as seasonal heavy included rainfall events and snow coverage on open spaces and sitespecific roadway traffic (Trenouth and Gharabaghi, 2016).…”
Road construction is mostly passed through mountainous regions or hilly terrains in Turkey like in all world. In hence, roadway construction and widening are being constructed through blasting and excavation, leading to rock slope instabilities and failures then poses threats to life and property. The reasons for failure sometime after construction are likely due to the deterioration of rock masses in cut slopes. However, slope instability and failures mainly occur due to adverse slope geomorphological complexities, joint discontinuities, weathering, man-made activities, unloading; and several induced factors such as seasonal heavy rainfall events, snow coverage, etc. The objectives of this paper are therefore to identify the most significant parameters influencing the behavior of cut slope rock masses with employing SMR ,and to perform a preliminary slope instability assessment along roadway D340-41.42, southwest of Turkey, where slopes located in a region of Taurus's rugged terrains with known complex geometry, then propose a suitable control measures to mitigate potential failures of rock slope stability. In this study, 19 rock cuts are selected based on the observed failure mechanisms, slope geometry and materials. A systematic site investigation incorporating relevant engineering geological and geotechnical parameters were carried out in detail. Based on slope instability observations and SMR results rating, concluded that these slopes were widely controlled by discontinuities (structurally controlled failures). As well, SMR classification scheme was successfully used for failure classification in Taurus's terrains. Finally, slope flattening with various angles method, wire mesh, toe support by detached rock blocks and drainage ditches redesign are proposed as a remedial measurement to protect road slope stability from failure.
“…The GEP model was trained using a subset (79%) of the dataset to avoid overfitting. The training data was chosen at random, and the remainder of the dataset was used to validate model performance as testing data (e.g., Thompson et al, 2016;Trenouth et al, 2016;Atieh et al, 2017). All variables were non-dimensionalised such that the input variables were: H s /L p , tanβ, and r/H s ; and the output variable was R 2% /H s .…”
This paper assesses the accuracy of seven empirical models and an explicit Gene-Expression Programming (GEP) model to predict wave runup against a large dataset of runup observations. Observations consist of field and laboratory measurements and include a wide array of beach types with varying sediment sizes (from fine sand to cobbles) and bed roughness (from smooth steel to asphalt). We show that the best performing models in the literature are prone to significant errors (minimum RMSE of 1.05 m and NMSE of 0.23) when used with unseen data, i.e., uncalibrated models; however, overall error values and correlations are significantly reduced when models are optimised for the dataset. The best performing empirical models use a Hunt type scaling with an additional parameter for wave induced setup. The predictive ability of the explicit GEP model, which better captures the complex nonlinear effects of the key factors on the wave runup length, resulted in a statistically significant improvement in predictive capacity in comparison to all other empirical models assessed here, even on unseen data. Wave height, wavelength, and beach slope are shown to be the three primary factors influencing wave runup, with grain size/bed roughness having a smaller, but still significant influence on the runup. The r 2 of the best optimised existing models (which takes the form of Holman (1986) and Atkinson et al. (2017) their M2 model) was 0.77, with a RMSE of 0.85 m. These were improved to an r 2 of 0.82 (6% increase) and RMSE of 0.75 m (12% decrease) in the GEP-based model. The sensitivity of the proposed GEP-based model to each input variable is assessed via a partial derivative sensitivity analysis. The results demonstrate a higher sensitivity in the model to small values of each input and that wave steepness and beach slope are the primary factors influencing wave runup.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.