Kuo-Wei Liao

Groutability estimation of grouting processes with cement grouts using Differential Flower Pollination Optimized Support Vector Machine

Display OmittedDifferential Flower Pollination-optimized Support Vector Machine for Groutability Prediction (DFP-SVMGP). A soft computing method for groutability estimation is proposed.A hybrid metaheuristic is constructed to optimize the SVM-based model.The effect of evaluation functions on the model performance is studied.Relevant influencing factors in two datasets have been revealed.The new approach attains high prediction accuracy. This research presents a soft computing methodology for groutability estimation of grouting processes that employ cement grouts. The method integrates a hybrid metaheuristic and the Support Vector Machine (SVM) with evolutionary input factor and hyper-parameter selection. The new prediction model is constructed and verified using two datasets of grouting experiments. The contribution of this study to the body of knowledge is multifold. First, the efficacies of the Flower Pollenation Algorithm (FPA) and the Differential Evolution (DE) are combined to establish an integrated metaheuristic approach, named as Differential Flower Pollenation (DFP). The integration of the FPA and the DE aims at harnessing the strength and complementing the disadvantage of each individual optimization algorithm. Second, the DFP is employed to optimize the input factor selection and hyper-parameter tuning processes of the SVM-based groutability prediction model. Third, this study conducts a comparative work to investigate the effects of different evaluation functions on the model performance. Finally, the research findings show that the new integrated framework can help identify a set of relevant groutability influencing factors and deliver superior prediction performance compared with other state-of-the-art approaches.

A probabilistic evaluation of pier-scour potential in the Gaoping River Basin of Taiwan

AbstractA probabilistic approach is used to create a preliminary inspection evaluation form (PIEF) for scour potential at bridge sites. In Taiwan, the risk of pier scour is often evaluated using a two-step procedure. First, a bridge is visually inspected based on a PIEF. An advanced scour risk analysis is conducted for a bridge with a high PIEF score. Because a PIEF can quickly evaluate scour potential, it can be used to build a maintenance sequence for a group of bridges. However, a PIEF is often created based on only engineers’ experience; the accuracy and reliability of PIEFs have not been examined systematically. Thus, a probabilistic-based PIEF is constructed by establishing a close correlation between the PIEF score and scour potential via Taguchi method. The scour potential is evaluated by Bayesian network (BN) that incorporates experts’ judgments and results of reliability analyses. For example, the conditional probabilities (CP) in the proposed BN are calculated based on an existing PIEF and resu...

A single loop reliability-based design optimization using EPM and MPP-based PSO

A reliability-based design optimization (RBDO) incorporates a probabilistic analysis with an optimization technique to find a best design within a reliable design space. However, the computational cost of an RBDO task is often expensive compared to a deterministic optimization, which is mainly due to the reliability analysis performed inside the optimization loop. Theoretically, the reliability of a given design point can be obtained through a multidimensional integration. Integration with multiple variables over the safety domain is, unfortunately, formidable in most cases. Monte- Carlo simulation (MCS) is often used to solve this difficulty. However, the inherit statistic uncertainty associated with MCS sometimes causes an unstable RBDO solution. To avoid this unstable solution, this study transforms a multi-variable constraint into a single variable constraint using an exponential function with a polynomial coefficient (EPM). The adaptive Gauss-Kronrod quadrature is used to compute the constraint reliability. The calculated reliability and its derivative are incorporated with an optimizer such as sequential quadratic programming (SQP) or most probable point particle swarm optimization (MPP-based PSO) to conduct the RBDO task. To ensure the design accuracy, the stability of the RBDO algorithm with respect to the initial point is investigated through several numerical examples.

Multilevel Optimization Considering Variability in Design Variables of Multidisciplinary System

The objective of this paper is to investigate the reliability-based design optimization (RBDO) for a multidisciplinary system (RBMDO). RBMDO has drawn attention recently because a system level analysis is usually needed in realistic engineering application and, in most cases, variability exists in design variables. However, the forward and feedback calculations among each sub-system and the reliability analysis within an optimization loop are very expensive, thus the RBMDO problem is computationally prohibited and has become one of the research topics in these days. Many researchers have focused on avoiding the system level analysis without sacrificing the accuracy. For this, Analytical Target Cascading (ATC) is used here to decompose the multidisciplinary system. As a result, RBMDO becomes several individual sub-system optimizations thus no system level analysis is required. ATC is a multi-level optimization framework and possesses the characteristic of distributed system. One of the key characteristics of ATC is the original problem is decomposed hierarchically at multiple levels, while the inconsistency among subsystems at each level is coordinated at one level above. ATC has been proven to be a robust approach for multidisciplinary optimization (MDO) problem. To accelerate the reliability-based optimization in each sub-system, the methodology of Sequential Optimization and Reliability Assessment (SORA) is utilized here. SORA is a single loop process wherein the RBO problem, a double-loop process in nature, is converted into a series of deterministic optimizations and reliability analyses, and therefore, the computational cost is reduced. Note that in the proposed ATC approach, the linking variables among each sub-system are the reliability-based optimal design variables. The formulation of the proposed method is then remains same as the ATC although the problem now is more complicated (probabilistic vs. deterministic). A numerical example is given to demonstrate the proposed process. Results are compared to the Fully Integrated Optimization (FIO) or All-In-One (AIO) method to verify the accuracy of the proposed process. Efficiency is also examined by comparing the method of Probabilistic Analytical Target Cascading (PATC). Results shown here indicate the proposed method can provide an optimal design in a very efficient way for a multidisciplinary system that usually involves extreme high computation costs.

A probabilistic bridge safety evaluation against floods.

To further capture the influences of uncertain factors on river bridge safety evaluation, a probabilistic approach is adopted. Because this is a systematic and nonlinear problem, MPP-based reliability analyses are not suitable. A sampling approach such as a Monte Carlo simulation (MCS) or importance sampling is often adopted. To enhance the efficiency of the sampling approach, this study utilizes Bayesian least squares support vector machines to construct a response surface followed by an MCS, providing a more precise safety index. Although there are several factors impacting the flood-resistant reliability of a bridge, previous experiences and studies show that the reliability of the bridge itself plays a key role. Thus, the goal of this study is to analyze the system reliability of a selected bridge that includes five limit states. The random variables considered here include the water surface elevation, water velocity, local scour depth, soil property and wind load. Because the first three variables are deeply affected by river hydraulics, a probabilistic HEC-RAS-based simulation is performed to capture the uncertainties in those random variables. The accuracy and variation of our solutions are confirmed by a direct MCS to ensure the applicability of the proposed approach. The results of a numerical example indicate that the proposed approach can efficiently provide an accurate bridge safety evaluation and maintain satisfactory variation.

Reliability-Based Design Optimization of a Hydraulic Cylinder Component

[Abstract] Deterministic optimization process does not consider variability in design variables/parameters and generally drives the optimum design to the vicinity of the imposed constraint boundary. However, when the inevitable variability in design variables/parameters is taken into consideration, the probability of failure for the deterministic optimum design significantly increases. Reliability-based design optimization (RBDO) incorporates probabilistic analysis into optimization process so that an optimum design has great chance of staying in the feasible design space when variability in design variables/parameters is considered. One of the biggest drawbacks of using the RBDO approach is high computational cost that is often impractical to use in industries. In search of the most suitable RBDO method for industrial applications, we, first, evaluated several existing RBDO approaches such as the double-loop RBDO, the Sequential Optimization and Reliability Assessment (SORA), the Response Surface Method (RSM) in detail. Then, we proposed a more practical RBDO approach called Sequential Optimization with Mean Value based Reliability Analysis (SOMVRA) by combining some of the existing RBDO techniques. The effectiveness of the proposed RBDO approach is demonstrated using a industry problem. It should be noted that the RSM is a very attractive approach for engineers, but it is very difficult to obtain an accurate surrogate model for a complex problem. Therefore, it should be used carefully.

A Stable Reliability-Based Optimization via a Decomposing Approach

A stable Reliability-Based Design Optimization (RBDO) algorithm is proposed to produce an optimal design with a desired reliability. The main idea behind the proposed approach is to use a set of deterministic variables, called auxiliary design points, to replace the random parameters. Thus, the reliability analysis in the inner loop of an RBDO problem is relaxed. The auxiliary design points are found through an optimization procedure. The auxiliary design points are updated using the sums of the auxiliary design points and the differences between the mean values of the “pseudo” and actual random parameters in the previous step. The auxiliary design points can force the iteration of deterministic optimization to the vicinity of the probabilistic boundary. Note that in the proposed method, the coupled reliability analysis and deterministic optimization are decomposed to form a weakly coupled system. The stability and accuracy of the proposed method were investigated through linear and nonlinear numerical problems.