Hybrid self-inertia weight adaptive particle swarm optimisation with local search using C4.5 decision tree classifier for feature selection problems

ABSTRACT

Feature selection is an important task to improve the classifier’s accuracy and to decrease the problem size. A number of methodologies have been presented for feature selection problems using metaheuristic algorithms. In this paper, an improved self-adaptive inertia weight particle swarm optimisation with local search and combined with C4.5 classifiers for feature selection algorithm is proposed. In this proposed algorithm, the gradient base local search with its capacity of helping to explore the feature space and an improved self-adaptive inertia weight particle swarm optimisation with its ability to converge a best global solution in the search space. Experimental results have verified that the SIW-APSO-LS performed well compared with other state of art feature selection techniques on a suit of 16 standard data sets.     

Genetic algorithm to simultaneously optimise stope sequencing and equipment dispatching in underground short-term mine planning under time uncertainty

ABSTRACT

The main issue in short-term planning optimisation for underground mining is organising the mining process with limited resources in the form of equipment and materials to satisfy production targets and stable feed grade requirements. In this paper, an integrated optimisation model is proposed based on an individual generation algorithm and an improved Genetic Algorithm to simultaneously optimise stope extraction sequencing and timing, extracted ore grade and equipment dispatching. The model objectives are to shorten the time gap between the stope mining processes and the overall working time. When the uncertainty of equipment working time is taken into account in a short-term scheduling model, the Monte Carlo simulation is applied to evaluate the risk of not meeting the production target. A modification strategy is defined to evaluate equipment failure. Consequently, any available equipment is automatically reassigned to the mining site to replace the broken-down equipment. A case study is used to validate the model in the Sanshandao gold mine of China to formulate an optimal monthly schedule. Compared with the conventional approach, the new model could reduce the variance of ore tonnage and feed grade and improve the equipment allocation efficiency. Discussions are presented to address the uncertainty.     

Robust optimisation of sustainable food grain transportation with uncertain supply and intentional disruptions

The proliferating need for sustainability intervention in food grain transportation planning is anchoring the attention of researchers in the interests of stakeholders and environment at large. Uncertainty associated with food grain supply further intensifies the problem steering the need for designing robust, cost-efficient and sustainable models. In line with this, this paper aims to develop a robust and sustainable intermodal transportation model to facilitate single type of food grain commodity shipments while considering procurement uncertainty, greenhouse gas emissions, and intentional hub disruption. The problem is designed as a mixed integer non-linear robust optimisation model on a hub and spoke network for evaluating near optimal shipment quantity, route selection and hub location decisions. The robust optimisation approach considers minimisation of total relative regret associated with total cost subject to several real-time constraints. A version of Particle Swarm Optimisation with Differential Evolution is proposed to tackle the resulting NP-hard problem. The model is tested with two other state-of the art meta-heuristics for small, medium, and large datasets subject to different procurement scenarios inspired from real time food grain operations in Indian context. Finally, the solution is evaluated with respect to total cost, model and solution robustness for all instances.     

An improved particle swarm optimisation for unit commitment in microgrids with battery energy storage systems considering battery degradation and uncertainties

Using electric storage systems (ESSs) is known as a viable strategy to mitigate the volatility and intermittency of renewable distributed generators (DGs) in microgrids (MGs). Among different electric storage technologies, battery energy storage (BES) is considered as the best option. In unit commitment (UC) module, the set of committed dispatchable DGs along with their power, power exported to/imported from macrogrid and status and power of ESS units are determined. In this paper, BES degradation is considered in UC formulation and an efficient particle swarm optimisation with quadratic transfer function is proposed for solving UC in BES‐integrated MGs, while the uncertainties of demand, renewable generation and market price are considered and dealt with robust optimisation. UC is formulated as a multi‐objective optimisation problem whose objectives are MG operation cost and BES degradation. The resultant multi‐objective optimisation problem is converted into a single‐objective optimisation problem and the effect of weight factors on MG operation cost and BES lifecycle are investigated. The results show that by consideration of BES degradation in objective function, BES lifecycle increases from 350 to 500 and the minimum depth of charge increases from 5.5% to 34%; however, MG operation cost increases from $8717 to $8910.2. The results also show that by consideration of uncertainties, MG's operation cost increases by 8.22%.     

A hybrid artificial bee colony algorithm for flexible job shop scheduling with worker flexibility

The traditional flexible job shop scheduling problem (FJSP) considers machine flexibility but not worker flexibility. Given the influence and potential of human factors in improving production efficiency and decreasing the cost in practical production systems, we propose a mathematical model of an extended FJSP with worker flexibility (FJSPW). A hybrid artificial bee colony algorithm (HABCA) is presented to solve the proposed FJSPW. For the HABCA, effective encoding, decoding, crossover and mutation operators are designed, and a new effective local search method is developed to improve the speed and exploitation ability of the algorithm. The Taguchi method of Design of Experiments is used to obtain the best combination of key parameters of the HABCA. Extensive computational experiments carried out to compare the HABCA with some well-performing algorithms from the literature confirm that the proposed HABCA is more effective than these algorithms, especially on large-scale FJSPW instances.     

Optimisation of the fuelling of hydrogen vehicles using cascade systems and ejectors

The present study investigates the replacement of expansion valves, used in the cascade system of hydrogen fuelling stations, by a series of ejectors. The major advantage of using ejectors is to recover part of the kinetic energy lost during the expansion of a high-pressure primary flow, in order to entrain a lower pressure secondary flow; thus resulting in a more efficient fuelling.Firstly, a quasi-steady 1-D simulation model of the ejector was calibrated using computational fluid dynamics in terms of the main geometry and pressure conditions.Secondly, the quasi-steady 1-D model of the ejector was used in a dynamic model of the hydrogen fuelling station, in order to investigate the influence of its geometry on the transient fuelling performances. Different fuelling scenarios were explored with varying number of buffer tanks in the cascade system of the fuelling station, and different initial pressures in the vehicle's tank. The results show that the replacement of the expansion valve by an ejector may reduce the energy consumption for hydrogen compression by up to 6.5% using two buffer tanks in the cascade system. On the other hand, increasing the number of buffer tanks reduces the energy savings as the driving pressure ratio decreases.     

Looking ahead: Joint small group detection and tracking in crowd scenes

Small group detection and tracking in crowd scenes are basis for high level crowd analysis tasks. However, it suffers from the ambiguities in generating proper groups and in handling dynamic changes of group configurations. In this paper, we propose a novel delay decision-making based method for addressing the above problems, motivated by the idea that these ambiguities can be solved using rich temporal context. Specifically, given individual detections, small group hypotheses are generated. Then candidate group hypotheses across consecutive frames and their potential associations are built in a tree. By seeking for the best non-conflicting subset from the hypothesis tree, small groups are determined and simultaneously their trajectories are got. So this framework is called joint detection and tracking. This joint framework reduces the ambiguities in small group decision and tracking by looking ahead for several frames. However, it results in the unmanageable solution space because the number of track hypotheses grows exponentially over time. To solve this problem, effective pruning strategies are developed, which can keep the solution space manageable and also improve the credibility of small groups. Experiments on public datasets demonstrate the effectiveness of our method. The method achieves the state-of-the-art performance even in noisy crowd scenes.     

Scheduling distributed flowshops with flexible assembly and set-up time to minimise makespan

The scheduling problems under distributed production or flexible assembly settings have achieved increasing attention in recent years. This paper considers scheduling the integration of these two environments and proposes an original distributed flowshop scheduling problem with flexible assembly and set-up time. Distributed production stage is deployed several homogeneous flowshop factories that process the jobs to be assembled into final products in the flexible assembly stage. The objective is to find a schedule, including a production subschedule for jobs and an assembly subschedule for products, to minimise the makespan. Such a scheduling problem involves four successive decisions: assigning jobs to production factories, sequencing jobs at every factory, designating an assembly machine for each product and sequencing products on each assembly machine. The computational model is first established, and then a constructive heuristic (TPHS) and two hybrid metaheuristics (HVNS and HPSO) are proposed. Numerical experiments have been carried out and results validate the algorithmic feasibility and effectiveness. TPHS can obtain reasonable solutions in a shorter time, while metaheuristics can report better solutions using more yet acceptable time. HPSO is statistically comparable yet less robust compared with HVNS for small-scale instances. For the large-scale case, HPSO outperforms HVNS on both effectiveness and robustness.     

An energy-efficient two-stage hybrid flow shop scheduling problem in a glass production

Energy-efficient scheduling is highly necessary for energy-intensive industries, such as glass, mould or chemical production. Inspired by a real-world glass-ceramics production process, this paper investigates a bi-criteria energy-efficient two-stage hybrid flow shop scheduling problem, in which parallel machines with eligibility are at stage 1 and a batch machine is at stage 2. The performance measures considered are makespan and total energy consumption. Time-of-use (TOU) electricity prices and different states of machines (working, idle and turnoff) are integrated. To tackle this problem, a mixed integer programming (MIP) is formulated, based on which an augmented ε-constraint (AUGMECON) method is adopted to obtain the exact Pareto front. A problem-tailored constructive heuristic method with local search strategy, a bi-objective tabu search algorithm and a bi-objective ant colony optimisation algorithm are developed to deal with medium- and large-scale problems. Extensive computational experiments are conducted, and a real-world case is solved. The results show effectiveness of the proposed methods, in particular the bi-objective tabu search.     

Studies on long-term storage stability of biodiesel (B100) and its blend (B20) using Box-Behnken response surface method

The gradual depletion of fossil fuels has greatly enhanced the necessity to look for alternative fuels for automobile engines. In response to this, biodiesel is being considered as a promising and potential alternative substitute to conventional petroleum diesel. However, long-term storage stability of biodiesel is poorer compared to conventional petroleum diesel. The aim of the project work is to study the long-term storage stability of biodiesel (B100) and its blend (B20) prepared from used frying oil in different conditions of storage. In this work, the effect of antioxidants and temperature on long storage stability of biodiesel obtained from with respect to storage period is analysed using response surface methodology (RSM). The long storage of biodiesel obtained from used frying oils were optimised by varying parameters such as antioxidant concentration, storage period by Box-Behnken RSM. The properties such as the acid value and the viscosity of biodiesel were initially measured. The results of the investigation showed that the addition of sufficient concentration of antioxidant (pyrogallol) significantly maintains the acid value and viscosity of biodiesel and helps to store for a longer storage period at the given storage temperature.