Packing Optimization Research Articles

Application of the Gray Wolf Optimization Algorithm and Neural Networks for Solving Discrete Problems

Relevance. In recent decades, metaheuristic optimization methods have become popular for solving complex problems that require searching for global extrema. Algorithms such as genetic algorithm (GA), ant colony optimization (ACO), particle swarm optimization (PSO), as well as more modern approaches such as cat pack optimization (CSO) and gray wolf pack optimization (GWO) demonstrate high efficiency, but their application is often limited by the conditions of continuity and differentiability of the objective functions. This is a challenge when solving problems with discrete data, where such requirements are not met. In this context, the search for methods that allow adapting metaheuristic algorithms to work with discrete functions is of particular relevance.Aim. The study is aimed at testing the hypothesis about the possibility of using a neural network trained on a limited set of discrete data as an approximation of a function sufficient for the correct execution of the GWO algorithm when searching for a global minimum. The implementation of this hypothesis can significantly expand the scope of GWO, making it available for a wider range of problems where functions are defined on discrete sets.Methods. The study is based on the analysis of existing approaches and experimental verification of the hypothesis on two test functions: a linear function and a Booth function, which are widely used as standards for evaluating the performance of optimization algorithms. Numerical experiments were conducted using neural networks as an approximating model to obtain the results. Solution. During the experiments, an analysis of the applicability of neural networks for approximating discrete functions was carried out, which showed the success of this approach. It was found that neural networks can approximate discrete functions with high accuracy, creating conditions for a successful search for a global minimum using the GWO algorithm.Novelty. For the first time, a hypothesis was proposed and tested on the use of neural networks for approximating objective functions in metaheuristic optimization problems on discrete data. This direction has not previously received due coverage in the scientific literature, which adds significance to the obtained results and confirms the effectiveness of the proposed approach.Practical significance. The results of the study open up new prospects for the application of algorithms such as GWO in optimization problems based on discrete data, expanding the capabilities of metaheuristic methods and facilitating their implementation in a wider class of applied problems, including problems where the use of other methods is limited.

Set Packing Optimization by Evolutionary Algorithms with Theoretical Guarantees.

The set packing problem is a core NP-complete combinatorial optimization problem which aims to find the maximum collection of disjoint sets from a given collection of sets, S, over a ground set, U. Evolutionary algorithms (EAs) have been widely used as general-purpose global optimization methods and have shown promising performance for the set packing problem. While most previous studies are mainly based on experimentation, there is little theoretical investigation available in this area. In this study, we analyze the approximation performance of simplified versions of EAs, specifically the (1+1) EA, for the set packing problem from a theoretical perspective. Our analysis demonstrates that the (1+1) EA can provide an approximation guarantee in solving the k-set packing problem. Additionally, we construct a problem instance and prove that the (1+1) EA beats the local search algorithm on this specific instance. This proof reveals that evolutionary algorithms can have theoretical guarantees for solving NP-hard optimization problems.

Discrete element simulation of powder layer spreading by blade sliding: packing factor, mechanism, and optimization

Discrete element simulation of powder layer spreading by blade sliding: packing factor, mechanism, and optimization

A Multi-Objective Optimization Design for Enhancing Space Utilization and Minimizing Cutting Time in Nuclear Facility Component Decommissioning

According to the International Atomic Energy Agency’s requirements for the minimization of radioactive waste, nuclear facility components need to be cut into smaller blocks and packaged in waste containers during decommissioning. Therefore, it is important to increase the space utilization (SU) of the cut blocks in the containers while reducing the cutting time (CT). In engineering practice, increasing SU often leads to longer CTs, which poses a great challenge to improve the efficiency of the nuclear decommissioning process. To overcome this challenge and to determine the optimal operational parameters, this paper introduces a multi-objective optimization design method for cutting and packaging nuclear facility components. The goal is to increase SU while concurrently reducing CTs, ultimately minimizing the waste and reducing the decommissioning cost. First, we project the intricate three-dimensional (3D) irregular parts packing problem onto a two-dimensional plane to simplify the complexity inherent in 3D parts packing and to formulate a packing optimization model. Second, we employ the Morris method to perform global sensitivity analysis on critical parameters, including cutting angle, height, component radius, and plate thickness parameters, throughout the cutting process of nuclear facility components. This analysis produces global sensitivity indicators for each parameter, facilitating a precise assessment of the sensitivity values associated with different operational parameters. Finally, we formulate a multi-objective design optimization model for cutting and packing nuclear facility components that yields a series of alternative operating parameter solutions upon solving it. This methodology offers a resolution for the selection of optimal operational parameters in the decommissioning process of nuclear facility components, thereby attaining optimal outcomes in waste disposal and furnishing guidance for subsequent decommissioning activities.

Proposed mix design improvements of compressed stabilized earth blocks (CSEB) with particle packing optimization and coir reinforcement

Proposed mix design improvements of compressed stabilized earth blocks (CSEB) with particle packing optimization and coir reinforcement

Variable neighborhood genetic algorithm for multi-order multi-bin open packing optimization

In the rapidly evolving e-commerce landscape, efficient packaging and logistics reduce costs and enhance customer satisfaction. This study addresses the problem of dynamic bin size optimization in e-commerce logistics by proposing a series of intelligent algorithms. Considering real-world constraints such as item separation requirements, a Mixed Integer Programming Model for Multi-Order Multi-Box Open-Dimension Rectangular Packing (MOMB-ODRPP) is formulated. The Stacked Clustering Algorithm (SCA) series, One-Dimensional Fixed Stacked Clustering Algorithm (ODF-SCA), Two-Dimensional Fixed Stacked Clustering Algorithm (TDF-SCA), and Variable Neighborhood Descent Spatial Ordering Algorithm (VND-SOA) series are employed to solve the MOMB-ODRPP model and improve order packing rates and optimize bin sizes. Computational experiments using real-world data from JD’s e-commerce operations reveal that the TDF-SCA algorithm series outperforms the ODF-SCA series by approximately 5% in Case 4. In contrast, the VND-SOA-S1 and VND-SOA-S2 algorithms achieve improvements of 0.83% and 0.76%, respectively, over the TDF-SCA-P2 algorithm in Cases 4 and 11. The comparative analysis highlights the practical implications of bin size optimization, with Case 11 providing a more viable option for standardizing bin sizes in e-commerce logistics.

Fabrication of high-performance recrystallized silicon carbide ceramic membrane based on particle packing optimization

Overcoming the challenges associated with achieving high uniformity and connectivity of pore channels in ceramic membranes, we designed silicon carbide ceramic membrane derived from the recrystallization process based on the Dinger-Funk equation of the closest-packing model with various grain grading. Furthermore, the effects of particle size distribution on the resulting microstructure and pore architecture of the ceramic membrane was also explored. The findings corroborated the critical importance of raw material particle size distribution in controlling pore size distribution and morphology. After sintering at 1900°C, the silicon carbide ceramic membrane, benefiting from ideal particle packing, exhibited a remarkably uniform pore structure. Notably, the most probable pore size constituted over 70 %, while achieving an open porosity of 51.3 % even without the addition of pore-forming agents. The silicon carbide ceramic membrane also demonstrated exceptional hydrophilicity (water contact angle:∼0°), impressive water permeation (1210 L m−2 h−1·bar−1), coupled with efficient turbidity removal (∼100 %) in carbon black wastewater treatment applications. Additionally, membrane regeneration proved effective using a dilute NaOH solution backwash, achieving a flux recovery efficiency of 98 %. This strategy had directive significance for designing high-performing silicon carbide ceramic membranes.

Crop disease detection via ensembled-deep-learning paradigm and ABC Coyote pack optimization algorithm (ABC-CPOA)

Crop disease detection via ensembled-deep-learning paradigm and ABC Coyote pack optimization algorithm (ABC-CPOA)

Geometric batch optimization for packing equal circles in a circle on large scale

The problem of packing equal circles in a circular container is a classic and famous packing problem, which is well-studied in academia and has a variety of applications in industry. The problem is computationally challenging, and researchers mainly focus on small to moderate-scale instances with the number of circular items n less than 320 in the literature. In this work, we aim to solve this problem on large scale, and it is the bottleneck for most global optimization problems. Specifically, we propose a novel geometric batch optimization method that makes batch gradient descent based on the geometric locations of packing items. This method not only can speed up the convergence process of continuous optimization significantly but also reduce the memory requirement during the program’s runtime. Then, we propose a heuristic search method, called solution-space exploring and descent, that can discover a feasible solution efficiently on large scale. Besides, we propose an adaptive neighbor object maintenance method to maintain the neighbor structure applied in the continuous optimization process. In this way, we can find high-quality solutions on large-scale instances within reasonable computational times. Extensive experiments on the benchmark instances sampled from n= 300 to 1000 show that our proposed algorithm outperforms the state-of-the-art algorithms and performs excellently on large-scale instances. In particular, our algorithm found 10 improved solutions among the 21 well-studied moderate-scale instances and 95 improved solutions among the 101 sampled large-scale instances. Furthermore, our geometric batch optimization, heuristic search, and adaptive maintenance methods are general and can be adapted to other packing and continuous optimization problems.

A joint sustainable order-packing vehicle routing optimisation for the cold chain e-fulfilment

AbstractDue to the new normal caused by the pandemic, consumer behaviour has now shifted to online shopping not only for general commodities but also for food and other perishable products. Therefore, e-commerce fulfilment is now integrated with cold chain capabilities to satisfy stringent requirements on time-criticality and product quality, leading to the concept of cold chain e-fulfilment. In the cold chain e-fulfilment process, perishable orders are packed in thermal packaging solutions and delivered to consumers before the quality preservation time window. To secure a sufficient time buffer during last mile delivery, excessive use of thermal packaging materials is applied, which creates an adverse environmental impact on our eco-system. Aligning with low-carbon business practices, this study proposes a novel joint optimization model, namely the Joint Optimization of Sustainable Order Packing and Multi-Temperature Delivery Problem (JOSOPMDP), for order packing and vehicle routing decisions, where the sustainable use of thermal packaging materials is promoted without negatively influencing product quality and customer satisfaction. To evaluate its viability and performance, three sets of computational experiments are subsequently conducted. It is found that the proposed model is feasible to strike a balance between order packing and vehicle routing decisions. Compared with the traditional strategy, the average total cost and satisfaction level are improved by 3.26% and 47.88%, respectively. Consequently, this research fosters sustainable thinking in the cold chain e-fulfilment process, minimizing environmental impact.

Optimization of 2D Irregular Packing: Deep Reinforcement Learning with Dense Reward

Optimization of 2D Irregular Packing: Deep Reinforcement Learning with Dense Reward

Thermally Driven Multi-Objective Packing Optimization Using Acceleration Fields

Abstract The packing optimization of three-dimensional components into a design space is a challenging and time-intensive task. Of particular concern is the thermal performance of the system, as tightly packed components typically exhibit poor heat dissipation performance which can result in overheating and system failure. As temperature modeling can be quite complex, there is a growing demand in the industry for software tools that aid designers in the packing process whilst considering heat transfer. This work outlines a novel multi-objective algorithm that considers temperature and thermal effects directly within the packing optimization process itself using thermal optimization objectives. In addition, the algorithm can consider functional objectives such as a desired center of mass position and minimizing rotational inertia. The algorithm packs components from initial to optimal positions within a design domain using a set of dynamic acceleration fields. There are multiple accelerations, each designed to improve the objective values for the systems (e.g., minimize temperature variance). Component temperatures are calculated using thermal finite element analyses modeling conduction and natural convection. Forced convection is approximated via computational fluid dynamics simulations. Numerical results for two academic and one real-world case studies are presented to demonstrate the efficacy of the presented algorithm.

An autonomous ore packing system through deep reinforcement learning

In the contemporary era, the limited availability of terrestrial resources has prompted an increasing number of nations to turn their attention towards space, wherein extraterrestrial minerals hold considerable allure for both resource provisioning and scientific inquiry. Numerous nations have initiated the deployment of unmanned operational platforms towards extraterrestrial asteroids with the objective of accomplishing sampling return missions. Given the restricted storage capacity and energy limitations of these platforms, the optimization of mineral placement algorithms assumes paramount importance in enhancing the efficacy of these missions. In this paper, we propose an autonomous ore packing system capable of autonomously measuring ore characteristics and addressing the ore packing optimization problem in extraterrestrial unfamiliar environments. A deep reinforcement learning method that utilizes physical constraints to enhance overall performance was proposed to solve the ore packing problem with uncertainty, while meeting the high demands for real-time performance in the mission. To augment the autonomy and adaptability of our approach, we leverage advanced visual technology to transform the spatial distribution of bin utilization and the characteristics of the ore into a matrix representation. This empowers the robotic system to autonomously perceive bin information and capture essential ore features. The empirical findings substantiate that our algorithm attains a human-level performance in the majority of instances, rendering an approximate optimal solution within a concise timeframe. Additionally, we introduce a novel reinforcement learning training technique known as Maximum Worth Reinforcement Learning (MWRL) to address the optimization conundrum associated with incomplete Markov chains, which outperforms existing approaches in our comparative analysis. Lastly, we validate the efficacy of our algorithm in real-world scenarios by deploying it on a robotic manipulator.

Optimization of packing and transportation of the fingerlings of cobia (Rachycentron Canadum (Linnaeus, 1766)) and silver pompano (Trachinotus blochii (Lacepède, 1801))

Optimization of packing and transportation of the fingerlings of cobia (Rachycentron Canadum (Linnaeus, 1766)) and silver pompano (Trachinotus blochii (Lacepède, 1801))

Particle packing optimization and pore structure assessment of ternary cementitious system based on X-ray computed tomography and mercury intrusion porosimetry

The introduction of high-volume steel slag into ordinary Portland cement (OPC) has a negative effect on the pore structure due to its poor hydraulic reactivity. Synergistic effects between steel slag and ground granulated blast furnace slag (GGBFS) in cementitious system have drawn increasing attention. In this study, the modified Andreasen and Andersen (MAA) model was adopted for the mixture design of ternary cementitious system incorporating high-volume ultrafine steel slag (USS) and GGBFS without a compromise in strength. X-ray computed tomography (X-CT) and mercury intrusion porosimetry (MIP) were applied to characterize the pore structure of various cementitious mortars in terms of porosity, pore size, pore number, pore morphology and homogeneity. Results manifested that the adverse impact of USS addition on the pore structure of binary cement was effectively mitigated in the ternary cement USS-GGBFS-OPC after mixture optimization, whereby the pore size was shifted toward a finer distribution and simultaneously with a higher uniformity and consequently promoting the compressive strength development. An increase of cumulative pore volume as captured by X-CT was associated with an exponential decrease of the number of pores while together with larger pore sizes. The increase in the number of small pores led to an increase in the pore tortuosity and degree of sphericity. The fractal dimension of pores was negatively correlated with pore inhomogeneity and compressive strength. These findings provide new insights into homogeneity-oriented mixture design of composite cementitious binders based on gap-graded particle packing, together with their synergistic effects on hydration progress.

Optimizing Two-Dimensional Irregular Packing: A Hybrid Approach of Genetic Algorithm and Linear Programming

The problem of two-dimensional irregular packing involves the arrangement of objects with diverse shapes and sizes within a given area. This challenge arises across various industrial sectors, where effective packing optimization can yield cost savings, enhanced productivity, and reduced material waste. Existing methods for addressing the two-dimensional irregular packing problem encounter several challenges, such as limited computing resources, a prolonged solving time, and the propensity to converge to local optima. To address this issue, this study proposes a hybrid algorithm called the GA-LP algorithm to optimize the two-dimensional irregular packing problem in the manufacturing industry. The algorithm combines the global search capability of a genetic algorithm with the precise solving characteristics of linear programming. Matheuristics merges the advantages of metaheuristics, such as genetic algorithms, and mathematical programming, such as linear programming. The algorithm employs the no-fit-polygon technique along with the bottom-left and lowest-gravity center mixing placement strategies to acquire an initial solution via the utilization of a genetic algorithm. The algorithm then optimizes the solution obtained by the genetic algorithm using linear programming to obtain the final packing result. Experimental results, drawn from a real case involving the European Special Interest Group on Cutting and Packing (ESICUP) demonstrate that the GA-LP algorithm outperforms two hybrid algorithms from the relevant literature. Compared with recent methods, this algorithm can increase the best and average utilization rates by up to 5.89% and 4.02%, respectively, with important implications for improving work quality in areas such as packing and cutting.

The application of new media communication technology in vocational education teaching under the background of big data

Abstract Exploring the application of new media communication technology in vocational education teaching is better for improving the skill level of vocational school students. In this paper, starting from the KNN algorithm in the context of big data, the basic principle and process of the algorithm are explained, and the principle and model of the wolf pack optimization algorithm are introduced. The parameters of the KNN algorithm are optimized using the wolf pack search algorithm, and the definition of the objective function, initialization and solution of the optimal K value are given, which leads to the WPOA-KNN analysis model. The new media communication technology is analyzed, including teaching media, new media teaching technology and the advantages of new media communication technology applied to vocational education teaching. The WPOA-KNN analysis model was used to analyze and demonstrate the teaching of new media technology for vocational education in a higher education institution. From the satisfaction evaluation, the percentage of those who said they liked it was 76.06%, and the percentage of those who disliked it was only 9.09%. In terms of students’ learning behavior, the overall percentage of those who rated above C grade was 92.37%. This shows that using new media communication technology for vocational education teaching can enhance students’ learning enthusiasm, make them have a more exquisite technical level, and meet the diversified talent needs of employing enterprises.

Arrhythmia Classification Based on Adaptive Refined Composite Multiscale Fluctuation Dispersion Entropy

To improve the accuracy of electrocardiography (ECG) signal classification and identify abnormal heart rhythms, an arrhythmia classification algorithm based on adaptive refined composite multiscale fluctuation dispersion entropy (ARCMFDE) is proposed. First, an improved QRS complex detection algorithm named the improved Pan-Tompkins algorithm (IPTA) is used. The QRS wave is detected, and the waveform is further processed; then, the signal is decomposed into multiple modal components using variational mode decomposition with the optimized number of decomposition layers (K). Subsequently, the RCMFDE is extracted from the different modal components as a classification feature. Finally, differential evolution (DE) and grey wolf optimization (GWO) are combined to form the hybrid differential evolution-grey wolf pack optimization (DE-GWO) algorithm to optimize the penalty factor c and the kernel function parameter g of the support vector machine for performing pattern recognition. Experimental results show that compared with other methods such as variational mode decomposition (VMD), fluctuation dispersion entropy (FDE), genetic algorithms (GA), and support vector machine (SVM). The proposed classification model has superior performance, with an average accuracy of 96.1%, a sensitivity of 95.9%, and a specificity of 98.7% for four types of heart rhythm recognition. Thus, accurate classification of ECG signals can be achieved using the proposed ARCMFDE-based DE-GWO method.

Flexural behaviour of fly ash incorporated ferrochrome slag aggregate reinforced concrete beam

The structural behaviour of fly ash integrated ferrochrome slag aggregate concrete (FCSAC) is not widely understood owing to lack of research, although some studies have focused on its mechanical and environmental performance. The real-world use of FCSAC relies on its large-scale structural tests. This research investigates the flexural response of reinforced concrete beams fabricated with fly ash and ferrochrome slag (FCS) aggregate. A total of sixteen full-scale beams were built and tested. The beams were cast using four different concrete compositions: natural aggregate concrete (NAC) without any fly ash and FCS as the reference; FCSAC comprising 100% FCS as coarse aggregate and fly ash as partial substitution of cement at different percentages: 0%, 20% and 30%. The beams were fabricated with two different longitudinal reinforcement ratios of 0.69% and 1.86%. An eco-efficient mix proportioning method based on Particle packing optimization technique (PPOT) was adopted aiming to develop sustainable concrete. The effect of alternate resources (FCS and fly ash) and reinforcement ratios on the flexural response, cracking, ultimate load, failure pattern, ductility and toughness were examined. The experimental outcomes were compared to the predictions derived from the existing code provisions. Results revealed that the flexural performance of the FCSAC with fly ash beams was superior to that of NAC beam, despite having a lower flexural capacity than the FCSAC without fly ash beams. Moreover, the comparative study demonstrated that the fly ash-based FCSAC beams may be designed in accordance with the same guidelines as conventional concrete.

Molecular Packing and Dielectric Property Optimization through Peripheral Halogen Swapping Enables Binary Organic Solar Cells with an Efficiency of 18.77%

AbstractPeripheral halogen regulations can endow non‐fullerene acceptors (NFAs) with enhanced features as organic semi‐conductors and further boost efficient organic solar cells (OSCs). Herein, based on a remarkable molecular platform of CH14 with more than six halogenation positions, a preferred NFA of CH23 is constructed by synergetic halogen swapping on both central and end units, rendering the overall enlarged molecular dipole moment, packing density and thus relative dielectric constant. Consequently, the CH23‐based binary OSC reaches an excellent efficiency of 18.77% due to its improved charge transfer/transport dynamics, much better than that of 17.81% for the control OSC of CH14. This work demonstrates the great potential for further achieving state‐of‐the‐art OSCs by delicately regulating the halogen formula on these newly explored CH‐series NFAs.