Orthogonal Packing Problem Research Articles

MGPM Methods for Rectangular Single-Size Printed Circuit Board Orthogonal Packing Problems

Printed circuit board (PCB) orthogonal packing problems derive from the massive circuit board production process in the electronic industry. In the early stage, it mainly relied on human experiences to make decisions on how to make the most of each sheet while meeting customers’ orders. Up till now, researchers in enterprises and academic circles are still trying to explore effective mathematical models and feasible optimization methods. In most cases, what PCB companies generally face is the orthogonal layout decision, which considers positioning each rectangle PCB piece (PCB-P) on a rectangle sheet board (panel) in an ideal way so that each panel has the minimal remains with the most PCB-Ps. In this paper, multi-round gradual packing methods (MGPMs) are proposed based on the idea of combinatorial optimization and dynamic programming. MGPMs include the depth priority-based method (MGPM-DP) and breadth priority-based branch-and-prune method (MGPM-BC). The former has the advantage of finding better solutions, while the latter has the advantage of consuming short computational time. Through extensive computational tests on real data from a PCB production enterprise in China, both MGPM-DP and MGPM-BC have achieved noticeable and satisfactory results compared with the simplex method, dynamic programming method, and a widely used industrial software (Yuanbo) in China.

A mixed‐integer linear programming model and a metaheuristic approach for the selection and allocation of land parcels problem

AbstractThis article is about the current agricultural scenario, where large‐scale production causes large amounts of food to be transported to various points of consumption, causing substantial emissions of so‐called greenhouse gases and increasing the carbon footprint. Land use optimization and land parcel allocation are essential areas of agriculture research that currently represent relevant challenges and are classified as combinatorial optimization problems. In this context, the Selection and Allocation of Land Parcels Problem (SA‐LPP) is proposed; its goal is to optimize the selection and allocation of land parcels with rectangular shapes in small areas available for food production. We propose a reformulation of the SA‐LPP as a variant of the two‐dimensional orthogonal packing problem (2OPP), called Group‐2OPP. This problem was solved through a Mixed‐Integer Linear Programming (MILP) model, but due to the model complexity, we also propose a Greedy Randomized Adaptive Search Procedure metaheuristic approach. Some sensitivity analyses were performed as well to evaluate the impact of parameters on the solutions. Computational results show that the proposed metaheuristic outperforms the MILP model in terms of solution quality and computational times.

Development of algorithms for the formation and placement of N-dimensional orthogonal polyhedrons into containers of complex geometric shape

The article is devoted to problems related with the development of algorithms for creating, optimizing and placing of orthogonal polyhedrons of arbitrary dimension. Under N-dimensional orthogonal polyhedron is understood a composite object represented as a set of N-dimensional parallelepipeds with a fixed position relative to each other, which is considered as a whole. The need to solve the problem of placing a set of objects in the form of orthogonal polyhedrons of arbitrary dimension arises when solving a large number of practical problems in the automation of design and production. In particular, solving the layout problems of equipment and space, problems of cutting materials, problems of designing very large-scale integrated circuits, and optimizing the distribution of resources in computing and production systems, as well as many other actual problems, can be reduced to solving the problem of packing orthogonal polyhedrons. To create a new N-dimensional orthogonal polyhedron, the operations of addition, subtraction and multiplication of orthogonal objects are implemented. With the aim to increase the placement speed of orthogonal polyhedrons which were created with using the voxel model, an algorithm for partitioning of an orthogonal polyhedron into many non-overlapping each other as large as possible large orthogonal objects is proposed. In the scientific literature, there are no solutions to the problem of partitioning an orthogonal polyhedron of arbitrary dimension. The proposed partitioning algorithm is based on the usage of a model of potential containers developed to solve the orthogonal packing problems of arbitrary dimension. To obtain a container of arbitrary shape, a possibility of setting its geometric constraints with an orthogonal polyhedron is implemented. The article presents an algorithm developed for packing an N-dimensional orthogonal polyhedrons inside containers of arbitrary geometric shape, based on the application of multiplication orthogonal polyhedrons operations to obtain the set of points of permissible placement of each considered object. The examples of solving the problems of cutting the industrial materials into objects of irregular shapes, as well as solving the problems of placement complex objects created with using the voxel model into containers of various geometric shapes (including sphere and cone) are given. The effectiveness of the application of the developed algorithms is shown on the example of solving the problem of generation a dense layout of details on a 3D printer platform.

Multimethod genetic algorithm for the three-dimensional orthogonal packing problem

The article is devoted to design and investigation of a set of heuristics intended to optimize the three-dimensional orthogonal packing problem with the multimethod genetic algorithm. The proposed heuristics are based on five rules for selecting objects and seven rules for selecting free spaces of containers. The quality and time effectiveness for all these rules were determined. The probabilities of including these rules into new heuristics are given. The article contains results of computational experiments carried out on the standard instances of the three-dimensional orthogonal bin packing problem.

A multi-objective genetic algorithm for a special type of 2D orthogonal packing problems

In this study, a multi-objective model is proposed for a specific two-dimensional orthogonal packing problem. The model has three objectives, namely: (i) to minimise the distances between the centres of rectangular items, (ii) to use a minimisation function to place the related rectangular items close to each other, and (iii) to minimise the area of each rectangular item that falls outside of the radius. In addition to the weighted-sum method, the model uses the conic scalarisation method for scalarisation of the nonlinear multi-objective optimisation problem. The proposed model is a hybridisation of a placement procedure and a multi-objective genetic algorithm, and introduces the concept of the defensive radius to the literature. The model is tested on a randomly generated set of instances and some test problems. The computational results validate the quality of the solutions and the effectiveness of the proposed multi-objective model compared to the cluster boundary algorithm. Besides, the results show that the conic scalarisation outperforms the weighted-sum method in terms of scalar results in most cases.

An open space based heuristic for the 2D strip packing problem with unloading constraints

This paper studies the two-dimensional strip packing problem with unloading constraints. Given a set of items (represented by rectangles) belonging to different customers and a rectangular strip with fixed width and open length, the objective is to pack all the items into the strip such that the used length is minimized. In addition, the resulting packing must satisfy the unloading constraints. Based on the characteristics of this problem, this paper employs the open space to represent the candidate position. An open space based first-fit heuristic is proposed to generate a packing pattern for a given sequence of items. An implementation using the segment tree is provided. Finally, a randomized local search without any parameter is used to improve the solution by trying different sequences. The computational results on well-known instances show that the proposed approach outperforms existing approaches in the literature. In additional, we test our approach on the two-dimensional orthogonal packing problem with unloading constraints, the results show that our approach is capable of finding feasible solutions for 283 open instances.

The minimum raster set problem and its application to the d-dimensional orthogonal packing problem

We consider the well-known d-dimensional Orthogonal Packing Problem (OPP-d). Using the toolset of conservative scales introduced by Fekete and Schepers we are able to change items’ sizes of the initial instance to obtain an equivalent instance with the same solution. In this paper, we present efficient algorithm for building equivalent instances with certain properties.We also consider the so-called raster model for OPP-d introduced by Belov, Kartak, Rohling and Scheithauer. It is a 0/1 ILP model in which the number of variables and constraints depends on the total number of raster points over all dimensions. Using our algorithm, we construct equivalent instances with a reduced number of raster points. We also present an algorithm to find a lower bound on the minimum possible number of raster points over all equivalent instances. Numerical results are presented.

Compaction algorithm for orthogonal packing problems

The article is devoted to an algorithm for increasing the density of placement schemes in orthogonal packing problems. The proposed heuristic packing compaction algorithm is based on the principle of local replacement of placed objects located as far from the origin of a container as well as located near the local free spaces inside it. The algorithm uses a list of six rules which select objects from a container for deleting and subsequent reallocation of them into freed spaces of the container. The article contains results of computational experiments carried out on the standard strip packing problems.

Training software for orthogonal packing problems

An open source architecture for the interactive solution of packing problems in two dimensions is presented. Although primarily developed for helping engineering students to understand the algorithmic approaches to the solution of difficult combinatorial optimization problems, the application can be useful to practitioners and developers thanks to its visual tools. The paper gives intuitive and formal definitions of the problems at hand, discusses two natural heuristic approaches, provides technical information on the application, and reports the results of classroom experimental testings.

The multiple container loading problem with preference

An international audio equipment manufacturer would like to help its customers reduce unit shipping costs by adjusting order quantity according to product preference. We introduce the problem faced by the manufacturer as the Multiple Container Loading Problem with Preference (MCLPP) and propose a combinatorial formulation for the MCLPP. We develop a two-phase algorithm to solve the problem. In phase one, we estimate the most promising region of the solution space based on performance statistics of the sub-problem solver. In phase two, we find a feasible solution in the promising region by solving a series of 3D orthogonal packing problems. A unique feature of our approach is that we try to estimate the average capability of the sub-routine algorithm for the single container loading problem in phase one and take it into account in the overall planning. To obtain a useful estimate, we randomly generate a large set of single container loading problem instances that are statistically similar to the manufacturer’s historical order data. We generate a large set of test instances based on the historical data provided by the manufacturer and conduct extensive computational experiments to demonstrate the effectiveness of our approach.

A New Search Procedure for the Two-dimensional Orthogonal Packing Problem

In this paper we propose a new exact procedure for the two-dimensional orthog- onal packing problem, based on F. Clautiaux et al. approach (Clautiaux et al. Eur. J. Oper. Res. 183(3), 1196-1211, 2007). The principle consists in searching first the positions of the items on the horizontal axis, so as that, at each position, the sum of the heights of the items does not exceed the height of the bin. Each time a valid placement of all the items is encountered, another procedure determines if it can be extended to a solution of the pack- ing problem, searching the positions of the items on the vertical axis. Novel aspects of our approach include a simple and efficient search procedure, which only generates restricted placements, at least in a first stage, in order to reduce the search space, and the memoriza- tion of unsuccessful configurations, which are then used to detect dead-ends. We tested our implementation on a selection of orthogonal packing problems and strip packing problems, and we compared our results with those of recent successful approaches.

A Hybrid Demon Algorithm for the Two-Dimensional Orthogonal Strip Packing Problem

This paper develops a hybrid demon algorithm for a two-dimensional orthogonal strip packing problem. This algorithm combines a placement procedure based on an improved heuristic, local search, and demon algorithm involved in setting one parameter. The hybrid algorithm is tested on a wide set of benchmark instances taken from the literature and compared with other well-known algorithms. The computation results validate the quality of the solutions and the effectiveness of the proposed algorithm.

An Exact Algorithm for the Two-Dimensional Orthogonal Packing Problem with Unloading Constraints

This paper describes an exact algorithm for solving a two-dimensional orthogonal packing problem with unloading constraints, which occurs as a subproblem of mixed vehicle routing and loading problems. The packing considered in this work is basically a feasibility problem involving a single bin. The problem is addressed through a decomposition approach wherein a branch-and-cut algorithm is designed for solving a one-dimensional relaxation of the original problem. When an integer solution is found in the branching tree, a subsidiary problem is solved to identify a two-dimensional packing that does not lead to any overlap and satisfies the unloading constraints. Cuts are added when the subsidiary problem proves to be infeasible. Several preprocessing techniques aimed at reducing the size of the solution space and uncovering infeasibility are also described. A numerical comparison with the best known exact method is reported at the end based on benchmark instances.

Multilevel Linked Data Structure for the Multidimensional Orthogonal Packing Problem

The actual NP-completed orthogonal bin packing problem is considered in the article. In practice a solution of a large number of different practical problems, including problems in logistics and scheduling comes down to the bin packing problem. A decision of an any packing problem is represented as a placement string which contains a sequence of objects selected to pack. The article proposes a new multilevel linked data structure that improves the effectiveness of decoding of the placement string and as a consequence, increases the speed of packing generation. The new data structure is applicable for all multidimensional orthogonal bin packing problems.

Effective Data Structure for the Multidimensional Orthogonal Bin Packing Problems

The actual in industry multidimensional orthogonal packing problem is considered in the article. Solution of a large number of different practical optimization problems, including resources saving problem, optimization problems in logistics, scheduling and planning comes down to the orthogonal packing problem which is NP-hard in strong sense. One of the indicators characterizing the efficiency of packing constructing algorithm is the efficiency of the used data structure. In the article a multilevel linked data structure that increases the speed of constructing of a packing is proposed. The carried out computational experiments show the high efficiency of the new data structure. Multilevel linked data structure is applicable for multidimensional orthogonal bin packing problems any kind.

Improved Data Structure for the Orthogonal Packing Problem

In paper is considered the actual in industry and engineering orthogonal multidimensional packing problem. This problem is NP-hard in strong sense therefore an important role is played effectiveness of the used packing representation model. To increase the speed of placement of a given set of orthogonal objects into containers is offered a new data structure – multilevel linked data structure. The carried out computational experiments demonstrate high time efficiency of the proposed data structure compared to the ordered simple linked list.

Efficient algorithms for orthogonal packing problems

The NP complete problem of the orthogonal packing of objects of arbitrary dimension is considered in the general form. A new model for representing objects in containers is proposed that ensures the fast design of an orthogonal packing. New heuristics for the placement of orthogonal packing are proposed. A single-pass heuristic algorithm and a multimethod genetic algorithm are developed that optimize an orthogonal packing solution by increasing the packing density. Numerical experiments for two- and three-dimensional orthogonal packing problems are performed.

Improved Packing Representation Model for the Orthogonal Packing Problem

The multidimensional NP-hard orthogonal bin packing problem is considered in the article. Usually the problem is solved using heuristic algorithms of discrete optimization which optimize a selection sequence of objects to be packed in containers. The quality and speed of getting the resulting packing for a given sequence of placing objects is determined by the used packing representation model. In the article presented a new packing representation model for constructing the orthogonal packing. The proposed model of potential containers describes all residual free spaces of containers in packing. The developed model is investigated on well-known standard benchmarks of three-dimensional orthogonal bin packing problem. The model can be used in development of applied software for the optimal allocation of orthogonal resources.

On the weak computability of a four dimensional orthogonal packing and time scheduling problem

This paper proposes a four dimensional orthogonal packing and time scheduling problem. The problem differs from the classical packing problems in that the position and orientation of each item in the container can be changed over time. In this way, the four dimensional space–time problem better uses the container time. Also, we consider a general case that all parameters are real numbers, which makes the problems more difficult to solve. This paper proposes an algorithm and proves that the algorithm could solve the problem optimally by a finite number of operations. We say this problem is weak computational, meaning that if there exists a universal machine that could represent real numbers and could do unit arithmetic or logical operation on real numbers in finite time, then the algorithm could find optimal solutions in finite time. This paper also presents a proof of the weak computability over a general case of the three dimensional orthogonal packing problem where all parameters are positive real numbers.

LP Bounds in an Interval-Graph Algorithm for Orthogonal-Packing Feasibility

We consider the feasibility problem OPP (orthogonal packing problem) in higher-dimensional orthogonal packing: given a set of d-dimensional (d ≥ 2) rectangular items, decide whether all of them can be orthogonally packed in the given rectangular container without rotation. The one-dimensional (1D) “bar” LP relaxation of OPP reduces the latter to a 1D cutting-stock problem where the packing of each stock bar represents a possible 1D stitch through an OPP layout. The dual multipliers of the LP provide us with another kind of powerful bounding information (conservative scales). We investigate how the set of possible 1D packings can be tightened using the overlapping information of item projections on the axes, with the goal to tighten the relaxation. We integrate the bar relaxation into an interval-graph algorithm for OPP, which operates on such overlapping relations. Numerical results on 2D and 3D instances demonstrate the efficiency of tightening leading to a speedup and stabilization of the algorithm.