Change search
Link to record
Permanent link

Direct link
Bengtsson, Magnus, DocentORCID iD iconorcid.org/0000-0002-3283-067x
Publications (10 of 41) Show all publications
Bengtsson, M. (2024). The AI Revolution: Demystifying Machine Learning and Neural Networks v.2.0 (1ed.). Borås: Borås studentbokhandel
Open this publication in new window or tab >>The AI Revolution: Demystifying Machine Learning and Neural Networks v.2.0
2024 (English)Book (Other (popular science, discussion, etc.))
Abstract [en]

The field of Machine Learning can be overwhelming, and you might feel like you're losing control. Instead of giving up, let me share a secret with you: it's easier than you think. All you need is a "Rosetta Stone" to fully accelerate your work with machine learning. This book takes you on an alternative route, starting with the fundamental concepts from calculus, linear algebra, numerical methods, and optimization, leading up to the state-of-the-art algorithms that have emerged over the last couple of decades. This is an ambitious promise, but my background in industry, research, and teaching has given me deep insights into the common challenges of developing efficient algorithms for prediction. This book will focus on the coding perspective-a "from-scratch" approach where the configuration includes setting up the environment properly, defining the dataset, and configuring training and validation. Moreover, this book will dedicate significant effort to eliminating version-related errors that could cause problems when maintaining the code for future development.

Place, publisher, year, edition, pages
Borås: Borås studentbokhandel, 2024. p. 241 Edition: 1
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Business and IT
Identifiers
urn:nbn:se:hb:diva-32324 (URN)978-91-983466-4-0 (ISBN)
Available from: 2024-08-07 Created: 2024-08-07 Last updated: 2025-01-17Bibliographically approved
Bengtsson, M. & Waidringer, J. (2022). A proposed method using GPU based SDO to optimize retail warehouses. In: : . Paper presented at NVIDIA GTC, San Jose, March 21-24, 2022..
Open this publication in new window or tab >>A proposed method using GPU based SDO to optimize retail warehouses
2022 (English)Conference paper, Oral presentation with published abstract (Refereed)
Abstract [en]

Research in warehouse optimization has gotten increased attention in the last few years due to e-commerce. The warehouse contains a waste range of different products. Due to the nature of the individual order, it is challenging to plan the picking list to optimize the material flow in the process. There are also challenges in minimizing costs and increasing production capacity, and this complexity can be defined as a multidisciplinary optimization problem with an IDF nature. In recent years the use of parallel computing using GPGPUs has become increasingly popular due to the introduction of CUDA C and accompanying applications in, e.g., Python. 

In the case study at the company in the field of retail, a case study including a system design optimization (SDO) resulted in an increase in throughput with well over 20% just by clustering different categories and suggesting in which sequence the orders should be picked during a given time frame. 

The options provided by implementing a distributed high-performance computing network based on GPUs for subsystem optimization have shown to be fruitful in developing a functioning SDO for warehouse optimization. The toolchain can be used for designing new warehouses or evaluating and tuning existing ones. 

Keywords
AI, Machine Learning, Retail, MSO, Optimization, GPU, NHATC, Warehouse, logistics, hybrid systems
National Category
Computational Mathematics
Identifiers
urn:nbn:se:hb:diva-27322 (URN)
Conference
NVIDIA GTC, San Jose, March 21-24, 2022.
Available from: 2022-01-20 Created: 2022-01-20 Last updated: 2022-04-19Bibliographically approved
Bengtsson, M. (2021). Empirical energy and size distribution model for predicting single particle breakage in compression crushing. Minerals Engineering, 171, Article ID 107094.
Open this publication in new window or tab >>Empirical energy and size distribution model for predicting single particle breakage in compression crushing
2021 (English)In: Minerals Engineering, ISSN 0892-6875, E-ISSN 1872-9444, Vol. 171, article id 107094Article in journal (Refereed) Published
Abstract [en]

Crusher models presented in research is calibrated using experimental data. This approach is everyday praxis and is made in many different ways. One method is to use two different compression tests. The single-particle breakage test (SPB) and the inter-particle breakage test (IPB). Models for predicting the breakage energy and size distribution for the SPB test and also to show the correlation between the SPB and IPB test is presented. The results show that Weibull analysis and Rosin-Rammer distributions are a successful way to model both energy and size distribution for SPB and IPB based compression crushing. The number of experiments conducted in both SPB and IPB tests can be drastically reduced by testing the lowest and highest compression ratio values used in the original SPB and IPB tests. The results also show a strong correlation between the SPB and IPB tests when evaluating the relationship between the consumed breakage energy and the coefficient of variance. The energy model is compared with Bond Work Index (BWI), and it was shown that the model parameter C shows a good correlation with BWI. A full-scale validation of a cone crusher is made, presenting a calculation scheme for addressing the use of the IPB and SPB models for predicting the size distribution.

Place, publisher, year, edition, pages
Elsevier, 2021
Keywords
Compression crushing, Modelling, Weibull analysis, Rosin-Rammler Distribution
National Category
Engineering and Technology
Research subject
Business and IT
Identifiers
urn:nbn:se:hb:diva-26104 (URN)10.1016/j.mineng.2021.107094 (DOI)000687775400010 ()2-s2.0-85111634698 (Scopus ID)
Available from: 2021-08-05 Created: 2021-08-05 Last updated: 2022-01-18Bibliographically approved
Bengtsson, M. (2020). Understanding Mineral Liberation during Crushing Using Grade-by-Size Analysis—A Case Study of the Penuota Sn-Ta Mineralization, Spain. Minerals, 10(2), Article ID 164.
Open this publication in new window or tab >>Understanding Mineral Liberation during Crushing Using Grade-by-Size Analysis—A Case Study of the Penuota Sn-Ta Mineralization, Spain
2020 (English)In: Minerals, Vol. 10, no 2, article id 164Article in journal (Refereed) Published
Abstract [en]

Coarse comminution test-work and modeling are powerful tools in the design and optimization of mineral processing plants and provide information on energy consumption. Additional information on mineral liberation characteristics can be used for assessing the potential of pre-concentration stages or screens in the plant design. In ores of high-value metals (e.g., Ta, W), standard techniques—such as the mineralogical quantification of grain mounts by quantitative evaluation of minerals by scanning electron microscopy (QEMSCAN) or chemical analysis by X-ray fluorescence (XRF) can be challenging, due to the low relative abundance of such valuable minerals. The cost of QEMSCAN is also a limiting factor, especially considering the large number of samples required for the optimization of coarse comminution. In this study, we present an extended analytical protocol to a well-established mechanical test of interparticle breakage to improve the assessment of coarse mineral liberation characteristics. The liberation of ore minerals is a function of the rock texture and the difference in size and mechanical properties of the valuable minerals relative to gangue minerals and they may fraction in certain grain sizes if they behave differently during comminution. By analyzing the bulk-chemistry of the different grain size fractions produced after compressional testing, and by generating element by size diagrams, it is possible to understand the liberation characteristics of an ore. We show, based on a case study performed on a tantalum ore deposit, that element distribution can be used to study the influence of mechanical parameters on mineral liberation. This information can direct further mineralogical investigation and test work

National Category
Materials Engineering
Research subject
Resource Recovery
Identifiers
urn:nbn:se:hb:diva-22813 (URN)10.3390/min10020164 (DOI)000522452900079 ()2-s2.0-85080892842 (Scopus ID)
Available from: 2020-02-14 Created: 2020-02-14 Last updated: 2021-10-21Bibliographically approved
Davoodi, A., Bengtsson, M., Hulthén, E. & Evertsson, M. (2019). Effects of screen decks’ aperture shapes and materials on screening efficiency. Minerals Engineering, 139
Open this publication in new window or tab >>Effects of screen decks’ aperture shapes and materials on screening efficiency
2019 (English)In: Minerals Engineering, ISSN 0892-6875, E-ISSN 1872-9444, Vol. 139Article in journal (Refereed) Published
Abstract [en]

Screening is a key unit operation for the large-scale separation of materials. There are certain different machine parameters and variables that affect the process of screening. The Discrete Element Method (DEM) is a suitable method to analyze parameters and variables. The main benefit of using the DEM for simulating the screening process is that, as a contact model, it provides the possibility of tracking each particle in the material flow and all collisions between particles and between particles and boundaries.

There are different types of materials used for screening media, such as rubber and polyurethane, which are used in modular systems as a panel, and such as steel, which are used as a wire in the mesh. This paper presents how different materials used in screen decks affect the screening process. The materials’ strength and elasticity have been examined in order to study how the aperture will change in different materials and how different shapes of the aperture and material of screening media affect the screening performance by analyzing the effect on material flow.

National Category
Mechanical Engineering
Research subject
Resource Recovery
Identifiers
urn:nbn:se:hb:diva-15871 (URN)10.1016/j.mineng.2019.01.026 (DOI)000487174400015 ()2-s2.0-85062264942 (Scopus ID)
Available from: 2019-03-05 Created: 2019-03-05 Last updated: 2022-03-29Bibliographically approved
Bengtsson, M. (2019). Modelling energy and size distribution in cone crushers. Minerals Engineering, 139
Open this publication in new window or tab >>Modelling energy and size distribution in cone crushers
2019 (English)In: Minerals Engineering, Vol. 139Article in journal (Refereed) Published
Abstract [en]

The modelling of breakage in compression breakage has traditionally been done using population balance modelling, and the research has been developed over the last decades into advanced dynamic models. This paper presents a model for predicting particle size distribution and energy consumption. The particle size distribution model is derived using a first-order differential equation for how the coefficient of variance depends on the compression length. The coefficient of variance model is combined with a bimodal Weibull distribution to predict the cumulative size distribution. The power consumption is modelled in a similar way using Weibull analysis to determine the relationship between power consumption and the coefficient of variance.

Keywords
Modelling, Weibull analysis, Piston and die test
National Category
Engineering and Technology Materials Engineering
Research subject
Resource Recovery
Identifiers
urn:nbn:se:hb:diva-21756 (URN)10.1016/j.mineng.2019.105869 (DOI)000487174400011 ()2-s2.0-85069603383 (Scopus ID)
Available from: 2019-09-22 Created: 2019-09-22 Last updated: 2021-10-20Bibliographically approved
Camuz, S., Bengtsson, M. & Söderberg, R. (2019). Reliability based design optimization of surface-to-surface contact for cutting tool interface designs. Journal of manufacturing science and engineering
Open this publication in new window or tab >>Reliability based design optimization of surface-to-surface contact for cutting tool interface designs
2019 (English)In: Journal of manufacturing science and engineering, ISSN 1087-1357, E-ISSN 1528-8935Article in journal (Refereed) Published
Abstract [en]

In recent year, cutting tool manufacturers are moving towards improving the robustness of the positioning of an insert in the tool body interface. Increasing the robustness of the interface involves designs with both chamfered and serrated surfaces. These designs have a tendency to over-determine the positioning and cause instabilities in the interface. Cutting forces generated from the machining process will also plastically deform the interface, consequently, altering the positioning of the insert. Current methodologies within positioning and variation simulation use point-based contacts and assume linear material behaviour. In this article, a first order reliability-based design optimization framework that allows robust positioning of surface-to-surface-based contacts is presented. Results show that the contact variation over the interface can be limited to pre-defined contact zones, consequently allowing successful positioning of inserts in early design phases of cutting tool designs.

Place, publisher, year, edition, pages
ASME: , 2019
Keywords
Cutting tools, Reliability-based optimization, Robustness, Design, Cutting, Machining, Simulation
National Category
Natural Sciences
Identifiers
urn:nbn:se:hb:diva-15739 (URN)10.1115/1.4042787 (DOI)000460839400007 ()2-s2.0-85062592650 (Scopus ID)
Available from: 2019-02-11 Created: 2019-02-11 Last updated: 2021-10-20Bibliographically approved
Leon, L. G., Bengtsson, M. & Evertsson, M. (2018). Analysis of the concentration in rare metal ores during compression crushing. Minerals Engineering, 120, 7-18
Open this publication in new window or tab >>Analysis of the concentration in rare metal ores during compression crushing
2018 (English)In: Minerals Engineering, ISSN 0892-6875, E-ISSN 1872-9444, Vol. 120, p. 7-18Article in journal (Refereed) Published
Abstract [en]

Given the increasing global demand for rare metals, there is a need for the development of fundamental predictive models to improve extraction processes. Comminution models commonly predict particle size reduction based on the compressive breakage behaviour; however, few of them include mineral concentration or mineral liberation at a coarse scale. This paper focuses on developing a model to predict the mineral concentration of rare metals as a function of the particle size distribution after a cycle of the compression crushing process. In this study, compressive breakage and geochemical analysis experiments were conducted on four different rare metal ores of tantalum and tungsten. The work is divided into two stages: the methodology of modelling particle size and modelling concentration by selecting a bimodal Weibull distribution for calibration. A novel model for simulating the concentration of rare metals as a function of the compression ratio is presented.

Keywords
Compression crushing, Rare metals, Element concentration analysis, Concentration modelling, Weibull analysis, Critical metals
National Category
Materials Engineering
Identifiers
urn:nbn:se:hb:diva-14932 (URN)10.1016/j.mineng.2018.01.041 (DOI)000430901200002 ()2-s2.0-85042194909 (Scopus ID)
Available from: 2018-08-10 Created: 2018-08-10 Last updated: 2018-08-10Bibliographically approved
Bengtsson, M., Bhadani, K., Asbjörnsson, G., Evertsson, M. & Hulthén, E. (2018). Comparative Study of Optimization Schemes in Mineral Processing Simulations. In: : . Paper presented at XXIX International Minerals Processing Congress Moscow, September 17-20, 2018.
Open this publication in new window or tab >>Comparative Study of Optimization Schemes in Mineral Processing Simulations
Show others...
2018 (English)Conference paper, Oral presentation with published abstract (Refereed)
Abstract [en]

Modelling and simulations for mineral processing plants have been successful in replicating and predicting predefined scenarios of an operating plant. However, there is a need to explore and increase the potential of such simulations to make them attractive for users. One of the tools to increase the attractiveness of the simulations is through applying optimization schemes. Optimization schemes, applied on mineral processing simulations, can identify non-intuitive solutions for a given problem. The problem definition itself is subjective in nature and is dependent on the purpose of the operating plant.The scope of this paper is to demonstrate two optimization schemes: Multi-Objective Optimization (MOO) using a Genetic Algorithm (GA) and Multi-Disciplinary Optimization (MDO) using an Individual Discipline Feasible (IDF) approach. A two stage coarse comminution plant is used as a case plant to demonstrate the applicability of the two optimization schemes. The two schemes are compared based on the problem formulations, types of result and computation time. Results show that the two optimization schemes are suitable in generating solutions to a defined problem and both schemes can be used together to produce complementary results.

National Category
Mechanical Engineering
Identifiers
urn:nbn:se:hb:diva-15654 (URN)
Conference
XXIX International Minerals Processing Congress Moscow, September 17-20, 2018
Available from: 2019-01-11 Created: 2019-01-11 Last updated: 2019-01-14Bibliographically approved
Davoodi, A., Evertsson, M., Hulthén, E. & Bengtsson, M. (2018). The effect of different aperture shape and material of screen deck on screening efficiency. In: : . Paper presented at Comminution '18, Cape Town, 15-19 April, 2018.
Open this publication in new window or tab >>The effect of different aperture shape and material of screen deck on screening efficiency
2018 (English)Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

Screening is a key unit operation for the large-scale separation of materials. There are a number of different machine parameters and variables which affect the process of screening. The Discrete Element Method (DEM) is a suitable method to analyze all parameters and variables. The main benefit of using DEM for simulating the screening process is that as a particle contact model it gives the possibility to track each particle in the flow and all collisions between particles and between particles and boundaries.<br />There are a number of different materials commonly used for screen media such as rubber and polyurethane which are used in modular systems as a panel and steel is usually used as steel wire mesh but sheet metal can also be used. This paper presents how different materials used in screen decks affect the screening process. The strength and elasticity has been examined in order to study how the aperture will change with different materials and also how different shapes of the aperture and the material of screen media affect the screening performance by analyzing different material flow.

National Category
Mechanical Engineering
Identifiers
urn:nbn:se:hb:diva-14934 (URN)
Conference
Comminution '18, Cape Town, 15-19 April, 2018
Available from: 2018-08-10 Created: 2018-08-10 Last updated: 2022-03-29Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-3283-067x

Search in DiVA

Show all publications