Wyniki wyszukiwania - BazTech

1

Effective data usage for the proper and beneficial automotive production cost improvement

Krzesniak G.

Journal of Achievements in Materials and Manufacturing Engineering

|

2023

|

Vol. 119, nr 1

27-34

EN

Purpose The article aims to present a proposal and discuss the investment cost calculation procedures based on data collected during the manufacturing process, according to standard SPC control chart evaluation and standard PDCA. It is applied as a tool to support the process of continuous improvement of the manufacturing process and improve profitability by proper allocation the cost of investment and resources. Design/methodology/approach The study uses the results of a literature review on the issue of cost analysis and their modelling. Key elements are the main cost components, but also those that are considered less important and maybe overall decisive. Application cost to benefit relations – as a method of data evaluation for cost modelling to improve overall cost structure is proposed. Findings The relationship between return on investment and amortisation time allows to easily visualise which of the proposed changes are the most cost-effective over time. Based on the analysis conducted the results, the change is proposed below, in order from the most cost-effective. Research limitations/implications Further research should focus on the impact if a decision were based on the findings and proposals defined. Practical implications Each production process is based on the use of resources. This applies to both production plants and other activities. A resource can be anything that will be used in the manufacturing process. Of key importance for the success of the project is their proper use and not only effective but most of all efficient. Originality/value The considerations presented in the study may be the basis for determining the key factors of the cost of production and investment. The proposed simulation model allows for determining the efficient direction for investment. This, in turn, should enable us to define the main directions of searching for the optimisation of the product cost to achieve the expected cost and quality level.

2

Production cost calculation approach based on data collected during manufacturing process

Krześniak Grzegorz

System Safety : Human - Technical Facility - Environment

|

2022

|

Vol. 4, nr 1

19-27

EN

The aim of the article is to present a proposal and discuss the production cost calculation procedures based on data collected during manufacturing process, according to standard SPC control chart evaluation. It is applied as a tool to support the process of continuous improvement of the manufacturing process and improve profitability by reducing the cost of production. Research methodology - the study uses the results of a literature review on the issue of cost analysis and their modeling. Key elements are the main cost components, but also those that are considered less important and may be overall decisive. Application of Statistical Process Control - as a method of data collection for cost modeling to improve overall cost structure is proposed. Originality/value - the considerations presented in the study may be the basis for determining the key components of the cost of production. The proposed simulation model allows for the determination of the main quality cost factors. This, in turn, should allow to define the main directions of searching for the optimization of the product cost in order to achieve the expected level of cost and quality.

3

Development of cost estimation models based on ANN ensembles and the SVM method

Juszczyk Michał

Civil and Environmental Engineering Reports

|

2020

|

Vol. 30, no. 3

48--67

EN

Cost estimation, as one of the key processes in construction projects, provides the basis for a number of project-related decisions. This paper presents some results of studies on the application of artificial intelligence and machine learning in cost estimation. The research developed three original models based either on ensembles of neural networks or on support vector machines for the cost prediction of the floor structural frames of buildings. According to the criteria of general metrics (RMSE, MAPE), the three models demonstrate similar predictive performance. MAPE values computed for the training and testing of the three developed models range between 5% and 6%. The accuracy of cost predictions given by the three developed models is acceptable for the cost estimates of the floor structural frames of buildings in the early design stage of the construction project. Analysis of error distribution revealed a degree of superiority for the model based on support vector machines.