A Machine-Learning-Assisted Simulation Approach for Incorporating Predictive Maintenance in Dynamic Flow-Shop Scheduling

In this paper, a machine-learning-assisted simulation approach for dynamic flow-shop production scheduling is proposed. This is achieved by introducing a novel framework to include predictive maintenance constraints in the scheduling process while a discrete event simulation tool is used to generate the dynamic schedule. A case study for a pharmaceutical company by the name of Factory X is investigated to validate the proposed framework while taking into consideration the change in forecast demand. The proposed approach uses Microsoft Azure to calculate the predictive maintenance slots and include it in the scheduling process to simplify the process of applying machine-learning techniques with no need for hard coding. Several machine-learning algorithms are tested and compared to see which one provides the highest accuracy. To gather the required dataset, multiple sensors were designed and deployed across machines to collect their vitals that allow the prediction of whether and when they require maintenance. The proposed framework with discrete event simulation generates optimized schedule with minimum makespan while taking into consideration predictive maintenance parameters. Boosted Decision Tree and Neural Network algorithms showed the best results in estimating the predictive maintenance slots. Furthermore, the Earliest Due Date (EDD) model produced the minimum makespan with 76.82 h while scheduling 25 products using 18 machines.

Anti-Crisis Stability of Break-Even Development Potential and its Resource Support in Agribusiness

The article considers the anti-crisis stability of the potential of break-even development and its resource support in agribusiness. The necessity of a synergetic approach to estimating the dynamic flow of resources capable of generating own sources of financing to activate the target parameters of crisis stability of break-even development potential and the development of an alternative scenario of self-financing of the production and financial cycle to stimulate economic growth of agribusiness is proved. The reproductive process of resource support of anti-crisis stability of the potential for safe development of agribusiness enterprises is substantiated. The model of estimation of target parameters of anti-crisis stability of potential of unprofitable development of agrarian business and a matrix of its point estimation at a choice of the alternative scenario of self-financing is presented. Scenarios of the flow of resource support of anti-crisis stability of the potential of unprofitable development of the agribusiness enterprise are developed. An indicator of the level of anti-crisis stability of the break-even development potential according to the determined target parameters of self-financing is offered. The dynamics of anti-crisis factor load on the stability of the potential of break-even development of agribusiness enterprises on average in one region of the Steppe zone of Ukraine by its territorial location is analyzed. Cluster analysis was used to assess the elements of the qualitative system-resource component of anti-crisis stability of the potential of break-even development with the separation of types of agribusiness enterprises in the regions of the Steppe zone of Ukraine with different structure of current assets. The forecast level of resource support according to the quantitative component of anti-crisis stability of the potential of break-even development on average in the regions of the Steppe zone of Ukraine and per one agribusiness enterprise of the region is determined. The forecast range of limits of target parameters of self-financing and their influence on the level of anti-crisis stability of potential of unprofitable development of agribusiness enterprises on the average on one region of the Steppe zone is presented