scholarly journals Predictive maintenance integrated production scheduling by applying deep generative prognostics models: approach, formulation and solution

Author(s):  
Simon Zhai ◽  
Meltem Göksu Kandemir ◽  
Gunther Reinhart

AbstractTo harness the full potential of predictive maintenance (PdM), PdM information has to be used to optimally plan production and maintenance actions. Hence, operation-specific modelling of degradation, i.e. predictions of the health condition under time-varying operational conditions, has to be realized. By utilizing operation-specific degradation information, maintenance and production can be planned with regard to each other and thus, predictive maintenance integrated production scheduling (PdM-IPS) is enabled. This publication proposes a novel PdM-IPS approach consisting of two interacting modules: an operation-specific Prognostics and Health Management (PHM) module and an integrated production scheduling and maintenance planning (IPSMP) module. Specifically, the mathematical problem of the IPSMP module based on an extended version of the maintenance integrated flexible job shop problem is formulated. A two-stage genetic algorithm to efficiently solve this problem is designed and subsequently applied to simulated condition monitoring, as well as real industrial data. Results indicate that the approach is able to find feasible high quality PdM integrated production schedules.

2015 ◽  
Vol 2015 ◽  
pp. 1-9 ◽  
Author(s):  
Jianfei Ye ◽  
Huimin Ma

In order to solve the joint optimization of production scheduling and maintenance planning problem in the flexible job-shop, a multiobjective joint optimization model considering the maximum completion time and maintenance costs per unit time is established based on the concept of flexible job-shop and preventive maintenance. A weighted sum method is adopted to eliminate the index dimension. In addition, a double-coded genetic algorithm is designed according to the problem characteristics. The best result under the circumstances of joint decision-making is obtained through multiple simulation experiments, which proves the validity of the algorithm. We can prove the superiority of joint optimization model by comparing the result of joint decision-making project with the result of independent decision-making project under fixed preventive maintenance period. This study will enrich and expand the theoretical framework and analytical methods of this problem; it provides a scientific decision analysis method for enterprise to make production plan and maintenance plan.


Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4424
Author(s):  
Udeme Inyang ◽  
Ivan Petrunin ◽  
Ian Jennions

Bearings are critical components found in most rotating machinery; their health condition is of immense importance to many industries. The varied conditions and environments in which bearings operate make them prone to single and multiple faults. Widespread interest in the improvements of single fault diagnosis meant limited attention was spent on multiple fault diagnosis. However, multiple fault diagnosis poses extra challenges due to the submergence of the weak fault by the strong fault, presence of non-Gaussian noise, coupling of the frequency components, etc. A number of existing convolutional neural network models operate on a distinct feature that is not enough to assure reliable results in the presence of these challenges. In this paper, extended feature sets in three homogenous deep learning models are used for multiple fault diagnosis. This ensures a measure of diversity is introduced to the health management dataset to obtain complementary solutions from the models. The outputs of the models are fused through blending ensemble learning. Experiments using vibration datasets based on bearing multiple faults show an accuracy of 98.54%, with an improvement of 2.74% in the overall effectiveness over the single models. Compared with other technologies, the results show that this approach provides an improved generalized diagnostic capability.


2020 ◽  
Author(s):  
Su Nguyen ◽  
Mengjie Zhang ◽  
Damminda Alahakoon ◽  
Kay Chen Tan

Evolving production scheduling heuristics is a challenging task because of the dynamic and complex production environments and the interdependency of multiple scheduling decisions. Different genetic programming (GP) methods have been developed for this task and achieved very encouraging results. However, these methods usually have trouble in discovering powerful and compact heuristics, especially for difficult problems. Moreover, there is no systematic approach for the decision makers to intervene and embed their knowledge and preferences in the evolutionary process. This article develops a novel people-centric evolutionary system for dynamic production scheduling. The two key components of the system are a new mapping technique to incrementally monitor the evolutionary process and a new adaptive surrogate model to improve the efficiency of GP. The experimental results with dynamic flexible job shop scheduling show that the proposed system outperforms the existing algorithms for evolving scheduling heuristics in terms of scheduling performance and heuristic sizes. The new system also allows the decision makers to interact on the fly and guide the evolution toward the desired solutions.


2021 ◽  
Vol 1 (2) ◽  
pp. 46-51
Author(s):  
Dwi Ayu Lestari, Vikha Indira Asri

Scheduling is defined as the process of sequencing the manufacture of a product as a whole on several machines. All industries need proper scheduling to manage the allocation of resources so that the production system can run quickly and precisely as of it can produce optimal product. PT. Sari Warna Asli Unit V is one of the companies that implements a make to order production system with the FCFS system. Thus, scheduling the production process at this company is also known as job shop production scheduling. The methods used in this research are the CDS method, the EDD method and the FCFS method. The purpose of this research is to minimize the production time and determine the best method that can be applied to the company. The results of this research showed that the makespan obtained in the company's scheduling system with FCFS rules was 458 minutes, and the results of scheduling using the CDS method obtained a makespan value of 329 minutes, then the best production scheduling method that had the smallest makespan value was the CDS method.


2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Inna Kholidasari ◽  

Production scheduling is the most important part in carrying out the production process that will be carried out on a production floor. Scheduling activities are carried out before the production process begins to ensure the smooth running of the production process. If the production scheduling is not done properly, there will be obstacles in the production process and will cause losses to the company. This study aims to determine the production machine scheduling in a company engaged in the manufacture of spare parts for automotive products. This company implements a job shop production process and uses the First In First Out method in completing its work. Due to the large number of products that have to be produced, there are often two or more products that must be worked on at the same time and machine. This condition causes some products to have to wait for the associated machine to finish operating and causes long product turnaround times. This problem is solved by making a production machine scheduling using the Non-Delay method. By applying this method, the makespan of completion time can be minimized.


Sign in / Sign up

Export Citation Format

Share Document