Researcher:
Khayyati, Siamak

Profile Picture
ORCID

Job Title

PhD Student

First Name

Siamak

Last Name

Khayyati

Name

Name Variants

Khayyati, Siamak

Email Address

Birth Date

Filters

2020 - 20215

Advanced Search

Filter by

Settings

Researcher Of Publications: search.filters.isAuthorOfPublication.49678769-b4b4-4e9a-bede-a692432f9bfe

Search Results

Now showing 1 - 5 of 5
  • Placeholder
    PublicationMetadata only
    A lab-scale manufacturing system environment to investigate data-driven production control approaches
    (Elsevier Sci Ltd, 2021) N/A; N/A; Department of Business Administration; Khayyati, Siamak; Tan, Barış; PhD Student; Faculty Member; Department of Business Administration; Graduate School of Sciences and Engineering; College of Administrative Sciences and Economics; N/A; 28600
    Controlling production and release of material into a manufacturing system effectively can lower work-inprogress inventory and cycle time while ensuring the desired throughput. With the extensive data collected from manufacturing systems, developing an effective real-time control policy helps achieving this goal. Validating new control methods using the real manufacturing systems may not be possible before implementation. Similarly, using simulation models can result in overlooking critical aspects of the performance of a new control method. In order to overcome these shortcomings, using a lab-scale physical model of a given manufacturing system can be beneficial. We discuss the construction and the usage of a lab-scale physical model to investigate the implementation of a data-driven production control policy in a production/inventory system. As a datadriven production control policy, the marking-dependent threshold policy is used. This policy leverages the partial information gathered from the demand and production processes by using joint simulation and optimization to determine the optimal thresholds. We illustrate the construction of the lab-scale model by using LEGO Technic parts and controlling the model with the marking-dependent policy with the data collected from the system. By collecting data directly from the lab-scale production/inventory system, we show how and why the analytical modeling of the system can be erroneous in predicting the dynamics of the system and how it can be improved. These errors affect optimization of the system using these models adversely. In comparison, the datadriven method presented in this study is considerably less prone to be affected by the differences between the physical system and its analytical representation. These experiments show that using a lab-scale manufacturing system environment is very useful to investigate different data-driven control policies before their implementation and the marking-dependent threshold policy is an effective data-driven policy to optimize material flow in manufacturing systems.
  • Thumbnail Image
    PublicationOpen Access
    Data-driven control of a production system by using marking-dependent threshold policy
    (Elsevier, 2020) Department of Business Administration; N/A; Tan, Barış; Khayyati, Siamak; Faculty Member; Department of Business Administration; College of Administrative Sciences and Economics; Graduate School of Sciences and Engineering; 28600; N/A
    As increasingly more shop-floor data becomes available, the performance of a production system can be improved by developing effective data-driven control methods that utilize this information. We focus on the following research questions: how can the decision to produce or not to produce at any time be given depending on the real-time information about a production system?; how can the collected data be used directly in optimizing the policy parameters?; and what is the effect of using different information sources on the performance of the system? In order to answer these questions, a production/inventory system that consists of a production stage that produces to stock to meet random demand is considered. The system is not fully observable but partial production and demand information, referred to as markings is available. We propose using the marking-dependent threshold policy to decide whether to produce or not based on the observed markings in addition to the inventory and production status at any given time. An analytical method that uses a matrix geometric approach is developed to analyze a production system controlled with the marking-dependent threshold policy when the production, demand, and information arrivals are modeled as Marked Markovian Arrival Processes. A mixed integer programming formulation is presented to determine the optimal thresholds. Then a mathematical programming formulation that uses the real-time shop floor data for joint simulation and optimization (JSO) of the system is presented. Using numerical experiments, we compare the performance of the JSO approach to the analytical solutions. We show that using the marking-dependent control policy where the policy parameters are determined from the data works effectively as a data-driven control method for manufacturing.
  • Thumbnail Image
    PublicationOpen Access
    A machine learning approach for implementing data-driven production control policies
    (Taylor _ Francis, 2021) Department of Business Administration; N/A; Tan, Barış; Khayyati, Siamak; Faculty Member; Department of Business Administration; College of Administrative Sciences and Economics; Graduate School of Sciences and Engineering; 28600; N/A
    Given the extensive data being collected in manufacturing systems, there is a need for developing a systematic method to implement data-driven production control policies. For an effective implementation, first, the relevant information sources must be selected. Then, a control policy that uses the real-time signals collected from these sources must be implemented. We analyse the production control policy implementation problem in three levels: choosing the information sources, forming clusters of information signals to be used by the policy and determining the optimal policy parameters. Due to the search-space size, a machine-learning-based framework is proposed. Using machine learning speeds up optimisation and allows utilising the collected data with simulation. Through two experiments, we show the effectiveness of this approach. In the first experiment, the problem of selecting the right machines and buffers for controlling the release of materials in a production/inventory system is considered. In the second experiment, the best dispatching policy based on the selected information sources is identified. We show that selecting the right information sources and controlling a production system based on the real-time signals from the selected sources with the right policy improve the system performance significantly. Furthermore, the proposed machine learning framework facilitates this task effectively.
  • Thumbnail Image
    PublicationOpen Access
    Supervised learning-based approximation method for single-server open queueing networks with correlated interarrival and service times
    (Taylor _ Francis, 2021) Department of Industrial Engineering; Department of Business Administration; N/A; Tan, Barış; Khayyati, Siamak; Faculty Member; Department of Industrial Engineering; Department of Business Administration; College of Engineering; College of Administrative Sciences and Economics; Graduate School of Sciences and Engineering; 28600; N/A
    Efficient performance evaluation methods are needed to design and control production systems. We propose a method to analyse single-server open queueing network models of manufacturing systems composed of delay, batching, merge and split blocks with correlated interarrival and service times. Our method (SLQNA) is based on using a supervised learning approach to determine the mean, the coefficient of variation, and the first-lag autocorrelation of the inter-departure time process as functions of the mean, coefficient of variation and first-lag autocorrelations of the interarrival and service times for each block, and then using the predicted inter-departure time process as the input to the next block in the network. The training data for the supervised learning algorithm is obtained by simulating the systems for a wide range of parameters. Gaussian Process Regression is used as a supervised learning algorithm. The algorithm is trained once for each block. SLQNA does not require generating additional training data for each unique network. The results are compared with simulation and also with the approximations that are based on Markov Arrival Process modelling, robust queueing, and G/G/1 approximations. Our results show that SLQNA is flexible, computationally efficient, and significantly more accurate and faster compared to the other methods.
  • Thumbnail Image
    PublicationOpen Access
    Supervised-learning-based approximation method for multi-server queueing networks under different service disciplines with correlated interarrival and service times
    (Taylor _ Francis, 2021) Department of Business Administration; N/A; Tan, Barış; Khayyati, Siamak; Faculty Member; Department of Business Administration; College of Administrative Sciences and Economics; Graduate School of Sciences and Engineering; 28600; N/A
    Developing efficient performance evaluation methods is important to design and control complex production systems effectively. We present an approximation method (SLQNA) to predict the performance measures of queueing networks composed of multi-server stations operating under different service disciplines with correlated interarrival and service times with merge, split, and batching blocks separated with infinite capacity buffers. SLQNA yields the mean, coefficient of variation, and first-lag autocorrelation of the inter-departure times and the distribution of the time spent in the block, referred as the cycle time at each block. The method generates the training data by simulating different blocks for different parameters and uses Gaussian Process Regression to predict the inter-departure time and the cycle time distribution characteristics of each block in isolation. The predictions obtained for one block are fed into the next block in the network. The cycle time distributions of the blocks are used to approximate the distribution of the total time spent in the network (total cycle time). This approach eliminates the need to generate new data and train new models for each given network. We present SLQNA as a versatile, accurate, and efficient method to evaluate the cycle time distribution and other performance measures in queueing networks.