Ferdous Alam
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ferdous Alam has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- David John Hoelzle
Department of Mechanical and Aerospace Engineering, The Ohio State University, Columbus, OH, USA
2 shared publications - Kira Barton
Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI, USA
2 shared publications - Anna C. Doris
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, USA
1 shared publication Antony George
Ohio State University Department of Mechanical and Aerospace Engineering Columbus, OH 43210
1 shared publication- Brandon Man
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, USA
1 shared publication - Chaitanya Krishna Prasad Vallabh
Stevens Institute of Technology, USA
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 1 July 2025
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 58 (9) , 1-75
From concept to manufacturing: evaluating vision-language models for engineering design
Engineering design is undergoing a transformative shift with the advent of AI, marking a new era in how we approach product, system, and service planning. Large language models have demonstrated impressive capabilities in enabling this shift. Yet, with text as their only input modality, they cannot leverage the large body of visual artifacts that engineers have used for centuries and are accustomed to. This gap is addressed with the release of multimodal vision-language models (VLMs), such as GPT-4V, enabling AI to impact many more types of tasks. Our work presents a comprehensive evaluation of VLMs across a spectrum of engineering design tasks, categorized into four main areas: Conceptual Design, System-Level and Detailed Design, Manufacturing and Inspection, and Engineering Education Tasks. Specifically in this paper, we assess the capabilities of two VLMs, GPT-4V and LLaVA 1.6 34B, in design tasks such as sketch similarity analysis, CAD generation, topology optimization, manufacturability assessment, and engineering textbook problems. Through this structured evaluation, we not only explore VLMs’ proficiency in handling complex design challenges but also identify their limitations in complex engineering design applications. Our research establishes a foundation for future assessments of vision language models. It also contributes a set of benchmark testing datasets, with more than 1000 queries, for ongoing advancements and applications in this field.
- 1 July 2025
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 58 (9) , 1-75
Top Cited PapersOpen AccessFrom concept to manufacturing: evaluating vision-language models for engineering design
Engineering design is undergoing a transformative shift with the advent of AI, marking a new era in how we approach product, system, and service planning. Large language models have demonstrated impressive capabilities in enabling this shift. Yet, with text as their only input modality, they cannot leverage the large body of visual artifacts that engineers have used for centuries and are accustomed to. This gap is addressed with the release of multimodal vision-language models (VLMs), such as GPT-4V, enabling AI to impact many more types of tasks. Our work presents a comprehensive evaluation of VLMs across a spectrum of engineering design tasks, categorized into four main areas: Conceptual Design, System-Level and Detailed Design, Manufacturing and Inspection, and Engineering Education Tasks. Specifically in this paper, we assess the capabilities of two VLMs, GPT-4V and LLaVA 1.6 34B, in design tasks such as sketch similarity analysis, CAD generation, topology optimization, manufacturability assessment, and engineering textbook problems. Through this structured evaluation, we not only explore VLMs’ proficiency in handling complex design challenges but also identify their limitations in complex engineering design applications. Our research establishes a foundation for future assessments of vision language models. It also contributes a set of benchmark testing datasets, with more than 1000 queries, for ongoing advancements and applications in this field.
- 18 November 2024
- Published by Wiley in Journal of Mechanical Design
- Vol. 147 (5) , 1-19
Representation Learning for Sequential Volumetric Design Tasks
Volumetric design, also called massing design, is the first and critical step in professional building design, which is sequential in nature. As the volumetric design process requires careful design decisions and iterative adjustments, the underlying sequential design process encodes valuable information for designers. Many efforts have been made to automatically generate reasonable volumetric designs, but the quality of the generated design solutions varies, and evaluating a design solution requires either a prohibitively comprehensive set of metrics or expensive human expertise. While previous approaches focused on learning only the final design instead of sequential design tasks, we propose to encode the design knowledge from a collection of expert or high-performing design sequences and extract useful representations using transformer-based models. Later we propose to utilize the learned representations for crucial downstream applications such as design preference evaluation and procedural design generation. We develop the preference model by estimating the density of the learned representations, whereas we train an autoregressive transformer model for sequential design generation. We demonstrate our ideas by leveraging a novel dataset of thousands of sequential volumetric designs. Our preference model can compare two arbitrarily given design sequences and is almost 90% accurate in evaluation against random design sequences. Our autoregressive model is also capable of autocompleting a volumetric design sequence from a partial design sequence.
- 18 November 2024
- Published by Wiley in Journal of Mechanical Design
- Vol. 147 (5) , 1-19
Representation Learning for Sequential Volumetric Design Tasks
Volumetric design, also called massing design, is the first and critical step in professional building design, which is sequential in nature. As the volumetric design process requires careful design decisions and iterative adjustments, the underlying sequential design process encodes valuable information for designers. Many efforts have been made to automatically generate reasonable volumetric designs, but the quality of the generated design solutions varies, and evaluating a design solution requires either a prohibitively comprehensive set of metrics or expensive human expertise. While previous approaches focused on learning only the final design instead of sequential design tasks, we propose to encode the design knowledge from a collection of expert or high-performing design sequences and extract useful representations using transformer-based models. Later we propose to utilize the learned representations for crucial downstream applications such as design preference evaluation and procedural design generation. We develop the preference model by estimating the density of the learned representations, whereas we train an autoregressive transformer model for sequential design generation. We demonstrate our ideas by leveraging a novel dataset of thousands of sequential volumetric designs. Our preference model can compare two arbitrarily given design sequences and is almost 90% accurate in evaluation against random design sequences. Our autoregressive model is also capable of autocompleting a volumetric design sequence from a partial design sequence.
- 12 January 2024
- Published by ASME International in Journal of Manufacturing Science and Engineering
- Vol. 146 (3) , 1-17
An Additive Manufacturing Testbed to Evaluate Machine Learning-Based Autonomous Manufacturing
This paper details the design and operation of a testbed to evaluate the concept of autonomous manufacturing to achieve a desired manufactured part performance specification. This testbed, the autonomous manufacturing system for phononic crystals (AMSPnC), is composed of additive manufacturing, material transport, ultrasonic testing, and cognition subsystems. Critically, the AMSPnC exhibits common manufacturing deficiencies such as process operating window limits, process uncertainty, and probabilistic failure. A case study illustrates the AMSPnC function using a standard supervised learning model trained by printing and testing an array of 48 unique designs that span the allowable design space. Using this model, three separate performance specifications are defined and an optimization algorithm is applied to autonomously select three corresponding design sets to achieve the specified performance. Validation manufacturing and testing confirms that two of the three optimal designs, as defined by an objective function, achieve the desired performance, with the third being outside the design window in which a distinct bandpass is achieved in phononic crystals (PnCs). Furthermore, across all samples, there is a marked difference between the observed bandpass characteristics and predictions from finite elements method computation, highlighting the importance of autonomous manufacturing for complex manufacturing objectives.
- 12 January 2024
- Published by ASME International in Journal of Manufacturing Science and Engineering
- Vol. 146 (3) , 1-17
An Additive Manufacturing Testbed to Evaluate Machine Learning-Based Autonomous Manufacturing
This paper details the design and operation of a testbed to evaluate the concept of autonomous manufacturing to achieve a desired manufactured part performance specification. This testbed, the autonomous manufacturing system for phononic crystals (AMSPnC), is composed of additive manufacturing, material transport, ultrasonic testing, and cognition subsystems. Critically, the AMSPnC exhibits common manufacturing deficiencies such as process operating window limits, process uncertainty, and probabilistic failure. A case study illustrates the AMSPnC function using a standard supervised learning model trained by printing and testing an array of 48 unique designs that span the allowable design space. Using this model, three separate performance specifications are defined and an optimization algorithm is applied to autonomously select three corresponding design sets to achieve the specified performance. Validation manufacturing and testing confirms that two of the three optimal designs, as defined by an objective function, achieve the desired performance, with the third being outside the design window in which a distinct bandpass is achieved in phononic crystals (PnCs). Furthermore, across all samples, there is a marked difference between the observed bandpass characteristics and predictions from finite elements method computation, highlighting the importance of autonomous manufacturing for complex manufacturing objectives.
- 4 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 7, 508-513
Reinforcement Learning Enabled Autonomous Manufacturing Using Transfer Learning and Probabilistic Reward Modeling
Here we propose a reinforcement learning enabled physical autonomous manufacturing system (AMS) that is capable of learning the manufacturing process parameters to autonomously fabricate a complex-geometry artifact with desired performance characteristics. The poor sample efficiency of traditional RL algorithms challenges real-world manufacturing decision making due to a high variable cost from raw material, machine utilization, and labor costs. To make decision making sample efficient, we propose to leverage a first-principles based source task for training, transfer effective representations from trained knowledge, and then use these representations to interact with the physical system to learn a probabilistic model of the target reward function. We deploy this idea to a novel dataset obtained from a custom physical AMS machine that can autonomously manufacture phononic crystals, a complex geometry artifact with spectral response as performance characteristic. We demonstrate that our method uses as low as 25 artifacts to model the interesting part of the target reward function and find an artifact with high reward. This task typically requires manual design of phononic crystals and extensive empirical iterations on the order of hundreds.
- 4 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 7, 508-513
Reinforcement Learning Enabled Autonomous Manufacturing Using Transfer Learning and Probabilistic Reward Modeling
Here we propose a reinforcement learning enabled physical autonomous manufacturing system (AMS) that is capable of learning the manufacturing process parameters to autonomously fabricate a complex-geometry artifact with desired performance characteristics. The poor sample efficiency of traditional RL algorithms challenges real-world manufacturing decision making due to a high variable cost from raw material, machine utilization, and labor costs. To make decision making sample efficient, we propose to leverage a first-principles based source task for training, transfer effective representations from trained knowledge, and then use these representations to interact with the physical system to learn a probabilistic model of the target reward function. We deploy this idea to a novel dataset obtained from a custom physical AMS machine that can autonomously manufacture phononic crystals, a complex geometry artifact with spectral response as performance characteristic. We demonstrate that our method uses as low as 25 artifacts to model the interesting part of the target reward function and find an artifact with high reward. This task typically requires manual design of phononic crystals and extensive empirical iterations on the order of hundreds.