Features feed

Optimising automotive performance with AI

Rob Roe — Fri, 14 Jul 2023 17:26:50 +0000

Optimisation software and next-gen AI technology are driving the automotive industry forward, writes Gemma Church

Credit: Altair

The automotive industry is accelerating into an uncertain future where increased design complexity coupled with mounting regulations and customer demands are impacting not only tomorrow’s vehicles but the engineers developing them, today.

Gary Brotman, chief executive officer at machine learning company Secondmind, said: “Today’s automotive engineers face a herculean task in efficiently and effectively modelling and simulating the systems that comprise today's cars. The complexity of vehicle software alone is 400 % greater than the pace of development productivity - complexity driven by an increasing number of design parameters and constraints, including tighter emissions and safety regulations, fuel economy, aerodynamics, drivability, cost and consumer desires, to name a few.”

Brotman added: “There's also the challenge of integrating multiple systems for hybrid and electric vehicles and achieving optimal performance in development and throughout the vehicle lifecycle. And for traditional car makers, the growing pressure to reduce emissions means engineers must develop innovative, long-term solutions while optimising legacy ones, which is costly, time-consuming and makes it harder to maintain competitive advantage, let alone survive.”

In short, automotive engineers are expected to do more with less. Increasing vehicle complexity sits at the heart of the many design and development challenges that engineers face. This is because today’s vehicles have moved away from mechanically dominated systems and into multi-physics, fully connected entities, driven by data and powered by electricity.

Zed Tang, technical account director at Ansys, explained: “The demand for designing more efficient and powerful electrified powertrains at a lower cost has incrementally increased. When we consider where a great source of cost savings and efficiency in the overall system can be found, the Electric Drive Unit (EDU) is it.”

An EDU comprises the power electronics consisting of the control software, the gearbox, and the electric machine – all of which must seamlessly work together to move the vehicle. “So, the designer must consider system performance instead of a single component and the interactions between the different units to meet these challenges. The only way to understand the system performance is through system-level simulations,” Tang added.

The development of a battery EV powertrain, for example, is another complex systems problem. Ansys Motor-CAD simulations were recently used to help engineers determine whether an interior permanent magnet (IPM), an induction magnet (IM) or a wound field synchronous magnet (WFSM) is the best motor design for an EV, examining the resulting trade-offs to identify the best solution.

Multiphysics solutions

The e-motor and battery pack are both further examples of where multi-physics designs are required. The design and development of each system require an understanding of thermo-electric behaviour and cooling, in addition to traditional structural mechanics.

Royston Jones, global head of automotive at Altair, explained: “Considering the tight limits on costs and the industry’s competitive time-to-market, developing innovative electric powertrains is a challenge for any manufacturer. Altair’s simulation optimisation technology can minimise weight and increase performance by rapidly exploring thousands of design permutations.”

Altair e-Motor Director lets users easily define a broad design space for a single baseline concept, where they can then copy, paste, and change design concepts to build a design of experiments (DoE) database with design information.

The solution creates competitive motor designs while considering all project requirements, according to Jones, who said: “Altair e-Motor Director mixes the advantages of simulation- and data-driven design to weigh conflicting constraints from multiple physics so you can accelerate the development of cutting-edge e-powertrains.”

“Altair e-Motor Director creates, manages, and stores study descriptions for multi-domain analyses, and handles design of experiments (DoE) data associated with your design studies. It also enables optimisation to identify a motor family or a specific motor based on a single DoE or multiple DoE studies.”

But advancing automotive electrification encompasses much more than a shift from an internal combustion engine (ICE) to battery power. Tang explained: “Infrastructure, maintenance, and a host of other variables must be considered. Currently, the automotive industry is facing a big challenge from other industries and other locations looking for expertise.”

Tang added: “There’s a workforce shortage everywhere, but even more so on the electrification side. If automakers can’t hire enough engineers, they need to think of ways to empower their engineers to be more efficient and effective.”

Optimisation matters

Optimisation is a key technology to help engineers who are working with increasingly tight deadlines and complex designs.

Altair’s solutions in automotive vehicle development, such as multi-disciplinary optimisation (MDO), are designed to optimise “skateboard” platform designs for a wide range of use cases (including Battery EV, Hybrid EV, Plug-in Hybrid EV), as well as different vehicle types to improve performance and reduce development costs.

Jones added: “Engineers will need to adopt optimisation tools – if they don’t their competitor OEMs will. Optimisation fits the artificial intelligence (AI) narrative. Traditionally, engineering has been data poor, so optimisation technology has been key.”

Jones added: “In the future, we will be data rich and that data will come from everywhere (for example: the field, warranty, physical testing, manufacturing etc) including massive amounts of synthetic (simulation) data. Engineers will become more conversant with data analytics techniques to provide increased insight into the product since the product complexity and refinement level will continue to increase.”

There are now a range of novel machine learning tools coming online to address these design challenges. Cambridge-based start-up Secondmind, for example, uses a specific branch of machine learning to help optimise the development of tomorrow’s vehicles (see the ‘Intelligent Engineering’ box).

Altair's digital twin solutions also use simulation, machine learning, and artificial intelligence to create virtual representations of physical assets. Jones explained: “Optimisation has been in Altair’s DNA for well over two decades and recently, with the ability to generate large volumes of synthetic (simulation) data we can efficiently utilize machine learning (ML).”

Jones added: “In Altair e-Motor Director, we utilize both optimisation and ML technologies to ensure that from a vast array of motor family permutations the correct e-Motor topology is selected with the ML ensuring a manufacturable shape has been selected.”

Likewise, Ansys has expanded its multiphysics capabilities “beyond automotive structure to meet challenges involving electromagnetics, controls, functional safety, reliability, materials intelligence, and more,” Tang explained. “Beyond Ansys multiphysics simulation capabilities, we have streamlined workflows, design automation and optimisation, high-performance computing (HPC), and cloud-enabled solutions to assist engineering teams.”

Whatever the underlying technology that’s sitting under the hood, it’s clear that a range of tools are now vital to streamline the design and development of tomorrow’s vehicles - and that machine learning and optimisation will continue to play a significant role, going forward.

Intelligent engineering

Secondmind is focused on using model-based design and optimisation solutions to overcome the many challenges today’s automotive engineers face. Scientific Computing World caught up with the company’s chief executive officer, Gary Brotman, to find out more about the Secondmind’s machine learning approach and work in the automotive industry.

Q: How is Secondmind addressing the challenges that today’s automotive engineers face and what makes it different from other simulation solutions?

A: The challenge of virtually achieving design and performance reliability through simulations that translate to validity and effectiveness in real-world scenarios, an already difficult exercise, is made even harder by the growing glut of data bogging down the design process. As a result, existing vehicle design and development technologies used to build complex models for simulating and optimising new components, systems and materials are struggling to keep pace at a time when they are needed the most.

The Secondmind Optimization Engine powers our cloud-based solutions for vehicle system design and control system calibration. And because it’s cloud-native it has the ability to continuously optimise the performance of complex systems throughout the vehicle lifecycle.

The Optimization Engine is designed from the ground up to solve the most difficult engineering problems in automotive and address the shortcomings of other AI-based solutions, by enabling intelligent, automated experiments, modelling of physical and virtual data, and providing engineers with better choices in design simulation and testing. The result is higher precision prototype designs, faster and more accurate performance optimisation, and less rework throughout the design and development process.

Most importantly, Secondmind slashes data dependencies by up to 80 percent to facilitate design and performance optimisation of high-dimensional problems more efficiently and accurately.

A good example of powertrain optimisation is the calibration of the e-motor and inverter pair, one of the most critical subsystems in electric vehicles. Calibration involves optimising myriad parameters and constraints to achieve optimal performance, such as effective use of energy from the battery, in as little time as possible.

The engineer is particularly interested in the rotor temperature because the motor’s magnetic field decreases as the magnet heats up, so a wide range of measurements is required. However, during the testing process the rotor temperature rises and the engineer must wait for it to cool and return to a stable state before they can take the next measurement, resulting in many lost hours.

Secondmind incorporates domain knowledge into its machine learning models in order to understand more precisely the physics of the e-motor. These models quickly learn and adapt to the e-motor’s unique personality, reducing the amount of data to collect for calibration. This further accelerates the calibration process and reduces the overall time required to generate accurate calibration maps that tell the e-motor and inverter how to function under certain conditions.

Q: Can you tell me a little more about the technology behind the Optimization Engine?

A: The technology fuel that powers the Optimisation Engine is Secondmind Active Learning, which intelligently automates the process of data acquisition, modelling, analysis and experimental design to achieve optimisation objectives faster. Traditional design of experiments (DoE) approaches are manual and linear, with engineers spending a lot of time upfront planning and acquiring more data than they need before running the experiment. This brute force approach more often than not results in a suboptimal outcome and the process needs to be repeated many times.

As an integral element of the Optimization Engine, Secondmind Active Learning significantly reduces the upfront preparation time and effort by giving the engineer a simple template to define the parameters, constraints and objective for a given optimisation session, and with a small sample of data, Active Learning algorithms intelligently design and run smaller experiments based on data from the targeted regions of interest deemed important enough to collect.

Knowledge of the problem increases with each iteration and, if left to run in a fully automated fashion, the optimisation objective is typically reached in half the time of existing DoE tools with results being as good or better. If engineers prefer a deeper level of engagement, they can participate by leveraging their domain knowledge in the process - knowledge not captured in the data, but potentially vital to achieving successful results.

Q: Can you tell me more about your System Design and Calibration products - why have you focused on these two areas for the automotive sector?

A: The broad design and calibration phases of vehicle development are the most complex, time-consuming, and costly and this is where we believed we could make the biggest initial impact. Our System Design and Calibration solutions offer capabilities that are unique to each development phase, application and engineering end user. At its core however, the Optimization Engine is designed to be system and application agnostic, offering flexibility in optimising system, subsystem and component-level designs, and in addition to the calibration of any number of vehicle control systems without the need for bespoke software development.

Secondmind for Calibration helps calibration engineers design high-value control strategies and produce high-precision calibration maps for complex systems like e-motors, internal combustion engines, and hybrid systems. A key capability of the Calibration solution is the intelligent automation of experiments to more quickly and easily generate calibration maps. Car makers like Mazda are using Secondmind for Calibration to halve calibration time using just 20% of the data they would otherwise need, and both modelling accuracy and less time on test benches has resulted in projections of significantly less prototype fabrication costs in future new vehicle programs.

Secondmind for System Design reduces design and simulation time, and error correction costs helping design engineers discover more design options and make better system configuration choices. By quickly identifying optimal design spaces, engineers can explore and innovate with better choices than they would have otherwise had due to data and time constraints.

Multiple engineers contributing to the design of complex vehicle systems are also empowered to experiment and make design trade-offs without having to worry about team or component-specific dependencies, resulting in efficient parallel planning that improves collaboration and ensures development schedules remain on track.

Enginering

Automotive

Optimisation

Altair

Secondmind

Ansys

The potential for quantum computing in biological research

Rob Roe — Thu, 13 Jul 2023 23:00:00 +0000

Quantum computing is opening up new possibilities to advance bioscience research by accelerating drug discovery and helping to develop treatments for cancer, writes Eugenia Bahit

Credit: Gorodenkoff/Shutterstock

Day by day, quantum computing is showing us its incredible potential for advancing biosciences and its ability to become integral to the future of several research areas. Many fields can benefit from quantum computing, and there are many compelling reasons for choosing to explore its capabilities. One of them is the need for more humane and effective science; the second one, is the promise of an emerging market.

The urgency for more constructive and efficient science

The need for more humane and effective science is clear. Animal Free Research UK reports over 3 million animal experiments are conducted in the UK, while Humane Society International claims that 50% are bred and killed without yielding any scientific benefit. According to their reports, in Europe, 32 beagles are used for each agrochemical and new drug tests, and 25,000 animals have died in cosmetic testing after the EU's ban. In the US, the situation seems to be more extreme. PeTA, the global organisation for the ethical treatment of animals, informs that more than 110 million animals are killed yearly for scientific experimentation. And although the evidence suggests that nearly 95% of drugs tested on animals fail in human trials, animal testing remains a regulatory requirement across almost all of the globe.

Dogs, cats, macaques, monkeys, pigs, guinea pigs, rabbits, fishes, birds, goats, llamas, hamsters, rats and mice are on the list of animal models for experimentation. "These animals are sentient beings", says Dr Luis Falcón^[1], the President of GNU Solidario^[2], a humanitarian organisation headquartered in Spain and involved in the GNU Project for advancing software for public health. "Science that harms does not deserve to be called science", he adds.

There are many scientists, like Dr Falcón, who think it's time to change the way to conduct science, proclaiming that animal experimentation is unethical and speciesist. In an interview with Nature Reviews Materials, Dr Donald Ingber, Director of the Wyss Institute at Harvard University^[3], challenged the reasons for animal testing by saying that "the question is whether we are fooling ourselves because we convince ourselves that what we see is what we thought it should be".

Similar questions are the ones that guide several organisations to research and promote alternatives to animal testing. Some institutions, such as the Center for Contemporary Sciences^[4] in the US, are promoting changes in legislation and education to reach more effective and human biology-based methods. Moreover, in partnership with an investment group, they are also offering opportunities for companies working on new technologies and products to replace animal experimentation. And it is here, among the technologies that can help to reduce animal experimentation, where quantum computing stands out as an emerging area in the realm of biosciences, with a market that could reach over 4,000 million dollars by 2028, according to market research firm MarketsandMarkets.

Drug discovery, for example, is where quantum computing has made the most significant advancements, followed by research areas such as cancer, genetics and genomics. All of them show promising results, whereas precision medicine and early diagnosis seem to be the next areas where quantum computing reveals its potential.

Accelerating the drug discovery process

Drug development is a complex, long process. Understanding disease to determine a biological target that can be modified by an external compound is an essential phase which can demand several years. Identifying a lead compound that can effectively modulate the molecule or protein involved in such disease, ensuring it can be safe, and understanding its metabolisation and interactions, is not as simple as just getting a name. It requires a long list of candidates and many tests to choose the most suitable one, and then several years to optimise it to reach its most effective and safe version.

Given this complexity, scientists have been researching ways to accelerate the drug discovery process. By leveraging quantum annealing mechanisms, they have managed to create algorithms capable of finding the best lead compound candidates in just a few minutes by binding prospects to biological targets among billions of molecules.

That is the case of the American POLARIS Quantum Biotech^[5] (POLARISqb), who have developed QuADD, a software as a service which leverages quantum annealing and distributed cloud computing for molecular library generation. In dialogue with Dr Anna Petroff^[6] and Dr SantiagoVilar^[7], computational chemists at POLARISqb, Dr Petroff explains that finding a small molecule that matches a protein target is challenging because the number of them is enormous. She notes that with QuADD, they can build a custom library of billions and "find a lead compound in less than a minute". Meanwhile, Dr Vilar remarks on the potential of quantum computing in optimising results by improving data quality and speed.

Other companies, such as River Lane coupled with AstraZeneca, in the UK, are advancing in harnessing the potential of quantum computing to calculate the solubility of lead compounds to estimate their effectiveness in the human body.

It is clear that quantum computing has a big potential in helping to identify and optimise lead compounds and could also help in the pre-clinical phase, where the current methods notoriously fail. In this respect, Dr Aysha Akhtar^[8], renowned neurologist and public health specialist, US veteran and Founder and CEO of the Center for Contemporary Sciences, emphasises that “Up to 95% of all drugs and vaccines that are tried end up failing at the human clinical trial phase because they don’t work or are too toxic and unsafe”. She adds, “This shows that animal testing is very bad at telling us which drugs and vaccines are actually going to work in humans and be safe for humans to use.”

Thankfully, scientists are making computational progress in predicting the toxicity of chemical compounds currently tested on animal models. An example is the work of Dr Teppei Suzuki^[9] and Dr Michio Katouda, who developed a quantum machine learning model to predict the toxicity of over 200 phenols used in various drugs and antiseptics. Another example is the quantum machine learning model developed by Dr Saad Darwish, using genetic programming to predict the toxicity level of different chemical compounds.

Advancements like these are driving drug regulatory agencies—such as the FDA in the US, under the Modernization Act 2.0—to support more humane requirements for approving drug releases to the market. Even so, many pharmaceutical companies sustain that the efficacy and side effects of new drugs can only be tested on animal models. Fortunately, quantum computing is shedding some light here. Indeed, Dr Shahar Keinan^[10], CEO and co-founder at POLARISqb, bets on the future of quantum computing for pharma. "Quantum computing has the potential to revolutionise drug design and development. It can aid in understanding how drugs interact with target proteins or enzymes, predicting their efficacy and potential side effects," she says.

Cancer detection and treatment: another potential area for quantum computing

According to official statistics, cancer is responsible for over a quarter of deaths in England, and the survival time after diagnosis is too low. WHO reports 10 million deaths worldwide from cancer just in 2020. Cancer kills, and scientists are not yet able to find a cure. Understanding the development and progression of cancer is essential to finding remission mechanisms and guiding the appropriate treatments.

Scientists are battling to beat these challenges from different perspectives. The most conservative ones keep trying to replicate cancer in animal models even though science itself has demonstrated that using animals does not work. However, other scientists are banking on developing organ-on-a-chip technology and exploring how to apply quantum computing mechanisms to foster better and more contemporary science. In this sense, Dr Akhtar thinks these technologies can help advance cancer research, proclaiming that "It is going to be one of the major technologies that are going to replace animal testing for drug development, but also for disease modelling."

And she is not wrong. Dr Dipesh Niraula^[11], an applied research scientist at Florida's Moffitt Cancer Center^[12], is working in the radiotherapy field and developed a quantum deep reinforcement learning (qDRL^[13]) framework to support clinical decisions in radiotherapy treatments. He explains the importance of this framework by making a parallelism with the decision process of buying a shirt available in different colours: "Before a shirt is purchased, shirt options are like superimposed quantum states. We wouldn't know their decision until they pick a shirt." He moves this analogy to clinical decisions and notes, "When doctors don't have complete information on the patient's state, disease progression, treatment response, etc., the clinical decision will be based on the physician's professional experience leading to inter-physician variability. And quantum computing helps in modelling such intrinsic uncertainty in human decision-making."

But the potential of quantum computing for cancer does not end there. Scientists are exploring the potential of quantum machine learning from different angles. Recent findings have shown that quantum transfer learning could help in histopathological cancer detection, while quantum convolutional neural networks could assist in breast cancer detection and brain tumour screening.

Moreover, the utility of quantum computing extends beyond the applied field. Theoretical approaches are trying to reach a better understanding of cancer by leveraging the potential of quantum computing wave functions to model the quantum mechanisms of genetic mutations involved in cancer development.

Advancing in genetics and genomics

Many diseases have a genetic cause, but the genome size makes it hard to understand some mechanisms with current technology. DNA and RNA sequencing, analysing, and assembling are essential to understand such diseases and, at the same time, are potential candidates to leverage the advantages of quantum computing. This is the case with phylogenetic trees, fundamental tools for understanding the evolution of certain organisms. Here, some scientists are exploring reconstruction via graph cutting using quantum annealing. Another crucial tool where quantum annealing is playing a key role is the de novo assembly, where the overlapping of DNA sequences benefits from the annealing's optimisation process.

But the quantum computing potential in genetics and genomics is even more promising. Quantum gene regulatory networks, for example, can aid in diagnoses and developing targeted treatments, while quantum comparison algorithms could detect DNA and RNA mutations to advance disease diagnosis and understanding.

We can save more lives with an early diagnosis

The potential of quantum computing to predict and identify diseases under uncertainties is crucial. As Dr Niraula notes, "Human decision-making process in the face of uncertainty gets unpredictable", and as he previously said, such uncertainties are like quantum states, which can be modelled with the help of quantum computing.

Scientists are using quantum computing to solve such uncertainties in many ways. Quantum neural networks, for example, are being explored for applications as different as electroencephalographic signals classification and personalised treatment for osteoarthritis, while quantum machine learning and quantum deep learning are being studied for heart failure detection, dementia prediction and diabetic retinopathy classification.

Dr Joseph Davids^[14], a clinical research fellow at Imperial College London, specialising in nanomedicine and neurosurgery, thinks that quantum computing could be the future tool to help in medical diagnosis. In this respect, remarks: "Quantum computing will be responsible for not just diagnostics but treatments too."

He also notes^[15] the importance of initiatives such as the National Quantum Computing Centre in Oxfordshire, which is aimed at accelerating quantum computing development in the UK and fostering patient-tailored therapeutics and diagnostics.

Quantum computing: the future of biomedical sciences

Many are the advancements of this emerging technology in the biosciences field. In just a few years, scientists have succeeded in exploring the quantum computing potential not only in a theoretical stage but also developing practical applications. Quantum computing is already underway and carving out a promising path.

Dr Akhtar thinks switching to these emerging technologies, may be expensive initially but asserts that over time "you don't have to worry about feeding computer chips". Excited by the conception of combining quantum computing with biological sciences, she pictures a future where "biological models like body-on-a-chip technology will be connected with computing models, where quantum computing will probably increasingly play a role because it's going to take a combination of these different techniques to give the best-combined understanding of human biology and human diseases."

Emphasising the existence of "lots of data that computing technology can screen to combine the information with biological models like organ-on-a-chip technology", she concludes, "This is going to be the future of biomedical science."