Category Archives: Manufacturing

Computational Intelligence Aids in Explosive Hazard Detection

Havens, TimTo detect buried explosive hazards in places like Afghanistan and to save the lives 
of civilians and US soldiers, Michigan Tech researcher Tim Havens realizes it requires
 a team: a team of sensors.

A new $983,000 research project, “Heterogeneous Multisensor Buried Target Detection Using Spatiotemporal Feature Learning,” will look at how forward-looking ground- penetrating radar, LiDAR, and video sensors can be combined synergistically to see into the ground, capture high-quality images, and then automatically notify the operator of threats. With funding from the US Army Research Laboratory’s Army Research Office (ARO), Havens and Tim Schulz, professor of electrical and computer engineering, will work with three Michigan Tech PhD students to create a high probability-of-detection/low false-alarm rate solution.

“It’s a very difficult problem
 to solve because most of the radar energy bounces right off the surface of the earth.” says Havens, the William and Gloria Jackson Assistant Professor of Computer Systems
 and ICC Center for Data Sciences Director. “ It’s hard enough finding the targets, but coupled with that is the amount of data that these sensors produce is massive. It is the perfect project to combine Tim’s (Schulz) statistical signal processing background and my machine learning in big data expertise. This technology has the potential to not only save lives, but also to advance the basic science of how to combine large amounts of sensor data and information together to get a whole that is better than the sum of its parts,” Havens explains.

This new project builds upon a previous sensor-related work Havens and collaborators completed between 2013-2015 and a current project on which Havens and Joe Burns, a Senior Research Scientist at Michigan Tech Research Institute, collaborate. These projects, also funded by the US Army, study signal processing and computer-aided detection and classification using both vehicle-mounted forward-looking and handheld downward-looking ground-penetrating radars. In total, Havens and his collaborators have secured over $2.5 million in funding to develop solutions for this problem.

Figure 1. High-level overview of multi-sensor feature learning and fusion for forward-looking explosive hazard detection. iECO: Improved evolution-constructed (features). DBN: Deep belief network. CNN: Convolutional neural network. GAMKLp: ℓp norm-based genetic algorithm for multiple kernel learning (feature-level fusion method). DeFIMKL: Decision level fuzzy integral multiple kernel learning.


The Army currently fields ground-penetrating radars in its fleet. The problem is they cannot detect hazards until they’re right above them, putting a multi-million dollar radar—and Soldiers—directly in the path of danger.

“The big ideas here are to process big data to obtain better images, see into the ground in a high-fidelity manner, and to develop algorithms that automatically find buried threats—even notifying operators of w
hat those threats might be—all while keeping the Soldiers and equipment as far away as possible,” Havens adds.

Havens has partnered with the Army since he was a PhD student in 2008.


Accurate Detection of Engine Knock

Engine knock is caused by the auto-ignition of the fuel and air mixture compressed in the cylinder before normal combustion is complete. A vehicle with engine knock will quickly suffer engine damage, yet operating at conditions far from the knock limit will quickly reduce fuel economy. Because engine knock typically generates high frequency vibrations in the engine, it can be measured by accelerometers mounted on the engine block. The intensity of the engine knock varies from cycle to cycle and can lead current knock detection systems to underestimate the level of knock resulting in possible engine damage or overestimate the level of knock resulting in fuel economy losses.

The solution to accurate engine knock measurement lies with statistical characterization. The invention is a software algorithm that capitalizes on current Engine Control Unit (ECU) hardware to fit the cycle-cycle knock intensities to a probability density function. The statistical characterization is more accurate for both stationery and non-stationery detection of engine knocks. The model was developed using a standard 3.0 liter, V-6 internal combustion engine.

Minimizing engine knock provides many advantages including reduced fuel consumption, reduced engine noise and improved tolerance to alternative fuels including biofuel blends. The developed software algorithm improves the robustness of existing ECU hardware with a more accurate measuring system. This calculation improves performance and extends internal combustion engine life while being applicable to most ECUs on the market.

Exclusive and nonexclusive license terms are available on this innovation (U.S. Patent No. 7,415,347, issued January 2008). For more information contact John Diebel in the Office of Innovation and Industry Engagement, 906-487-1082.

Wet Oxidation of Lactose

Lactose is a low-value by-product of cheese production. Altogether, about 1.2 million tons are generated annually worldwide by the dairy industry. Most of the resulting lactose is disposed of in waste water leading to environmental problems. To reduce the environmental impact the dairy industry needs to minimize this waste, either by converting lactose to smaller organic and inorganic carbon compounds more suitable for disposal or, preferably, to a lactose derivative compound with significant value.

At Michigan Tech, researchers have modified a catalytic wet oxidation process (common in sewage treatment) where O2 is added to a 3 percent lactose-water solution in the presence of a catalyst under heat and pressure. Catalytic wet oxidation converts whey (comprised of water, proteins, minerals and lactose) to carbon dioxide and water. The process has been modified to produce lactobionic acid, a marketable by-product for food preservation, cosmetics and pharmaceutical applications.  During the process, heat is generated and may provide additional value as recovered energy.  In addition to producing a marketable by-product, this process is simple and offers a safer and more environmentally friendly alternative to conventional waste treatment methods.

Exclusive or nonexclusive licensing is available on this technology (U.S. Patent No. 7,371,362, issued May 13, 2008). For more information contact John Diebel in the Office of Innovation and Industry Engagement, 906-487-1082.

Smart Control System for Suppressing Boom Oscillation in Heavy Hydraulic Equipment

A major problem facing operators of heavy hydraulic equipment is boom oscillation. Speed fluctuations resulting from moving and stopping payloads cause boom oscillations to occur. In turn, these oscillations transfer along the boom to longitudinal oscillation of the excavator body where they result in early wear on mechanical parts and harmful effects on human health including operator fatigue.

Manual correction is impossible given the time to dampen the oscillation for accurate placement of the bucket is greater than the time gained through increasing the maneuver speed. In addition to machine wear and operator health issues, this results in lower productivity.

The solution to this problem is a smart control system, developed at Michigan Tech, that implements an active boom oscillation control in hydraulic equipment. The control system continuously monitors the sensor signal inputs such as the hydraulic pressure profile of boom cylinder. The smart control system continuously analyzes the sensor profiles and evaluates the data to predict boom oscillations. When the system anticipates an upcoming boom oscillation, it generates one or more control impulse input motions to counteract the impending oscillation. The level of oscillation control experienced by test operators operating with this system is substantially greater than experienced with any competing oscillation control strategy or technology.

This technology offers a number of advantages when implemented on excavators, backhoes, wheel loaders and other similar equipment. It can be retrofitted onto existing equipment designs and improves operator’s working environment and performance. This technology also enhances dynamic stability and maximizes the life expectancy of the machine.

The smart control system has been tested at the laboratory and field scale on a commercially produced excavator. Development was in cooperation with a heavy equipment manufacturing company who holds a non-exclusive license. The smart control technology can be incorporated into existing heavy equipment designs and only requires the addition of an inexpensive signal processing control unit.

Additional non-exclusive license terms are available. For licensing information contact Mike Morley in the Office of Innovation and Industry Engagement, 906-487-3485.