Identification and Tracking‐Control for an Optomechatronical Image Derotator Using Neural Networks

Altmann, Bettina; Rohloff, Benjamin; Pape, Christian; Reithmeier, Eduard

doi:10.1002/pamm.201610386

Cited by 3 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the second case an adaptation algorithm is required to adjust GRNN parameters. The second approach is shown in Fig Some of the applications of GRNN in control systems include dead-zone estimation and compensation in motion control of a traveling wave ultrasonic motor [15], fault diagnosis of power system [16], intelligent battery charger [17], microgrid hybrid power systems control [18], bipedal standing stabilization [19], air conditioning control [20], wind generation system [21], helicopter motion control [22], active vibration control [23], active noise cancellation [24], rat-like robot control [25], pipe climbing robot control [26], tracking-control for an optomechatronical Image derotator [27], tracking in marine navigational radars [28], factory monitoring [29], and flapping wing micro aerial vehicle control [3].…”

Section: Applications Of Grnn In Control Systemsmentioning

confidence: 99%

Applications of General Regression Neural Networks in Dynamic Systems

Al-Mahasneh¹,

Anavatti²,

Garratt³

et al. 2018

Digital Systems

View full text Add to dashboard Cite

This paper depicts a brief revision of Generalized Regression Neural Networks (GRNN) applications in system identification and control of dynamic systems. In addition, a comparison study between the performance of back-propagation neural networks and GRNN is presented for system identification problems. The results of the comparison confirms that, GRNN has shorter training time and higher accuracy than the counterpart back-propagation neural networks.

show abstract

Section: Applications Of Grnn In Control Systemsmentioning

confidence: 99%

Applications of General Regression Neural Networks in Dynamic Systems

Al-Mahasneh¹,

Anavatti²,

Garratt³

et al. 2018

Digital Systems

View full text Add to dashboard Cite

show abstract

“…In all current approaches the velocity of the measurement object is investigated by a speed sensor (e.g. a rotary encoder) [2]. Nevertheless, only few measurement objects are equipped with such a sensor.…”

Section: Introductionmentioning

confidence: 99%

Implementing an image based control algorithm for an optomechanical image derotator

Bettina

Pape

Reithmeier

2017

Proc Appl Math and Mech

Self Cite

View full text Add to dashboard Cite

In this paper an image-based control for an optomechanical image derotator is implemented. A derotator is an optical system to support measurements on rotating components by tracking their rotational movement. As a consequence, the position and rotational velocity of the measurement object has to be known continuously. In general this would be accomplished by measuring these variables using a rotary encoder. However, not all measuring objects are equipped for this task. As a solution universally applicable to a wide range of measuring objects, an image-based approach is developed in the scope of this work. The object is captured with a high-speed camera to determine its position and velocity by image processing algorithms. To proof the applicability of this concept, a controller using the data acquired with the camera and a controller using data of the rotary encoder are compared.

show abstract

Determining angular velocities of fast rotating objects based on motion blur to control an optomechanical derotator

Bettina

Pape

Reithmeier

2018

Proc Appl Math and Mech

Self Cite

View full text Add to dashboard Cite

Investigations of machine components are important for a faultless functioning of the machine. Ideally, the components are investigated during operation. Thus, a realistic performance of the machine can be analyzed. However, measurements of fast rotating machine components can be quite challenging especially under bad illumination conditions leading to the necessity of high exposure times. In case high-speed cameras reach their limits due to motion blur resulting of high exposure times or high velocities, an optomechanical image derotator can still lead to sufficient results. This is due to its operating principle consisting of a rotating reflector assembly inspired by a Abbe-Koenig-prism which optically eliminates the rotational movement. To generate a stationary image, the optomechanical image derotator containing the reflector assembly has to rotate exactly half as fast as the rotating object. Therefore, the angular velocity of the object has to be determined. A common way for this is the use of rotary encoders although not every machine can be equipped with such sensors. A flexible solution for this is to identify the angular position and thereby the velocity with a high speed camera capturing images of the rotating object. Using image processing algorithms the marker can be detected and thus the velocity can be calculated from the image data. However, due to high rotational velocities and long exposure times motion blur of the marker can occur. Generally, motion blur can be treated as an artifact since it impedes the image analysis. However, motion blur can be used to determine the velocity of the rotating objects in knowing the shutter speed as well as the length of the streaking of a blurred object. This work presents an approach which determines the rotational velocity from image blur for different velocities. The resulting information will be used as the input source for a velocity control of the derotator. Furthermore it will be discussed whether the velocity information is precise enough to control the derotator leading to a resting image of the rotating object.

show abstract

Identification and Tracking‐Control for an Optomechatronical Image Derotator Using Neural Networks

Cited by 3 publications

References 3 publications

Applications of General Regression Neural Networks in Dynamic Systems

Applications of General Regression Neural Networks in Dynamic Systems

Implementing an image based control algorithm for an optomechanical image derotator

Determining angular velocities of fast rotating objects based on motion blur to control an optomechanical derotator

Contact Info

Product

Resources

About