Why: Problem statement

It seems like there are a few different topics mentioned in the passage, but I'll try my best to summarize the main points:

Cleaning storage tanks is an important maintenance activity to ensure safe operations and facility longevity, and is often required by regulations.
Tank cleaning can be hazardous, and proper planning and risk mitigation strategies are necessary to reduce threats to employees and the environment.
Traditional manual tank cleaning methods are labor-intensive and time-consuming, but an automatic tank cleaning mechanism has been developed to reduce time and human effort.
The automatic tank cleaning mechanism can clean industrial chemical tanks quickly and efficiently, and is particularly useful for cylindrical storage tanks with difficult access to the interior space.
Crack detection is an important research topic for pavement images, and various image processing techniques can be used to detect cracks. The accuracy of crack detection depends on the quality of the images and the algorithms used.
Overall, the passage highlights the importance of tank cleaning and the potential risks associated with the task, as well as the benefits of using an automatic cleaning mechanism. Additionally, it touches on the topic of crack detection in pavement images, which may be relevant in industrial settings.

How: Solution description

It seems like there are two different topics being discussed here. The first part is about the contribution of activity analysis and involving operators in iterative design of a robot rover manufacturing system, and the second part is about the development of a mechanical cleaning system using a raspberry pi and actuator with dc motors for overhead tank cleaning, as well as the testing of a crack detection system using images.

Regarding the first part, it's good to involve operators in the design process to ensure that the robot rover manufacturing system meets their needs and is easy to use. The qualitative results should help illustrate the benefits of this approach.

Regarding the second part, the development of a mechanical cleaning system using a raspberry pi and actuator with dc motors for overhead tank cleaning sounds like a promising solution to the challenges of manual tank cleaning. However, it's important to ensure that the system is safe to use and doesn't pose any new risks to human health or the environment.

The testing of a crack detection system using images is also an interesting approach. It's important to ensure that the system is accurate and reliable, especially since cracking can affect the quality of the chemical tanks. It's good to hear that the system can achieve 90-95% accuracy with clear images, but more testing and validation may be necessary before implementing it in a real-world setting.

How is it different from competition

It sounds like your work focuses on developing a methodology for gas leak discovery using a rover in unrestricted surroundings, as well as performing a quantitative assessment of acoustic emission signals for structural integrity assessment of a globular storehouse tank. The use of time-sphere statistical features and a support vector machine classifier led to an average accuracy of 95% in distinguishing between normal and cracked conditions. In the future, you plan to implement different types of gas detectors in mobile detectors to improve their sensitivity and effectiveness in different types of surroundings.

Who are your customers

Industries:

• Textile
• Petrochemicals
• Chemicals
• Colours and Dye
• Galvanization
• Steel
• Tyre
• Plastic
• Paper

Project Phases and Schedule

Here the crack detection methodology can be classified into some following steps below:

• Image capture

• Image processing

• Image Segmention

• Feature extraction

Image capture

Any device can be installed on a vehicle zenith point or in a pole that is capable of capturing high resoluted imgaes of higways from any angle but focus should be perfect. If needed then the original images could be resized. Here are some examples of images on which we are going to detect cracks.

Image processing techniques

All the steps in the processing section are being explained below.

Gray scaling and averaging

Firstly, the images is transformed in a new one in grayscale and blur. These make the images easier to visualize the processed images in next steps.

Logarithmic transformation

Logarithmic transformation is used to replace all the pixels values of an image with its logarithmic values. This transformation is used for image enhancement as it expands dark pixels of the image as compared to higher pixel values. So if we apply this method in an image having higher pixel values then it will enhance the image more and actual information of the image will be lost. Now after applying the log transformation in to our sample blurred images, they look like below.

Image smoothing: bilateral filter

The bilateral filter also uses a Gaussian filter in the space domain, but it also uses one more (multiplicative) Gaussian filter component which is a function of pixel intensity differences. This method preserves edges, since for pixels lying near edges, neighboring pixels placed on the other side of the edge, and therefore exhibiting large intensity variations when compared to the central pixel, will not be included for blurring. So the sample logarithmic transformed images become as following after applying the bilateral filtering.

Image Segmention Techniques

Canny edge detection

Canny edge detection is a technique to extract useful structural information from different vision objects and dramatically reduce the amount of data to be processed. It uses a multi-stage algorithm to detect a wide range of edges in images. Canny algorithm consists of three main steps:

Find the intensity gradient of the image: In this step the scale of the gradient vector is calculated for each pixel.

Non-maximum suppression: The aim of this step is to “thin” the edge to obtain a one-pixel width edge.

Threshold hysteresis: Finally, a two-step threshold hysteresis is applied in order to decrease the fake edges.

Now we apply canny algorithm to detect the crack edges in our bilateral filtered as following.

Morphological closing operator

Morphological transformations are some simple operations based on the image shape. It is normally performed on binary images. It needs two inputs, one is our original image, second one is called structuring element or kernel which decides the nature of operation.

There are many different types of morphological filtering, but after analyzing the results, the best filter for this detection is the closing filter. Closing filter helps to fill minor gaps in the image making the main crack continuous and more detailed. It is useful in closing small holes inside the foreground objects, or small black points on the object. Closing filter is defined as a dilation followed by an erosion.

Here we go to apply the morphological closing operator onto our canny edges detected images.

Resources Required

Hardware requirement:

Raspberry pi 4

Motor driver - DC motor

MQ2 - ADC1115

Ultrasonic sensor

USB camera

Water pump

DC motor

5v relay