The concept of Big Data is at the forefront of new technology in rail freight sector. Analytics based on Big Data is a new field in the transportation sector which presents challenges to implement & the opportunities to gain from the Big Data based analytics in terms of better preventive & predictive Asset maintenance activities. The Indian Railways has been in the last ten years implemented various condition monitoring mechanisms for its fleet of Freight wagons like Wheel Impact Load Detector (WILD), Hot Box Detector (HBD), Online Monitoring of Rolling Stock (OMRS)   &  RFID tags for wagons. All these packages will help to improve the service availability & enhanced maintenance periodicity. Mostly the data generated is used to give maintenance alerts. Data is also generated at the maintenance points while the maintenance is being undertaken & periodic checking at the en route stations. Most of this data is now available in digital form & can be utilized for gaining predictive insights. 

Big Data can be defined as data so huge which is beyond the normal computing capacity available. The volume can be several GBs per day. Big data can be characterized by several attributes called as the Vs of Big Data : Volume, Variety, Veracity, Valence , Velocity & Value. 

A basic Big Data model works towards acquiring, pre processing, analyzing & getting insights from the various streams of data which is being generated by various sources- Machines, People & Organizations in the ambit of Indian Railways. Each of this step is a major step involving various iterations with a single objective of getting Actionable Insights from the torrents of data. 

These insights will be valuable for the Indian Railways in achieving high standards of serviceability, key decisions related to the sufficiency of new technology, increasing the modal share, optimization of the available infrastructure for freight maintenance & prepare a course of action for the heavy haul traffic.

Bio toilet working models have been displayed at Hubli  & VSG Railway station. The advantages and the working system of Bio toilets has been displayed on Eco solvent vinyl boards in vernacular language for awareness of passenger.  

UBL

VSG

Bio toilet cleaning tool has been developed by UBL Division to clear the scales formed in commode pan neck area. The scales and muck accumulated in this area is the main cause for foul smell in bio toilets. Till now about 75% of the coaches of UBL Division have been covered and the results are satisfactory.  

Name of the Gadget: Gadget for lifting of Side Buffers for fitment in coaches
Make: Developed at Coaching Depot, Santragachi, South Eastern Railway

Youtube link:  https://www.youtube.com/watch?v=Gw54o-vMNr4

Rectangular shaped Gadget

Description:

This rectangular shaped (120”x 14.5”) gadget (shown in picture below) is made up of SS pipes of  28 mm OD,1.5 mm thick with Sliding Table arrangement. This table is provided in such a way that the table with buffer can move freely on the longitudinal pipes of the gadget. There is a fixing arrangement at the ends of ‘A’ to be fixed with the bottom holes (2 nos.) on the head stock where the buffer to be fitted. Handles at the end ‘B’ have been provided for easy lifting of gadget manually. The gadget works as a Class 2 lever with fulcrum at end ‘A’ i.e. the head stock, effort at end ‘B’ and load (buffer) in between to achieve maximum Mechanical Advantage. Thus the gadget works successfully with less man power, time and ensuring safety.

Use of the Gadget: 

i) Fitment of soft buffer in ICF designed CBC fitted coaches

ii) Replacement of buffer in conventional coaches

Requirements for fitment of buffer:

i) Gadget for lifting of Side Buffers for fitment in coaches developed at SRC

ii) Box Spanner, Size 36

iii) Manpower-3 persons to be provided

iv) Wooden Skids- 4 nos.

Procedure for fitment of buffer: 

Before fitment of buffer in a coach, ensure protection of lines and provide skids on the lines to avoid rolling of wheels of the coach. Steps for fitment of buffer are mentioned as under:

Step-1

End ‘A’ of the gadget to be fixed on the bottom holes (2 nos.) on the head stock where the buffer to be fitted.

Step-2

Fix buffer on Sliding Table provided on the gadget

Step-3

Push the table manually from end ‘B’’ to end ‘A’

Step-4

Simultaneously end ‘B’ of the Gadget is to be  lifted gradually with the help of handles provided.

Step-5

Place the buffer on the head stock and fix two upper Nylock nut bolts provided in the head stock to hold the buffer securely.

Step-6

Release the gadget

Step-7

Fix the lower two Nylock nut bolts. Ensure proper tightness of all  Nylock nut bolts.

Benefit:

I) The gadget is simple and portable.
II) Fitment of buffer is easy because of its mechanical advantage always more than 1.
III) Only 3 staffs instead of 9 staffs earlier are required for fitment of buffer.
IV) Fitment time is also very less. 3 staffs can easily fit a buffer within 10 minutes.
V) It is very safe as there is no chance of dropping of buffer during fitment.

What is Machine Learning?
The common belief is that we use computer program when we need to perform routine, repetitive tasks. We often perceive such tasks as “boring”. These tasks might involve significant numerical calculations to be performed in a short span of time, which are beyond the scope of an ordinary human being. Such a belief assumes that computer programs cannot “think” and adapt to cases which are not already built into the code. Machine learning changes this paradigm. Arthur Samuel, an employee of IBM coined the term machine learning in 1959 . While Samuel used the phrase, machine learning extensively in this work, he did not provide a formal definition. Tom Mitchell a professor at the Carnegie Mellon University defines machine learning as building computer programs that automatically improve through experience . More formally, he defines machine learning as a study of algorithms that improve their performance (P) at some task (T) with experience (E). The key words here are “improve performance” and “experience”. 

Some Examples
Machine learning (hence forth abbreviated as ML), applications have become ubiquitous. Our e-mail app automatically classifies mails as spam and not-spam. The task here is to classify an e-mail, the performance is measured by how accurate the classification is and the experience is through study of specific works featuring/not featuring in each category of mail. Computer programs can also recognize handwritten text. The task is to recognize text, the performance is measured by how accurately the text has been recognized. Here, the program is “taught” by labelling the text and allowing the program to recognize patterns that corresponds to a particular alphabet or numeral. X-Ray scans classified by expert radiologists are processed by ML programs to identify patters. Based on these patters the program analyzes hitherto unclassified X-rays and automatically assigns a classification, as would be done by a human radiologist. Programming by example is another way to think about ML.

How does it work?
The reader will note that ML is about predicting. Mark Twain the American writer once said, “making predictions is difficult, especially if it is about the future”. The good news is – predicting using machine learning techniques is getting better with time. The following images will help illustrate the concept.

We feed the above images of cats and dogs to a ML program. The images are converted to matrix of pixel values, and we assign the label of “0” for a cat and “1” for a dog, as appropriate for each image. The ML program looks at the common features among images classified as “0”. Similarly, the ML program tries to identify common features among images classified as “1”.
 
Thus the ML program “learns” about features that are unique to cats. When fed a new unclassified image, the ML program compares the features of the new image with the ones it has learned earlier and assigns the new image a classification based on its past “training”.

This was hitherto considered to be an exclusive attribute of animals in general and humans in particular. Cognition is a term that means using our brain to make sense of the environment. “Machines” were not expected to display cognitive behavior. Since ML is in the business of predictions, there is an element of uncertainty. No ML algorithm can claim to have perfected the art of prediction. The subjects of predictions and uncertainty are classified under the subject of probability, which itself falls under the broader subject of statistics. Thus, when analyzing a new image, the ML program compares it with the earlier images it has “seen” and assigns the “most likely” label to the new image. ML practitioners must therefore be well versed in computer programming as well as statistics. 

Getting the predictions right
We need to feed a lot of data to the ML program so that it is able make its predictions accurately. This is called “training the model”. We feed lots of data already classified by humans and let the ML program “learn” the features common to each type of classification. Once we have “trained” the model, we test it with data, which the model has hot seen so far and see if it able to get its predictions right. We might need to “tune” the model to improve its performance. Once we have tested the model, and we are satisfied with its accuracy, we are good to go.

Can I learn ML?
Is ML subject suited for only persons who are experts in computer programming and statistics? The answer is yes and no. One must have knowledge of both these subjects to understand and apply ML techniques. Those who are novices in one or both subjects need not feel dismayed as there are plenty of opportunities available for beginners. The biggest hurdle is within us. Over the years, as we grow within the organization, we feel uncomfortable to declare ourselves as novices. There are plenty of resources available to pick up ML skills. Some of them are for free and others are paid. I’ve listed a couple of links at the end of this post that point to some of these resources. The bottom line is -if machines can learn, then why can’t we?

https://medium.freecodecamp.org/every-single-machine-learning-course-on-the-internet-ranked-by-your-reviews-3c4a7b8026c0
https://analyticsindiamag.com/udacity-or-coursera-which-mooc-is-the-best-for-artificial-intelligence-and-machine-learning-upskilling/

Every component, part and critical asset can tell a story – of its manufacture, of its use, of its possible misuse. DPM is a technology that allows this story to be known – accurately and instantly. The medical screw on the right is used for joining broken bones. It has a squarish mark on the right side in the head – that is DPM at work. Each mark is unique to that piece anywhere across the world, Once marked, always marked, always known.

With DPM, parts and components are marked once with some essential information that allow for its continued track-and-trace through its lifetime. This applies to individual components and also to their assembly. The largest users of DPM technology in India is the automotive sector. From individual fasteners, to piston rings, to rubber components, to even tools used in assembly– all use DPM.

This mark  can take several forms dependent on the surface quality. DPM has methods for working with al kinds of surface – rough cast surfaces, machined surfaces, dust-covered surfaces, oil and grease covered surfaces etc. These marks are permanent and cannot fall off or fadeaway.

Interestingly, the encoding system for DPM is the same as the one being currently used for RFID tags for Rolling Stock and major assemblies, such as, bogies. This is an internationally accepted standard by the governing body – GS1. As such, a smooth technological continuum currently exists that allows components along with the final assembly to be treated as one with a common data flow. So a bearing on an axle, fitted on some bogie, being used some coach can be tracked individually and as a whole at the same time.

CCB 1.5 Brake Valve testing bench is prepared in Quality Unit Air Brake of Diesel Shed Ratlam. After preparing this Test Bench all Pneumatic Brake Valve of CCB 1.5 system can be tested after the overhauling /necessary investigations after any line failure.

Railway

Western Railway

Subject

Reliability and Safety improvement

Name of Good Work

Test Bench for testing of CCB 1.5 Brake Valves.

Summary

CCB 1.5 Brake Valve testing bench is prepared in Quality Unit Air Brake of Diesel Shed Ratlam. After preparing this Test Bench all Pneumatic Brake Valve of CCB 1.5 system can be tested after the overhauling /necessary investigations after any line failure.

Detailed Description

Computer controlled brake system (CCB 1.5)  designed by the M/s Knorr Bremse is a powerful braking system, which make it possible to apply as well as release the Loco & Train brakes quickly thus prevents time loss and also ensures safety during  emergency application of the brakes. The system involves various Pneumatic as well as electrically operated complicated valves to run this brake system efficiently. Malfunctioning of any of the associated valves needs to be identified and rectified promptly to prevent detention of the loco in the shed.    RTM shed had received its first CCB 1.5 Alco Loco in 2010. Presently there are 3 HHP Locomotives in shed which are having this type of brake system.

CCB 1.5 brake System is having total 24 Brake Valves.  M/s KBIL provides total 12 no. of Test Benches for the testing of all these Brakes valves. Each Test Bench is designed to test one or more than one types of valves only. RTM Diesel shed has made a single Test Bench to test 12 pneumatic valves of CCB 1.5 brake system. The total cost of M/s KBIL made Test Benches for testing of these 12 Valves are Rs.42 Lacs as per copy of a BQ available with us, whereas the shed has used available resources of Diesel Shed Ratlam to make this Test Bench.

Many times brake valves are needed to be overhauled and tested in out of course/in schedule, but due to non-availability of testing facility, RTM shed has to test the culprit valves in OEM premises, which increases downtime of the  concerned locomotives besides loss of man power of the shed.

To overcome these entire issues, this Test Bench is made indigenously by available resources of Diesel Shed, Ratlam. As this Test Bench is made by scrap/condemn released material of Diesel Loco hence this Test Bench made by the RTM shed is not only a  cost saver but also a very compact one, thus occupying lesser area on the shop floor. This will help to enhance the reliability of all 12 valves, those are supposed to be tested on this Test Bench.

Impact/Benefit

Helps to reduce BWMS cases pertaining to CCB 1.5 System

Uploaded support  documents / Photographs/Diagrams

Contact Person Name

Shri Vinod Kumar

Contact Person Designation

Sr.DME(DL)-RTM

Contact Number

+919752492450

FIAT Bogie Shop - Centre of Excellence

Cleaning of Bogies
Movement of Bogies: stripping & assembly
Improvements in flow of components/ other materials
Palletization for segregating good, serviceable & condemned items and easy handling of materials
Availability of drawings and quick accessibility of maintenance information/ guidelines
Computerised Traceability of items
Total Quality Management
Human Resource Development

Click Here to view more information.