Cancel Preloader

Big data in manufacturing: a guide on how to start

hosting image
Big data in manufacturing: a guide on how to start

Big data in manufacturing: a guide on how to start

 http://smartclouds.co/ +1(619) 800-3614  SEO services San Diego

After looking through big data manufacturing use cases, you may be impressed. You may even rush to seize big data’s powers to outrace your rivals. But it’s not all that simple. Before stepping on it and starting your big data adoption project, you need to know the tricks that may be waiting for you. So, here’s a guide to make your big data adoption ‘ride’ as smooth as possible:

  • Preparation
  • Onset and acceleration
  • Endurance

To prepare for a big data adoption project, you need to find the right approach. Rather than getting obsessed with the idea of big data, rushing to get the budget and then failing to extract value from it, first, you should lay the groundwork for the possible future ‘novelty.’ The following steps aim at that and are characteristic of business-IT alignment. So, let’s look at them from the perspective of improving product quality in an enterprise.

Big Data


Step 1. After reading enough about the possibilities of big data, look through your business strategy and understand what goals in it can be achieved with big data’s help.

Step 2. As an IT professional, you should get more details on your company’s manufacturing problems and needs. The best way to do it is talking to the engineering management at your factory and asking them how the quality improvement process is going. Chances are, the process is problematic and no solution has yet been found, which is where you – very cautiously, without too much IT slang – explain that such challenges can be solved with a thing called big data analytics.

Step 3. Try to get the consent of the engineering management to prove (if needed) to the company’s top management that they do need big data. And also warn them that their involvement will also be necessary later to help data analysts understand the needed details of the manufacturing process.

Step 4. Determine a certain range of how much a particular big data project costs and talk to your top management about big data adoption and what effects it will bring.

 http://smartclouds.co/ +1(619) 800-3614  SEO services San Diego
Go!

You can’t test big data’s capabilities on complex tasks right at the start. Just like you can’t go to space a few days after deciding to become an astronaut. Manufacturing companies should start out with a simple project (for example, trying to achieve a stable output quality at a vaccine factory). A simple starting project allows you to see how big data can solve your problems with low risks and investments. Which, in its turn, is likely to positively affect your top management’s opinion on big data and encourage them to plan further big data investments (for more serious analytical projects). Whereas an overly complex and high-risk starting project, such as reorganizing the whole production process at the vaccine factory, can forever set them against big data because the project’s high investments can easily disappear without trace.

And if we speak about any big data adoption project more globally, they should always be broken down into ‘digestible’ phases that are to be approached separately. Here, we propose the following phases for your big data adventure:

  • Aggregating data.
  • Using simple analytical algorithms.
  • Turning to more sophisticated analytical methods.
  • Incrementally automating your production management.

 http://smartclouds.co/ +1(619) 800-3614  SEO services San Diego

Aggregating data

Long before any analysis can happen, you have to start aggregating data. In some cases, it’s not a problem at all: you just deploy/add sensors on your manufacturing equipment, prepare data storing facilities and enjoy the flow of ‘freshly-cut’ data.
But in other cases, such as if your production cycle is months- or even years-long, it can prove difficult because you may lack the info on how your production process parameters influence output. And without knowing it, it’s all really a shot in the dark. But don’t get upset: there are ways to fight it. For example, try not to concentrate on the entire manufacturing cycle at once. Rather, focus on one part of your manufacturing process (say, inoculation in cheese production), gather data about it, analyze it and see how you can improve it.

Making analytical baby steps and advancing to big data strides

As your big data solution evolves, you can get different levels of analytics results according to these stages of revealing big data insights in manufacturing:

  1. At first, you can perform relatively simple big data analysis to make targeted changes in your manufacturing processes (to improve product quality, for instance).
  2. Then, you can dig your data deeper to find ways to change your business processes. For example, you used to perform reactive maintenance and, with big data, you start preventive maintenance.
  3. When the time comes, you can even transform your business model, finding a better way to do it through big data analysis (say, you decide to get closer to the customer by making the cars you produce a smart connected product; you deploy sensors on them, analyze data from cars in use and provide after sales services).


At early stages, you’ll only need the most usual analytical methods, such as correlations and regression analysis. And as your big data competences and needs grow, analytical methods become more elaborate. With time, you’ll ‘employ’ predictive analytics and machine learning. And, as you can image, if you find simple correlations helpful, complex analytical methods will make you feel dizzy with new opportunities.

 http://smartclouds.co/ +1(619) 800-3614  SEO services San Diego
Production management automation

Automation of your production management is probably the most sophisticated way of using big data in manufacturing processes. This is the point where you as a human being are rarely seen on the manufacturing site. The concept of automated production management is fairly simple: your historical and incoming sensor data is analyzed in real time and the control apps send targeted commands to actuators on your equipment.
A good example of production management automation is the case with General Electric’s wind turbines. Sensors provide data on energy generation and wind direction, according to which the blade pitch is changed to optimize the wind turbine’s efficiency.
An example to make it clear
Suppose your company produces baby food and decides to go big data. The first thing to do here is find the needed expertise to guide you through the adoption project (here, reading a lot and hiring big data consultants would be a good choice). And after gaining a deep big data understanding, you hire needed staff and start data aggregation (deploy/add data sensors on your production floor and prepare data storage).
For the sake of the example, let’s imagine that systematically a few times a month your baby food batches substantially drop in quality. Now, the big data staff (together with the engineering technologists) can find out what causes these quality drops. And they realize that your manufacturing process doesn’t allow for the variations in the quality of raw material (baby food ingredients). If the ingredients’ quality is lower, the machinery isn’t ‘tuned’ to get a better quality output (say, you don’t adjust temperature and cooking times). And besides that, they also find a way to reduce your overall production times. This big data application (better quality assurance) can be a good first project.
Getting valuable insights quickly and cheaply makes your company more interested in further big data capabilities and more complex analytical algorithms. And in a while, your enterprise starts running predictive analytics, equipment wear-out analysis and machine learning. Among other things, it allows you to perform preventive maintenance, which enables the staff to react to alarming trends on the manufacturing floor before any real damage is caused.
And when the time comes to expand globally, your company decides to go with franchising and use your big data powers to assure and control baby food quality across all your franchisees.

 http://smartclouds.co/ +1(619) 800-3614  SEO services San Diego
Now, survive

As soon as you start real big-data-adoption action, there will be some impediments in the way (say, from the project management side). And that’s why you need to look out for management challenges that big data can bring in manufacturing:

  • Lacking in-house technical skills.

As tempting as it is, you shouldn’t completely outsource the whole adoption project. Otherwise, it will be difficult to gain much-needed big data understanding. Moreover, outsourcing completely is not a way out, because – especially at early stages – you’ll need to experiment a lot. And it is simply easier, if your ‘domestic’ people are involved. Which is why it’s only natural to hire new skilled tech employees or retrain old ones.
Before starting some real action, it would be a good idea to turn to big data consulting, since it can ease the hardships of big data projects and contribute to big data understanding. But before you head towards the closest consultant, there’s something you need to know: it’ll only be advantageous, if you organize knowledge transfer to your tech employees.

  • Missing engineering technologists in the team.

Not only developers work with big data. Your tech-team will need to work closely with engineering technologists. Firstly, because techs need to understand your manufacturing processes and technologists can help with it. Secondly, because your technologists themselves can see precious ways to improve production and its management, if they learn general big data opportunities. So, you should make sure your big data team has a sufficient number of skilled engineering technologists.

  • Resisting the new technologies.

Some employees – let’s hope the lesser part – will probably resist big data. And there’s nothing personal about it: for creatures of habit, it’s just more convenient to use the old technologies. Training your staff as well as controlling their usage of the new solution can help deal with this challenge.

 http://smartclouds.co/ +1(619) 800-3614  SEO services San Diego
Let’s rehearse it one more time

To start using big data in manufacturing, you:
– Find the right approach to your big data. Carefully analyze your business needs, find a way to fulfill them with big data and never chase after trends just for fun.
– Prudently plan your big data adoption. Don’t jump to the most difficult part right off the start. Find a small-scale project to test big data on. Aggregate data, test simple algorithms and then try more daring ones.

0 comments

    Leave your comment