As cutting-edge technologies such as artificial intelligence, Internet of Things (IoT), big data analytics and robotics become easier to deploy, manufacturers are rapidly adopting automation and digitization to drive new levels of efficiency, productivity and competition. releasing power.
The combined power of OT and IT data with domain-specific AI and ML models that can be deployed across environments will enable manufacturers to unlock new levels of efficiency, productivity and competitiveness.
However, there are challenges to overcome before realizing the full potential of smart manufacturing. Based on conversations at the Manufacturing Digitalization Summit, this article explores strategies for overcoming these challenges and driving transformation across the enterprise.
Smart manufacturing refers to using state-of-the-art technologies, such as investments in advanced digitalization and analysis of critical data, to optimize the entire manufacturing process, from production to distribution and maintenance.
These technologies enable manufacturers to make data-driven decisions, automate complex tasks, and optimize operations, resulting in lower costs, enhanced quality control, and faster time to market. will be Its success depends heavily on culture and on a clear focus on business outcomes.
The adoption of advanced tools, solutions and processes in smart manufacturing is gaining attention across industries. The global smart manufacturing market is projected to grow from $297.2 billion to $787.5 billion by 2030 at a CAGR of 14.9% (Source: Grand View Research).
According to MarketsandMarkets, the use of AI in the manufacturing market is forecast to reach $16.7 billion at a CAGR of 47.9% from 2022 to 2027. These numbers highlight the immense business value of smart manufacturing practices.
Roundtable Approach The roundtable discussion at the Digitalization Summit used a retrospective methodology of the 4Ls where leaders present Love, Learn, Lack and Long, and participants were asked to rank their experiences and preferences in key areas. I was asked to review, rate, and elaborate on. Smart manufacturing, namely:
1. Product implementation and ROI
2. Change management
3. Smart technologies in manufacturing such as digital twins
Certainly the most popular topic was change management.
Achieving ROI and Product Legacy Complexity
One of the major challenges in scaling smart manufacturing initiatives is the complexity of integrating diverse systems and technologies. According to Deloitte, 44% of executives see legacy systems as a barrier to adopting advanced solutions.
Modern manufacturing environments are a complex mix of disconnected systems that do not communicate with each other. This lack of interoperability hampers data sharing and insight, preventing the organization from maximizing its potential and measuring her ROI.
A Frost & Sullivan survey revealed that 79% of manufacturers face challenges in integrating legacy systems with new technology. To overcome these, enterprises must invest in a robust digital infrastructure that can seamlessly connect and integrate disparate systems.
Change management
Change management is a key factor that can drown many digital transformation projects in smart manufacturing. After in-depth discussions with multiple stakeholders in the manufacturing organization, a near unanimous conclusion emerged. Unless everyone in your organization understands the clear benefits and job expectations of the changes brought about by digital transformation, your efforts will fail. As an example, I gave a small change to a well-intentioned effort called dynamic scheduling.
Most scheduling is reactive and work is performed according to production needs. While the shop floor adjusts to complete work as it comes in, dynamic scheduling is a proactive capability that adjusts schedules to maximize production. A dynamic scheduling system adjusts production to minimize resource issues (machine failure, tool failure, quality issues, etc.) or job-related (rush jobs or cancellations) and saves shop floor resources. guarantees optimal use of
In one example given by a participant, a manufacturing organization had made a large investment in a dynamic scheduling system. However, it failed to bring the desired results to the organization and was abandoned after a lot of time and money was spent on the project.
The reason for this is that the change did not take into account the critical human factor, requiring employees working on certain assembly lines to log in via a keypad or card swipe to indicate work has begun. there was. Without it, the dynamic scheduling system will not work. No repercussions or incentives were explained to the workers in doing so. They thought it wouldn’t add any value, especially considering they’d already spent the day at work.
In another example witnessed by the author, it was proposed to use IoT sensors to detect phase current changes in a rail car door motor in order to implement predictive maintenance. By repeating phase current variation detection, the state of the motor can be predicted. However, even though the actual cost of adding the new sensor was less than $2, the change in workers and workflows was immeasurable.
First, it meant that the way work was recorded had to be digitized on the tablet. The sensor was sending a digital signal, so the recording had to be digital. Changes to paperwork and recording procedures meant long-standing changes to trade union law. This meant involving the rail operator’s HR, legal and IT departments, and he estimated it would take more than two years to implement.
Ultimately, even a simple, low-cost change to digitization would have far-reaching implications for companies, and after a significant investment in research time and money, the effort was abandoned.
Obstacles abound, but careful analysis of change for all stakeholders is essential to achieving a sustained digital transformation process.
smart manufacturing technology
1. Predictive maintenance (PdM)
Traditionally, manufacturers use post-mortem maintenance, repairing equipment only when it fails. By leveraging AI/ML-driven algorithms, such as analyzing historical data, manufacturers can predict and prevent equipment failures before they occur.
These algorithms can identify patterns and anomalies so manufacturers can proactively schedule maintenance, optimize spare parts inventories, and minimize unplanned downtime. PdM also prevents waste by eliminating unnecessary maintenance needs.
2. Digital twin
A digital twin is a virtual representation of a physical product, process, or system. By leveraging real-time data from sensors and ML algorithms, manufacturers can create digital replicas that mirror their physical counterparts.
This digital twin can simulate and optimize different scenarios, predict performance, and improve decision-making throughout the product lifecycle. The use of digital twins is projected to reach $183 billion during the forecast period 2023-2030 with a CAGR of 41.6% (Source: Meticulous Research).
3. Quality control
Another major application of AI and ML in smart manufacturing is quality control. AI and ML algorithms can be trained to analyze vast amounts of data such as images, sensor readings and production parameters to detect defects and anomalies in real time. By automating the inspection process, manufacturers can achieve greater accuracy and consistency while reducing the need for manual inspection.
A Capgemini study found that AI-based quality management systems can reduce quality costs by up to 50% and improve productivity by up to 25%. PdM, digital twins, and quality control are examples of many great technologies and tools, but very few of them achieve repeatable success at scale.
In fact, digital industry transformation is a very high-touch activity, requiring more than software products and single services that enable long-term and repeatable success. This requires bridging the worlds of IT, OT and business operations with a portfolio of factory-hardened industrial IoT solutions, versatile and easy-to-use software products, expert system integration and advisory services and support. .
Customer case study
A customer embarked on a smart manufacturing journey for an aluminum sheet rolling mill. They invested in data collection, integration, integration, and data contextualization using standard data warehousing and data curation solutions, using Historian and his SCADA system. To ensure that the developed aluminum sheet rolls have no quality problems, we focused on a solution consisting of an IoT solution and an analytics solution.
We were able to implement a smart system that ingests and blends up to 500,000 IoT tags per second without the need for rip-and-replace and exports to factories elsewhere. The system helped quantify defects, identify root causes and predict factory failures. Using video analytics, we started visualizing safety metrics for every zone across a huge rolled metal plant.
Predict equipment failures in hot mill gearboxes and motors, providing a platform for operational analytics and data science to maximize furnace uptime and optimize energy usage.
Secure IT + OT data system
As the use of IoT, analytics, digital twins, and other advances is facilitated and pervasive by better gathering insights from contextual IT and OT system data, their impact on smart manufacturing will continue to grow. it will be serious.
However, the continued success of AI and ML requires a sound approach that includes investments in people, data infrastructure, and robust OT cybersecurity. As more connected devices collect massive amounts of data, we need to focus on implementing robust cybersecurity measures to protect that information.
The risks are significant. According to IBM, 61% of cybersecurity incidents in OT-connected organizations last year were in manufacturing. Implementing strong cybersecurity and establishing a strong governance framework are essential to protecting sensitive data. This includes implementing strong access controls, encrypting data, updating software and firmware, and conducting rigorous vulnerability assessments.
Additionally, organizations should establish a strong governance framework to define policies and procedures for data processing, storage, and sharing. This is the only way manufacturers can build trust and confidence among customers, suppliers and other stakeholders, thereby increasing the sustainability of smart manufacturing technology.
To the point:
- Smart manufacturing is a key driver of industrial success, with the global market projected to reach $787.5 billion by 2030.
- Overcoming integration challenges and investing in a robust digital infrastructure are essential to enabling seamless connectivity and gaining real-time insights.
- Communicating change management and KPIs to all stakeholders, from the shop floor to the boardroom, is critical to the continued success of digital transformation in smart manufacturing.
- A shortage of skilled talent is a major impediment to sustaining smart manufacturing practices, with organizations looking to upskill and reskill to fill skills gaps and capitalize on the potential of advanced technologies. You should focus on your program.
- Smart manufacturing efforts must prioritize data security with strong cybersecurity measures and governance to protect sensitive information and build trust.
About the author
Shamic Mehta is Director of Industrial Digital Services at Hitachi Vantara and has 25 years of industry experience. IIoT, AI/ML-based data analytics, semiconductors, renewable energy, e-mobility.he specialtysS In thought leadership for technology applications in smart manufacturing, energy and electrified transportation.
