Introduction
The results we achieve are inextricably linked to what and how we measure. The saying “What gets measured, gets done” is often used to highlight the importance of measuring the right things to achieve desired results. Essentially, it means that the things we focus on measuring are the outcomes we are likely to achieve or improve.
OEE level as a decision criterion
The question of where our organisation currently stands and what its OEE level is represents one of the criteria that will facilitate decision-making regarding further strategic actions in data analysis. An OEE value above 85% remains the benchmark for organisations; to achieve it, three components are essential: the right structure, basic continuous improvement skills, and MES.
Data acquisition and analysis
How we acquire data, how frequently, what we measure, and how much we can rely on this data are some of the questions faced by organisations entering the next stage of their development.
Others, which already possess advanced measurement systems like MES, face the challenges of analysing massive amounts of data flowing in every day, responsibility for individual indicators, incorporating them into employee goals, properly describing events, and dealing with their specific characteristics. I am referring here to significant licensing or maintenance costs, limited flexibility to change parameters, or the creation of additional reports or visualisations. Each of these changes entails additional costs that require justification, which is difficult to demonstrate in the short term, and the process is time-consuming.
Furthermore, the systems used by large multinational companies are complex, and their implementation process is characterised by adapting processes to the tool rather than vice versa, leaving little room for the organisation to implement its own needs and involve individual stakeholder groups in building an agile organisation.
Challenges related to data analysis
Regardless of the stage of an organisation’s development, it is worth considering the implementation of IT solutions for production management and analysis. This is not just a matter of “Industry 4.0” trends or competitive advantage, but a necessity that enables decision-making based on objective, real-time data. Without MES systems, OEE results of 75-80% can be achieved, but reaching higher values requires deeper data analysis, the use of online information, and the application of the Pareto principle.
It is worth noting that while data analysis is a powerful tool for improving production, there are several challenges that companies may face.
- Data quality: production data can be complex and chaotic, with missing, inconsistent, or inaccurate data points. This can make it difficult to gain meaningful insights from data analysis.
- Data integration: Production data can come from multiple sources, including machines, sensors, and software systems. Integrating data from different sources can be difficult and require a significant commitment of resources.
- Data security: Production data can be sensitive and requires strict security protocols to ensure confidentiality, integrity, and availability.
- Lack of data expertise: Analysing production data can require specialised skills in data science, statistics, and machine learning. Companies may need to invest in training or hiring data analysis experts to fully leverage data analysis capabilities.
- Interpretation of results: Even if data analysis is successful, interpreting the results can be difficult.
Overall, these challenges can prevent companies from fully exploiting the potential of data analysis. Addressing these challenges requires careful planning, investment in technology and talent, and a commitment to continuous improvement.
Benefits of implementing an MES system
MES system: the key to optimising and increasing production efficiency
An MES (Manufacturing Execution System) is an essential tool for improving production efficiency. By providing real-time data on production processes, identifying bottlenecks, and streamlining workflows, manufacturers are able to reduce production times, decrease downtime, and increase throughput.
One of the key aspects of production optimisation is quality control. The MES system supports this process by monitoring production processes, detecting defects, and providing real-time feedback to operators. As a result, this contributes to fewer defective products, reduced waste, and rapid identification of quality-related issues.
Supporting compliance with regulatory requirements is another task of the MES system. It provides real-time monitoring and reporting of production processes, leading to compliance with industry standards and enabling the traceability of materials and products.
The MES system also allows for the real-time visualisation and control of production processes, translating into better decision-making and faster responses to production issues. This enables manufacturers to forecast and analyse their business activities more accurately.
Successful implementation of an MES system can yield an increase in the OEE (Overall Equipment Effectiveness) index of around 5 percentage points. Consequently, it is key to optimising and increasing production efficiency, which translates into the overall growth and success of the enterprise.
Examples of using data analysis in production
Data analysis plays a key role in manufacturing, providing insights into production processes, identifying areas for improvement, and optimising efficiency. Finally, here are a few examples of how data analysis is used in production:
Quality control: data analysis can be used to identify patterns and anomalies in production data, helping to identify quality issues and improve product quality.
Predictive maintenance: By analysing machine data, it is possible to predict when machines might fail and perform maintenance before a breakdown occurs, reducing downtime and increasing productivity.
Energy efficiency: By analysing energy consumption data, companies can identify opportunities to reduce energy use and costs, improve sustainability, and reduce environmental impact.
Production optimisation: Data analysis can be used to optimise production processes, changeovers, repairs, service activity times within TPM, operator improvement through knowledge sharing, identifying inefficiencies and bottlenecks, and improving overall efficiency.
Summary
Overall, data analysis is a key tool for improving production processes at the point when our organisation’s OEE level starts to approach 80%, we have defined savings projects, and continuous improvement is part of the company’s DNA. By collecting, analysing, and interpreting data with the support of MES, companies can gain insight into production processes, identify areas for improvement, and optimise performance, leading to higher product quality, lower costs, and greater customer satisfaction.
