The chemical industry is closely related to various aspects of daily lives. Many of the raw materials used by the industries producing daily necessities and the high-tech industries are supplied by the chemical industry, such as the petrochemical, plastic, and rubber sectors. According to the Department of Statistics, Ministry of Economic Affairs, the output value of the chemical industry exceeded NT$5 trillion in 2022, ranking third among the four major sectors in Taiwan's manufacturing industry, following the information electronics and the metal and electromechanical sectors.
The upstream of the petrochemical and plastic and rubber industry chain is crude oil; a variety of by-products are produced from the refinement of crude oil; the midstream sector uses the basic raw materials from light oil cracking in the upstream, such as benzene, phenol, and alkenes, as well as the chemical raw materials, such as plastics, rubber, and synthetic fibers, produced through polymerization, esterification, alkylation, and other chemical reactions using the above raw materials. The downstream sector is manufacturing all kinds of daily necessities using chemical raw materials, including plastic, rubber, and synthetic fibers, such as electronic product cases, plastic products, rubber products, adhesives, synthetic fibers, plasticizers, and cosmetics, with a wide range of applications.
In recent years, the chemical industry has faced a variety of challenges. Particularly, the environmental, social, and governance (ESG) trend in the international community will pose a daunting challenge to the chemical industry in the next ten years. How to conserve energy, reduce carbon emissions, and avoid waste will be the most formidable issue.
Moreover, in addition to the impact of ESG on the industry, the transformation of industry structure and industry trends will inevitably put the chemical industry in a dilemma. Due to the high-tech industry's advantages in the salary and remuneration structure and the industry environment, and complex factors of school talent cultivation and talents' employment choices in recent years, a serious talent shortage has occurred to the chemical industry. This issue has, directly or indirectly, affected business operations and will present a tremendous challenge to the passing of business experience on to new talents, new product development efficiency, and business operations optimization.
Future chemical industry workers must be professionals with proficiency in AI technology
Although the above external environmental factors and internal talent shortage are the challenges facing the chemical industry nowadays, they also represent a new opportunity or turning point as young new talents are accustomed to adopting new technologies to assist with optimization. In recent years, the chemical industry has gradually adopted artificial intelligence (AI) technology in production or material research and development (R&D). The main application aspects are stated below:
1. Use AI technology to assist with product R&D, to identify key factors and simulate formulas to shorten the product R&D cycle and reduce costs
First, AI technology is adopted as data analysis and modeling tools in the new product or material R&D process. With AI technology, the past R&D data is used to create models, to identify the key factors affecting products. In addition, such models can be used to assist R&D personnel in observing the impact of changes in different formula components on the product quality objectives, thereby greatly shortening the product R&D cycle and passing on the experience through modeling.
2. Use AI technology to analyze the key to poor production quality, to shorten the troubleshooting time and improve the quality
Due to a number of monitoring parameters in a chemical production system, along with the chemical formulas for incoming materials, the production data is complex. It was difficult to effectively identify the key factors that affected the quality through statistics in the past. With the production big data from the DCS or SCADA system, along with AI technology for data analysis, the key factors affecting the quality can be quickly identified, thereby shorten shortening the troubleshooting time and reducing defective or substandard products and waste.
3. Use AI technology to predict the quality of production process
It often requires quality inspection during the chemical process, but a comprehensive real-time quality inspection is impossible. AI technology is adopted to create a prediction model with the past production and quality inspection data. By combining AI and the Internet of Things (IoT), the quality change trend can be identified and countermeasures can be taken early before the quality deviates from the trend. As such, quality issues can be responded to in advance through an AI-based prediction model to avoid the scrapping of substandard products.
4. Use AI technology to optimize the of the operational efficiency of systems and reduce energy waste
To respond to the ESG requirements and challenges, how to optimize the energy use efficiency of high energy -consuming equipment is also one of the ways that AI technology is applied in the chemical industry. The modeling of the past system parameters with AI technology can strike a balance between production efficiency, quality, and energy consumption, to obtain optimal production parameters.
Recognizing the pain points in the industry, Profet AI has created a 'virtual AI data scientist' for businesses that operates 24/7 without interruption.
To allow data analysis and AI technology to be adopted and developed in the chemical industry, more companies in the industry have recruited data scientists or trained personnel to be equipped with AI and data analysis capabilities. However, we have observed a trend that data scientists tend to be less willing to work in the chemical industry. Meanwhile, it takes a long time to train internal personnel's adopt new AI technologies to analyze data.
In response to the demand for AI applications and talent in the manufacturing industry, Profet AI is dedicated to developing an AI platform for that industry. Its Automated Machine Learning (AutoML) platform aims to solve the problems of AI application and implementation for enterprises. Profet AI's developed platform is like a virtual data scientist for enterprises, allowing production experts to quickly conduct AI analysis with past production history data without having to write code or study complex algorithms.
During the production process, Profet AI's tools assist R&D departments in optimizing product development, quality experts in identifying causes of abnormalities through tools, and process experts in quickly finding the optimal parameters to improve the production process. Through innovative AI machine learning techniques, the platform simplifies complicated algorithms into user-friendly data analysis tools and quickly establishes a standardized smart decision system, helping factories further expand production scales and improve production and product development efficiency. Meanwhile, Profet AI's platform is not only applied in the quality prediction of petrochemical production, but also helps various industries through its products, allowing 80% of key personnel in various fields to independently use AI, fostering a culture of using data to assist decision-making in the enterprise.
The innovative Profet AI "AutoML platform" acts like a "virtual data scientist" and is an AI data analysis tool that makes operations simpler and more intuitive through visuals and graphics. It quickly empowers business experts with the ability to use AI by simply understanding their data. From uploading to completing analysis, only a few steps are required, allowing traditional manufacturing to quickly adopt AI and easily apply it in applications such as formula R&D optimization in chemical processes and energy consumption prediction, for example, as shown in Figure 1.
(Figure 1) Profet AI's "AI Automated Machine Learning (AutoML) Platform" acts like a virtual data scientist for enterprises.
Take the formula R&D in the chemical industry as an example, the formulas developed and experimental results can be uploaded to the AutoML platform of Profet AI to create a formula R&D model. Through this model, two benefits can be achieved:
1. It can quickly identify the key factors of multiple formulas (X) influencing the physicochemical properties of multiple products, to quickly identify the key formula parameters that affect each quality objective.
2. AI models are adopted to perform virtual experiments and simulate different formula parameters, to understand their impact on quality objectives, thereby reducing the number of physical experiments, shortening time, and cutting costs.
How to adopt AI technology for modeling
After confirming the customer's clear requirements, Profet AI begins the relevant steps to assist the customer in solving problems and applying AI:
Step 1: Compilation of experimental data
Clients organize the past experimental data and convert experimental test results (Y) and each formula(X) to an Excel or CSV sheet，and the structural data format is shown in Figure 2
(Figure 2) Structural data format according to the logic of Y=F(X)
Step 2: Building the AI Predictive Model
Upload the data table to the Prophet AI platform. The system will first perform data pre-processing, allowing the user to confirm the data quality again and understand the relevance of each feature value to the result Y. Then the data set will be automatically modeled after the personnel simply confirm the modeling content and plan settings and start the modeling, activating fully automatic AI machine learning modeling operations.
Step3: Cause Analysis, Simulation Prediction, and Parameter Optimization Recommendation
1.Cause Analysis：
After the model is built on the Profet AI platform, the best AI prediction model can be identified through model scores. The key factors affecting each quality objective can be immediately analyzed using the prediction model and sorted by weight factors, to learn about the impact of changes in components on quality objectives.
2.Simulation Prediction：
Based on the prediction model established from historical data, the R&D personnel can adjust the ratio, and the system can predict possible outcomes. This way, engineers can perform pre-adjustment simulations without having to go through physical experiments as in the past, reducing the time and costs associated with manual adjustment and experimentation.
3.Parameter Optimization Recommendation：
When a prediction model established is confirmed to be accurate, the Profet AI platform allows R&D personnel to set the quality objectives, and the system can recommend relevant formula parameters. With slight adjustment to the formula by experts, subsequent product development can be carried out on a solid foundation and more formulas may be identified.
Profet AI allows the chemical industry to easily adopt AI technology in the aspects of R&D, processes, and quality inspection, effectively transforming the experience of senior engineers into expert systems, making it more convenient and more efficient for users to utilize and identify the root causes of problems for continuous improvement. However, the most important thing is that many user companies have found that when a large amount of production data from different processes can generate more value through the platform, a data-driven and continuous improvement culture has gradually been established within the company and a habit of collecting data assets has been cultivated. When this culture is deeply rooted, the company will be able to improve both tangible and intangible benefits and increase profits.
In the chemical industry, many companies have used the Profet AI platform and the practical methodologies of one-day on-boarding and one-week landing. Through the assistance of the platform, 80% of key experts from various companies and functions can use AI independently. As more and more manufacturing industries adopt AI, they aim to use it to create a strategic high ground for competitiveness and lay the foundation for the next five years of upgrading and transformation. Therefore, more and more senior managers are unanimously saying: "AI empowerment is no longer a question of whether or not to do it, but how to do it faster and more widely than our competitors."