What DC Operators Need To Know About AI and Machine Learning
By Steve Yurick, Lucas Systems
The concept of Artificial Intelligence has been around since the 1950s, but the use of AI to improve warehouse and DC operations is still in its infancy. Nevertheless, AI is expected to have a growing role in warehouse management over the next five years. Rather than replacing human-decision-making, AI-based tools will give managers insights and recommendations then need to better plan, manage and optimize their operations. Here are some of the key things DC managers should know about the technology.
Why The Sudden Interest in AI
Real-world uses of AI in business have exploded in the past decade due to the exponential growth in data storage capacity and computer processing power. Armed with cost-effective data storage and computing resources, companies and software providers are applying machine learning techniques to analyze and interpret the masses of data collected in DCs.
These new AI/machine learning applications have the potential to provide DC managers and industrial engineers with insights to:
- • Dramatically improve workforce planning and management
- • Proactively re-slot products to improve efficiency
- • Predict and eliminate stock outs and other exceptions
- • Optimize automation/robotics alongside human workers
- • Identify and implement process improvements
AI and Machine Learning in Layman’s Terms
Most of today’s cutting-edge applications of AI use machine learning, a form of AI in which learning algorithms are applied to large sets of data to create predictive models relating to specific business outcomes. The thing that makes machine learning so compelling is that the machine learning models are not developed or maintained by teams of engineers, and machine learning systems do not require explicit programming. (An example of explicit programming is software code that follows specific steps to determine what move to make on a chess board, or how to calculate the time it should take to perform a given activity.) Machine learning systems apply algorithms to existing data to come up with their models and answers.
Machine learning is widely used for things like facial recognition, speech recognition and email spam detection. In the supply chain space, machine learning is being used in multi-site inventory planning by predicting consumer demand. And robotics systems use machine learning to master complex tasks like navigating a warehouse.
Machine Learning Finds Meaning in IoT Data
Machine learning requires large amounts of fine-grained data and tremendous amounts of computing power to process the data. But it’s not just about having lots of data.
To be effective, machine learning requires the right data for the questions it is intended to answer. For DC applications, that data would not usually be found in enterprise software systems that capture general transaction data, such as an ERP or WMS.
Instead, machine learning relies on streams of fine-grained data that is often associated with IoT (the Internet of Things) devices. IoT refers to interconnected machines (conveyors or sorters with sensors, etc.) and mobile devices that collect and share massive amounts of real-time data. For example, mobile devices used in RF or voice picking applications often collect time-stamped data about every user interaction with the system, in addition to data about the technical environment.
In the past, some of this data may have been used for short term purposes (debugging, training, etc.), but it was not usually collected or saved for other uses. The data had no value beyond those immediate uses. But machine learning changes that by automatically discerning patterns and finding meaningful information buried in the wealth of IoT data that many DCs already have.
How Machine Learning Changes DC Planning and Management
As a DC planning tool, machine learning represents an alternative to traditional engineering and process modeling for things like workforce planning, inventory slotting, or process optimization.
For example, the traditional approach to workforce planning is to use an engineered labor standards system. ELS-based systems are explicitly programmed to calculate expected work completion times (for a given task or group of tasks) using a pre-defined model of the process, a limited number of variables, and recorded average values. ELS requires a significant upfront investment of time and money in engineering and measurement (and maintenance).
In contrast to the highly manual engineering approach, machine learning uses algorithms to analyze warehouse data and to develop a predictive model for workforce planning. The data can come from a number of sources, including work execution systems, mobile devices, and automation systems (or WCS). The machine learning model will account for indirect influences on results, and it will detect and adapt to changes in the process.
Machine Learning Will Not Replace Managers and Engineers
In the workforce planning example, above, machine learning provides an alternative method for predicting labor requirements (i.e., how many full time and temporary staff will I need to pick today’s orders?). It eliminates the detailed process modeling and engineering required in a system using ELS, but engineers will still be needed for process design and optimization.
Likewise, with machine learning managers will still need to provide input to determine target productivity rates, and supervisors will still be responsible for taking action based on the recommendations and predictions generated by machine learning systems.
Machine learning tools will reduce the time managers spend poring over reports and data to identify trouble spots, but it will not replace management decision-making. ML tools will provide input to management planning, rather than automating those functions.
The Benefits of Machine Learning for Warehouse Management
The majority of DCs do not use engineered models and systems to plan, manage and optimize their operations today. Machine learning tools can fill this void without adding new burdens on management and engineering teams. The tools will help optimize operations and improve planning without massive new investments in systems and consulting services.