Real-world uses of AI in business have exploded in the past decade, but few of those applications are focused on warehousing and distribution. That is changing as companies like Lucas introduce machine learning tools to improve planning and decision-making in the DC. These new tools will free time for managers and engineers, making them more productive and their DCs more efficient and effective. This article provides an introduction to machine learning for warehouse managers.
New AI/machine learning applications will 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
- Rapidly identify and implement other process improvements
Engineered Standards vs. Machine Learning
As a DC planning tool, machine learning represents an alternative to traditional engineering and process modeling.
For example, the traditional approach to workforce planning is to use an engineered labor standards system. ELS-based systems are programmed to calculate expected work completion times for a given task or group of tasks. They use pre-defined models of the process, a limited number of variables, and pre-determined or recorded average time values. ELS usually requires a significant upfront investment of time and money in engineering and measurement (and maintenance).
In contrast, a machine learning solution uses algorithms to analyze warehouse data and 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).
One drawback of an engineered approach is that the formulas and measures need to be updated when the operating environment changes. Likewise, the models don’t account for all of the indirect variables that may affect results – for example, how congestion due to volume increases may impact efficiency. Finally, the more complex the engineered model, the longer it takes to process the data and provide an output. Machine learning addresses each of these issues.
Machine Learning For Warehouse Managers: Workforce Planning
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 is easier to implement than ELS systems, more accurate, and more flexible. It eliminates the detailed process measurement and engineering required in a system using ELS. And 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, however, replace engineers and managers. Engineers will still design and optimize processes. Managers will still provide critical input and manage target productivity rates. And supervisors will still be responsible for taking action based on the recommendations and predictions generated by machine learning systems.
In the end, machine learning will reduce time managers and engineers spend poring over reports and data to identify trouble spots. ML tools will provide input to management planning, rather than automating those functions.
Making Managers More Productive
The majority of DCs do not use engineered standards today to manage labor or other elements of operations. In that sense, machine learning can fill a void without adding new burdens on management and engineering teams. And for DCs that have dedicated staff maintaining complex ELS systems, machine learning will free time for managers and engineers to focus on process improvement and optimization strategies.
Interested in digging deeper into the complex topic of AI, machine learning and deep learning? Our new whitepaper offers an introduction to ML geared to operations and engineering executives.