Automating Part Programming Cuts the Time to Engaging Work

One commonly known benefit of robotic machine tending is that it automates repetitive, low-interest work on the shop floor, freeing up staff members to tackle more challenging and stimulating work. CAM Assist, an AI-driven program from CloudNC, aims to bring this same benefit to programming.

Generating Programs Through AI

CAM Assist is the result of nine years of labor on the part of CloudNC CEO and Co-Founder Theo Saville and his team. Saville says that he was accustomed to inputting parameters and getting a working program at the press of a button during his time in additive manufacturing, and CAM Assist is his method for doing the same in subtractive machining.

Unlike a lot of programs in the recent AI boom, CAM Assist does not rely on language learning models. Instead, CAM Assist directly relies upon CloudNC’s own work and optimization efforts. “You can’t build technology like this unless you know how to make parts,” Saville says, and the data set CAM Assist uses consists of thousands of parts CloudNC has run through its manufacturing facility, with tens of thousands of simulations of these parts to refine the software.

Further optimization of the software will also rely on CloudNC’s efforts, as the company does not train its software on customer inputs. For one thing, Saville and his team would see it as a breach of privacy. For another, the company expects that generated tool paths are only around 80% of the way to a completed program for most supported applications, and they will not know the full scope of refinements and adjustments users make to these tool paths.

Instead, the team will continue to rely on the wide variety of parts its own machine shop produces. When users notify CloudNC of difficulties getting a particular part to run, the team engineers that part on their own to “figure out the science of how those parts are made,” as Saville puts it. After determining how to successfully produce the part at a profit, CloudNC’s software engineers figure out what about it is giving the software trouble and update CAM Assist with methods to produce the necessary features.

Shortening the Programming Process

For the right part, CAM Assist can deliver an almost-complete part at a button press. For the wrong part — one that is too complex or has unsupported features — the software might only produce up to 30% of the final program. For most supported parts, however, Saville estimates that CAM Assist can get users about 80% of the way to a functional tool path. This leaves the more complicated, engaging parts of part programming — optimizing fixtures, tooling, quality and the like — while drastically cutting the amount of time spent programming. Saville points to an example of one part that he says would have taken one of his experienced programmers between four and eight hours to program without macros. CAM Assist calculated the tool path in about 12 minutes, and the programmer spent half an hour optimizing the result.

Saville says this massive reduction in programming time not only improves shops’ distribution of labor resources, but also helps upskill newer employees. By providing the structure of a successful program, one that uses proven methods for roughing and finishing on supported components, students can learn programming from models rather than starting from scratch, then continue on under an experienced programmer’s wing, but for less time.

Widening Support

CAM Assist is not compatible with every type of milling or every type of part — yet. The company went into its beta test phase last year with three-axis roughing, finishing, holemaking and deburring support, and even then, the program saved users an average of 68 minutes of programming per part. CloudNC’s optimizations have only enhanced its effectiveness, especially with recent expansion of support into 3+2-axis machining and a new feature for providing cutting parameter recommendations.

Supporting 3+2-axis machining was a massive undertaking, Saville says, because the ability to alter the approach direction adds so many tool path options that it can overwhelm the computer. CloudNC’s software engineers needed to optimize how the solver constrained potential solutions, helping it discard options that would end in failure or cause undue trouble during machining (such as using tools of the wrong size). Percentage-wise, the results are similar to what CAM Assist can accomplish for three-axis machining — that is, it still produces programs about 80% of the way to a final program — but 3+2-axis programming saves more time in practice due to the ability to program multiple surfaces of a part at once rather than needing to specify the approach direction and orientation for each flat surface. What’s more, Saville says supporting this type of milling expands the system’s compatibility to about two-thirds of CNC milling work.

CloudNC has also recently launched a physics-based cutting parameters module to generate cutting speeds and feeds for aluminum, steels and stainless steels, with plans to support more niche materials in the future. Saville says that the physics engine combines machine learning with a complex mathematical model and simulation of the cutting process, including cutting dynamics, workpiece and tool material, tool holder geometry and surface finish models to provide safe, effective speeds and feeds for tools and materials that may be unfamiliar to a shop. The company estimates that replacing speeds and feeds testing with this feature will boost users’ productivity by at least 20%.

Fieldwork

Though CAM Assist only officially launched in late 2023, with major new features releasing every few months, its early adopters have high praise for it. Total Manufacturing Solutions, an Ocala, Florida-based job shop producing small-batch production runs of parts for industries including the defense, aerospace and aftermarket automotive markets, has seen a seismic shift in its process since adopting the software in late October 2023.

Even as a small shop with multiple people working on part programs, programming was always a bottleneck for the facility, says Chris Battelene, president of Total Manufacturing Solutions. Its CAM software’s standard templates and feature recognition only went so far in automating programming, especially with the wide variety of parts the shop makes. CAM Assist went much further, even with the required optimization for each program, with the only real friction stemming from a need to input tool speeds and feeds into the software — which Battelene believes will mostly fade away with the introduction of CloudNC’s cutting parameters module.

Battelene says the move toward using CAM Assist’s speed and feed calculations will standardize a lot of the cutting parameters around the shop, as tool speeds and feeds previously relied on tribal knowledge and manual inputs into its CAM software. His shop has also experienced the benefits for inexperienced coders that Saville discussed. Battelene says that CAM Assist “helps bridge that gap in the learning curve and gets a guy that has limited experience in programming to generate his own programs relatively quickly,” with most operations organized into subfolders for simple parsing.

In practice, he points to the software proving especially useful for a job that required many differently sized iterations of a part. The team at Total Manufacturing Solutions created a tool database within CAM Assist and assigned the software to create tool paths for each iteration. A job that would have taken the shop’s experienced programmers 45 minutes to an hour for each iteration instead only required between five to 10 minutes total, drastically shortening the overall programming time.

The Future of CAM Assist

CAM Assist is still in its early days, but Saville and his team are actively releasing new features and expanding CAM Assist’s capabilities. After updating the software with 3+2 machining support and the cutting parameters module, further 2024 update plans include inspection and verification tool paths, as well as a feature to help with estimation. Saville hopes that the software will be able to shorten the entire process of designing and preparing a part, turning “a process that could have taken two days into potentially as little as an hour of work.” The CloudNC team also plans to expand the availability of the program from its status as an Autodesk Fusion plugin, with Mastercam and Siemens NX support planned around the middle of 2024.

Post-2024, the team hopes to further optimize roughing and fixture assistance, then expand CAM Assist’s applicability to CMM work, turning and turn-mills — but milling remains the team’s top priority.