Monday, September 29, 2025

Acuitas Diary #88 (September 2025)

This month I returned to the Text Parser after letting it be for almost a year. My focus was on nailing the final major feature that I needed to handle all the sentences in my three children's book benchmarks: "parenthentical noun phrases." I don't know if that's the technical term, but that's what I'm calling them. They come after another noun and provide further description or elaboration of it, like this:

I was brought to see Philip Erto, the great engineer.
I was brought to see the great engineer, Philip Erto.

In both examples above, the "parenthetical noun phrase" appears at the end of the sentence, and is paired with the direct object of "see." In this case, the noun phrase that acts as the direct object and the noun phrase that acts as the parenthetical elaboration are interchangeable - the order depends on the speaker's desired emphasis.

Notice also that the same meaning can be captured by a dependent adjective clause instead:

I was brought to see Philip Erto, who is a great engineer.
I was brought to see the great engineer whose name is Philip Erto.

So in the Text Interpreter, I can reduce both the parenthetical noun phrases and the dependent adjective clauses to the same output: they produce extra semantic relationships, such as "Philip Erto <is-a> engineer <has-quality> great." But the Parser is the first stage of the text processing chain, and must handle their grammatical differences. So I added new code to pick out parenthetical noun phrases and attempt to distinguish them from other nouns that follow previous nouns (it's complicated).

Three pie charts showing the percentage correct and incorrect for the three test sets: "Magic Schoolbus: Inside the Earth (53%/47%)," "Out of the Dark (54%/46%)," and "Log Hotel(81%/19%)."
Percentage correct and incorrect for the three test sets: "Magic Schoolbus: Inside the Earth": (53%/47%), "Out of the Dark": (54%/46%), and "Log Hotel: (81%/19%).

After adding this feature, I spent some time on cleanup and a few more ambiguity resolution abilities. (See the November 2024 Diary for previous examples of this type of thing.) All in all, I was able to move every sentence in the Out of the Dark and Magic Schoolbus: Inside the Earth test sets into the "Parseable" category! (All sentences in Log Hotel were already parseable as of January 2024.) This just means that I can construct a data structure that represents the ideal parsed version of the sentence, and it's something the Parser is theoretically capable of generating. I still have a long way to go on getting the Parser to produce correct outputs for all the sentences. (For more information on my benchmarking methods and some early results for comparison, refer to the June 2021 and February 2022 diaries.

I've also done new work on Episodic Memory, but I'll save discussion of that for next month.

Until the next cycle,
Jenny

Wednesday, September 10, 2025

Hydraulic Heaven?

Since getting my custom pump to work well earlier this year, I've been pushing ahead on hydraulic actuator designs. There isn't a lot of miniature hydraulic equipment available for hobbyists, at least not at a good price, so I'm trying to make my own. I've settled on inflatable bladders as a fruitful direction to investigate - they don't have the same friction and seal wear issues as cylinders (syringes especially), and they can be customized in all manner of ways. In parallel, I've been working on moving parts designed to contain the bladders and be actuated by them.

Bladder Geometry

In the hydraulic demo from last year, I showcased my very first working bladder, which was a simple "pillow" - two rectangles of plastic film, with a valve stem inserted through the center of one rectangle, sealed together at their four edges. The problem with a bladder like this is that you can't get much range of motion out of it. When filled with fluid, it bulges a little - maybe a centimeter or so, at the small scales where I'm working. That wasn't enough for everything I wanted to do. I needed bladders with more complex geometries that could expand further, while still collapsing flat when fully deflated.

First of all I bought a heat-sealer, so I could melt plastic films together the professional way. (My first bladders were sealed with a soldering iron. The thought of going back to that method gives me the horrors.) This greatly improved the ease of making "pillows." Then I started trying for three-dimensional pouches with accordion folds. Getting all the little pieces of plastic lined up in the heat-sealer before they were attached to each other was too difficult, so I hit on the idea of sewing them together before sealing the seams. I even bought some plastic thread so that it could melt and be incorporated into the seal.

Two bladders sewn together from sheet plastic to make a "wedge" shape. There are visible seams with stitching, and each bladder has an inlet valve on the broad top side.

In short, I gave it a good try, but it was such a struggle. Sewing the little bladders together was a lot of work, and I never got one that was leak-free. It was particularly hard to get good seals where three seams met at a corner; no matter how much I might practice and refine the process, trying to make that on the heat-sealer was just plain awkward. Given how little success I had making wedge-shaped bladders with just one fold, I shuddered to think about my dreams of piston drivers with five or more. Manufacturing the bladders this way simply wasn't realistic.

Five plastic rectangles sealed together in their centers but not sealed at the edges yet, laid out on a table. The "Thriftbooks" logo side of the plastic is up. A two-pillow bladder with a tube attached to its inlet valve, fully inflated with water. The visible plastic is silver in color.

So I found a better way. You can make accordion folds by sealing the sides of two pillows together at the center, cutting a tiny hole in the middle of the seal, and then sealing the edges of both pillows. This avoids a lot of fiddly cutting and sewing, and more importantly, there are zero three-seam corners. All the seals are two-dimensional even if the bladder as a whole is not!

Photo of a bladder being made, showing creation of the center join on a heat sealer (model PFS-200).Photo of a heat gun being aimed at some plastic. All but a small circular region is protected with aluminum foil and a stack of large washers.
Methods of creating central seals 

I made my first center seals by folding the plastic around a strip of cardboard and putting it in the end of the heat-sealer, once on each side. This was non-ideal; it created a very small sealed area, the crease where the film bent around the cardboard got melted too much and could develop holes, etc. A better method is to shield all but the circular region you want to want to seal together, then blast that area with a heat gun. You might think I should be using an insulator (like cardboard) for the shielding, but from my experience so far, metallic objects that will soak up the heat actually work better! So you can fuse your two pillows in the middle, then snip the very center of the sealed area with scissors to allow fluid through.

Bladder Materials

Throughout the process of figuring this out, I had lots of general quality problems. I seemed to need a double seal at each edge (seal once, fold the edge over, seal again) to have decent chances of a working bladder, and they still sometimes leaked. Well ... I think the printed layer on one side of my film was interfering with a good seal. You may recall that I was using plastic cut from salvaged Thriftbooks poly mailers. I started noticing that the green side with the company logos didn't seal as well. In fact, when I'm doing center seals with the heat gun, those must be made silver side to silver side; the printed sides simply won't fuse (though I can get them to fuse, somewhat poorly, on the heat sealer). And then the pillow edges have to be sealed green side to green side, which doesn't work so well! I also lost at least one bladder because a tiny flaw or strain in the plastic popped open the first time I put it under pressure. These flaws are present because the plastic has already been wrapped around a book and beaten up in transport.

So I finally bit the bullet and got some pristine plastic films to try out. When you buy materials, you have more control over what you're getting, so I sampled two different thicknesses: a 2 mil painter's dropcloth (transparent) and a 4 mil plant bed cover (black). Neither has any coating or printing on it, and they both heat-seal wonderfully. Now I can get good edge seals on the first try, without folding the edge over and doubling the seal.

Bladder Inlets

The last element I need to talk about is the attachment of the valve stems. After some early experiments with silicone gel that didn't have much success, I used cyanoacrylate (Super Glue) for my first working bladders. Eventually I also tried a polyurethane sealer intended for use on nylon tents and such. The brand I got is Gear Aid Seam Grip+WP. The cyanoacrylate works okay, but in my tests (sample size = 3 each), the polyurethane proved more likely to make a good seal. It is necessary to respect its long cure time; I actually consider that a positive, since I cannot seem to use Super Glue without getting it on my fingers and possibly other things nearby. One thing I have NOT tried yet is two-part epoxy.

The hinge joint described in the text, fully extended with a fully inflated two-pillow bladder inside. A syringe is attached to the bladder via a tube that emerges through a hole in the joint's backshell.

So, okay, the glues are tolerable. But for real quality and durability, I would love to melt the valve stem and the plastic film together. So far all my attempts to heat-seal this part have been unsuccessful; they are two different materials and don't want to adhere. The option that remains is some sort of chemical weld. But it's hard to find anything that is safe and available for in-home use that will dissolve HDPE/LDPE film. I tried acetone on the off chance that it might work. It did smooth the surface of my PLA valve stems, but it never seemed to get them to a tacky or gooey state, and it did absolutely nothing to the films. So this may be a non-starter, unless I hear tell of a magical solvent that can do it.

Hydraulic Actuators

So how can we use all these bladders, exactly? After pondering how I might get one of them to operate my existing quadruped joint designs, I decided it would make more sense to come up with a new joint that was optimized to hold a bladder. Meet my hydraulic spade joint. A wedge-shaped bladder fits into one side of the backshell and pushes the spade upward (or forward, depending on the joint's orientation) when inflated. There are attachment holes for a tension element to return the spade to its original position when the bladder is depressurized. The spade's edge is constrained to remain in contact with the center of the backshell by a string tied through a hole in the spade and the backshell.

The cylinder taken apart, showing three pieces (the cylinder shell, the rod with its pressure-plate base, and the cap), and the fluid bladder installed inside the bottom of the shell. The bladder outside the cylinder, attached to the syringe, and partially inflated, showing all five pleats

The other actuator I tried out was this simple cylinder. To produce its relatively large linear motion, I made a bladder with five accordion folds, my most ambitious one to date. I hadn't worked out the quality problems yet at that time, so this bladder leaked in multiple places ... but if I inflated it quickly enough, I could still practice driving the cylinder. So it worked as a proof-of-concept.

Conclusion

I think I have all the components I need now: the pump, the valves, and the actuators are working well enough that it's about time to see how things play in an integrated system. I might be ready to start the process of designing and budgeting full projects that use these parts. Look out for more of my hydraulics work next year (if not sooner).

Until the next cycle,
Jenny