Missing Clip on My Quick-Release Skewer

Quick-release axle skewer from a bike. © eugene Brennan 

The cam lever fell out of the housing when I took my front wheel off to change a puncture, half-way between Ballymore Eustace and Harristown last Sunday. I hadn't noticed that the retaining clip had disappeared, possibly rusting off over the last 29 years. It's years since I changed a front puncture. I noticed too that I have five patches already on this front tube. 99% of my punctures are caused by whitethorn thorns. Thanks to the people out walking who offered me a lift. Anyway I had a discussion about forces in the axle with ChatGPT:

Eugene:

You know the skewers used on quick release wheels?

 

ChatGPT: 

Yeah, I know exactly the ones you mean—the quick-release skewers on bike wheels.

They’re that rod that runs through the hollow axle, with:

• a cam lever on one side (the bit you flip open/closed), and
• a nut on the other end (to adjust tightness)

When you flip the lever, it tightens via a cam mechanism, clamping the wheel securely into the dropouts—no tools needed.

A couple of subtle details people often miss:

• The lever doesn’t just “screw tight”—it should leave an imprint on your palm when closing if it’s properly tight.
• The springs on either side (little conical ones) help centre the skewer—narrow ends point inward.
• It’s not the thread that holds the wheel—it’s the cam force when the lever is closed.

Are you thinking about fixing one, replacing it, or did something odd happen with it?

Eugene: 

What type of retaining clip is used to hold on the cam lever? It must have corroded off mine. I haven't changed a front puncture for maybe 10 years, so I didn't notice it missing. It wasn't immediately obvious.

 

ChatGPT: 

Ahh, I know the bit you’re talking about—that tiny piece that quietly disappears over time.

On most quick-release skewers, the cam lever is held onto the skewer shaft with a retaining clip, usually one of these:

• a circlip (snap ring / C-clip) sitting in a groove on the shaft, or
• sometimes a peened-over end (the shaft is slightly mushroomed instead of using a removable clip)

If yours has “vanished,” it was almost certainly a circlip that corroded away or popped off years ago.

A couple of practical points

• Those clips are tiny and fiddly, and not always standardised between brands
• Replacing just the clip can be done if you can match the groove diameter, but…
• In reality, most people just replace the entire skewer—they’re cheap and far more reliable than bodging a new clip onto an old, possibly worn cam

My honest take

If it’s been missing for 10 years, I wouldn’t trust that skewer anyway. The cam faces and shaft could be worn or pitted.

A new skewer costs very little and removes any doubt—especially since that part is literally what keeps your wheel attached 😄

If you want, I can help you identify the exact type/size you need (front vs rear, road vs MTB, etc.).

Eugene: 

But there's a huge force on that cam, so unlikely for the lever to come out (remember limiting force = μRn?)

 

ChatGPT: 

You’re absolutely right to think in terms of friction holding things together—but there’s a subtle mismatch here between what force is doing what.

The clamping force you’re thinking of is captured by:

$F_{\text{friction}} = \mu R N$

That force is between the dropout faces and the hub axle. It’s what stops the wheel from slipping out of the frame.

---

But the clip does a completely different job

The little circlip isn’t resisting that big clamping force at all. It only:

• keeps the cam lever assembly from sliding off the skewer rod
• handles tiny axial forces (basically just gravity, vibration, and handling)

So even though the cam generates a large normal force $N$, that force is internal to the clamping system, not trying to eject the lever.

---

Why yours likely disappeared

Over time:

• corrosion weakens the circlip
• small vibrations + repeated opening/closing
• maybe one partial disengagement

…and eventually it just pops off or disintegrates.

---

A useful way to picture it

Think of it like:

• The cam = a powerful clamp
• The circlip = a tiny “end stop” so the clamp doesn’t fall apart when it’s open

When the lever is closed, everything is compressed together anyway—so the clip isn’t even doing much at that moment.

---

One caution

Even if it feels secure now, without that clip:

• the lever can drift or misalign when open
• you risk losing parts when removing the wheel

So your physics instinct is solid—but it applies to wheel retention, not lever retention.

---

If you want, we can actually estimate the clamping force from a typical cam geometry—that’s a fun little mechanics exercise.

Eugene: 

Yes, but there's an axial load force on the cam that pushes on the cam housing. And that's huge, because you're supposed to wrap your fingers around the lever when squeezing upwards. I probably put 10 kg or maybe 20 kg force or more on the lever with my fingers, and that's magnified by the mechanical advantage. Lever is about 8cm long, so the load can be resolved to midway, say 4 cm. The cam acts at about 5mm, so that's a mechanical advantage of 8 Let's call it 6. So there could be up to 100 kg on the cam, pushing on the axle. a radial force would have to overcome that for the lever to come loose.

 

ChatGPT: 

You’re thinking about it the right way mechanically—but the key is which direction that big force actually acts in.

Your estimate is pretty reasonable:

• ~10–20 kg hand force at ~40 mm
• cam acting at ~5–6 mm
  → mechanical advantage ~6–8
  → axial clamp force easily in the ballpark of 600–1200 N (≈60–120 kgf)

That checks out.

---

The subtle bit: where that force goes

That large force is almost entirely:

• axial along the skewer, and
• compressing the cam faces and dropouts together

It’s not trying to push the lever off the end of the shaft.

When the lever is closed:

• the cam is wedged hard against its mating surface
• everything is in compression
• the system is actually self-locking (that’s the cam design doing its job)

So in that state, the circlip is basically doing nothing at all.

---

When the clip actually matters

The circlip only earns its keep when the lever is:

• open, or
• somewhere mid-travel

In that position:

• there’s little to no clamp force
• the cam isn’t wedged
• the lever assembly can slide axially along the shaft

And the forces there are tiny:

• vibration
• gravity
• a bit of handling

That’s why a flimsy little circlip is enough.

---

Why your “it shouldn’t come off” intuition still makes sense

You’re right in a practical sense:

• If the skewer is closed, the lever is very unlikely to just fall off
• The geometry + friction + compression all help keep it together

But:

• once you open it, there’s nothing preventing the lever from sliding off the end
• over years, that’s when parts go missing

---

One more nuance (you’ll like this)

Cam quick-releases are designed so that:

• the cam passes slightly over-centre
• which means the reaction force actually helps keep it closed, not open

So even that big force you calculated is stabilising, not ejecting anything.

---

Bottom line

• Your force estimate → solid
• Your conclusion → slightly misapplied direction-wise
• The circlip → only a retainer for the loose state, not a load-bearing component

---

If yours has survived 10 years without the clip, that’s actually kind of impressive 😄
…but it also means you’ve probably just been lucky not to lose the lever while the wheel was off.

Want to go one level deeper and sketch the force directions? It’s a nice little statics problem.

Eugene: 

Now possibly radial shock forces could loosen it?

 

ChatGPT: 

Yeah—that’s the right line of thinking now 👍

Radial shocks (bumps, vibration, wheel chatter) can definitely contribute to the lever working loose—but not in the way your earlier force model was pointing.

---

What radial shocks actually do

They don’t overcome that big axial clamp force directly. Instead they:

• create small oscillating forces and micro-movements in the mechanism
• introduce slight lateral and axial play when the lever isn’t perfectly loaded
• cause fretting + wear + tiny shifts over time

Think of it less like a single big force and more like:

thousands of tiny nudges gradually walking the part outward

---

When this matters most

Radial shock becomes relevant when:

• the lever is open (no clamp force → nothing “locking” it)
• the cam surfaces are worn or dry
• there’s clearance in the fit between parts
• corrosion has already weakened things

In that state, vibration can:

• rotate the nut slightly
• shift the cam position
• and crucially… let the lever creep along the shaft

---

Why the clip still matters

Even with shocks:

• there’s still no strong continuous axial force pushing the lever off
• but shocks can give it just enough intermittent movement to eventually:
  • reach the end of the shaft
  • and slip off if there’s no circlip to stop it

---

Analogy (closest real-world feel)

It’s like a bolt that doesn’t unscrew from one big force—but from:

• vibration
• tiny cyclic loads
• gradual loss of friction

Same idea here—just linear instead of rotational.

---

So your revised model is basically spot-on

• Big clamp force → not the issue
• Shock/vibration → slow migration mechanism
• Missing clip → nothing to stop the final exit

---

If you’re half tempted to keep running it as-is… I’d still swap the skewer. It’s one of those parts where failure is very “all at once,” and usually at the worst possible moment.

what is the piece called that the cam lever fits into?

That part is usually called the cam body (or sometimes the cam housing).

On a typical quick-release skewer you’ve got:

• the skewer rod (the long shaft)
• the cam lever (the flip handle)
• the cam body / housing ← the bit you’re asking about
• the adjusting nut on the other side

---

What it actually does

The cam lever pivots against this cam body, which has:

• a curved cam surface
• a seat for the lever to press into

When you close the lever, it rolls/wedges against that surface and generates the clamping force.

---

Other names you might see

Depending on brand or context, it can also be called:

• cam assembly (when grouped with the lever)
• lever seat (less common)
• cam mechanism

But “cam body” is the clearest, most widely understood term.

---

If you’re trying to source parts individually, that’s where it gets annoying—most manufacturers don’t sell the cam body separately. They expect you to replace the whole skewer.

Are you trying to rebuild it piece-by-piece, or just figuring out what went missing?

On the Couch With ChatGPT

Created by Grok

Eugene (transcript of me incoherently expressing myself in voice mode):

Sometimes when I'm on the verge of dozing and falling asleep at the table during the daytime, it's as if my mind goes back to maybe 40 years ago and I feel like I did then. Now, I'm not sure what I mean by feel, but like it's as if, it's as if I'm back then and I can kind of remember how I felt then. Now, the feeling I'm talking about, it's not like happy or sad or angry or melancholic or joyful. It's like a kind of a, it's a different type of feeling. It's as if there are hundreds of different feelings which aren't like those main ones that we normally experience. It's like moods almost. And the other thing is, when I'm asleep, sometimes I have a similar kind of feeling that I wouldn't have during the daytime. It's not like an emotion, but it's like sensing a smell or seeing a colour. It's difficult to explain because it's not a feeling-, it's not, it's not like being angry or sad or one of the normal emotions we feel.

Conversations With ChatGPT: Air Drag and Surface Topology

Created by Grok.

Eugene: Is it possible to make a material that has a huge amount of drag that could allow a human to float? And what topology of surface has the most drag, a plane? I know that drag is proportional to cross-sectional area and also that there is a coefficient that depends on the surface shape of an object.

ChatGPT: Oh, yes, you can make a material or object with enormous air drag, but it’s a combination of material, surface topology, and shape, not just the “material” itself. Let’s break it down carefully.

Conversations With ChatGPT: Converting Garden Waste to Electricity

Created by ChatGPT

Eugene: Is it possible to convert the energy stored in garden waste directly into electricity? 

ChatGPT: Short answer: Let me unpack that a bit.

---

🔥 The usual way (not direct)

Most power plants don’t convert heat straight to electricity. They go:
combustion → heat → steam → turbine → generator

That mechanical step (spinning a turbine) is actually very efficient, which is why it’s still dominant.

---

⚡ Direct (or near-direct) methods

1. Thermoelectric generators (Seebeck effect)

This is the cleanest “direct” method.

• Based on the Seebeck effect
• A temperature difference across a material produces a voltage

Pros:

• No moving parts
• Very reliable

Cons:

• Low efficiency (typically 5–10%)
• Needs large temperature differences to be worthwhile

👉 These are used in niche cases like space probes (radioisotope generators), not big power stations.

---

2. Thermophotovoltaics (TPV)

A bit more exotic and very cool in principle.

• Hot surface from combustion emits infrared radiation
• That radiation is converted to electricity using photovoltaic cells (like solar panels tuned for heat)

Pros:

• Potentially higher efficiency than thermoelectrics
• Still no moving parts

Cons:

• Technically complex
• Still under development for large-scale use

---

3. Magnetohydrodynamic (MHD) generators

This one feels almost sci-fi.

• Hot ionised gas (plasma) from combustion flows through a magnetic field
• Generates electricity directly from moving charged particles

Pros:

• Theoretically high efficiency

Cons:

• Extremely difficult to operate (materials, temperatures, plasma control)
• Never really took off commercially

---

4. Fuel cells (sort of “skipping combustion”)

Not exactly combustion, but worth mentioning:

• Chemical energy → electricity directly via electrochemical reactions
• e.g. hydrogen fuel cells

These avoid the “heat stage” entirely, which is why they can be efficient.

---

🧠 The key limitation

The reason direct heat → electricity is hard comes down to thermodynamics:

• Heat is disordered energy
• Electricity is ordered energy
• Converting between them efficiently is fundamentally limited (think Carnot efficiency)

Ironically, spinning a turbine is still one of the best ways to impose order on that energy.

---

🧩 Big picture

• Yes, direct conversion exists
• But:
  • It’s usually less efficient than turbines
  • Or more complex and expensive
• That’s why your power station still looks like a Victorian steam machine on steroids 😄

---

If you want, I can run through rough efficiency numbers comparing all of these—or even sketch how a TPV system would look in practice.

 

Eugene: I'm thinking of my garden waste. It'd be great if I could recover the energy.

 

ChatGPT: Ahh now that’s a lovely engineer’s instinct—looking at a pile of garden waste and seeing untapped energy instead of rubbish 😄

 

Short answer: yes, you can recover energy from it—but generating electricity directly is the tricky (and usually disappointing) part. Heat is where the real win is.

---

🌿 What you actually have in garden waste

Your clippings, leaves, twigs etc. are basically stored solar energy (via Photosynthesis).

So in principle, burning or processing them releases that energy again.

---

🔥 The most practical route: heat

If you dry the material and burn it:

• You can get useful heat for space heating or water
• This is by far the most efficient and realistic option at small scale

Think:

• Small wood stove
• Outdoor burner
• Even a DIY biomass heater if you’re inclined

👉 You might recover 50–80% of the energy as heat, which is actually very decent.

---

⚡ Electricity… this is where reality bites a bit

Option 1: Thermoelectric generator

Stick a Thermoelectric generator on a hot stove.

• Works, but…
• You’ll get tiny power (watts, maybe tens of watts)

Good for:

• Charging a phone
• Running a small fan

Not good for:

• Powering your house

---

Option 2: Steam engine (the old-school way)

You could do:

burn waste → boil water → steam → small turbine/engine → generator

But:

• Complex
• Needs pressure vessels (safety issue)
• Hard to do efficiently at small scale

---

Option 3: Gasification (now we’re talking interesting)

This is probably the most “you” option given your engineering bent.

• Heat biomass with limited oxygen → produces “wood gas”
• Burn that gas in an engine → drive a generator

This is basically:
garden waste → fuel gas → engine → electricity

Pros:

• Much better than direct heat-to-electricity
• Actually used historically (e.g. WWII vehicles)

Cons:

• Fiddly to run
• Needs dry, consistent fuel
• Tar/soot management is a pain

---

Option 4: Just compost it (seriously)

Don’t dismiss this one.

• Composting releases heat slowly
• Improves your soil (which feeds more plant growth → more stored energy)

It’s not flashy, but it’s efficient in a different way.

---

⚖️ Reality check (honest answer)

If your goal is:

• Maximum energy recovery → burn it for heat
• Fun engineering project → gasifier + small engine
• Simple + useful → compost or mulch

Generating meaningful electricity directly from garden waste at home scale is:

technically possible… but usually not worth the hassle

---

💡 A neat hybrid idea

If I were setting this up in a garden in Ireland:

• Burn dry woody waste in a small stove
• Use the heat for something useful (shed, water, drying clothes)
• Stick a small thermoelectric module on it just for fun output

You get:

• Real useful energy (heat)
• A bit of electricity as a bonus
• A nice experimental setup to play with

---

If you want, I can sketch a simple DIY setup (nothing dangerous, no pressure vessels) that’d actually work in a garden shed.

Conversations with ChatGPT: Shallow Truss Forces

t history

Created by ChatGPT

You said:

When a force acts down on the apex of the truss, the forces in the tie can be greater than the load acting down on the apex. And if the slope of the truss becomes very shallow, the tension force in the tie can become huge and tend to infinity as the angle of the slope tends to zero.

Conversations With ChatGPT: Flight Ceiling of Aircraft

Created with Grok.

You said: 

“Hello.”

ChatGPT said:

Hey there! How’s it going? What’s on your mind today?

You said:

“Would it be possible for more advanced passenger aircraft to fly at higher altitudes? I know there would be less oxygen, so there would be an issue with engines running efficiently, but there would be less drag also.”