I have a Keeley Compressor Plus guitar pedal, which has a design problem that it is OTA based, thus non-linear system, and creates very annoying audible intermodulation. I wonder if it could be modified to remove the intermodulation from the sound?
Asking AI it answers this about the problem:
The Culprit: The LM13700 OTA Stage (IC1A) – Specifically Nonlinear Transconductance + Possible Control-Current Ripple
Your calculation is textbook-perfect: the phantom is a classic third-order intermodulation product (2f₂ - f₁). This only appears in nonlinear systems. Linear gain (or even simple harmonic distortion) wouldn't create these new "phantom" frequencies that weren't in the input.
In the Keeley Compressor Plus:
- The core compressor is built around the **LM13700 dual OTA** (IC1A section). Signal goes through the input buffer (Q3 MMBT6429 emitter follower), AC-couples via C11 1 µF, then hits the OTA differential inputs.
- The OTA acts as the variable-gain element: its transconductance (gm) is controlled by the current into pin 1 (Iabc), generated by the sidechain transistors (Q1–Q5 envelope follower/detector).
- OTAs are inherently nonlinear. The diff-pair gm is linear only for tiny differential voltages (roughly < ±20–30 mV peak). Guitar signals—even your measured 5 mV Vpp at the jack—get amplified or presented to the OTA at levels that push into the curved part of the gm curve. Two tones = multiplicative mixing = sum/difference products. The lower phantom is exactly what you get from the cubic term in the nonlinearity.
- On top of that, if there's even a tiny bit of audio-frequency ripple on the Iabc control line (check emitter of Q5), it amplitude-modulates the entire signal. Two input tones × modulation = sidebands = more IMD. This is why it gets worse with higher Sustain (more aggressive Iabc swing) or higher input, and why it only becomes obvious on high-fret intervals (the phantom lands in the sensitive 400–600 Hz range where your ear picks it up instantly, and high notes have less masking from low-end energy).
Here is the schematics and photos of the panels:
Keeley Compressor
Anyone any idea?
[i]AI: Could you provide a link to the Keeley Compressor Plus schematic you’re referencing, or upload a clear image of the relevant OTA section?
https://aionfx.com/news/tracing-journal-keeley-compressor-plus/
AI: What’s your experience level with pedal modifications and electronics—are you comfortable with tasks like SMT soldering and circuit debugging?
I am if the process is described to me in detail, without that not.[/i]
Asking AI it answers this about the problem:
The Culprit: The LM13700 OTA Stage (IC1A) – Specifically Nonlinear Transconductance + Possible Control-Current Ripple
Your calculation is textbook-perfect: the phantom is a classic third-order intermodulation product (2f₂ - f₁). This only appears in nonlinear systems. Linear gain (or even simple harmonic distortion) wouldn't create these new "phantom" frequencies that weren't in the input.
In the Keeley Compressor Plus:
- The core compressor is built around the **LM13700 dual OTA** (IC1A section). Signal goes through the input buffer (Q3 MMBT6429 emitter follower), AC-couples via C11 1 µF, then hits the OTA differential inputs.
- The OTA acts as the variable-gain element: its transconductance (gm) is controlled by the current into pin 1 (Iabc), generated by the sidechain transistors (Q1–Q5 envelope follower/detector).
- OTAs are inherently nonlinear. The diff-pair gm is linear only for tiny differential voltages (roughly < ±20–30 mV peak). Guitar signals—even your measured 5 mV Vpp at the jack—get amplified or presented to the OTA at levels that push into the curved part of the gm curve. Two tones = multiplicative mixing = sum/difference products. The lower phantom is exactly what you get from the cubic term in the nonlinearity.
- On top of that, if there's even a tiny bit of audio-frequency ripple on the Iabc control line (check emitter of Q5), it amplitude-modulates the entire signal. Two input tones × modulation = sidebands = more IMD. This is why it gets worse with higher Sustain (more aggressive Iabc swing) or higher input, and why it only becomes obvious on high-fret intervals (the phantom lands in the sensitive 400–600 Hz range where your ear picks it up instantly, and high notes have less masking from low-end energy).
Here is the schematics and photos of the panels:
Keeley Compressor
Anyone any idea?
[i]AI: Could you provide a link to the Keeley Compressor Plus schematic you’re referencing, or upload a clear image of the relevant OTA section?
https://aionfx.com/news/tracing-journal-keeley-compressor-plus/
AI: What’s your experience level with pedal modifications and electronics—are you comfortable with tasks like SMT soldering and circuit debugging?
I am if the process is described to me in detail, without that not.[/i]
