US-20260126198-A1 - AIR CONDITIONER CAPACITOR EFFICACY LOSS DETECTION

US20260126198A1US 20260126198 A1US20260126198 A1US 20260126198A1US-20260126198-A1

Abstract

The startup time of a fan, compressor, or other hardware component inside an air conditioning condenser unit is monitored to determine whether startup of that component is taking longer than usual. Present principles recognize that this may be indicative of imminent or eventual failure of the condenser unit’s capacitor, and therefore the apparatus monitoring startup time may provide a notification to the user to replace the capacitor in advance of complete capacitor failure if the apparatus determines that startup is taking longer than usual. The apparatus may be a control module on the condenser unit, a smart thermostat, or even a smartphone in communication with the thermostat and/or condenser unit. In some specific instances, the apparatus may even use machine learning models and/or artificial neural networks to detect capacitor failure based on hardware component startup time.

Inventors

Russell Speight VanBlon

Assignees

East Coast IP, LLC

Dates

Publication Date: 20260507
Application Date: 20241107

Claims (20)

1 . An apparatus, comprising: a processor system; and storage accessible to the processor system and comprising instructions executable by the processor system to: identify a fan startup time for an air conditioner system; determine, based on the fan startup time, that a capacitor of the air conditioner system is losing efficacy; and based on the determination, present a graphical user interface (GUI) at a device, the GUI comprising a notification indicating that the capacitor is losing efficacy.
2 . The apparatus of claim 1 , wherein the device is a thermostat.
3 . The apparatus of claim 2 , comprising the thermostat.
4 . The apparatus of claim 3 , comprising the air conditioner system.
5 . The apparatus of claim 1 , wherein fan startup time relates to time for a fan of the air conditioning system to reach a target rotations per minute.
6 . The apparatus of claim 1 , wherein the fan startup time is a current fan startup time, and wherein the instructions are executable to: access a metric for average past fan startup times; and make the determination based on the current fan startup time and the metric for average past fan startup times.
7 . The apparatus of claim 6 , wherein the instructions are executable to: store the past fan startup times; and based on the stored past fan startup times, determine the metric for the average past fan startup times.
8 . The apparatus of claim 1 , wherein the notification indicates that the capacitor is about to fail.
9 . The apparatus of claim 8 , wherein the GUI comprises a selector that is selectable to initiate a repair of the air conditioner system.
10 . A method, comprising: identifying a startup time of a hardware component of an air conditioner system; determining, based on the startup time, that a capacitor of the air conditioner system is losing efficacy; and based on the determination, presenting a graphical user interface (GUI) at a device, the GUI comprising a notification indicating that the capacitor is losing efficacy.
11 . The method of claim 10 , wherein the hardware component comprises a fan of the air conditioner system.
12 . The method of claim 10 , wherein the hardware component comprises a compressor of the air conditioner system.
13 . The method of claim 10 , wherein the startup time is a current startup time, and wherein the method comprises: executing a model to infer that the current startup time is inconsistent with previous startup times for the hardware component; and determining, based on the inference, that the capacitor is losing efficacy.
14 . The method of claim 13 , wherein the model comprises an artificial neural network.
15 . An apparatus, comprising: at least one computer readable storage medium (CRSM) that is not a transitory signal, the at least one CRSM comprising instructions executable by a processor system to: identify an operational metric for a component of an air conditioner system; determine, based on the operational metric, that a capacitor of the air conditioner system is going to fail; and based on the determination, present a notification indicating that the capacitor is going to fail.
16 . The apparatus of claim 15 , wherein the component comprises a fan of the air conditioner system.
17 . The apparatus of claim 15 , wherein the component comprises a compressor of the air conditioner system.
18 . The apparatus of claim 15 , wherein the instructions are executable to: input the operational metric to a model; and receive an output from the model, the output indicating that the capacitor of the air conditioner system is losing efficacy.
19 . The apparatus of claim 18 , wherein the operational metric relates to a current startup time, and wherein the instructions are executable to: input, to the model, the current startup time and one or more past startup times for the component; and execute the model to receive, based on the input of the current startup time and the one or more past startup times, the output.
20 . The apparatus of claim 19 , wherein the model is a machine learning (ML) model configured for pattern recognition.

Description

FIELD The disclosure below relates to technically inventive, non-routine solutions that are necessarily rooted in computer technology and that produce concrete technical improvements. In particular, the disclosure below relates to detection of impending air conditioner capacitor failure and remediation. BACKGROUND Air conditioner systems often include a capacitor that can fail. But when the capacitor fails, the air conditioner system is rendered inoperable until a replacement part is installed. This means that users are often left without air conditioning during critical times when they need air conditioning the most, like during heat waves or even just a normal hot summer day. No adequate solutions currently exist to remedy the foregoing technological problem. SUMMARY Accordingly, in one aspect an apparatus includes a processor system and storage accessible to the processor system. The storage includes instructions executable by the processor system to identify a fan startup time for an air conditioner system. The instructions are also executable to determine, based on the fan startup time, that a capacitor of the air conditioner system is losing efficacy. The instructions are then executable to, based on the determination, present a graphical user interface (GUI) at a device. The GUI includes a notification indicating that the capacitor is losing efficacy. In some example embodiments, the device may be a thermostat, and the apparatus may even include the thermostat. The apparatus may also include the air conditioner system if desired. In various example implementations, fan startup time may relate to time for a fan of the air conditioning system to reach a target rotations per minute (RPMs). Also in various example implementations, the fan startup time may be a current fan startup time, and the instructions may be executable to access a metric for average past fan startup times to then make the determination based on the current fan startup time and the metric for average past fan startup times. In some cases, the instructions may even be executable to store the past fan startup times and, based on the stored past fan startup times, determine the metric for the average past fan startup times. In some examples, the notification may indicate that the capacitor is about to fail. Additionally, if desired the GUI may include a selector that is selectable to initiate a repair of the air conditioner system (e.g., by ordering a part online, contacting a technician, and/or scheduling a repair). In another aspect, a method includes identifying a startup time of a hardware component of an air conditioner system and determining, based on the startup time, that a capacitor of the air conditioner system is losing efficacy. Based on the determination, the method includes presenting a graphical user interface (GUI) at a device, where the GUI includes a notification indicating that the capacitor is losing efficacy. In some examples, the hardware component may include a fan of the air conditioner system and/or a compressor of the air conditioner system. Also in some examples, the startup time may be a current startup time, and the method may include executing a model to infer that the current startup time is inconsistent with previous startup times for the hardware component. Here the method may then include determining, based on the inference, that the capacitor is losing efficacy. In certain non-limiting examples, the model may specifically include an artificial neural network. In still another aspect, an apparatus includes at least one computer readable storage medium (CRSM) that is not a transitory signal. The at least one CRSM includes instructions executable by a processor system to identify an operational metric of a component of an air conditioner system. The instructions are also executable to determine, based on the operational metric, that a capacitor of the air conditioner system is going to fail. The instructions are further executable to, based on the determination, present a notification indicating that the capacitor is going to fail. In various examples, the component may include a fan of the air conditioner system and/or a compressor of the air conditioner system. Additionally, in some cases the instructions may be executable to input the operational metric to a model, and to receive an output from the model. The output may indicate that the capacitor of the air conditioner system is losing efficacy. In some specific instances, the operational metric may be a current startup time, and the instructions may be executable to input, to the model, the current startup time and one or more past startup times for the component. The instructions may then be executable to execute the model to receive, based on the input of the current startup time and the one or more past startup times, the output. If desired, in non-limiting embodiments the model may be a machine learning (ML) model configured for pattern recogniti