Infusion Pump Battery Alarming with Neural Capacity Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing infusion pumps rely on inaccurate battery gas gauge ICs for estimating remaining battery voltage or capacity, leading to incorrect battery alarms and potential interruptions in infusion therapy.
Innovation Solution
Implement a neural network-based system that monitors battery parameters in real-time, generating alarms based on actual remaining battery voltage or capacity using a trained neural network to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If battery gas gauge IC is used to estimate remaining battery voltage or capacity, then battery status monitoring is provided, but measurement accuracy deteriorates due to unknown factors affecting battery performance
Solution Approach 1:
The patent introduces a neural network as an intermediary component between the battery gas gauge IC and the alarm system. The neural network processes multiple battery parameters (voltage, current, temperature, gas gauge readings) and learns to predict actual battery capacity, thereby improving measurement accuracy while maintaining system manageability through a modular architecture.
Solution Approach 2:
The patent replaces the traditional mechanical/electrical battery monitoring approach (relying solely on gas gauge IC) with an intelligent system using neural networks. This substitution enables the system to account for complex battery behaviors and unknown factors that traditional methods cannot capture, significantly improving measurement precision.
2Reliability
If battery alarms are generated based on gas gauge IC readings, then power management is provided, but reliability deteriorates due to incorrect alarm timing causing therapy interruptions
Solution Approach 1:
The patent implements a feedback mechanism where the neural network continuously monitors battery parameters and adjusts alarm thresholds based on learned patterns. The system uses historical data and real-time measurements to predict actual battery capacity, providing feedback that corrects for gas gauge IC inaccuracies and prevents false alarms, thereby ensuring therapy continuity.
Solution Approach 2:
The patent performs preliminary action by training the neural network offline with extensive battery data before deployment. This pre-training enables the system to anticipate battery behavior patterns and accurately predict capacity depletion, allowing alarms to be generated at appropriate times without causing unnecessary therapy interruptions.
3Reliability
If battery power margins are added to compensate for inaccurate readings, then safety is improved, but productivity deteriorates due to reduced usable battery time
Solution Approach 1:
The patent changes the parameters used for battery monitoring from simple gas gauge IC readings to a multi-parameter approach including voltage, current, temperature, and gas gauge readings processed through a neural network. This parameter transformation enables accurate battery status detection without requiring conservative power margins, maximizing the usable time of the infusion pump while maintaining safety.
Data Source
AI summary
A system and method are disclosed for detecting remaining battery voltage or capacity in an infusion device and generating alarms based on the detection. A battery lifetime extension method includes providing an infusion device that derives its power from a rechargeable battery. The infusion device may derive its power from a rechargeable battery. Furthermore, the infusion device receives, at predetermined intervals of time in real-time sensor data comprising a voltage, a change in the voltage over the predetermined interval of time, an average current, a temperature, and a remaining voltage or capacity reported by a battery gas gauge integrated circuit (“IC”) associated with the rechargeable battery. A customized neural network model utilizes the sensor data to determine an indicia of the actual remaining voltage or capacity of the rechargeable battery in real-time. The indicia may be used to lengthen and/or abate ongoing medical infusion therapy.