Rechargeable battery protection bin of anastomat and intelligent monitoring system

Abstract

The invention relates to the technical field of anastomats, and discloses an anastomat rechargeable battery protection bin which comprises a shell box and an anastomat body, a shell cover is rotationally connected to the shell box, two battery packs are installed on the inner wall of the shell box, two nail bins are arranged on the inner wall of the shell box, and a shell display screen is arranged on the surface of one side of the shell box; a fingerprint recognition device is arranged on the surface of one side of the shell box, a charging port is formed in the side, away from the fingerprint recognition device, of the shell box, a power supply battery is installed on the inner wall of the shell box, and a circuit board used for control is further installed on the inner wall of the shell box. Especially, the economical efficiency is more prominent in a high-frequency use scene, the long-term use cost can be reduced, the battery waste amount is greatly reduced through the rechargeable design, the green medical treatment trend is met, the environment-friendly treatment pressure of medical institutions is reduced, medical waste is reduced, and the environment friendliness is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of staplers, and in particular to a rechargeable battery protection compartment and an intelligent monitoring system for a stapler. Background Art

[0002] A stapler is a medical device primarily used to replace traditional manual suturing. Resembling a stapler, it uses titanium or polymer staples to separate or staple tissues. It's easy to use and provides stable results. In surgery, staplers can be used to anastomose and close various tissues, including the gastrointestinal tract, blood vessels, and biliary tract. This reduces operative time and bleeding risk, and offers superior tissue healing after suturing. Common types include linear, circular, and cutting staplers, each suitable for different surgical scenarios, such as gastrointestinal reconstruction and tumor resection.

[0003] In the existing technology, the continuous operation of electric staplers is highly dependent on the stability and durability of their power supply, and most of them use disposable batteries as energy sources. This not only increases the cost of use, but also brings about environmental pollution and problems with waste battery disposal. Disposable batteries often cannot monitor the battery status in real time during use, and doctors cannot confirm whether the product meets the surgical requirements, which increases the risk of surgery and affects the progress of the surgery.

[0004] To this end, we propose a rechargeable battery protection compartment and intelligent monitoring system for the stapler. Summary of the Invention

[0005] (1) Technical problems solved

[0006] In response to the shortcomings of the existing technology, the present invention provides a rechargeable battery protection compartment and intelligent monitoring system for the anastomosis device, which solves the problem that the existing technology mostly uses disposable batteries as energy sources, which not only increases the cost of use, but also often cannot monitor the battery status in real time during use. The doctor cannot confirm whether the product meets the surgical requirements, which increases the risk of surgery and affects the progress of the surgery.

[0007] (2) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a rechargeable battery protection compartment for a stapler, comprising an outer shell box and a stapler body, an outer shell cover being rotatably connected to the outer shell box, two groups of battery packs being installed on the inner wall of the outer shell box, two groups of nail magazines being provided on the inner wall of the outer shell box, an outer shell display being provided on one side surface of the outer shell box, a fingerprint recognition device being provided on one side surface of the outer shell box, a charging port being provided on the side of the outer shell box away from the fingerprint recognition device, a power supply battery being installed on the inner wall of the outer shell box, a circuit board for control being also installed on the inner wall of the outer shell box, and a magnetic device for fixing the outer shell cover being provided on the inner wall of the outer shell cover.

[0009] An intelligent monitoring system for a stapler rechargeable battery, comprising a multi-dimensional constant detection module, a health status assessment algorithm module, and a real-time early warning and fault tolerance mechanism;

[0010] The multi-dimensional constant detection module dynamically monitors the electrochemical parameters, environmental parameters, and mechanical parameters of the battery pack. The electrochemical parameters include internal resistance, voltage, and capacity. The environmental parameters include temperature and humidity. The mechanical parameters include vibration and impact.

[0011] The health status assessment algorithm module: Through hybrid model fusion, integrating physical laws and data-driven methods, it can achieve accurate assessment of battery health status and life prediction, providing a scientific basis for decision-making;

[0012] Real-time warning and fault-tolerant mechanism: Through three-level warning, based on health assessment results, warning signals are triggered in stages, and hardware fault-tolerant design is used to maximize surgical safety and reduce operation interruptions caused by battery failure.

[0013] Preferably, the multi-dimensional constant detection module is the perception center of the battery health monitoring system. Through multi-sensor fusion technology, it captures the key physical quantities, electrochemical states and environmental parameters of the battery pack in real time, providing a high-precision data basis for health assessment and early warning.

[0014] Preferably, the multi-dimensional constant detection module includes an electrochemical parameter monitoring auxiliary module and an environmental adaptability monitoring auxiliary module, and the electrochemical parameter monitoring includes dynamic internal resistance analysis DRA and differential voltage curve dV / dQ;

[0015] Dynamic internal resistance analysis (DRA): Through high-frequency pulse current injection, the battery internal resistance change is measured in real time. Combined with the temperature compensation algorithm, the interference of ambient temperature on the measurement is eliminated. The accuracy is ±0.5mΩ. The temperature compensation algorithm is nonlinear. The battery internal resistance has a nonlinear relationship with temperature. The measured value needs to be corrected by the temperature sensor data. The method combines the Arrhenius correction model and piecewise linear compensation:

[0016] Arrhenius temperature correction model:

[0017]

[0018] Activation energy of battery materials, Boltzmann constant, Reference temperature, is the compensated internal resistance output by the Arrhenius model, The measured internal resistance value is Natural constants, bases of natural logarithms, The current absolute temperature of the battery;

[0019] Piecewise linear compensation addresses rapid temperature fluctuations, solves the Arrhenius model response lag problem, and enables instantaneous correction of internal resistance measurements in scenarios with drastic temperature changes.

[0020] Differential voltage curve dV / dQ: Monitors the differential change of voltage with respect to capacity during charge and discharge, accurately identifying battery aging patterns.

[0021] Preferably, the environmental adaptability monitoring module includes synchronous temperature and humidity acquisition and vibration and shock detection;

[0022] Synchronous temperature and humidity collection: Integrates high-precision temperature and humidity sensors to assess the impact of the operating room environment on battery performance.

[0023] Vibration and shock detection: MEMS accelerometers are used to monitor mechanical vibrations during stapler operation to prevent micro-short circuits in the battery's internal structure caused by shock.

[0024] Preferably, the hybrid model fusion includes a physical model, a machine learning model and an adaptive threshold adjustment;

[0025] The physical model calculates the battery SOC state of charge and SOH state of health based on the equivalent circuit model ECM+;

[0026] The machine learning model uses an LSTM long short-term memory network to analyze historical charge and discharge data and predict the remaining cycle life (RUL) with an error of ≤5%.

[0027] The adaptive threshold adjustment: dynamically adjusts the warning threshold according to the ambient temperature and humidity and the frequency of use to avoid false alarms.

[0028] Preferably, the equivalent circuit model ECM uses a second-order RC model to simulate the dynamic characteristics of the battery, and simulates the complex electrochemical kinetic process inside the battery through circuit elements, so as to describe the dynamic voltage response characteristics of the battery.

[0029] Preferably, LSTM is used in the machine learning model to predict the remaining cycle life RUL. LSTM analyzes historical charge and discharge data, which includes time series such as voltage, current, temperature, and capacity decay curves, to capture the long-term dependence and nonlinear degradation laws in the battery aging process, thereby achieving accurate prediction of the remaining cycle life.

[0030] Preferably, the three-level warning includes:

[0031] Level 1 warning: refers to a mild warning, SOH < 80% or internal resistance increases by 20%, prompting planned maintenance;

[0032] Level 2 warning: refers to a moderate warning, SOC < 20% or temperature > 45°C, triggering an audible and visual alarm and recommending suspension of use;

[0033] Level 3 warning: refers to a severe warning. If an internal short circuit or voltage drop >10% is detected, the output will be immediately cut off and the battery will be locked.

[0034] Preferably, the battery pack includes an upper shell, a lower shell, a cover plate, a battery display screen and a battery body, the battery body is arranged in the upper shell and the lower shell, the cover plate is arranged below the lower shell, and the battery display screen is arranged on the surface of the upper shell.

[0035] In summary, the technical effects and advantages of the present invention are as follows:

[0036] 1. In the present invention, the rechargeable battery pack significantly reduces the battery cost of a single operation through repeated use, especially in high-frequency usage scenarios. It is more economical and can reduce long-term use costs. The rechargeable design greatly reduces the amount of battery waste, which is in line with the trend of green medical care, reduces the environmental treatment pressure of medical institutions, reduces medical waste, and improves environmental protection.

[0037] 2. In the present invention, the rechargeable battery pack is equipped with a battery intelligent monitoring system. Through the multi-dimensional constant detection module, health status assessment algorithm and real-time warning and fault-tolerant mechanism, the system monitors the electrochemical, environmental and mechanical parameters in real time, adopts temperature compensation algorithm and differential voltage curve to analyze the aging mode, combines the synchronous acquisition of temperature and humidity with vibration detection, and comprehensively evaluates the battery status. The hybrid model integrates physical laws and LSTM machine learning, with RUL prediction error ≤5%, accurately calculates SOC and SOH, and dynamically adjusts the warning threshold to avoid false alarms. The three-level warning system has a hierarchical response, can analyze the battery life, prompt replacement or maintenance, and avoid the risk of power outage during surgery.

[0038] 3. In the present invention, the device information (model, number of times used, responsible person) can be bound to achieve precise management of "one device, one warehouse". BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a schematic diagram of the overall structure of a rechargeable battery protection compartment of a stapler according to the present invention;

[0040] Figure 2 This is a schematic cross-sectional view of a rechargeable battery protection compartment of a stapler according to the present invention;

[0041] Figure 3 This is a schematic structural diagram of a rechargeable battery protection compartment of a stapler during operation according to the present invention;

[0042] Figure 4 This is a schematic diagram of the battery pack structure of a rechargeable battery protection compartment of a stapler according to the present invention;

[0043] Figure 5 The present invention is a rechargeable battery protection chamber for an anastomosis device Figure 4Schematic diagram of the cross-sectional structure at AA in the middle;

[0044] Figure 6 This is a schematic structural diagram of a battery pack of a rechargeable battery protection compartment of a stapler according to the present invention from another perspective;

[0045] Figure 7 This is a schematic diagram of an intelligent monitoring system for a rechargeable battery of a stapler according to the present invention.

[0046] In the figure: 1. Outer shell cover; 2. Magnetic device; 3. Fingerprint recognition device; 4. Outer shell box; 5. Outer shell display screen; 6. Nail magazine; 7. Battery pack; 71. Battery display screen; 72. Upper outer shell; 73. Cover plate; 74. Lower outer shell; 75. Battery body; 8. Charging port; 9. Circuit board; 10. Battery; 11. Stapler body. DETAILED DESCRIPTION

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0048] The present invention specifically relates to a rechargeable battery protection compartment for a stapler, comprising an outer shell box 4 and a stapler body 11, wherein an outer shell cover 1 is rotatably connected to the outer shell box 4, two groups of battery packs 7 are installed on the inner wall of the outer shell box 4, two groups of nail magazines 6 are provided on the inner wall of the outer shell box 4, an outer shell display 5 is provided on one side surface of the outer shell box 4, a fingerprint recognition device 3 is provided on one side surface of the outer shell box 4, a charging port 8 is provided on the side of the outer shell box 4 away from the fingerprint recognition device 3, a power supply battery 10 is installed on the inner wall of the outer shell box 4, a circuit board 9 for control is also installed on the inner wall of the outer shell box 4, a magnetic device 2 for fixing the outer shell cover 1 is provided on the inner wall of the outer shell cover 1, the battery pack 7 comprises an upper outer shell 72, a lower outer shell 74, a cover plate 73, a battery display screen 71 and a battery body 75, the battery body 75 is arranged in the upper outer shell 72 and the lower outer shell 74, the cover plate 73 is arranged below the lower outer shell 74, and the battery display screen 71 is arranged on the surface of the upper outer shell 72.

[0049] Working principle: When in use, it is used as an accessory of the electric stapler. In order to analyze the battery life, it prompts replacement or maintenance to avoid the risk of power outage during surgery; it binds the instrument information model, number of uses, and responsible person to achieve precise management of "one machine and one warehouse". When in use, the fingerprint needs to be entered in the fingerprint recognition device 3. The magnetic device 2 receives the instruction of the circuit board 9 and cuts off the power. The outer shell cover 1 can be opened, and the power level of the battery pack 7 as well as the model, number of uses, responsible person, etc. can be observed through the outer shell display 5. The nail magazine 6 and battery pack 7 are taken out from the outer shell box 4 and installed on the stapler body. The battery status can be observed through the battery display 71 on the battery pack 7. After use, the nail magazine 6 is a disposable product and can be treated as medical waste. The battery pack 7 is placed in the outer shell box 4 and charged by the built-in power supply battery 10. If the power supply battery 10 is insufficient, the battery pack 7 and the power supply battery 10 can be charged through the charging port 8.

[0050] The present invention specifically provides an intelligent monitoring system for rechargeable batteries used in staplers, which ensures the safe and reliable operation of batteries during surgery through multi-dimensional parameter detection, accurate health status assessment, and a multi-level early warning mechanism.

[0051] Multi-dimensional constant detection module: Dynamically monitors the electrochemical parameters, environmental parameters, and mechanical parameters of the battery pack. Electrochemical parameters include internal resistance, voltage, and capacity; environmental parameters include temperature and humidity; and mechanical parameters include vibration and impact. The multi-dimensional constant detection module is the sensing center of the battery health monitoring system. Through multi-sensor fusion technology, it captures the key physical quantities, electrochemical states, and environmental parameters of the battery pack in real time, providing a high-precision data foundation for health assessment and early warning. The multi-dimensional constant detection module includes an electrochemical parameter monitoring subsidiary module and an environmental adaptability monitoring subsidiary module. Electrochemical parameter monitoring includes dynamic internal resistance analysis (DRA) and differential voltage curve (dV / dQ).

[0052] Dynamic internal resistance analysis (DRA): Through high-frequency pulse current injection, the battery internal resistance change is measured in real time. Combined with the temperature compensation algorithm, the interference of ambient temperature on the measurement is eliminated. The accuracy is ±0.5mΩ. The temperature compensation algorithm is nonlinear. The battery internal resistance has a nonlinear relationship with temperature. The measured value needs to be corrected by the temperature sensor data. The method combines the Arrhenius correction model and piecewise linear compensation:

[0053] Arrhenius temperature correction model:

[0054]

[0055] Activation energy of battery materials, Boltzmann constant, Reference temperature, is the compensated internal resistance output by the Arrhenius model, The measured internal resistance value is Natural constants, bases of natural logarithms, The current absolute temperature of the battery;

[0056] Piecewise linear compensation addresses rapid temperature fluctuations, solves the Arrhenius model response lag problem, and enables instantaneous correction of internal resistance measurements in scenarios with drastic temperature changes.

[0057]

[0058] Temperature coefficient, The final internal resistance value after compensation, The internal resistance value after compensation obtained by Arrhenius calculation is: The current instantaneous measured temperature of the battery, Reference temperature;

[0059] Differential voltage curve dV / dQ: monitors the differential change of voltage to capacity during charge and discharge, accurately identifying battery aging patterns;

[0060] The environmental adaptability monitoring module includes synchronous temperature and humidity collection and vibration and shock detection;

[0061] Synchronous temperature and humidity acquisition: Integrates high-precision temperature and humidity sensors to assess the impact of the operating room environment on battery performance;

[0062] Vibration and shock detection: MEMS accelerometers are used to monitor mechanical vibrations during stapler operation to prevent micro-short circuits in the battery's internal structure caused by shock.

[0063] Among them, the health status assessment algorithm module: Through hybrid model fusion, integrating physical laws and data-driven methods, it can achieve accurate assessment of battery health status and life prediction, providing a scientific basis for decision-making. The hybrid model fusion includes physical models, machine learning models and adaptive threshold adjustment;

[0064] Physical model: The battery's SOC (state of charge) and SOH (state of health) are calculated based on the equivalent circuit model (ECM+). The ECM uses a second-order RC model to simulate the battery's dynamic characteristics. It simulates the complex electrochemical kinetics inside the battery through circuit elements to describe the battery's dynamic voltage response characteristics.

[0065] Its circuit structure is as follows:

[0066] Ohmic internal resistance : Characterizes the instantaneous voltage drop of the battery;

[0067] Polarization resistance 、 With polarized capacitance 、 : Describes the short-term and long-term polarization effects of the battery, Battery terminal voltage, Open circuit voltage, a function of SOC, Working current, and is the polarization voltage of the RC link;

[0068] Circuit equation:

[0069]

[0070] in, , ;

[0071] SOC estimation, extended Kalman filter, EKF

[0072] Equation of state:

[0073]

[0074] in is the Coulomb efficiency, is the nominal capacity of the battery, and The state of charge at the moment, No. The current at the moment, Time step.

[0075] Observation equation:

[0076]

[0077] in, No. The terminal voltage at the moment, 、 No. Polarization voltage at the moment.

[0078] EKF steps:

[0079] Prediction: Update the SOC prior estimate based on current integration;

[0080] Correction: SOC is calibrated by voltage observation and Kalman gain is calculated;

[0081] SOH estimation parameter identification and capacity fading model

[0082] Online parameter identification: real-time update using recursive least squares (RLS) , , , , ;

[0083] SOH Definition:

[0084] ;

[0085] in, The current maximum available capacity, Nominal capacity;

[0086] Machine learning model: LSTM long short-term memory network is used to analyze historical charge and discharge data to predict the remaining cycle life (RUL) with an error of ≤5%. LSTM is used in the machine learning model to predict the remaining cycle life (RUL). LSTM analyzes historical charge and discharge data, which includes time series such as voltage, current, temperature, and capacity decay curves. It captures the long-term dependence and nonlinear degradation laws of the battery aging process to achieve accurate prediction of the remaining cycle life.

[0087] Input features and data preprocessing

[0088] Input features:

[0089] ECM parameters , , ;

[0090] Charge and discharge cycle data capacity attenuation rate, average temperature, and depth of discharge;

[0091] Environmental data: temperature and humidity.

[0092] Preprocessing:

[0093] Normalization: scale the data to the interval [-1, 1];

[0094] Sliding window: takes 10 consecutive cycles as the time step input.

[0095] LSTM network architecture

[0096] Input layer: 10 time steps × 7 features, , , , capacity, temperature, humidity, depth of discharge);

[0097] Hidden layer: 2 layers of LSTM, 64 neurons per layer;

[0098] Output layer: fully connected layer, output RUL.

[0099] Training and validation

[0100] Loss function: mean square error MSE;

[0101] Optimizer: Adam;

[0102] Verification indicators: mean absolute error MAE ≤ 5%;

[0103] Dataset: NASA battery aging dataset + self-built stapler battery data;

[0104] Adaptive threshold adjustment: Dynamically adjust the warning threshold according to the ambient temperature, humidity and frequency of use to avoid false alarms, SOC lower limit adjustment:

[0105]

[0106] in, Temperature compensation coefficient, The minimum SOC threshold after dynamic adjustment, Basic minimum SOC threshold, Current ambient temperature, Reference temperature;

[0107] Among them, the real-time warning and fault-tolerant mechanism: through a three-level warning, based on the health assessment results, the warning signal is triggered in stages, and the hardware fault-tolerant design maximizes surgical safety and reduces operation interruptions caused by battery failure. The three-level warning includes:

[0108] Level 1 warning: refers to a mild warning, SOH < 80% or internal resistance increases by 20%, prompting planned maintenance;

[0109] Level 2 warning: refers to a moderate warning, SOC < 20% or temperature > 45°C, triggering an audible and visual alarm and recommending suspension of use;

[0110] Level 3 warning: refers to a severe warning. If an internal short circuit or voltage drop >10% is detected, the output will be immediately cut off and the battery will be locked.

[0111] Example 1

[0112] This embodiment provides a rechargeable battery protection compartment for a stapler and an intelligent monitoring system for an electrochemical parameter precision detection system. Specific implementation details include:

[0113] Implementation purpose: To achieve high-precision measurement of dynamic internal resistance in the full temperature range and identification of charge and discharge aging characteristics, and to solve the problem of interference of sudden temperature changes on internal resistance measurement.

[0114] hardware:

[0115] The battery pack integrates a 24-bit ADC voltage sensor (ADS1256, accuracy of ±0.05% FS), a closed-loop Hall current sensor (CSM050, accuracy of ±0.2% FS), and a 4-wire Kelvin internal resistance measurement circuit (contact resistance <0.1mΩ), and communicates with the STM32H743 main control chip via the CAN bus (baud rate 1Mbps).

[0116] software:

[0117] The Arrhenius model and piecewise linear compensation algorithm are run in real time, and the compensated internal resistance is output every 200ms (resolution 0.1mΩ). The dV / dQ curve calculation cycle is 1 second, and an aging code is marked in case of abnormality (0x01: SEI film growth; 0x02: active material decay).

[0118] Implementation effect: In the temperature range of -10℃~50℃ and the temperature rise rate of 15℃ / s, the internal resistance measurement error is ≤0.5mΩ, and the aging pattern recognition accuracy is ≥95%.

[0119] Example 2

[0120] This embodiment provides a rechargeable battery protection compartment for a stapler and an intelligent monitoring system for an environmental adaptability monitoring system. Specific implementation details include:

[0121] Implementation purpose: To evaluate the impact of the operating room environment on battery performance in real time and prevent battery failure caused by abnormal temperature and humidity and mechanical vibration.

[0122] Temperature and humidity module:

[0123] The SHT30 sensor is connected to the MCU via an I2C interface (rate 400kHz) to establish a temperature and humidity joint control model. When the external humidity is detected to be greater than 85%RH, the heating element is activated until the internal humidity stabilizes at 55%RH±5%.

[0124] Vibration module:

[0125] The MPU-6050 accelerometer uses DMA to transfer data (reducing CPU load), calculates vibration RMS values ​​and shock peak values ​​in real time, records abnormal events at a frequency of 100Hz, and stores them in 2MB Flash (capable of recording ≥10,000 events).

[0126] Implementation effect: In high temperature and high humidity scenarios, the internal humidity of the battery is controlled below 60% RH, the vibration and shock missed detection rate is less than 3%, and the incidence of mechanical damage-related failures is reduced by 70%.

[0127] Example 3

[0128] This embodiment provides a rechargeable battery protection compartment for a stapler and an intelligent monitoring system for a hybrid model health assessment system. Specific implementation details include:

[0129] Implementation purpose: By integrating physical models with machine learning, high-precision SOC estimation and accurate RUL prediction can be achieved, solving the problem of large prediction errors caused by a single model.

[0130] Physical Model:

[0131] The EKF algorithm based on the second-order RC model runs on an STM32 chip (main frequency 400MHz), the SOC estimation update frequency is 10Hz, and the error is calibrated through a constant current discharge test once a week (calibration current 0.5C).

[0132] LSTM model:

[0133] The preprocessed data (normalized to [-1, 1]) is transmitted to the host computer (Python environment, TensorFlow framework) via USB2.0 for training. A single training session takes ≤30 minutes. The model parameters are downloaded to the MCU via UART, and the RUL is predicted every 10 charge and discharge cycles (about 2 hours).

[0134] Implementation effect: SOC estimation error ≤ 1.5% (typical value), RUL prediction error ≤ 4%, and prediction accuracy improved by 30% compared with the single EKF model.

[0135] Example 4

[0136] This embodiment provides a rechargeable battery protection compartment for a stapler and an intelligent monitoring system for a three-level warning and fault-tolerance system. Specific implementation details include:

[0137] Implementation purpose: To establish a hierarchical fault response mechanism, ensure surgical safety through hardware redundancy design, and avoid operation interruptions caused by battery failure.

[0138] Early warning logic:

[0139] The main control chip (STM32H7) analyzes and evaluates module data in real time. A level one warning is sent to the nurse station terminal via UART (9600bps). A level two warning drives the onboard LED (red, 200cd brightness) and buzzer. A level three warning triggers a hardware interrupt to immediately cut off power.

[0140] Fault-tolerant design:

[0141] The dual-channel ADC sampling circuit uses 0.1% precision voltage divider resistors (TC ≤ 50ppm / °C), and the supercapacitor is connected to the battery through an anti-reverse diode (voltage drop ≤ 0.3V) to ensure that the system power consumption is ≤ 10mA after power failure.

[0142] Implementation effect: The response time of the three-level warning is ≤200ms. The redundant design makes the sensor failure misjudgment rate less than 0.1%. The warning state is maintained for 12 seconds after power failure (meeting the emergency processing time requirements for surgery).

[0143] Comparative Example 1

[0144] This comparative example provides a monitoring system for traditional missing piecewise linear compensation, and the specific implementation includes:

[0145] System Configuration:

[0146] The same hardware architecture and Arrhenius temperature correction model as in Example 1 are used, but the piecewise linear compensation module is not implemented (ie, the temperature compensation relies solely on the Arrhenius model).

[0147] Performance drawbacks:

[0148] Temperature sudden change response hysteresis:

[0149] In a rapid temperature rise scenario (e.g., from 25°C to 40°C, ΔT / Δt=10°C / s), the Arrhenius model takes 8 seconds to reach steady state. During this period, the internal resistance measurement error reaches 3mΩ (the error in Example 1 during the same period is ≤0.8mΩ), resulting in a SOH assessment deviation of >5% (the standard requires ≤3%).

[0150] Warning of misjudgment risk:

[0151] Under temperature fluctuations (ΔT = 5°C, duration 2 minutes) caused by the start and stop of the operating room air conditioner, the system frequently triggered the first-level warning due to internal resistance fluctuations, and the false alarm rate increased by 30% compared with the embodiment (actually measured 2-3 false alarms per hour).

[0152] Lifespan prediction bias:

[0153] Due to untimely temperature correction, the noise of the LSTM model input data increased (root mean square error RMSE=0.08), and the RUL prediction error rose to 8%, exceeding the patent requirement of ≤5%, resulting in a battery replacement plan error of ≥15 cycles.

[0154] Engineering breakthrough in temperature compensation algorithm: By synergizing the Arrhenius model with piecewise linear compensation, an internal resistance measurement accuracy of ±0.5mΩ in dynamic temperature scenarios was achieved for the first time in medical device battery monitoring. This solves the evaluation bias problem caused by the response lag of traditional models and provides a reliable basis for battery status judgment in precision surgery.

[0155] Cross-domain fusion innovation of hybrid models: Combining the physical interpretability of electrochemical equivalent circuit models with the data-driven advantages of LSTM neural networks, high-precision predictions of SOC ≤ 2% and RUL ≤ 4.5% are achieved in embedded systems, achieving performance improvements of over 40% compared to traditional single models, meeting the need for accurate prediction of battery life in surgical planning.

[0156] The safety design of the three-level fault-tolerant system: Multi-layer protection from sensor redundancy (dual ADC) to hardware disconnection (solid-state relay + electromagnetic lock) ensures that the system's response speed in extreme faults such as short circuit and overheating meets the medical equipment safety standard (≤200ms). Combined with supercapacitor backup technology, it ensures that warning information is not lost after power failure, reducing the risk of battery-related surgery by more than 90%.

[0157] Compared with Examples 1-4 and Comparative Example 1, Example 1: Through the dual mechanisms of Arrhenius model + piecewise linear compensation, the problems of temperature nonlinearity and drastic response hysteresis are solved, and the internal resistance measurement accuracy of ±0.5mΩ in the full temperature range (0-50°C) is achieved. In combination with the differential voltage curve (dV / dQ), the aging mode (SEI film growth, active material decay) is recognized with an accuracy rate of more than 95%.

[0158] Comparative Example: Relying solely on the Arrhenius model without piecewise linear compensation results in internal resistance errors of up to 3mΩ (six times that of Example 1) in scenarios with rapid temperature fluctuations (e.g., a 10°C / s temperature rise), SOH assessment deviations exceeding 5%, and a 30% increase in false alarm rates due to temperature fluctuations. Core difference: Piecewise linear compensation technology fills the gap in instantaneous correction in dynamic temperature scenarios, avoiding the response lag inherent in a single model.

[0159] Example 2: Integrating temperature and humidity control (SHT30 sensor + moisture-proof heating plate, humidity control ≤60%RH) and vibration and shock detection (MPU-6050 accelerometer, missed detection rate <3%) to proactively address the high temperature (>35°C), high humidity (>80%RH) and high-frequency vibration environment in the operating room, reducing the incidence of mechanical damage-related failures by 70%.

[0160] Comparative Example: Without an environmental parameter monitoring module, potential threats to the battery from abnormal temperature and humidity, as well as mechanical vibration, cannot be identified. Battery performance degradation due to environmental factors accelerates, and there is no early warning mechanism. Core Differentiation: The environmental adaptability design of multi-sensor fusion upgrades "passive monitoring" to "active protection," significantly improving system robustness.

[0161] Example 3: A hybrid architecture of a second-order RC physical model (SOC estimation) + LSTM neural network (RUL prediction) + adaptive threshold is used. The SOC estimation error is ≤2%, the RUL prediction error is ≤4.5% (RMSE = 4.2%), and the warning threshold is dynamically adjusted through a three-dimensional mapping table (for example, a 5% advance warning in high-temperature and high-frequency scenarios), reducing the false alarm rate to 7.5%.

[0162] Comparative Example: Using only a single physical model without machine learning prediction and adaptive adjustment resulted in an 8% RUL prediction error (exceeding the patent requirement by 60%), and was unable to adapt to environmental changes, resulting in a lifespan prediction deviation of 15 cycles or more. Core Differentiation: Cross-domain model fusion overcomes the accuracy bottleneck of traditional single models, and LSTM effectively captures the long-term nonlinear degradation patterns of battery aging.

[0163] Example 4: Build a three-level hierarchical warning system (level 1 maintenance reminder, level 2 audible and visual alarm + forced cooling, level 3 hardware disconnection + electromagnetic lock), with a response time of ≤ 200ms (level 3 warning only 100ms), equipped with dual-channel ADC redundant sampling (false positive rate < 0.1%) and supercapacitor backup (power failure warning lasts 12 seconds), meeting medical device safety standards (IEC60601-1-2).

[0164] Comparative Example: Only a simple first-level warning, no hardware fault tolerance design, fault response time ≥ 1s, and the warning function immediately fails after power failure, which cannot guarantee emergency fault handling during surgery. Core difference: From "single warning" to "multi-layer protection", through hardware redundancy and rapid response mechanism, the risk of battery-related surgery is reduced by more than 90%.

[0165] Through the closed-loop design of "multi-dimensional detection-precise evaluation-graded fault tolerance", the embodiment has achieved four core technological breakthroughs in temperature compensation, model fusion, environmental adaptation, and safety redundancy in anastomosis battery monitoring for the first time, solving the pain points of traditional systems of "inaccurate measurement, unclear judgment, and inability to prevent".

[0166] Key indicators (such as internal resistance accuracy of ±0.5mΩ and RUL error ≤4.5%) meet the special standards for medical equipment. The three-level warning mechanism and hardware fault-tolerant design meet the "zero tolerance for failure" requirements during surgery, providing a replicable technical paradigm for battery safety of precision instruments.

[0167] Each embodiment provides specific hardware selection (STM32H7 / ADS1256), algorithm parameters (LSTM network structure / Kalman filter configuration), and measured data (error rate / response time), forming a technical solution that can be directly applied to product development, significantly reducing R&D costs and cycles.

[0168] The electrical components mentioned in this article are all connected to an external main controller and 220V mains electricity, and the main controller can be a conventional known device that performs control such as a computer.

[0169] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A rechargeable battery protection compartment for a stapler, comprising an outer shell (4) and a stapler body (11), characterized in that: The outer shell box (4) is rotatably connected to an outer shell cover (1), the inner wall of the outer shell box (4) is installed with two groups of battery packs (7), the inner wall of the outer shell box (4) is provided with two groups of nail magazines (6), a side surface of the outer shell box (4) is provided with an outer shell display screen (5), a side surface of the outer shell box (4) is provided with a fingerprint recognition device (3), a side of the outer shell box (4) away from the fingerprint recognition device (3) is provided with a charging port (8), a power supply battery (10) is installed on the inner wall of the outer shell box (4), a circuit board (9) for control is also installed on the inner wall of the outer shell box (4), and a magnetic attraction device (2) for fixing the outer shell cover (1) is provided on the inner wall of the outer shell cover (1).

2. An intelligent monitoring system for a stapler rechargeable battery, characterized by: Including multi-dimensional constant detection module, health status assessment algorithm module and real-time warning and fault tolerance mechanism; The multi-dimensional constant detection module dynamically monitors the electrochemical parameters, environmental parameters, and mechanical parameters of the battery pack. The electrochemical parameters include internal resistance, voltage, and capacity. The environmental parameters include temperature and humidity. The mechanical parameters include vibration and impact. The health status assessment algorithm module: Through hybrid model fusion, integrating physical laws and data-driven methods, it can achieve accurate assessment of battery health status and life prediction, providing a scientific basis for decision-making; Real-time warning and fault-tolerant mechanism: Through three-level warning, based on health assessment results, warning signals are triggered in stages, and hardware fault-tolerant design is used to maximize surgical safety and reduce operation interruptions caused by battery failure.

3. The intelligent monitoring system for a rechargeable battery of a stapler according to claim 2, characterized in that: The multi-dimensional constant detection module is the perception center of the battery health monitoring system. Through multi-sensor fusion technology, it captures the key physical quantities, electrochemical states and environmental parameters of the battery pack in real time, providing a high-precision data basis for health assessment and early warning.

4. The intelligent monitoring system for a rechargeable battery of a stapler according to claim 2, characterized in that: The multi-dimensional constant detection module includes an electrochemical parameter monitoring auxiliary module and an environmental adaptability monitoring auxiliary module. The electrochemical parameter monitoring includes dynamic internal resistance analysis DRA and differential voltage curve dV / dQ; Dynamic internal resistance analysis (DRA): Through high-frequency pulse current injection, the battery internal resistance change is measured in real time. Combined with the temperature compensation algorithm, the interference of ambient temperature on the measurement is eliminated. The accuracy is ±0.5mΩ. The temperature compensation algorithm is nonlinear. The battery internal resistance has a nonlinear relationship with temperature. The measured value needs to be corrected by the temperature sensor data. The method combines the Arrhenius correction model and piecewise linear compensation: Arrhenius temperature correction model: Activation energy of battery materials, Boltzmann constant, Reference temperature, is the compensated internal resistance output by the Arrhenius model, The measured internal resistance value is Natural constants, bases of natural logarithms, The current absolute temperature of the battery; Piecewise linear compensation addresses rapid temperature fluctuations, solves the Arrhenius model response lag problem, and enables instantaneous correction of internal resistance measurements in scenarios with drastic temperature changes. Differential voltage curve dV / dQ: Monitors the differential change of voltage with respect to capacity during charge and discharge, accurately identifying battery aging patterns.

5. The intelligent monitoring system for a rechargeable battery of a stapler according to claim 2, characterized in that: The environmental adaptability monitoring module includes synchronous temperature and humidity acquisition and vibration and shock detection; Synchronous temperature and humidity acquisition: Integrates high-precision temperature and humidity sensors to assess the impact of the operating room environment on battery performance; Vibration and shock detection: MEMS accelerometers are used to monitor mechanical vibrations during stapler operation to prevent micro-short circuits in the battery's internal structure caused by shock.

6. The intelligent monitoring system for a rechargeable battery of a stapler according to claim 2, characterized in that: The hybrid model fusion includes a physical model, a machine learning model and an adaptive threshold adjustment; The physical model calculates the battery SOC state of charge and SOH state of health based on the equivalent circuit model ECM+; The machine learning model uses an LSTM long short-term memory network to analyze historical charge and discharge data and predict the remaining cycle life (RUL) with an error of ≤5%. The adaptive threshold adjustment: dynamically adjusts the warning threshold according to the ambient temperature and humidity and the frequency of use to avoid false alarms.

7. The intelligent monitoring system for a rechargeable battery of a stapler according to claim 6, characterized in that: The equivalent circuit model (ECM) uses a second-order RC model to simulate the dynamic characteristics of the battery, and simulates the complex electrochemical kinetic process inside the battery through circuit elements, so as to describe the dynamic voltage response characteristics of the battery.

8. The intelligent monitoring system for rechargeable batteries of a stapler according to claim 6, characterized in that: The machine learning model uses LSTM to predict the remaining cycle life (RUL). LSTM analyzes historical charge and discharge data, which includes time series such as voltage, current, temperature, and capacity decay curves, to capture the long-term dependence and nonlinear degradation laws during battery aging, thereby achieving accurate prediction of the remaining cycle life.

9. The intelligent monitoring system for a rechargeable battery of a stapler according to claim 2, characterized in that: The three-level warning includes: Level 1 warning: refers to a mild warning, SOH < 80% or internal resistance increases by 20%, prompting planned maintenance; Level 2 warning: refers to a moderate warning, SOC < 20% or temperature > 45°C, triggering an audible and visual alarm and recommending suspension of use; Level 3 warning: refers to a severe warning. If an internal short circuit or voltage drop >10% is detected, the output will be immediately cut off and the battery will be locked.

10. The rechargeable battery protection compartment for a stapler according to claim 1, characterized in that: The battery pack (7) comprises an upper shell (72), a lower shell (74), a cover plate (73), a battery display screen (71) and a battery body (75); the battery body (75) is arranged inside the upper shell (72) and the lower shell (74); the cover plate (73) is arranged below the lower shell (74); and the battery display screen (71) is arranged on the surface of the upper shell (72).

Images