阅读说明：本技术 基于智能温度感知的超声刀血管自适应剪切方法及系统 (Ultrasonic knife blood vessel self-adaptive shearing method and system based on intelligent temperature sensing ) 是由 姚龙洋 王福源 刘振中 丁飞 骆威 于 2021-08-30 设计创作，主要内容包括：本发明揭示了一种基于智能温度感知进行血管密闭及切开的超声软组织切割止血手术方法和系统。该系统包括发生器、换能器和超声刀头,发生器在工作时实时收集手术器械的反馈参数,然后通过温度分布函数模型根据这些反馈参数和器械特征参数预估手术部位的实时温度,发生器根据第一自适应能量控制算法来控制血管手术部位的温度位于第一温度范围来完成血管密闭过程,然后根据第二自适应能量控制算法来控制血管的温度位于第二温度范围来完成血管干燥凝固和切开过程,精准可靠。(The invention discloses an ultrasonic soft tissue cutting hemostasis operation method and system for vessel sealing and cutting based on intelligent temperature sensing. The system comprises a generator, a transducer and an ultrasonic cutter head, wherein the generator collects feedback parameters of surgical instruments in real time when in work, then predicts the real-time temperature of a surgical part according to the feedback parameters and instrument characteristic parameters through a temperature distribution function model, controls the temperature of the vascular surgical part to be in a first temperature range according to a first adaptive energy control algorithm to complete a vascular sealing process, and controls the temperature of a blood vessel to be in a second temperature range according to a second adaptive energy control algorithm to complete a blood vessel drying, solidifying and cutting process, so that the system is accurate and reliable.)

1. An ultrasonic knife blood vessel self-adaptive shearing method based on intelligent temperature sensing is characterized by comprising the following steps,

s1, pre-estimating the real-time temperature T of the ultrasonic cutter bar according to the temperature distribution function model_est；

S2, judging the real-time temperature T_estThe temperature range in which the catalyst is used;

and S3, adjusting the power level applied to the ultrasonic blade transducer according to the judgment result to control the current output of the ultrasonic blade, thereby controlling the temperature change rate.

2. The method of claim 1, wherein the temperature distribution function model is a neural network algorithm model, and comprises one or more algorithm model combinations of a feedforward neural network, a memory neural network and an attention neural network, and the model training method is one or more combinations of supervised learning, semi-supervised learning, unsupervised learning and reinforcement learning.

3. The method as claimed in claim 2, wherein the model training method is specifically to extract input features from a training set, input the features into the neural network algorithm model to calculate a mean value and a gradient value of each neuron, the loss function of the model may be mean square error MSE or mean absolute error MAE, update weights by using a gradient descent method, repeat the above processes until the model reaches a predetermined stopping condition, stop training and save the model after the stopping condition is reached.

4. The method of claim 3, wherein the temperature distribution function model is composed of layers and corresponding neurons and weights, the weight parameters and applications are stored in a generator memory, the memory is Flash, EEPROM or other non-volatile storage device, the applications are run in a processor, the processor is either an ARM, DSP, FPGA, CPU, GPU or ASIC chip present in the generator, or a remote server connected through a network.

5. The method according to claim 1, wherein the step S1 of estimating the real-time temperature of the ultrasonic tool bar according to the temperature distribution function model specifically includes inputting characteristic parameters to the temperature distribution function model, wherein the characteristic parameters include one or more combinations of working feedback parameters, physical structure characteristic parameters, and environmental parameters.

6. The method according to claim 5, wherein the working feedback parameters comprise one or more parameters of real-time voltage U, real-time current I, power P, impedance R, real-time resonant frequency f, and real-time voltage current phase difference θ; the physical structure characteristic parameters comprise one or more parameters of ultrasonic knife bar materials and knife bar lengths; the environmental parameters comprise one or more of environmental temperature and environmental humidity.

7. The method according to claim 1, wherein the step S2 of determining the temperature range of the real-time temperature specifically comprises,

presetting three temperature thresholds, namely a first temperature threshold T from low to high₁A second temperature threshold T₂A third temperature threshold T₃；

A preset temperature range lower than the first temperature threshold T₁Is a first temperature range, the first temperature threshold value T₁And a second temperature threshold T₂With a second temperature range, said second temperature threshold T₂And a third temperature threshold T₃A third temperature range therebetween;

determining a real-time temperature T_estIn the temperature range.

8. The method according to claim 7, wherein in step S3, when the real-time temperature T is determined to be obtained_estAt the first temperatureIn the temperature range, the power level of the ultrasonic knife energy converter is adaptively adjusted in the first current value output range, so that the ultrasonic knife bar reaches a second temperature threshold value T on the basis of keeping the first temperature change rate₂(ii) a When the real-time temperature T is obtained through judgment_estWhen the temperature is in the second temperature range, the power level of the ultrasonic knife energy converter is adaptively adjusted in the second current value output range, so that the ultrasonic knife bar reaches a third temperature threshold value T on the basis of keeping the second temperature change rate₃(ii) a When the real-time temperature T is obtained through judgment_estAnd when the temperature is in the third temperature range, the power level of the ultrasonic knife energy converter is adaptively adjusted in the third current value output range, so that the ultrasonic knife keeps the third temperature change rate for the time t 1.

9. The method of claim 8, wherein the first current value, the second current value, and the third current value are a fixed value or a range of values; the first current output value is greater than the second current output value, and the second current output value is greater than the third current output value.

10. The method of claim 9, wherein the first, second, and third temperature change rates are each within 0-50 ℃/s, and the first temperature change rate is at a maximum.

11. The method of claim 10, wherein the ultrasound blade bar is heated up by no more than 200 ℃ while maintaining a third temperature change rate, the third temperature range corresponding to an optimum closing temperature range of the blood vessel.

12. The method of claim 11, wherein after the ultrasonic blade bar is warmed for a period of time t1 based on maintaining the third rate of temperature change, the power level applied to the ultrasonic blade transducer is adjusted to control the current output of the ultrasonic blade such that the ultrasonic blade bar is warmed and maintained within the fourth temperature range based on maintaining the fourth rate of temperature change.

13. The method of claim 12, wherein the fourth temperature range does not exceed 300 ℃, the fourth temperature range corresponding to a vessel drying and cutting temperature range.

14. An ultrasonic knife blood vessel self-adaptive shearing system based on intelligent temperature perception is characterized by comprising

A real-time temperature pre-estimating unit for pre-estimating the real-time temperature T of the ultrasonic cutter bar according to the temperature distribution function model_est；

A processing unit for judging the real-time temperature T_estThe temperature range in which the catalyst is used;

and the adjusting unit is used for adjusting the power level applied to the ultrasonic knife energy converter according to the judgment result so as to control the current output of the ultrasonic knife and further control the temperature change rate.

15. A generator for ultrasonic knife blood vessel self-adaptive shear control based on intelligent temperature perception is characterized by comprising

A control circuit coupled to a memory, the control circuit configured to be capable of:

predicting real-time temperature T of ultrasonic cutter bar according to temperature distribution function model_est；

Judging the real-time temperature T_estThe temperature range in which the catalyst is used;

and according to the judgment result, adjusting the power level applied to the ultrasonic knife transducer to control the current output of the ultrasonic knife so as to control the temperature change rate.

16. An ultrasonic scalpel surgical instrument based on intelligent temperature sensing and ultrasonic scalpel blood vessel adaptive shear control is characterized by comprising

An ultrasonic electromechanical system comprising an ultrasonic transducer coupled to an ultrasonic blade via an ultrasonic waveguide; and

a generator configured to supply power to the ultrasound transducer, wherein the generator comprises a control circuit configured to be capable of:

predicting real-time temperature T of ultrasonic cutter bar according to temperature distribution function model_est；

Judging the real-time temperature T_estThe temperature range in which the catalyst is used;

and according to the judgment result, adjusting the power level applied to the ultrasonic knife transducer to control the current output of the ultrasonic knife so as to control the temperature change rate.

Technical Field

The invention relates to the field of medical instruments, in particular to a control method and a control system of an ultrasonic scalpel, and particularly relates to an ultrasonic scalpel blood vessel self-adaptive shearing method and system based on intelligent temperature sensing, a generator with the system and an ultrasonic scalpel surgical instrument.

Background

An ultrasonic surgical system for cutting and hemostasis of soft tissue (called ultrasonic knife system for short) is an instrument which further amplifies ultrasonic vibration obtained by a piezoelectric converter (electric energy is transmitted to the piezoelectric converter through an energy generator and is converted into mechanical energy by the piezoelectric converter), and uses the amplified ultrasonic vibration for cutting and coagulating the soft tissue by an ultrasonic knife rod. Clinical use of such devices allows for focal resection with lower temperatures and less bleeding, and ensures minimal lateral thermal tissue damage. With the popularization of minimally invasive surgery, an ultrasonic surgical knife has become a conventional surgical instrument.

The ultrasonic blade system is mainly composed of a generator, a transducer and an ultrasonic blade bar, as shown in fig. 1, the transducer 11 of the ultrasonic blade is coupled with an ultrasonic blade housing 12, a sleeve 13 is located at the distal end of the ultrasonic blade housing 12, an ultrasonic blade bar 14 located at the most distal end is coupled with the transducer 11 inside the sleeve 13, and the transducer 11 is connected with the generator (not shown) through a cable 15. The current of ultrasonic frequency in the generator is conducted to the transducer, the transducer converts the electric energy into mechanical energy of back and forth vibration, the transmission and amplification of the ultrasonic cutter rod enable the tail end (also called an ultrasonic cutter head) of the ultrasonic cutter rod to vibrate at a certain frequency (such as 55.6kHz), the heat generated by friction causes the water in tissue cells contacted with the cutter tip to be vaporized, the protein hydrogen bonds are broken, the cells are disintegrated and fused again, and the tissue is cut after being solidified.

When the blood vessel is closed, the knife tip is contacted with tissue protein, heat is generated through mechanical vibration, collagen in the tissue is denatured, the upper and lower blood vessel walls are fused together under the action of the pressure of the knife tip and the jaw, and the blood vessel is dried and solidified at high temperature to form a firm closed area so as to achieve the purpose of hemostasis. Generally speaking, the blood vessel cutting process can be divided into two stages of blood vessel closing and cutting by controlling a proper temperature range, the blood vessel is controlled to output a relatively low power level to be in the proper temperature range to ensure that the blood vessel can be better fused and not cut, research shows that the best fusion effect can be achieved when the temperature of the blood vessel is 110-180 ℃, and then the output power level is increased to control the blood vessel to be at a high temperature of more than 200 ℃ to achieve the rapid drying, solidification and cutting process of the blood vessel. In view of the above, there is a need for an adaptive shearing method that can intelligently control the ultrasonic blade holder temperature and the transducer power level.

Disclosure of Invention

In order to solve the technical problems, the invention provides an ultrasonic knife blood vessel self-adaptive cutting method and system based on intelligent temperature sensing, a generator provided with the system and an ultrasonic knife surgical instrument.

In order to solve the technical problems, the technical scheme of the invention is as follows:

an ultrasonic knife blood vessel self-adaptive shearing method based on intelligent temperature perception comprises the following steps,

s1, pre-estimating the real-time temperature T of the ultrasonic cutter bar according to the temperature distribution function model_est；

S2, judging the real-time temperature T_estThe temperature range in which the catalyst is used;

and S3, adjusting the power level applied to the ultrasonic blade transducer according to the judgment result to control the current output of the ultrasonic blade, thereby controlling the temperature change rate.

Preferably, the temperature distribution function model is a neural network algorithm model, and comprises one or more algorithm model combinations of a feedforward neural network, a memory neural network and an attention neural network, and the model training method is one or more combinations of supervised learning, semi-supervised learning, unsupervised learning and reinforcement learning.

Preferably, the model training method specifically includes extracting input features from a training set, inputting the input features into the neural network algorithm model to calculate a median value and a gradient value of each neuron, updating weights by using a gradient descent method, repeating the above processes until the model reaches a predetermined stop condition, stopping training after the stop condition is reached, and storing the model, wherein a loss function of the model can be Mean Square Error (MSE) or Mean Absolute Error (MAE).

Preferably, the temperature distribution function model is composed of layers and corresponding neurons and weights, weight parameters and an application program are stored in a generator memory, the memory is Flash, EEPROM or other nonvolatile storage devices, the application program runs in a processor, and the processor is either an ARM, DSP, FPGA, CPU, GPU or ASIC chip existing in the generator or a remote server connected through a network.

Preferably, in the step S1, the "estimating the real-time temperature of the ultrasonic tool bar according to the temperature distribution function model" specifically includes inputting characteristic parameters to the temperature distribution function model, where the characteristic parameters include one or more combinations of working feedback parameters, physical structure characteristic parameters, and environmental parameters.

Preferably, the working feedback parameters include one or more parameters of real-time voltage U, real-time current I, power P, impedance R, real-time resonant frequency f and real-time voltage and current phase difference theta; the physical structure characteristic parameters comprise one or more parameters of ultrasonic knife bar materials and knife bar lengths; the environmental parameters comprise one or more of environmental temperature and environmental humidity.

Preferably, in the step S2, the step "determining the temperature range of the real-time temperature" includes specifically,

presetting three temperature thresholds, namely a first temperature threshold T from low to high₁A second temperature threshold T₂A third temperature threshold T₃；

A preset temperature range lower than the first temperature threshold T₁Is a first temperature range, the first temperature threshold value T₁And a second temperature threshold T₂With a second temperature range, said second temperature threshold T₂And a third temperature threshold T₃A third temperature range therebetween;

determining a real-time temperature T_estIn the temperature range.

Preference is given toIn the step S3, when the real-time temperature T is determined to be obtained_estWhen the temperature is in the first temperature range, the power level of the ultrasonic knife energy converter is adaptively adjusted in the first current value output range, so that the ultrasonic knife bar reaches a second temperature threshold value T on the basis of keeping the first temperature change rate₂(ii) a When the real-time temperature T is obtained through judgment_estWhen the temperature is in the second temperature range, the power level of the ultrasonic knife energy converter is adaptively adjusted in the second current value output range, so that the ultrasonic knife bar reaches a third temperature threshold value T on the basis of keeping the second temperature change rate₃(ii) a When the real-time temperature T is obtained through judgment_estAnd when the temperature is in the third temperature range, the power level of the ultrasonic knife energy converter is adaptively adjusted in the third current value output range, so that the ultrasonic knife keeps the third temperature change rate for the time t 1.

Preferably, the first current value, the second current value and the third current value are a fixed value or a numerical range; the first current output value is greater than the second current output value, and the second current output value is greater than the third current output value.

Preferably, the first temperature change rate, the second temperature change rate and the third temperature change rate are all within 0-50 ℃/s, and the first temperature change rate is the maximum.

Preferably, the temperature of the ultrasonic knife bar is increased by no more than 200 ℃ on the basis of keeping a third temperature change rate, and the third temperature range corresponds to the optimum closing temperature range of the blood vessel.

Preferably, after the ultrasonic blade bar is warmed up for a time period t1 based on maintaining the third rate of temperature change, the power level applied to the ultrasonic blade transducer is adjusted to control the current output of the ultrasonic blade such that the ultrasonic blade bar is warmed up and maintained within the fourth temperature range based on maintaining the fourth rate of temperature change.

Preferably, the fourth temperature range does not exceed 300 ℃, preferably is from 200 ℃ to 300 ℃, and the fourth temperature range corresponds to the blood vessel drying and cutting temperature range.

The invention also discloses an ultrasonic knife blood vessel self-adaptive shearing system based on intelligent temperature sensing, which comprises the following components:

a real-time temperature pre-estimating unit for pre-estimating the real-time temperature T of the ultrasonic cutter bar according to the temperature distribution function model_est；

A processing unit for judging the real-time temperature T_estThe temperature range in which the catalyst is used;

and the adjusting unit is used for adjusting the power level applied to the ultrasonic knife energy converter according to the judgment result so as to control the current output of the ultrasonic knife and further control the temperature change rate.

The invention also discloses a generator for ultrasonic knife blood vessel self-adaptive shearing control based on intelligent temperature perception, which comprises:

a control circuit coupled to a memory, the control circuit configured to be capable of:

predicting real-time temperature T of ultrasonic cutter bar according to temperature distribution function model_est；

Judging the real-time temperature T_estThe temperature range in which the catalyst is used;

and according to the judgment result, adjusting the power level applied to the ultrasonic knife transducer to control the current output of the ultrasonic knife so as to control the temperature change rate.

The invention also discloses an ultrasonic scalpel surgical instrument based on intelligent temperature sensing and ultrasonic scalpel blood vessel adaptive shearing control, which comprises:

an ultrasonic electromechanical system comprising an ultrasonic transducer coupled to an ultrasonic blade via an ultrasonic waveguide; and

a generator configured to supply power to the ultrasound transducer, wherein the generator comprises a control circuit configured to be capable of:

predicting real-time temperature T of ultrasonic cutter bar according to temperature distribution function model_est；

Judging the real-time temperature T_estThe temperature range in which the catalyst is used;

and according to the judgment result, adjusting the power level applied to the ultrasonic knife transducer to control the current output of the ultrasonic knife so as to control the temperature change rate.

The invention has the following beneficial effects: when the ultrasonic cutter bar works, the actual temperature of the cutter bar is distributed along the one-dimensional space of the cutter bar, the temperature distribution of the cutter bar is determined by the real-time working feedback parameter of the ultrasonic cutter bar, the characteristic parameter of the physical structure and the parameter set of the surrounding environment, each temperature distribution corresponds to a solution of a temperature distribution function, and the function can be approximated by a machine learning algorithm; when the ultrasonic cutter bar works, according to the characteristic parameters of the ultrasonic cutter bar, such as real-time resonant frequency, voltage, current, impedance, power, appearance, environment and the like, the real-time temperature distribution of the ultrasonic cutter bar can be estimated by inputting a machine learning algorithm model, and then power control is carried out according to the estimated temperature, so that the method is accurate and effective. Inputting the real-time characteristic parameter set into at least one machine learning algorithm model to estimate the temperature of a tool nose of the ultrasonic tool; adjusting the output power level according to a first energy control algorithm to keep the target temperature within a first temperature range, and completing the blood vessel sealing process; and adjusting the output power level according to a second energy control algorithm to keep the target temperature controlled within a second temperature range, thereby completing the blood vessel drying, coagulating and cutting process.

Drawings

FIG. 1 is a schematic view of a prior art ultrasonic blade configuration;

FIG. 2 is a flow chart of the present invention for estimating real-time temperature of the ultrasonic tool bar based on a temperature distribution function model;

FIG. 3 is a schematic flow chart of the blood vessel adaptive shearing method based on the intelligent temperature sensing ultrasonic knife of the invention;

FIG. 4 is a flow chart of a first adaptive energy control algorithm for an ultrasonic blade based on smart temperature sensing in accordance with the present invention;

FIG. 5 is a flow chart of a second adaptive energy control algorithm for an ultrasonic blade based on smart temperature sensing according to the present invention;

FIG. 6 is a graph of an embodiment of predicted target temperature changes in the smart temperature sensing based ultrasonic blade vessel adaptive shearing of the present invention.

Detailed Description

The present invention will be described in detail below with reference to specific embodiments shown in the drawings. These embodiments are not intended to limit the present invention, and structural, methodical, or functional changes that may be made by one of ordinary skill in the art in light of these embodiments are intended to be within the scope of the present invention.

The ultrasonic knife system utilizes the phase-locking algorithm to change the working frequency of the transducer in the working process so that the transducer works in the maximum working efficiency state, namely the resonance state. In a resonance state, a standing wave condition must be satisfied when a sound wave propagates on the ultrasonic knife bar, and assuming that the ultrasonic knife bar length is L, the sound wave wavelength is λ, the sound velocity is v, and the resonance frequency is f, the following operating conditions must be satisfied in the resonance state:

wherein n is a positive integer.

Assuming that the period of the sound wave is τ, the following formula is satisfied:

it is possible to obtain:

in actual work, heat is diffused along the arrangement direction of the ultrasonic knife rod, so that the temperature may be different at different positions of the ultrasonic knife rod, and the temperature t at different positions is expressed as:

t＝T(l) (4)

t (L) is a position temperature distribution function on the cutter bar, the range of L is 0-L, and the vertex position of one side of the tool nose of the ultrasonic cutter bar is a coordinate origin.

Temperature can affect the young's modulus of the tool holder and ultimately the acoustic velocity, and the speed of sound v at different locations on the tool holder can be expressed as a function of temperature:

v(l)＝V(T(l)) (5)

equation (1) can be expressed as:

equation (6) can be expressed as:

equation (7) is an integral equation, for a certain time point, f is a certain resonance frequency, and the temperature t (l) is influenced by parameters such as voltage, current, power, impedance, tool holder shape, environmental parameters, and the like. With n, f and L being defined, the temperature distribution function t (L) of the integral equation may have an infinite number of solutions, with a greater variety of different temperature distributions for different tool shanks.

In view of this, the present invention discloses a machine learning algorithm model, specifically a neural network algorithm model, which is a mathematical model developed by the human cranial nerve system, and is similar to biological neurons, and is formed by connecting a plurality of nodes (artificial neurons) with each other, and can be used for modeling complex relationships between data. Connections between different nodes are given different weights, each weight representing the magnitude of the effect of one node on another node. Each node represents a specific function, and information from other nodes is input into an activation function through the corresponding weight comprehensive calculation and obtains a new activity value. The activation function is used for introducing nonlinear elements and increasing the expression capability of the neural network, and commonly used activation functions include Sigmoid, Tanh, ReLU and the like.

From a system perspective, an artificial neuron is an adaptive nonlinear dynamical system composed of a large number of neurons connected by extremely rich and perfect connections. At present, the most common neural network learning algorithm is a back propagation algorithm, and the optimization method is a gradient descent algorithm. Theoretically, a two-layer neural network can approach any function, and the increase of the network layer number can enable the neural network to have stronger expression capability under the same neuron number. The neural network models which are commonly used at present include a feedforward neural network model, a memory neural network model, an attention neural network model and the like: a Multilayer Perceptron (MLP) and a Convolutional Neural Network (CNN) are feedforward Neural Network models; a Recurrent Neural Network (RNN) is a Memory Neural Network model, and commonly used RNN models include a gated Neural Unit (GRU) and a Long-Short Term Memory Neural Network (LSTM); the attention neural network model includes a Transformer and the like.

The memory neural network model increases the memory capacity on the basis of a feedforward neural network, is commonly used for processing time sequence data, and commonly used memory neural networks comprise RNN, GRU, LSTM and the like. GRU and LSTM have long-term memory and are capable of handling long-term sequences.

The temperature distribution function model can comprise one or more algorithm model combinations in a neural network algorithm model based on a machine learning algorithm model. The input characteristics comprise one or more combinations of working feedback parameters, physical structure characteristic parameters and environment parameters. The working feedback parameters include, but are not limited to, real-time voltage U, real-time current I, power P, impedance R, real-time resonant frequency f; the physical structure characteristic parameters include but are not limited to ultrasonic cutter bar material and length; the environmental parameters include, but are not limited to, ambient temperature, ambient humidity.

The more complete the input features, the stronger the approximation capability of the neural network model. In the model of the invention, the voltage U and the current I are obtained by real-time sampling of a generator, and the real-time power P and the impedance R can be calculated by the following formula:

P＝U×I (15)

the real-time frequency f is calculated by the following formula:

f＝k×(θ-θ₀) (17)

wherein k is determined by a functional relationship between the real-time voltage U and the current I:

k＝K(U,I) (18)

theta is the real-time voltage and current phase difference, and the calculation formula is as follows:

θ＝θ_U-θ_I (19)

voltage phase theta_UAnd current phase θ_IObtained by real-time sampling by a generator, theta₀Is a constant.

The sampling frequency of the voltage and current sensor can be 64 times or 128 times of the actual signal frequency, and the parameters of the output voltage U, the output current I, the resonant frequency f, the first derivative df of the frequency, the impedance R, the phase theta, the power P and the like are obtained by performing mathematical operations such as FFT on the sampling values. Physical structure characteristic parameters such as ultrasonic knife bar material, length and the like can be stored in a storage chip of the ultrasonic knife or the generator, the generator can directly read the corresponding storage chip to obtain the characteristic parameters, and the environmental parameters can be obtained by real-time measurement through a sensor.

The model training method can be in modes of supervised learning, semi-supervised learning, unsupervised learning, reinforcement learning and the like. All input characteristic information and training labels of a model required to be acquired for supervised learning can be acquired at a certain time interval, the time interval can be 1ms or 10ms, real-time temperature is measured to serve as a supervised training label, a real-time shearing temperature point can be obtained by adopting an embedded or external temperature sensor or an infrared thermometer, and a large amount of label data is acquired to serve as a training data set S.

A neural network model training process implemented by model supervised learning may be: the input features are taken from a training data set S, the input features are input into a neural network model to calculate the intermediate value and the gradient value of each neuron, the loss function of the model can be Mean Square Error (MSE) or Mean Absolute Error (MAE), the weight is updated by using a gradient descent method, the processes are repeated until the model reaches a preset stopping condition, for example, the prediction precision reaches a target value or the loss is not reduced any more, the training is stopped and the model is stored after the stopping condition is reached, and the model can represent the function of the temperature distribution of the cutter bar on the cutter point when all target ultrasonic cutters work.

The trained model is composed of each layer and corresponding neurons and weights, weight parameters and an application algorithm program are stored in a generator memory, the memory can be Flash, EEPROM or other nonvolatile storage devices, the application program runs in a processor, the processor can be an ARM, DSP, FPGA, CPU, GPU or ASIC chip which is stored in the generator, and the processor can also be a remote server which is connected through a network.

The method for predicting the temperature by using the temperature distribution function model is shown in figure 2, a real-time ultrasonic knife characteristic parameter set X is input into the model, and the model can find the most probable knife bar temperature distribution, temperature T and the like according to the input characteristic set_estCan be derived from this temperature distribution, T_estNamely the estimated real-time temperature of the ultrasonic cutter bar.

As shown in fig. 3, the invention discloses an ultrasonic knife blood vessel adaptive cutting method based on intelligent temperature sensing, which comprises the following steps:

s1, pre-estimating the real-time temperature T of the ultrasonic cutter bar according to the temperature distribution function model_est；

S2, judging the real-time temperature T_estThe temperature range in which the catalyst is used;

and S3, adjusting the power level applied to the ultrasonic blade transducer according to the judgment result to control the current output of the ultrasonic blade, thereby controlling the temperature change rate.

In conjunction with one embodiment disclosed in fig. 4 and 5, the present invention can control the output power level of the ultrasonic blade transducer based on the estimated real-time temperature to achieve the sealing and cutting process of the blood vessel.

Firstly, the generator controls the temperature of the vascular operation part to be in a first temperature range according to a first energy control algorithm to complete the vascular sealing process, the first temperature range can be an appropriate temperature range within 0-200 ℃, one implementation mode of the first energy control algorithm is shown in figure 4, a real-time temperature value is estimated through a temperature estimation model, and output energy is controlled according to the temperature value.

Specifically, the real-time temperature T is first determined_estWhen the temperature is in the first temperature range, the power level of the ultrasonic knife energy converter is adaptively adjusted in the first current value output range, so that the ultrasonic knife bar reaches a second temperature threshold value T on the basis of keeping the first temperature change rate₂The first current range can correspond to a larger current value, so that larger power level output is realized, and the aims of quickly removing the surface moisture of the blood vessel and quickly heating the blood vessel are fulfilled.

When the real-time temperature T is obtained through judgment_estIn the second temperature range, the first temperature threshold T is reached₁And is below a second temperature threshold T₂In the process, the power level of the ultrasonic knife energy converter can be adaptively adjusted within the output range of the second current value, so that the ultrasonic knife bar reaches a third temperature threshold value T on the basis of keeping the second temperature change rate₃So as to gradually increase the temperature value of the blood vessel and gradually denature the collagen in the blood vessel tissue.

When the real-time temperature T is obtained through judgment_estIn a third temperature range, the second temperature threshold T is reached₂And is below a third temperature threshold T₃During the process, the power level of the ultrasonic knife transducer can be adjusted in a self-adaptive mode within the output range of the third current value, so that the ultrasonic knife keeps the third temperature change rate and lasts for t1, and therefore complete fusion of the vascular walls on two sides is achieved.

The temperature range can be an appropriate temperature range within 0-200 ℃, the temperature change rate can be an appropriate rate within 0-50 ℃/s, and the first temperature change rate is the largest. The temperature of the ultrasonic cutter bar is raised to be not more than 200 ℃ on the basis of keeping a third temperature change rate, and the third temperature range corresponds to the optimum closing temperature range of the blood vessel. The first current value, the second current value and the third current value are a fixed value or a numerical range; the first current output value is greater than the second current output value, and the second current output value is greater than the third current output value.

After the vessel sealing is completed, a second energy control algorithm is used to realize the incision process, and one control process is shown in fig. 5. And when the estimated target temperature reaches the sealing end temperature threshold or exceeds a preset time threshold, the vessel sealing can be judged to be finished. After the completion of the blood vessel sealing is confirmed, namely after the temperature of the ultrasonic cutter bar is raised for a period of time t1 on the basis of keeping the third temperature change rate, the power level applied to the transducer of the ultrasonic cutter is adjusted to control the current output value of the ultrasonic cutter, and the current value is adjusted to a fourth larger current range, so that the higher power level is ensured, the temperature of the ultrasonic cutter bar is raised and kept in the fourth temperature range on the basis of keeping the fourth temperature change rate, and the rapid drying, solidification and incision of the blood vessel are realized. The fourth temperature range does not exceed 300 ℃, and may be 200 ℃ to 300 ℃, the fourth temperature range corresponding to the blood vessel drying and cutting temperature range.

The above control process is only a specific implementation for realizing the blood vessel cutting process according to the temperature distribution function model, and it is within the scope of the present invention that the control process may be combined into one or divided into a plurality of control processes.

A temperature change curve of the blood vessel cutting according to the above process is shown in fig. 6, and the temperature is the maximum temperature at a specific region of the blade tip estimated by the neural network model. Briefly, the power level is adjusted up and down in a real-time self-adaptive manner according to the real-time temperature change rate in three temperature ranges to maintain the target temperature change rate, the current is reduced when the temperature rise rate is too high, and the current is increased when the temperature rise rate is too low. Firstly, starting a sealing process at a higher power level, rapidly increasing the temperature, and reaching a temperature threshold T1 at time T1; the output power level is then adjusted at a second current range, reaching a temperature threshold T2 at time T2; then adjusting the output power level in a third current range, and reaching a temperature threshold T3 at time T3, and finishing the blood vessel sealing process; and finally, adjusting the output power level by the fourth current level to finish the processes of drying, coagulating and cutting the blood vessel.

The above is only a preferred embodiment of the present invention, and it should be noted that the above preferred embodiment should not be considered as limiting the present invention, and the protection scope of the present invention should be subject to the scope defined by the claims. It will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the spirit and scope of the invention, and these modifications and adaptations should be considered within the scope of the invention.