Ultrasonic scalpel protection method and device based on temperature estimation

Abstract

An ultrasonic scalpel protection method and device based on temperature estimation. A temperature extreme value and an average temperature trend of a tip are predicted, and adaptive determination is performed on the basis of the temperature extreme value and the average temperature trend, so that when cutting has been completed or when the temperature of the tip region exceeds the melting point of a pad, the output power can be reduced in a timely manner to reduce the wear of the ultrasonic scalpel and prolong the service life of the ultrasonic scalpel, thereby effectively protecting the ultrasonic scalpel. During continuous activation or continuous cutting of the ultrasonic scalpel, this approach can improve cutting efficiency of the ultrasonic scalpel while reliably protecting the pad, adaptively switch between protection and high-efficiency cutting states of the ultrasonic scalpel, and adapt to the operating style of an operator. In addition, by performing adaptive determination on the basis of the temperature extreme value and the average temperature trend, compared with methods for tip protection solely based on single temperature prediction, the precision and reliability of tip protection can be improved.

Description

A method and device for protecting ultrasonic scalpels based on temperature prediction

[0001] This application claims priority to Chinese Patent Application No. 2024119982994, filed on December 30, 2024, entitled "A Method and Device for Protecting an Ultrasonic Scalpel Based on Temperature Prediction", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of ultrasonic equipment technology, and in particular to an ultrasonic scalpel protection method and device based on temperature prediction. Background Technology

[0003] The ultrasonic scalpel transmits electrical energy to a piezoelectric transducer via an energy generator. The transducer converts the electrical energy into ultrasonic mechanical energy, thereby generating ultrasonic vibration. The ultrasonic scalpel head then amplifies the ultrasonic vibration and uses it to cut the object being cut.

[0004] When cutting objects, medical personnel using ultrasonic scalpels often habitually use a continuously excited ultrasonic scalpel head to improve the efficiency of the cutting process. Because this type of operation involves continuous excitation, maintaining a high energy output even after the cutting is complete causes the ultrasonic scalpel jaws to continuously wear down the gasket. This results in high temperatures at the ultrasonic scalpel head, potentially leading to gasket melting and wear, and ultimately reducing the lifespan of the ultrasonic scalpel. Summary of the Invention

[0005] This application provides a method and device for protecting an ultrasonic scalpel based on temperature prediction. When cutting an object, the operator or doctor using the ultrasonic scalpel avoids the jaws of the ultrasonic scalpel constantly wearing down the pad, thereby preventing the ultrasonic scalpel tip from generating high temperatures, which could lead to melting and wear of the pad and reduce the service life of the ultrasonic scalpel.

[0006] By predicting the extreme and average temperature trends of the ultrasonic scalpel tip and adaptively determining these trends, the output power can be reduced in a timely manner when shearing is complete or the temperature in the tip area exceeds the melting point of the gasket. This reduces ultrasonic scalpel wear and extends its service life, effectively protecting the ultrasonic scalpel. During continuous ultrasonic excitation or shearing, the shearing efficiency of the ultrasonic scalpel can be further improved while reliably protecting the gasket. The scalpel adaptively switches between ultrasonic scalpel protection and high-efficiency shearing states, adapting to the operator's operating methods. Compared to methods that protect the tip based on a single temperature prediction, this technical solution improves the accuracy and reliability of tip protection.

[0007] This application provides a method for protecting an ultrasonic scalpel based on temperature prediction, including:

[0008] Predicting the extreme and average temperature trends of the ultrasonic scalpel head when shearing an object;

[0009] If the extreme temperature value is greater than or equal to the first temperature threshold, then adjust the output current of the ultrasonic scalpel generator to the first current.

[0010] If the extreme temperature value is less than the first temperature threshold and greater than or equal to the second temperature threshold, the predicted shear point of the ultrasonic scalpel is obtained. If the predicted shear point is true, the output current of the ultrasonic scalpel generator is adjusted to the first current, and the first temperature threshold is greater than the second temperature threshold.

[0011] After adjusting the output current of the ultrasonic scalpel generator to the first current, if the average temperature trend indicates that the ultrasonic scalpel is in a continuous shearing state, then adjust the output current of the ultrasonic scalpel generator to the second current, which is greater than the first current.

[0012] In one possible implementation, the step of determining that the ultrasonic scalpel is in a continuous shearing state based on the average temperature trend includes:

[0013] If the average temperature drop of the blade head is greater than the first preset value within a first preset time period, and the average temperature of the blade head rises to a value greater than the second preset value within a second preset time period, then the ultrasonic scalpel is determined to be in a continuous shearing state, wherein the second preset time period is later than the first preset time period.

[0014] In one possible implementation, the step of predicting the extreme and average temperature trends of the ultrasonic scalpel in the case of ultrasonic scalpel shearing the object being cut includes:

[0015] When an ultrasonic scalpel is cutting an object, obtain the output voltage, output current, first derivative of the resonant frequency, and voltage-current phase difference of the ultrasonic scalpel generator.

[0016] The output voltage, output current, first derivative of resonant frequency, and voltage-current phase difference are input into a pre-established extreme temperature prediction model to obtain the extreme temperature output by the extreme temperature prediction model.

[0017] In one possible implementation, before predicting the extreme and average temperature trends of the ultrasonic scalpel during ultrasonic shearing of the object being cut, the following steps are also included:

[0018] The output voltage, output current, first derivative of resonant frequency, and voltage-current phase difference of the ultrasonic scalpel generator at the same historical moment are obtained, as well as the corresponding temperature extreme value at the same historical moment.

[0019] A first initial model is established, with the output voltage, output current, first derivative of resonant frequency and voltage-current phase difference at the same historical moment as the input of the first initial model, and the temperature extreme value corresponding to the same historical moment as the output of the first initial model. The first initial model is trained to obtain the extreme temperature prediction model.

[0020] In one possible implementation, the step of predicting the extreme and average temperature trends of the ultrasonic scalpel in the case of ultrasonic scalpel shearing the object being cut includes:

[0021] When an ultrasonic scalpel is cutting an object, the phase difference between the output current and voltage current of the ultrasonic scalpel generator is obtained.

[0022] The phase difference between the output current and the voltage current is input into a pre-established temperature trend prediction model to obtain the average temperature trend output by the temperature trend prediction model.

[0023] In one possible implementation, before predicting the extreme and average temperature trends of the ultrasonic scalpel during ultrasonic shearing of the object being cut, the following steps are also included:

[0024] Obtain the phase difference between the output current and voltage of the ultrasonic scalpel generator at the same historical moment, as well as the average temperature at the same historical moment;

[0025] A second initial model is established, with the phase difference between the output current and voltage current at the same historical moment as the input of the second initial model, and the average temperature corresponding to the same historical moment as the output of the second initial model. The second initial model is trained to obtain a temperature trend prediction model.

[0026] In one possible implementation, the step of obtaining the predicted shear point of the ultrasonic scalpel includes:

[0027] The variable parameters of the third historical electrical signal of the ultrasonic scalpel generator within a preset time period are obtained, and the variable parameters of the third historical electrical signal are preprocessed so that the cutting point of the ultrasonic scalpel cutting the object is always within the preset time period.

[0028] The results corresponding to the variable parameters of the third historical electrical signal in the first time period are marked as true to obtain the first training set; the results corresponding to the variable parameters of the third historical electrical signal in the second time period are marked as true to obtain the second training set. The first time period and the second time period are within a preset time period, and the first time period is earlier than the second time period.

[0029] Construct a third initial model and a fourth initial model, and train the third initial model with the first training set to obtain the first model; train the fourth initial model with the second training set to obtain the second model;

[0030] When cutting an object with an ultrasonic scalpel, obtain the variable parameters of the real-time electrical signal of the ultrasonic scalpel generator;

[0031] The variable parameters of the real-time electrical signal are used as inputs to the first model and the second model to obtain the first output of the first model and the second output of the second model.

[0032] Obtain the forecast demand, and based on the forecast demand, the first output, and the second output, obtain the forecast result at the cutoff point.

[0033] In one possible implementation, the steps for obtaining the predicted demand include:

[0034] Get the thickness of the object being cut;

[0035] Based on the thickness of the object being cut and a preset correspondence, the weight corresponding to the predicted demand is determined. The preset correspondence includes the weight relationship between the thickness of the object being cut and the predicted demand.

[0036] In one possible implementation, the step of preprocessing the variable parameters of the third historical electrical signal includes:

[0037] Calculate the average value of each parameter in the variable parameters of the third historical electrical signal in the third time period, and mark it as the reference parameter of each parameter. The third time period is the start time period in the preset time period.

[0038] Based on the baseline parameters of each parameter, adjust the values ​​of each parameter in the variable parameters of the third historical electrical signal.

[0039] In one possible implementation, the step of preprocessing the variable parameters of the historical electrical signal includes:

[0040] Based on preset rules, outliers in the variable parameters of historical electrical signals are removed.

[0041] In one possible implementation, the step of preprocessing the variable parameters of the third historical electrical signal includes:

[0042] The exponential moving average model is used to process the variable parameters of the third historical electrical signal. The exponential moving average model is: X t =βX t-1 +(1-β)θ t ;

[0043] Where β is the weighting parameter, θ t Let X be the weight parameter obtained in the t-th update. t Let be the moving average of the variable parameters of the third historical electrical signal obtained from the t-th update.

[0044] In one possible implementation, the step of preprocessing the variable parameters of the third historical electrical signal includes:

[0045] The variable parameters of the third historical electrical signal are scaled and standardized according to a preset ratio. The standardization model is as follows:

[0046] Where μ is the mean of each variable parameter of the third historical electrical signal, and σ is the standard deviation of each variable parameter of the third historical electrical signal.

[0047] This application also provides an ultrasonic scalpel protection device based on temperature prediction, comprising:

[0048] The temperature prediction module is used to predict the extreme and average temperature trends of the ultrasonic scalpel head when cutting an object.

[0049] An adjustment module is used to adjust the output current of the ultrasonic scalpel generator to the first current if the extreme temperature value is greater than or equal to the first temperature threshold.

[0050] And, if the extreme temperature value is less than the first temperature threshold and greater than or equal to the second temperature threshold, then obtain the shearing point prediction result of the ultrasonic scalpel; if the shearing point prediction result is true, then adjust the output current of the ultrasonic scalpel generator to the first current, and the first temperature threshold is greater than the second temperature threshold.

[0051] Furthermore, it is also used to adjust the output current of the ultrasonic scalpel generator to a second current, which is greater than the first current, after adjusting the output current of the ultrasonic scalpel generator to a first current, if the average temperature trend indicates that the ultrasonic scalpel is in a continuous shearing state.

[0052] This application provides a method and apparatus for protecting an ultrasonic scalpel based on temperature prediction. By predicting the extreme and average temperature trends of the scalpel tip and adaptively judging based on these trends, the output power can be reduced in a timely manner when shearing is completed or the temperature in the scalpel tip area exceeds the melting point of the gasket. This reduces ultrasonic scalpel wear and extends its service life, effectively protecting the ultrasonic scalpel. During continuous ultrasonic excitation or continuous shearing, the shearing efficiency of the ultrasonic scalpel can be further improved while reliably protecting the gasket. The method adaptively switches between ultrasonic scalpel protection and high-efficiency shearing states, adapting to the operator's operating methods. Compared to methods that protect the scalpel tip based on a single temperature prediction, this application's technical solution can improve the accuracy and reliability of scalpel tip protection. Attached Figure Description

[0053] Figure 1 is a schematic flowchart of an ultrasonic scalpel protection method based on temperature prediction provided in an embodiment of this application;

[0054] Figure 2 is a schematic diagram of the extreme temperature curve and average temperature trend curve of the ultrasonic scalpel head region provided in the embodiment of this application;

[0055] Figure 3 is a schematic diagram of the structure of a fully connected neural network and a recurrent neural network combined in a serial structure according to an embodiment of this application;

[0056] Figure 4 is a schematic diagram of the structure of the fully connected neural network model provided in the embodiment of this application;

[0057] Figure 5 is a schematic diagram of the structure of the recurrent neural network model provided in the embodiment of this application;

[0058] Figure 6 is a schematic diagram of the average temperature trend during the continuous shearing process provided in the embodiments of this application;

[0059] Figure 7 is a schematic diagram of the cutter head structure provided in an embodiment of this application;

[0060] Figure 8 is a schematic diagram of the cutter head structure provided in an embodiment of this application;

[0061] Figure 9 is a schematic diagram of the resonant frequency and current-voltage phase difference as a function of shear provided in the embodiments of this application;

[0062] Figure 10 is a schematic diagram of the output current and output voltage as a function of shear provided in an embodiment of this application;

[0063] Figure 11 is a schematic flowchart of an ultrasonic scalpel protection method based on temperature prediction provided in an embodiment of this application.

[0064] Figure 12 is a schematic diagram of a combined structure of the first model and the second model provided in the embodiments of this application. Detailed Implementation

[0065] When an operator uses an ultrasonic scalpel to cut an object, in order to prevent the ultrasonic scalpel tip from overheating, which would reduce the service life of the ultrasonic scalpel, this application provides an ultrasonic scalpel protection method and device based on temperature prediction.

[0066] An ultrasonic scalpel protection method based on temperature prediction is provided in this application embodiment, as shown in Figure 1, including steps S110 to S140.

[0067] S110, predicts the extreme and average temperature trends of the ultrasonic scalpel tip when the object being cut is being sheared by an ultrasonic scalpel.

[0068] As shown in Figure 2, this is a schematic diagram of the extreme temperature curve and the average temperature trend curve obtained from the cutting head region of the ultrasonic scalpel provided in this embodiment. Clearly, the extreme temperature curve is characterized by a large range of change and greater fluctuations compared to the average temperature trend curve, while the average temperature trend curve is more stable and better represents the temperature trend change.

[0069] The specific steps for predicting extreme temperatures are as follows: when the object being cut is being cut by an ultrasonic scalpel, the output voltage, output current, first derivative of the resonant frequency, and voltage-current phase difference of the ultrasonic scalpel generator are obtained; the output voltage, output current, first derivative of the resonant frequency, and voltage-current phase difference are input into a pre-established extreme temperature prediction model to obtain the extreme temperature output by the extreme temperature prediction model.

[0070] The extreme temperature prediction model utilizes first historical electrical signal data as training data. Specifically, firstly, it acquires the output voltage, output current, first derivative of the resonant frequency, and voltage-current phase difference of the ultrasonic scalpel generator at the same historical moment, as well as the corresponding extreme temperature value at the same historical moment; that is, the first historical electrical signal data includes the output voltage, output current, first derivative of the resonant frequency, and voltage-current phase difference of the ultrasonic scalpel generator at the same moment, and also includes the corresponding extreme temperature value of the scalpel head at the same moment. Then, it establishes a first initial model, using the first derivative of the output voltage, output current, and resonant frequency, and voltage-current phase difference at the same historical moment as the input of the first initial model, and using the corresponding extreme temperature value at the same historical moment as the output of the first initial model, to train the first initial model and obtain the extreme temperature prediction model.

[0071] The step of predicting the average temperature trend is as follows: when the object being cut is being cut by an ultrasonic scalpel, the phase difference between the output current and voltage current of the ultrasonic scalpel generator is obtained; the phase difference between the output current and voltage current is input into a pre-established temperature trend prediction model to obtain the average temperature trend output by the temperature trend prediction model.

[0072] The temperature trend prediction model utilizes second historical electrical signal data as training data. Specifically, firstly, the phase difference between the output current and voltage of the ultrasonic scalpel generator at the same historical moment, as well as the corresponding average temperature at the same historical moment, are obtained. The second historical electrical signal data includes the phase difference between the output current and voltage of the ultrasonic scalpel generator at the same historical moment, and also includes the corresponding average temperature of the scalpel tip at the same moment. Then, a second initial model is established, using the phase difference between the output current and voltage at the same historical moment as the input and the corresponding average temperature at the same historical moment as the output, to train the second initial model and obtain the temperature trend prediction model.

[0073] During the training of the first and second initial models, the initial temperature of the cutting head is affected by various factors, including the cutting head's working state, material, shape, and ambient temperature, when acquiring the training data. Therefore, this application uses the average trend temperature over the first 0.5 seconds as the baseline temperature when collecting training data, and uses this as the initial temperature of the cutting head. This ensures that the acquired cutting head temperature has good representativeness and resistance to interference.

[0074] In some embodiments, the extreme temperature prediction model and the temperature trend prediction model provided in this application are two prediction models with similar structures but different weights. For example, as shown in Figure 3, a fully connected neural network and a recurrent neural network are combined in a cascaded structure, with the recurrent neural network serving as the first input network and the fully connected neural network serving as the second input network, thereby constructing a first initial model or a second initial model. In this way, the output of the fully connected neural network is used as the prediction result of the extreme temperature or the average temperature trend.

[0075] More specifically, a neural network algorithm is a mathematical model inspired by neurons, consisting of multiple interconnected nodes, used to model complex relationships between data. A fully connected neural network has a multi-layered structure, with all neurons in each layer interconnected. As shown in Figure 4, in some embodiments, the fully connected neural network model used in the first or second initial model includes an input layer, hidden layers, and an output layer. The fitting ability of a fully connected neural network model is highly correlated with its number of layers and neurons. For example, in Figure 4, the first or second initial model has two hidden layers, with each hidden unit corresponding to the number of output units in a recurrent neural network model. The number of neurons can be set to 8, 16, 32, or 64. The multi-layer neural network model used in this application has four layers, with the number of nodes in each layer set to 40, 16, 4, and 1 respectively. The output layer has 1 node, and the output result is a prediction of the extreme temperature or average temperature trend.

[0076] In some embodiments, considering that the acquired ultrasonic scalpel electrical signals are highly time-series signals, a recurrent neural network model with memory capability is employed to better process the temporal information relationships of the electrical signals. As shown in Figure 5, a recurrent neural network model is used to construct the first input network of the first initial model or the second initial model. The recurrent neural network model can memorize the preceding signals, thus exhibiting stronger feature extraction capabilities for time-series signals. Therefore, this embodiment utilizes a recurrent neural network model and a fully connected neural network model to construct the first initial model or the second initial model.

[0077] Because the electrical signals of the ultrasonic generator exhibit stronger correlation over short periods, in some embodiments, the time interval for acquiring the ultrasonic generator's electrical signals is set to 10 milliseconds, and the number of loop nodes in the recurrent neural network is set to 40, during the prediction of the extreme and average temperature trends of the cutting head. This allows the recurrent neural network to process electrical signals within a 400-millisecond time interval simultaneously, thereby strengthening the correlation between extreme and average temperature trends over time. It should be noted that variations of the recurrent neural network model with memory capabilities are also within the scope of this application's embodiments, such as long short-term memory networks or gated neural units.

[0078] In some embodiments, the first initial model or the second initial model may also be a combination of one or more machine learning algorithms or deep learning algorithms. More specifically, the machine learning algorithms may include linear regression algorithms, support vector machine algorithms, nearest neighbor algorithms, decision tree algorithms, random forest algorithms, or Naive Bayes algorithms, and the deep learning algorithms may include fully connected neural networks, convolutional neural networks, generative adversarial networks, or recurrent neural networks.

[0079] In some embodiments, the signals directly acquired from the ultrasonic scalpel generator are: the output voltage, output current, resonant frequency, current phase value, and voltage phase value of the ultrasonic scalpel generator. Then, the first derivative of the resonant frequency and the voltage-current phase difference are calculated.

[0080] After acquiring the output voltage, output current, resonant frequency, current phase value, and voltage phase value, the data needs to be preprocessed. First, the preprocessing considers the impact of vibrations generated during the ultrasonic scalpel shearing process and the transmission process of high-speed circuits on the electrical signals, which can lead to abnormal values ​​in the acquired electrical signals. Therefore, significantly abnormal electrical signals are removed, such as negative values ​​in current and voltage, resonant frequencies below 40kHz, and current-voltage phase differences when frequency locking fails. Removing such abnormal data is beneficial for the accurate training and inference results of the extreme temperature prediction model and the temperature trend prediction model.

[0081] In some embodiments, for extreme temperature prediction models, the output voltage, output current, first derivative of the resonant frequency, and voltage-current phase difference are collected, which have a greater correlation. For temperature trend prediction models, the output current and output voltage, which have a greater correlation, are collected, and the phase difference between the output current and the voltage is obtained. However, in practical applications, it is not limited to collecting only the above electrical signals; multi-dimensional variables such as temperature, resistance, ultrasonic scalpel parameters, or generator parameters can also be collected from sensors with relatively low correlation.

[0082] To enable the first or second initial model to better learn the deep features of the electrical signal, in some embodiments, all input first or second historical electrical signals are standardized. Since the electrical signal obtained from each ultrasonic scalpel excitation has a certain offset, this application calculates the standard mean and standard deviation of the acquired first or second historical electrical signals. The input electrical signals need to be standardized using the standard mean and standard deviation to obtain new input variables. The corresponding first standardization model is as follows:

[0083] The first standardization model is as follows: x represents each parameter in the first or second historical electrical signal, μ represents the mean of each parameter in the first or second historical electrical signal, and σ represents the standard deviation of each parameter in the first or second historical electrical signal.

[0084] When preprocessing the collected data, it is considered that the data adjustment rate is much greater than the electrical signal acquisition rate, resulting in a still relatively large fluctuation amplitude in the collected electrical signal. In some embodiments, an exponential moving average method is used to process the electrical signal, and the corresponding first exponential moving average model is: X t =βX t-1 +(1-β)θ t .

[0085] Where, θ t Let X be the weighting parameter of each parameter in the first or second historical electrical signal obtained in the t-th update. t This is the moving average of each parameter in the first or second historical electrical signal updated for the t-th time. β is a weighting parameter; the larger β is, the more correlated the moving average value is with the historical values. In this embodiment, setting the β weighting parameter to 0.90 yields a signal curve with better smoothing. It should be noted that this weighting parameter is only used in this embodiment, and other reasonable weighting parameters are also within the scope of selection.

[0086] In the process of predicting the extreme and average temperature trends of the ultrasonic scalpel tip, in this embodiment, the effect of the delay of the data electrical signal on the electrical signal generated in the first 0.5 seconds is considered. The average value of each parameter in the electrical signal collected in the first 0.5 seconds is calculated and set as a benchmark. The parameters in the electrical signal collected after 0.5 seconds are subtracted from the benchmark to obtain the valid data.

[0087] Since the temperature of the cutting head is an accumulated variable, it is continuous and highly correlated over time. Therefore, this application sets the data volume for the cutting time to 5 seconds as the uniform length of the training data for both the first and second initial models. Generally, a length of 2 seconds is used. nAt the same time, the device used to train the model can have better computational parallelism. Specifically, in this embodiment, 512 is used as the length of the training input data.

[0088] In some embodiments, the training parameters for the first and second initial models are set as follows: the input data length is set to 512, the batch size of the input training data is set to 128, and an optimizer with a decay parameter of 0.01 is used for learning. This improves the adaptability of the first and second initial models to temperature prediction under different generator input signals and prevents the models from overfitting to the training set. Considering that the temperature prediction errors of the first and second initial models are relatively large in the initial stage, a relatively large learning rate of 0.05 is set at the beginning of training to appropriately accelerate the learning rate. After the training reaches a certain accuracy, the learning rate is gradually reduced to gradually fine-tune the model.

[0089] In some embodiments, to optimize the training performance of the first and second initial models, considering that temperature prediction is essentially a regression prediction and that the predicted features contain large values, SoothL1Loss is used as the loss function for model training. The SoothL1Loss model is as follows:

[0090] By employing the SoothL1Loss loss function, when the predicted temperature differs significantly from the actual temperature, the training process is less prone to gradient explosion due to the piecewise calculation of the loss, thus ensuring stable convergence of the training of the first and second initial models.

[0091] S120, if the extreme temperature value is greater than or equal to the first temperature threshold, then adjust the output current of the ultrasonic scalpel generator to the first current.

[0092] The first temperature threshold is greater than the melting point temperature of the gasket. For example, if the first temperature threshold is set to 280 degrees Celsius, the ultrasonic scalpel tip will not experience an extreme temperature exceeding the first temperature threshold during normal shearing of the object being cut. However, when the tip is shearing the gasket, the tip temperature rises rapidly, leading to an extreme temperature exceeding the first temperature threshold. In this embodiment, when the extreme temperature is greater than or equal to the first temperature threshold, the output current of the ultrasonic scalpel generator is adjusted to a first current, thereby effectively reducing the tip temperature of the ultrasonic scalpel and preventing continuous damage to the gasket.

[0093] S130, if the extreme temperature value is less than the first temperature threshold and greater than or equal to the second temperature threshold, then obtain the predicted result of the ultrasonic scalpel's shearing point. If the predicted result of the shearing point is true, then adjust the output current of the ultrasonic scalpel generator to the first current, and the first temperature threshold is greater than the second temperature threshold.

[0094] The second temperature threshold is greater than the temperature of the object being cut. For example, the second temperature threshold is set to 210 degrees Celsius. When the extreme temperature value is greater than or equal to the second temperature threshold, it is necessary to determine whether the ultrasonic scalpel has completed the shearing operation on the object being cut.

[0095] Specifically, the shear point prediction result of the ultrasonic scalpel is obtained. If the shear point prediction result is false, it indicates that there is no shear point on the object being cut. In this case, the output current of the ultrasonic scalpel is not adjusted to ensure continuous operation. If the shear point prediction result is true, it indicates that there is a shear point on the object being cut. In this case, to prevent the temperature of the ultrasonic scalpel tip from continuously rising, the output current of the ultrasonic scalpel generator is adjusted to the first current to prevent continuous damage to the gasket.

[0096] S140, after adjusting the output current of the ultrasonic scalpel generator to the first current, if the average temperature trend indicates that the ultrasonic scalpel is in a continuous shearing state, then adjust the output current of the ultrasonic scalpel generator to the second current, which is greater than the first current.

[0097] Specifically, in order to meet the requirements of gasket protection, this embodiment controls the ultrasonic scalpel to output a lower first current when the predicted shear point is true. In practical applications, if the object being cut is a free object, multiple shear points will occur during the ultrasonic scalpel shearing process. When a shear point appears, it does not mean that the shearing of the object is complete; further shearing operations are still required.

[0098] Specifically, the ultrasonic scalpel is used to determine whether it is in continuous shearing mode based on the average temperature trend. If it is not in continuous shearing mode, it indicates that the object being cut has been completely severed, meaning the shearing operation is complete. In this case, the ultrasonic scalpel is stopped. If the ultrasonic scalpel is in continuous shearing mode, continuing to control it to output a lower first current will not allow for a faster shearing operation. In this case, the output current of the ultrasonic scalpel generator is adjusted to a second current to raise the temperature of the ultrasonic scalpel tip, thus allowing the ultrasonic scalpel to continue the shearing operation.

[0099] To achieve continuous shearing operations, this embodiment utilizes the characteristics of average temperature trends to better determine temperature changes within the shearing gap. Figure 6 illustrates the average temperature trend during continuous shearing. After shearing, the temperature decreases as the ultrasonic scalpel leaves the tissue and pad, and then rises again during continuous shearing.

[0100] In this embodiment of the application, the step of determining that the ultrasonic scalpel is in a continuous shearing state based on the average temperature trend includes: if the average temperature drop of the scalpel head is greater than a first preset value within a first preset time period; and the average temperature of the scalpel head rises to a value greater than a second preset value within a second preset time period, then the ultrasonic scalpel is determined to be in a continuous shearing state, wherein the second preset time period is later than the first preset time period.

[0101] In the technical solution of this application embodiment, the ultrasonic scalpel is judged to be in a continuous shearing state based on two features. The first feature is the average temperature decrease feature. Specifically, the average temperature occurs within a first preset time after the scalpel head leaves the object being cut and the pad. For example, the first preset time is set to 0.5 seconds, and the first preset value is set to 40 degrees Celsius. That is, if the average temperature of the scalpel head drops to more than 40 degrees Celsius within 0.5 seconds, it is determined that the ultrasonic scalpel head stops clamping and opening. The second feature is the average temperature continuously rising feature. As the secondary shearing proceeds, the average temperature rises again. For example, the average temperature is set to occur within a second preset time after the scalpel head contacts the object being cut and the pad. The second preset time is set to 0.5 seconds, meaning the first preset time is 0.5 to 1 second after the scalpel head leaves the object being cut and the pad, and the first preset value is set to 50 degrees Celsius. That is, if the average temperature of the scalpel head rises to more than 50 degrees Celsius within 0.5 to 1 second after the scalpel head leaves the object being cut and the pad, it is determined that the ultrasonic scalpel is shearing the object being cut. If the above two characteristics are met, the ultrasonic scalpel is determined to be in a continuous shearing state.

[0102] As shown in Figure 7, the gasket after 300 shearing operations using the cutting head of the present application's embodiment shows that the gasket was almost undamaged. As shown in Figure 8, the control group, which did not implement any protective measures, showed that the gasket was severely damaged after 300 shearing operations.

[0103] This application provides a temperature-prediction-based ultrasonic scalpel protection method. By predicting the extreme and average temperature trends of the scalpel tip and adaptively judging based on these trends, the method can reduce the output power in a timely manner when shearing is completed or the temperature in the scalpel tip area exceeds the melting point of the gasket. This reduces ultrasonic scalpel wear and extends its service life, effectively protecting the ultrasonic scalpel. During continuous ultrasonic excitation or continuous shearing, the method can further improve the shearing efficiency of the ultrasonic scalpel while reliably protecting the gasket. It adaptively switches between ultrasonic scalpel protection and high-efficiency shearing states, adapting to the operator's operating methods. Compared to methods that protect the scalpel tip based on a single temperature prediction, this application's technical solution can improve the accuracy and reliability of scalpel tip protection.

[0104] In some embodiments, when identifying whether the ultrasonic scalpel is in a connected shearing state, it is not limited to determining it by the average temperature trend, but can also be determined by relevant variables such as voltage values ​​and resonant frequencies that change due to load variations.

[0105] In some embodiments, the first current value is set to 0.7 times the second current value. When the ultrasonic scalpel outputs the first current value, it can successfully complete the shearing operation on the object being cut, and provide better protection for the gasket.

[0106] When an ultrasonic scalpel performs shearing operations, the electrical signal parameters of the ultrasonic scalpel generator exhibit distinct characteristics. The output current is constant, while the output voltage changes with the shearing of the object being cut. Figure 9 shows the resonant frequency and the current-voltage phase difference as a function of shearing. To ensure the ultrasonic scalpel operates at its highest efficiency, the current-voltage phase difference is typically set to 0. This positions the ultrasonic scalpel's operating circuit at its resonant point. As the shearing process continues, Figure 10 shows the output current and output voltage as a function of shearing. The actual impedance changes with the load, and the piezoelectric crystal also changes in real time with the operating temperature.

[0107] In some embodiments, as shown in FIG11, the step of obtaining the predicted shear point of the ultrasonic scalpel includes S1110 to S1160.

[0108] S1110: Obtain the variable parameters of the historical electrical signal of the ultrasonic scalpel generator within a preset time period, and preprocess the variable parameters of the historical electrical signal to ensure that the cutting point of the ultrasonic scalpel cutting the object is within the preset time period.

[0109] During the shearing process, the output voltage of the ultrasonic scalpel changes depending on the material the ultrasonic scalpel head contacts. Specifically, the output voltage is relatively low when the ultrasonic scalpel is shearing the object being cut. As shearing continues and the scalpel head contacts the pad, the output voltage increases.

[0110] The electrical parameters used in this application—current phase value, voltage phase value, target phase value, and resonant frequency—are closely related to changes in the object being cut. Specifically, during the stable shearing process of the ultrasonic scalpel, the difference between the detected current and voltage phase values ​​and the target phase value is approximately zero, and the rate of change of the resonant frequency is relatively constant. As shearing progresses and the scalpel tip contacts the pad, the difference between the current and voltage phase values ​​and the target phase value deviates from zero, the rate of change of the resonant frequency increases, and the waveform exhibits significant fluctuations. Thus, using the resonant frequency as the acquired electrical signal parameter provides a more distinct distinguishing characteristic.

[0111] The third historical electrical signal refers to the output current value, output voltage value, current phase value, voltage phase value, target phase value, and resonant frequency. To obtain training data with higher information content and better feature representation, the third historical electrical signal can be further processed to obtain its variable parameters. For example, the current phase value and voltage phase value can be subtracted to obtain the current-voltage phase difference; the current-voltage phase difference and the target phase value can be subtracted to obtain the difference between the current-voltage phase difference and the target phase difference; and the first derivative of the resonant frequency can be calculated. Thus, the variable parameters of the historical electrical signal are: output current value, output voltage value, current-voltage phase difference, the difference between the current-voltage phase difference and the target phase difference, and the first derivative of the resonant frequency.

[0112] It should be noted that this application collects the current phase value, voltage phase value, target phase value, and resonant frequency of the ultrasonic scalpel generator because these electrical signal parameters are closely related to changes in the object being cut. In practical applications, it is not limited to collecting only these electrical signal parameters. For example, given the differences in the circuit characteristics of ultrasonic scalpel generators, if other electrical signal parameters closely related to changes in the object being cut exist, they can also be used as collected electrical signal parameters. Furthermore, the collected electrical signal parameters can also include multi-dimensional variables such as temperature, resistance, ultrasonic scalpel parameters, or generator parameters collected by sensors.

[0113] In addition, when determining the variable parameters of the third historical electrical signal, the ratio of voltage to current can be calculated to obtain the impedance value, and the product of voltage and current can be calculated to obtain the power value. The impedance value and the power value can then be used as the variable parameters of the third historical electrical signal.

[0114] In the subsequent training of the third and fourth initial models, in order to enable the third and fourth initial models to better learn the deep features of the training data, this application performs scale scaling on the input training data to scale the variable parameters of the historical electrical signals to a similar scale.

[0115] For example, if the resonant frequency is around 55000Hz and the current-voltage phase difference is within ±180°, and the first derivative of the resonant frequency and the current-voltage phase difference are directly input into the third and fourth initial models for training, the third and fourth initial models will have difficulty learning effective features.

[0116] In response, this application employs a scaling method to process the variable parameters of the third historical electrical signal or the third historical electrical signal. For example, the resonant frequency is first reduced by 55000Hz, and then multiplied by a scaling factor of 0.1 to obtain a new frequency variable. In this way, the new frequency variable has the same order of magnitude as the phase difference variable.

[0117] Furthermore, during data acquisition, the electrical signal parameters of the acquired ultrasonic scalpel generator exhibit a certain degree of offset. To avoid the influence of this offset on data characteristics, in some embodiments, firstly, the standard mean and standard deviation of each parameter in the third historical electrical signal are calculated. Then, the standard mean and standard deviation are used to standardize each parameter in the third historical electrical signal. The corresponding model for the second standardization process is as follows:

[0118] The second standardized processing model is as follows: x′ represents each parameter in the third historical electrical signal, μ′ represents the mean of each parameter in the third historical electrical signal, and σ′ represents the standard deviation of each parameter in the third historical electrical signal.

[0119] In some embodiments, the variable parameters of the acquired third historical electrical signal are used for model training. In practical applications, a certain amount of data will be acquired. For example, relevant parameters are collected during multiple shearing processes with an ultrasonic scalpel. The preset time needs to include the time when the object being cut is severed (the moment of the cutting point). For example, if the data acquisition time interval is 10ms, the data acquired during the preset time will be from the 400 data points before the cutting point to the 50 data points after the cutting point.

[0120] In some embodiments, when acquiring the electrical signal of the ultrasonic scalpel generator, a frequency locking process occurs. Therefore, the acquired electrical signal of the ultrasonic scalpel generator is unstable in the initial stage of acquisition. To solve this problem, this application includes the following steps in the preprocessing of the variable parameters of the third historical electrical signal: calculating the average value of each parameter in the variable parameters of the third historical electrical signal in the third time period, and labeling it as the reference parameter for each parameter; the third time period is the beginning time period in the preset time period; and adjusting each parameter in the variable parameters of the historical electrical signal based on the reference parameters. For example, the average value of the parameters acquired in the first 0.5 seconds is calculated, and the average value of the parameters acquired in the first 0.5 seconds is set as the reference. The parameters acquired after 0.5 seconds are subtracted from this reference value to obtain the valid data.

[0121] Because the electrical signal of the ultrasonic scalpel generator is susceptible to various uncertainties such as temperature and load, resulting in an unstable waveform, some embodiments include a step of preprocessing the variable parameters of the third historical electrical signal, which involves processing the variable parameters of the historical electrical signal using a second exponential moving average model. The corresponding second exponential moving average model is: X t ′=β′X t-1 ′+(1-β′)θ t ′.

[0122] Where β′ is the weighting parameter, θ tLet X' be the weight parameters of each parameter in the third historical electrical signal obtained in the t-th update. t Let ' be the moving average of the variable parameters of the third historical electrical signal obtained from the t-th update. For example, using an average sliding window with a window size of 30 to smooth the generated signal does not change the original trend, but it is smoother after removing high-frequency small-amplitude fluctuations. In addition, the variable parameters of the third historical electrical signal can also be processed by moving average, low-pass filtering, polynomial fitting, locally weighted scatter smoothing, or Kalman filtering.

[0123] S1120, mark the results corresponding to the variable parameters of the historical electrical signal in the first time period as true to obtain the first training set; mark the results corresponding to the variable parameters of the third historical electrical signal in the second time period as true to obtain the second training set. The first time period and the second time period are within a preset time period, and the first time period is earlier than the second time period.

[0124] In some embodiments, the data collection time for the first training set is earlier; for example, the variable parameters of the third historical electrical signal in the first time period are data points from 200 to 100 before the cutoff point. Thus, the model trained using the first training set has better predictive accuracy. The data collection time for the second training set is later; for example, the variable parameters of the third historical electrical signal in the second time period are data points from 50 to 50 after the cutoff point. Thus, the model trained using the second training set has more reliable predictive performance.

[0125] It should be noted that after marking the result of the variable parameter corresponding to the third historical electrical signal as true, it is also necessary to mark the results of the variable parameters corresponding to the third historical electrical signals in other stages as false. Specifically, a result of the variable parameter corresponding to the third historical electrical signal being true means that the object being cut was indeed cut; a result of the variable parameter corresponding to the third historical electrical signal being false means that the object being cut was not indeed cut. It should be noted that when a variable parameter is marked as true, the corresponding variable parameter is a real sample; when a variable parameter is marked as false, the corresponding variable parameter is a fake sample.

[0126] In this embodiment, it is necessary to cut a large number of collected real and valid variable parameters and use the cut data to train the model. In order to take advantage of the batch training capability of the training device, the training input data needs to have a uniform length. The step of preprocessing the variable parameters of historical electrical signals includes: obtaining the time-sensitive value at the warning cutoff point; and cutting the training data in the first training set and the second training set based on the time-sensitive value.

[0127] For example, based on the characteristics of the object being cut, the timeliness of the shearing warning must be less than 1 second. Simultaneously, the electrical signals of the ultrasonic scalpel generator have a strong temporal correlation. This application sets the shearing time of the training data in the first and second training sets to 1 second, that is, sets the amount of data with a shearing time of 1 second as the uniform length of the training data. Furthermore, the length of the training data is set to 2. n At that time, the device used to train the model has better parallelism, and this application uses 128 as the uniform length of the training input data. On the other hand, the present invention slides and truncates segments of length 128 in the original data with a step size of 16 as the training input for the subsequent third and fourth initial models, which can effectively increase the number of data samples in the training set, enabling the fusion model to fully learn the deep data features.

[0128] S1130, construct the third initial model and the fourth initial model, and train the third initial model with the first training set to obtain the first model; train the fourth initial model with the second training set to obtain the second model.

[0129] In this application, the first and second models are structurally similar but with different weights. To obtain the first and second models with different weights, after constructing the first and second initial models, the first and second initial models are first pre-trained using the variable parameters of a third historical electrical signal to obtain the basic weights. During the pre-training process, the batch size of the training input is set to 1024, and the learning rate is set to 0.05. Then, the basic weights are loaded, and the first initial model with the loaded basic weights is trained using the training data in the first training set. During the training of the first initial model after loading the basic weights, the batch size of the training input is set to 254, the decay parameter is set to 0.01, the learning rate is set to 0.005, and the cross-entropy loss function is set as follows: in, p represents the label values ​​of the real samples in the first training set. t The predicted probability of the true shearing is the output of the first initial model. p represents the label value of the fake samples in the first training set. f α represents the predicted probability of spurious pruning output by the first initial model, and α is the influence factor on the label values ​​of the real samples in the first training set.

[0130] Furthermore, the basic weights are loaded, and the second initial model with the loaded basic weights is trained using the training data from the second training set. During the training of the second initial model with the loaded basic weights, the batch size of the training input is set to 254, the decay parameter is set to 0.01, the learning rate is set to 0.005, and the cross-entropy loss function is set as follows: in, p represents the label values ​​of the real samples in the second training set. t ′ represents the predicted probability of the true shearing from the output of the second initial model. p represents the label value of the fake samples in the second training set. f ' represents the predicted probability of spurious pruning from the output of the second initial model, and α' represents the influence factor on the real samples in the second training set.

[0131] Among them, using the cross-entropy loss function with an impact factor can increase the loss of the label values ​​of real samples, affect the model's learning of real samples, improve the overall accuracy, and avoid the situation where real samples occupy a very small part of the training data, leading to an imbalance in training labels.

[0132] In this embodiment of the application, when α = 1.2 and α′ = 1.2, the third initial model and the fourth initial model have better training effects. In addition, the loss function is not limited to the cross-entropy loss function, and the mean squared error loss function, the squared loss function, or the absolute value loss function can also be used.

[0133] S1140: When the ultrasonic scalpel is cutting the object, acquire the variable parameters of the real-time electrical signal of the ultrasonic scalpel generator.

[0134] It should be noted that before inputting the variable parameters of the real-time electrical signal into the first and second models, necessary preprocessing of the variable parameters of the real-time electrical signal is required. The preprocessing process is the same as the processing process of the variable parameters of the third historical electrical signal when training the third and fourth initial models. That is, referring to the above-mentioned preprocessing process for the variable parameters of the third historical electrical signal, the same preprocessing process is performed on the variable parameters of the real-time electrical signal before inputting them into the first or second model.

[0135] S1150 takes the variable parameters of the real-time electrical signal as the input of the first model and the second model to obtain the first output of the first model and the second output of the second model.

[0136] The first output and the second output are the probability values ​​that the predicted cut point of the object being cut is true. The probability value that is true can be a probability value in the range of 0-1 or a set of probability values ​​that sum to 1.

[0137] The first output of the first model has better predictive advance capability, meaning it can provide a prediction of the shear point earlier than the actual shear point. The second output of the second model has higher reliability, meaning it provides a more reliable shear point prediction.

[0138] S1160: Obtain the prediction requirement, and based on the prediction requirement, the first output, and the second output, obtain the prediction result at the shearing point.

[0139] Among these, the prediction requirements mainly reflect the operator's expectations for the prediction results. For example, the operator's prediction requirement is to know the predicted cut point time earlier, so as to control the adjustment of the ultrasonic scalpel parameters in advance. Another example is that the operator's requirement is for the cut point prediction results to be more reliable, so as to ensure more accurate operation of the ultrasonic scalpel.

[0140] In practical applications, after using the variable parameters of the real-time electrical signal as input to the first and second models to obtain the first output of the first model and the second output of the second model, the result of the first output can be judged independently. For example, if the first output represents the successful identification of the signal characteristics at the time of cutting, the predicted result of the cutting point time is given, and prompts are given to the operator directly through sound, light, electricity, etc., so that the operator can implement protective measures such as limiting the output power of the ultrasonic scalpel generator.

[0141] Alternatively, after the first output characterizing the signal feature identification at the time of shearing is successful, the result of the second output is judged. If the second output characterizing the signal feature identification at the time of shearing is successful, then the prediction result of the shearing point time is given in a weighted manner according to the prediction requirements.

[0142] The weighted model is: Y = α” × y1 + (1 - α”) × y2, where the weight α” is a set of adjustable values ​​depending on the application scenario. Operators can determine the weight values ​​that reflect the prediction requirements based on the characteristics of the object being cut. For example, setting α” = 0.9 provides stronger predictability when dealing with thicker objects. Alternatively, setting α” = 0.7 provides stronger reliability when dealing with thinner objects.

[0143] In other words, the weight of the predicted demand can be determined by the thickness of the object being cut. For example, first, the thickness of the object being cut is obtained, and then, based on the thickness of the object being cut and a preset correspondence, the weight corresponding to the predicted demand is determined, that is, the value of the predicted demand α is determined. Here, the preset correspondence includes the weight relationship between the thickness of the object being cut and the predicted demand.

[0144] The first or second model provided in this application embodiment may be a combination of one or more models based on machine learning algorithms or deep learning algorithms. More specifically, the machine learning algorithm may include linear regression algorithm, support vector machine algorithm, nearest neighbor algorithm, decision tree algorithm, random forest algorithm, or Naive Bayes algorithm, and the deep learning algorithm may include fully connected neural network, convolutional neural network, generative adversarial network, or recurrent neural network.

[0145] For example, the first model uses a combination of a fully connected neural network model formed from the aforementioned optional range and a recurrent neural network model formed from the above-mentioned recurrent neural network.

[0146] A fully connected neural network (WNN) is a mathematical model inspired by neurons, consisting of multiple interconnected nodes, and can be used to model complex relationships between data. A WNN has a multi-layered structure, with all neurons in each layer interconnected. For example, in some embodiments, the WNN model includes an input layer, hidden layers, and an output layer.

[0147] Furthermore, the fitting ability of a fully connected neural network model is highly correlated with the number of layers and neurons; the more layers and the richer the number of neurons, the stronger the mathematical fitting ability of the fully connected neural network model. In this embodiment, two hidden layers are set, and the number of hidden units in each layer corresponds to the number of output units of the recurrent neural network. Generally, the number of neurons is set to 8, 16, 32, 64, or 128; in this embodiment, the number of neurons is set to 16.

[0148] In this context, considering that the acquired ultrasonic scalpel electrical signals are highly time-series signals, and to better handle the temporal information relationships, in some embodiments, a recurrent neural network (RNN) model with memory capabilities can be used to construct a third or fourth initial model. The RNN model can memorize preceding signals and has a stronger ability to extract features from time-series signals. Thus, a first or second initial model can be constructed using a combination of a RNN model and a fully connected neural network model.

[0149] For example, considering the temporal continuity of the electrical signals of an ultrasonic generator in practical applications, and the stronger correlation of these signals over a short period, in some embodiments, the time interval for acquiring the ultrasonic generator's electrical signals is set to 10 milliseconds. Therefore, the number of loop nodes in the recurrent neural network is designed to be 40. This allows for the simultaneous processing of electrical signals within a 400-millisecond time interval, enhancing the temporal correlation of the output results.

[0150] It should be noted that the first and second models in this application can be various combinations of machine learning algorithm models and deep learning algorithm models, or combinations of algorithm models of the same type. The combination method can be parallel, serial, or cross-functional. As shown in Figure 12, this is a specific method adopted in an embodiment of this application, a model structure in which the first and second models constructed above are fused in parallel. Specifically, the two basic model structures are the same, but the training data are different, resulting in different weight parameters and different discrimination results derived from forward inference.

[0151] This application's technical solution establishes a first model with better predictive accuracy and a second model with better reliability using third historical electrical signal parameters. When an ultrasonic scalpel is cutting an object, it acquires the variable parameters of the real-time electrical signal from the ultrasonic scalpel generator. This yields the first output of the first model and the second output of the second model. Based on the operator's prediction requirements, and according to the prediction requirements, the first output, and the second output, it obtains the predicted cut point time, providing a cut point prediction result that meets the requirements. This avoids situations where the operator, anticipating that the object has been cut, experiences excessively high temperatures in the ultrasonic scalpel tip, thus reducing the ultrasonic scalpel's lifespan.

[0152] This application embodiment also provides an ultrasonic scalpel protection device based on temperature prediction, including: a temperature prediction module and an adjustment module. The temperature prediction module is used to predict the extreme temperature value and average temperature trend of the scalpel tip when the ultrasonic scalpel is cutting an object; the adjustment module is used to adjust the output current of the ultrasonic scalpel generator to a first current if the extreme temperature value is greater than or equal to a first temperature threshold; and to obtain the ultrasonic scalpel cutting point prediction result if the extreme temperature value is less than the first temperature threshold but greater than or equal to a second temperature threshold; if the cutting point prediction result is true, adjust the output current of the ultrasonic scalpel generator to a first current, where the first temperature threshold is greater than the second temperature threshold; and further, after adjusting the output current of the ultrasonic scalpel generator to the first current, if the average temperature trend indicates that the ultrasonic scalpel is in a continuous cutting state, adjust the output current of the ultrasonic scalpel generator to a second current, where the second current is greater than the first current.

[0153] This application provides a method and apparatus for protecting an ultrasonic scalpel based on temperature prediction. By predicting the extreme and average temperature trends of the scalpel tip and adaptively judging based on these trends, the output power can be reduced in a timely manner when shearing is completed or the temperature in the scalpel tip area exceeds the melting point of the gasket. This reduces ultrasonic scalpel wear and extends its service life, effectively protecting the ultrasonic scalpel. During continuous ultrasonic excitation or continuous shearing, the shearing efficiency of the ultrasonic scalpel can be further improved while reliably protecting the gasket. The method adaptively switches between ultrasonic scalpel protection and high-efficiency shearing states, adapting to the operator's operating methods. Compared to methods that protect the scalpel tip based on a single temperature prediction, this application's technical solution can improve the accuracy and reliability of scalpel tip protection.

Claims

1. A method for protecting an ultrasonic scalpel based on temperature prediction, characterized in that, include: Predicting the extreme and average temperature trends of the ultrasonic scalpel head when shearing an object; If the extreme temperature value is greater than or equal to the first temperature threshold, then the output current of the ultrasonic scalpel generator is adjusted to the first current. If the extreme temperature value is less than the first temperature threshold and greater than or equal to the second temperature threshold, the predicted shear point of the ultrasonic scalpel is obtained. If the predicted shear point is true, the output current of the ultrasonic scalpel generator is adjusted to the first current, and the first temperature threshold is greater than the second temperature threshold. After adjusting the output current of the ultrasonic scalpel generator to the first current, if it is determined that the ultrasonic scalpel is in a continuous shearing state based on the average temperature trend, then the output current of the ultrasonic scalpel generator is adjusted to the second current, which is greater than the first current.

2. The ultrasonic scalpel protection method based on temperature prediction according to claim 1, characterized in that, The step of determining that the ultrasonic scalpel is in a continuous shearing state based on the average temperature trend includes: If the average temperature drop of the blade head is greater than the first preset value within a first preset time period, and the average temperature of the blade head rises to a value greater than the second preset value within a second preset time period, then the ultrasonic scalpel is determined to be in a continuous shearing state, wherein the second preset time period is later than the first preset time period.

3. The ultrasonic scalpel protection method based on temperature prediction according to claim 1, characterized in that, In the case of ultrasonic scalpel shearing an object, the step of predicting the extreme and average temperature trends of the ultrasonic scalpel includes: When an ultrasonic scalpel is cutting an object, obtain the output voltage, output current, first derivative of the resonant frequency, and voltage-current phase difference of the ultrasonic scalpel generator. The output voltage, output current, first derivative of resonant frequency, and voltage-current phase difference are input into a pre-established extreme temperature prediction model to obtain the extreme temperature output by the extreme temperature prediction model.

4. The ultrasonic scalpel protection method based on temperature prediction according to claim 3, characterized in that, Before predicting the extreme and average temperature trends of the ultrasonic scalpel in the case of ultrasonic scalpel shearing the object being cut, the method further includes: The output voltage, output current, first derivative of resonant frequency, and voltage-current phase difference of the ultrasonic scalpel generator at the same historical moment are obtained, as well as the corresponding temperature extreme value at the same historical moment. A first initial model is established, with the output voltage, output current, first derivative of resonant frequency and voltage-current phase difference at the same historical moment as the input of the first initial model, and the temperature extreme value corresponding to the same historical moment as the output of the first initial model. The first initial model is trained to obtain the extreme temperature prediction model.

5. The ultrasonic scalpel protection method based on temperature prediction according to claim 1, characterized in that, In the case of ultrasonic scalpel shearing an object, the step of predicting the extreme and average temperature trends of the ultrasonic scalpel includes: When an ultrasonic scalpel is cutting an object, the phase difference between the output current and voltage current of the ultrasonic scalpel generator is obtained. The phase difference between the output current and the voltage current is input into a pre-established temperature trend prediction model to obtain the average temperature trend output by the temperature trend prediction model.

6. The ultrasonic scalpel protection method based on temperature prediction according to claim 5, characterized in that, Before predicting the extreme and average temperature trends of the ultrasonic scalpel in the case of ultrasonic scalpel shearing the object being cut, the method further includes: Obtain the phase difference between the output current and voltage of the ultrasonic scalpel generator at the same historical moment, as well as the average temperature at the same historical moment; A second initial model is established, with the phase difference between the output current and voltage current at the same historical moment as the input of the second initial model, and the average temperature corresponding to the same historical moment as the output of the second initial model. The second initial model is trained to obtain the temperature trend prediction model.

7. The ultrasonic scalpel protection method based on temperature prediction according to claim 1, characterized in that, The step of obtaining the predicted shear point of the ultrasonic scalpel includes: The variable parameters of the third historical electrical signal of the ultrasonic scalpel generator during a preset time period are obtained, and the variable parameters of the third historical electrical signal are preprocessed, wherein the cutting point of the ultrasonic scalpel cutting the object is always within the preset time period. The results corresponding to the variable parameters of the third historical electrical signal in the first time period are marked as true to obtain the first training set; the results corresponding to the variable parameters of the third historical electrical signal in the second time period are marked as true to obtain the second training set. The first time period and the second time period are within a preset time period, and the first time period is earlier than the second time period. Construct a third initial model and a fourth initial model, and train the third initial model with the first training set to obtain the first model; train the fourth initial model with the second training set to obtain the second model; When cutting an object with an ultrasonic scalpel, obtain the variable parameters of the real-time electrical signal of the ultrasonic scalpel generator; The variable parameters of the real-time electrical signal are used as inputs to the first model and the second model to obtain the first output of the first model and the second output of the second model. Obtain the prediction requirement, and based on the prediction requirement, the first output, and the second output, obtain the prediction result for the shearing point time.

8. The ultrasonic scalpel protection method based on temperature prediction according to claim 6, characterized in that, The step of obtaining the predicted demand includes: Get the thickness of the object being cut; Based on the thickness of the object being cut and a preset correspondence, the weight corresponding to the predicted demand is determined. The preset correspondence includes the weight relationship between the thickness of the object being cut and the predicted demand.

9. The ultrasonic scalpel protection method based on temperature prediction according to claim 7, characterized in that, The step of preprocessing the variable parameters of the third historical electrical signal includes: Calculate the average value of each parameter in the variable parameters of the third historical electrical signal in the third time period, and mark it as the reference parameter of each parameter. The third time period is the start time period in the preset time period. Based on the baseline parameters of each parameter, the values ​​of each parameter in the variable parameters of the third historical electrical signal are adjusted.

10. An ultrasonic scalpel protection device based on temperature prediction, characterized in that, The temperature-prediction-based ultrasonic scalpel protection device is used to perform the temperature-prediction-based ultrasonic scalpel protection method according to any one of claims 1-9, wherein the temperature-prediction-based ultrasonic scalpel protection device comprises: The temperature prediction module is used to predict the extreme and average temperature trends of the ultrasonic scalpel head when cutting an object. An adjustment module is used to adjust the output current of the ultrasonic scalpel generator to a first current if the extreme temperature value is greater than or equal to a first temperature threshold. And, if the extreme temperature value is less than a first temperature threshold and greater than or equal to a second temperature threshold, then obtain the shearing point prediction result of the ultrasonic scalpel; if the shearing point prediction result is true, then adjust the output current of the ultrasonic scalpel generator to a first current, wherein the first temperature threshold is greater than the second temperature threshold. Furthermore, it is also used to adjust the output current of the ultrasonic scalpel generator to a second current, wherein the second current is greater than the first current, after adjusting the output current of the ultrasonic scalpel generator to a first current, if the average temperature trend determines that the ultrasonic scalpel is in a continuous shearing state.

Images