Energy output control system based on skin tension feedback and treatment equipment

Abstract

The invention relates to the technical field of medical beauty, and particularly discloses an energy output control system and treatment equipment based on skin tension feedback, and the system comprises a treatment head which is used for enabling energy to act on skin; the skin tension sensor is used for accurately measuring skin tension data of the skin surface and converting the skin tension data into digital signals; the data acquisition module is used for acquiring the skin tension data output by the skin tension sensor, preprocessing the skin tension data and transmitting the preprocessed skin tension data to the central control unit; the central control unit is used for extracting and analyzing key features of the skin tension data, performing nonlinear transformation and feature learning on the key features based on a deep neural network model, automatically mining potential modes and features in the data, and predicting a current most suitable energy output value through linear combination; and the energy output device is used for outputting energy to the treatment head according to the energy output value predicted by the central control unit.

Description

Technical Field

[0001] This invention relates to the field of medical aesthetics technology, specifically to an energy output control system and treatment device based on skin tension feedback. Background Technology

[0002] In the field of medical aesthetic devices today, traditional energy output control systems are widely used in various treatment methods, such as ultrasound therapy, laser therapy, radiofrequency therapy, photon therapy, shockwave therapy, and microwave therapy. However, these energy output control systems mainly rely on fixed parameters preset in a program to regulate energy output, which has limitations that cannot be ignored:

[0003] The human body's physiological state is constantly changing during treatment. Taking ultrasound cosmetic treatment as an example, as the treatment progresses, the skin undergoes a series of changes due to the energy, including increased temperature and changes in water content caused by evaporation, which in turn affect the skin's ability to absorb and tolerate energy. However, traditional systems operate according to preset programs and cannot perceive these dynamic changes in real time. If the patient's skin becomes more sensitive after the initial treatment, the preset energy output may be too high, causing adverse reactions such as skin burns and redness; conversely, if the energy output is too low, it will be difficult to achieve the expected treatment effect, prolonging the treatment cycle and increasing the patient's time and financial costs.

[0004] Patients exhibit significant differences in physiological characteristics, encompassing skin type (e.g., dry, oily, normal), thickness, and tissue structure. For example, dry skin has low moisture content and relatively slow heat dissipation, resulting in different energy absorption and tolerance compared to oily skin. Elderly skin, due to collagen loss, has lower elasticity and a slower metabolic rate than younger individuals. Traditional pre-designed procedures often fail to adequately consider these individual differences, typically employing a more conservative energy delivery strategy. While this can mitigate serious side effects to some extent, for patients with good skin tolerance, conservative energy delivery may not fully stimulate the therapeutic effect, reducing treatment efficiency and potentially requiring more treatments to achieve the desired results. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an energy output control system and treatment device based on skin tension feedback. Based on precise information from skin tension feedback, an intelligent algorithm enables real-time dynamic adjustment of energy output, thus solving the problems in the prior art.

[0006] The present invention provides an energy output control system based on skin tension feedback, comprising:

[0007] The treatment head is used to apply energy to the skin;

[0008] Skin tension sensors are evenly distributed in the area where the treatment head contacts the skin to accurately measure skin tension data on the skin surface and convert the skin tension data into digital signals;

[0009] The data acquisition module is used to acquire the skin tension data output by the skin tension sensor, preprocess the skin tension data, and transmit the preprocessed skin tension data to the central control unit.

[0010] The central control unit is used to extract and analyze the key features of the skin tension data, and to perform nonlinear transformation and feature learning on the key features based on a deep neural network model, automatically mining the potential patterns and features in the data, and predicting the most suitable energy output value at the moment through linear combination.

[0011] An energy output device is used to output energy to the treatment head based on the energy output value predicted by the central control unit.

[0012] The data acquisition module preprocesses the skin tension data, including:

[0013] The skin tension data collected within the first time unit is averaged and filtered to remove data fluctuations caused by friction and undulation of the treatment head on the skin.

[0014] The average filtered skin tension data is then subjected to low-pass filtering to remove high-frequency noise that is not related to changes in skin tension.

[0015] As a preferred approach, when performing average filtering, whenever new skin tension data is generated, the filtering time window is shifted back by one first time unit to ensure that the skin tension data within the latest first time unit is filtered each time.

[0016] As a preferred embodiment, the data acquisition module also pre-stores a skin tension data calibration curve to supplement the data that the skin tension sensor may have missed during a certain period of time due to human error in operating the treatment head or insufficient application of coupling agent on the treatment head.

[0017] As a preferred approach, when performing data completion, the nearest known data point to the missing data point is obtained, and the information of these two points is substituted into the quadratic polynomial of the skin tension data calibration curve to estimate the tension data of the missing data point.

[0018] As a preferred embodiment, the data acquisition module further includes the following steps for preprocessing the skin tension data: after completing average filtering, low-pass filtering, and data completion, selecting matching skin tension data based on the skin tension data calibration curve as the preprocessed skin tension data and transmitting it to the central control unit.

[0019] As a preferred embodiment, the central control unit extracts key features of the skin tension data, including the rate of change of skin tension, mean, standard deviation, median, peak value, waveform features, and time-frequency features, and performs statistical analysis, time-domain analysis, and frequency-domain analysis on the extracted key feature data.

[0020] As a preferred embodiment, the deep neural network model includes an input layer, a hidden layer, and an output layer; wherein, the input layer is used to receive skin tension data after feature extraction and detailed individual information of different patients; the hidden layer performs complex nonlinear transformations and feature learning on the data received by the input layer through a nonlinear activation function to automatically mine potential patterns and features in the data; the output layer predicts the most suitable energy output value of the energy output device at the current time based on the features learned by the hidden layer through linear combination.

[0021] As a preferred embodiment, the central control unit utilizes massive amounts of clinical treatment data to perform deep training on the deep neural network model. The clinical treatment data covers changes in skin tension, treatment effects, and corresponding energy output parameters of patients of different ages, genders, and skin types under various treatment scenarios. By continuously adjusting the weights and biases of the neural network, the deep neural network model can accurately predict energy output values ​​that are highly matched with the physiological state of the skin.

[0022] The present invention also provides a treatment device comprising an energy output control system based on skin tension feedback according to any of the above-described embodiments.

[0023] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0024] (1) By monitoring skin tension in real time and accurately, and using this as feedback to precisely adjust the energy output, the system can closely match the physiological changes of the patient's skin during the treatment process, so that the energy output can perfectly match the actual needs of the skin.

[0025] (2) It effectively avoids the problem of excessively high or low energy output that may be caused by traditional preset programs, fundamentally reducing the risk of adverse reactions and side effects during treatment. By dynamically adjusting the energy output in real time according to skin tension, it ensures that the skin is always within a safe energy tolerance range, comprehensively protecting the patient's health and allowing the patient to enjoy effective treatment under safe conditions.

[0026] (3) By fully integrating individual patient characteristics and detailed treatment history data, the energy output control algorithm is deeply optimized to tailor a unique personalized treatment plan for each patient. Different patients have significantly different skin responses and tolerance to energy. Personalized treatment based on skin tension feedback can accurately meet the special needs of patients, greatly improve patient satisfaction and treatment compliance, and make patients more willing to actively cooperate with treatment.

[0027] (4) Precise energy output control can achieve the expected therapeutic effect in a shorter time, significantly reduce unnecessary treatment times and time, improve the patient's recovery speed, reduce the patient's physical and psychological burden, and at the same time reduce medical costs and improve the utilization efficiency of medical resources. Attached Figure Description

[0028] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0029] Figure 1 This is a schematic diagram of the system structure of an energy output control system based on skin tension feedback according to an embodiment of the present invention.

[0030] In the diagram: 1. Central control unit; 2. Energy output device; 3. Treatment head; 4. Data acquisition module; 5. Skin tension sensor. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms "a" and "the" as used in the embodiments of this application are also intended to include the plural forms unless the context clearly indicates otherwise. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0033] In the description of this application, "multiple" and "several" mean two or more. Unless otherwise explicitly defined, the term "and / or" as used herein is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Furthermore, the character " / " in this document generally indicates that the preceding and following related objects are in an "or" relationship.

[0034] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0035] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a product or system comprising a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a product or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the product or system that includes said element.

[0036] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0037] like Figure 1 As shown, the present invention provides an energy output control system based on skin tension feedback, comprising: a central control unit 1, an energy output device 2, a treatment head 3, a data acquisition module 4, and a skin tension sensor 5, wherein:

[0038] The central control unit 1 is electrically connected to the energy output device 2 and is used to control the energy output parameters of the energy output device 2. The treatment head 3 is connected to the energy output device 2 and is used to apply the energy output by the energy output device 2 to the skin.

[0039] Unlike traditional energy output control systems, in this invention, skin tension sensors 5 are evenly arranged in the area where the treatment head 3 contacts the skin to accurately measure skin tension data on the skin surface and convert the skin tension data into digital signals; data acquisition module 4 is electrically connected to skin tension sensor 5 to acquire the skin tension data output by the skin tension sensor, preprocess the skin tension data, and transmit the preprocessed skin tension data to the central control unit 1.

[0040] The central control unit 1 is electrically connected to the data acquisition module 4. It is used to receive the skin tension data after preprocessing by the data acquisition module 4, extract and analyze the key features of the skin tension data, and perform nonlinear transformation and feature learning on the key features based on a deep neural network model to automatically mine the potential patterns and features in the data, and predict the most suitable energy output value at the current time through linear combination. The energy output device 2 outputs energy to the treatment head 3 according to the energy output value predicted by the central control unit 1.

[0041] In this invention, the skin tension sensor 5 is a piezoresistive skin tension sensor based on MEMS (Micro-Electro-Mechanical Systems) technology. This type of sensor has significant advantages such as small size, extremely high sensitivity, and extremely fast response speed, enabling precise measurement of extremely small tension changes on the skin surface. Its core sensing element is made of silicon-based material, and the piezoresistive element is fabricated on a silicon wafer using advanced microfabrication technology. When skin tension acts on the surface of the skin tension sensor 5, the piezoresistive element will change its resistance value due to stress, thereby converting the skin tension data into a digital signal (electrical signal) that is easy to detect and process. For example, when the skin tension change range is 0-10 N / cm², the resistance change rate of the skin tension sensor 5 can reach 0.1% / N / cm², ensuring accurate sensing of skin tension changes.

[0042] The data acquisition module 4 performs a series of preprocessing steps on the skin tension data signal generated by the skin tension sensor 5: First, a high-precision instrumentation amplifier is used to amplify the acquired skin tension electrical signal, amplifying the weak original signal to an acceptable amplitude range suitable for subsequent processing.

[0043] Then, the skin tension data collected within the first time unit is averaged and filtered to remove data fluctuations caused by friction and undulation of the treatment head 3 on the skin. Whenever new skin tension data is generated, the filtering time window is shifted forward by one first time unit to ensure that the filtered data is the latest skin tension data within the first time unit. For example, the data acquisition module 4 averages and filters the skin tension data collected within 200ms to make the data more stable and remove data fluctuations caused by friction and undulation of the handle on the skin. Whenever new data is available, the time window is shifted forward by 200ms to ensure that the filtered data is the latest data within the last 200ms, thus ensuring the real-time performance and accuracy of data acquisition.

[0044] Data acquisition module 4 performs low-pass filtering on the averaged skin tension data to remove high-frequency noise that is not related to skin tension changes and is generated during the process of skin tension variation. By designing a specific frequency response, high-frequency signals are selectively attenuated (only low-frequency useful signals are allowed to pass), which can specifically remove high-frequency noise that was not cleaned by the average filtering, while reducing the high-frequency loss of useful signals, because skin tension change is a slow process and the high-frequency part is not caused by skin tension changes.

[0045] The data acquisition module 4 also pre-stores a skin tension data calibration curve to supplement missing data from the skin tension sensor during a certain period due to special circumstances. Specifically, by inputting multiple sets of skin tension data from different skin areas and skin tension sensor data into the data acquisition module 4, the module obtains the skin tension data calibration curve through quadratic linear fitting. During treatment, issues such as the doctor's manipulation technique of the treatment head 3 or insufficient application of coupling agent may cause the skin tension sensor 5 to fail to acquire skin tension data during a certain period, resulting in data gaps. The data acquisition module 4 uses interpolation to fill in the missing parts to ensure data continuity. During data completion, the module obtains the nearest known data point to the missing data point and substitutes the information from these two points into the quadratic polynomial of the skin tension data calibration curve to estimate the tension data at the missing data point.

[0046] After completing averaging, low-pass filtering, and data completion, the data acquisition module 4 selects matching skin tension data as preprocessed data based on the skin tension data calibration curve and transmits it to the central control unit. For example, facial and abdominal skin tension data differ, therefore, the skin tension data calibration curves also differ. The data acquisition module 4 selects the corresponding skin tension data calibration curve based on the treatment area to eliminate abnormal data and further improve the accuracy of skin tension data acquisition.

[0047] After the data acquisition module 4 sends the preprocessed skin tension data to the central control unit 1, the central control unit 1 extracts key features of the skin tension data. These key features include the rate of change of skin tension, mean, standard deviation, median, peak value, waveform characteristics, and time-frequency characteristics. The extracted key feature data is then subjected to statistical analysis, time-domain analysis, and frequency-domain analysis. Specifically, the rate of change of skin tension represents the amount of change in skin tension per unit time, reflecting the speed of change in skin condition. For example, in the early stages of treatment, a rapid rate of change in skin tension may indicate a strong response of the skin to the initial energy input, suggesting that the system needs to closely monitor subsequent changes and may adjust the energy output in a timely manner. The rate of change of skin tension can be obtained by performing a difference operation on the skin tension values ​​at adjacent time points and dividing by the time interval.

[0048] Peak values ​​represent the maximum skin tension reached over a given period. The appearance of a peak may indicate that the skin is experiencing significant tension at a particular moment, which could be related to the concentrated effect of treatment energy or the skin's own physiological response. For example, during laser treatment, when an energy pulse is applied to the skin, it may cause a momentary increase in skin tension, forming a peak. Recording these peak values ​​and the timing of their occurrence can help the system analyze the relationship between treatment energy and skin response, providing a reference for optimizing subsequent energy output.

[0049] The mean represents the average skin tension over a period of time, reflecting the overall tension level of the skin during that time. By calculating the mean, some random fluctuations can be eliminated, resulting in a relatively stable indicator for assessing the skin's condition. For example, if the mean skin tension consistently increases throughout the treatment, it may indicate that the skin's tolerance to the current energy output is gradually increasing, and the system may consider appropriately increasing the energy output to enhance the treatment effect; conversely, if the mean decreases, it may be necessary to reduce the energy output to avoid damaging the skin.

[0050] Time-domain analysis reveals the change of tension over time, while frequency-domain analysis reveals the frequency components of the tension and periodic vibrations. This invention employs wavelet analysis to perform both time-domain and frequency-domain analyses on the extracted key feature data. Wavelet analysis is a time-frequency analysis method that decomposes a signal into wavelet coefficients of different frequencies, enabling simultaneous analysis of the signal in both the time and frequency domains.

[0051] Several features can be extracted from the calculated wavelet coefficients: for example, the energy distribution of the wavelet coefficients at different scales, which reflects the degree of energy concentration of the signal at different frequency components. If the energy of the wavelet coefficients at a certain scale is high, it indicates that the frequency component plays an important role in changes in skin tension.

[0052] Furthermore, statistical features of wavelet coefficients, such as mean and variance, can be extracted. These features can further describe the signal's variation characteristics at different time scales. Combining these time-frequency features with conventional features can provide richer and more accurate information for energy output control algorithms, enabling the algorithms to more accurately determine the physiological state of the skin and thus achieve more optimized energy output control.

[0053] For example, when the time-frequency features obtained by combining wavelet analysis reveal that the changes in skin tension in a certain frequency range are closely related to the treatment effect, the energy output control algorithm can specifically adjust parameters such as the frequency or pulse width of the energy output to better match the physiological needs of the skin and improve the treatment effect.

[0054] The central control unit 1 is equipped with a deep neural network model, which is trained using a large amount of historical clinical treatment data. This historical clinical treatment data is a large amount of clinical data collected by doctors through long-term clinical accumulation. It covers the changes in skin tension, treatment effects and corresponding energy output parameters of patients of different ages, genders and skin types in various treatment scenarios. By continuously adjusting the weights and biases of the neural network, the deep neural network model can accurately predict the energy output value that is highly matched with the physiological state of the skin.

[0055] After the deep neural network model is trained, the central control unit 1 performs nonlinear transformation and feature learning on the extracted key features based on the deep neural network model, automatically mines the potential patterns and features in the data, and predicts the most suitable energy output value at the moment through linear combination.

[0056] Specifically, the deep neural network model includes an input layer, a hidden layer, and an output layer. The input layer receives skin tension data after feature extraction, as well as detailed individual information of different patients. The hidden layer performs complex nonlinear transformations and feature learning on the data received by the input layer through a nonlinear activation function, automatically mining potential patterns and features in the data. The output layer predicts the most suitable energy output value for the energy output device based on the features learned by the hidden layer through linear combination.

[0057] The present invention also provides a treatment device comprising an energy output control system based on skin tension feedback according to any of the above-described embodiments.

[0058] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0059] (1) By monitoring skin tension in real time and accurately, and using this as feedback to precisely adjust the energy output, the system can closely match the physiological changes of the patient's skin during treatment, ensuring a perfect match between the energy output and the actual needs of the skin. For example, in laser freckle removal treatment, the system can adjust the laser energy promptly and accurately based on the real-time changes in skin tension, more effectively breaking down pigmented tissue while minimizing damage to surrounding normal skin, significantly improving treatment effectiveness, enabling patients to recover faster, and reducing post-treatment complications.

[0060] (2) It effectively avoids the problem of excessively high or low energy output that may be caused by traditional preset programs, fundamentally reducing the risk of adverse reactions and side effects during treatment. By dynamically adjusting the energy output in real time according to skin tension, it ensures that the skin is always within a safe energy tolerance range, comprehensively protecting the patient's health. For example, in ultrasound cosmetic treatment, it can prevent skin burns, blisters, and other problems caused by excessive energy, allowing patients to enjoy effective treatment under safe conditions.

[0061] (3) By fully integrating individual patient characteristics and detailed treatment history data, the energy output control algorithm is deeply optimized to tailor a unique personalized treatment plan for each patient. Different patients exhibit significant differences in their skin's response to and tolerance to energy. Personalized treatment based on skin tension feedback can precisely meet the specific needs of patients, greatly improving patient satisfaction and treatment compliance. For example, for patients with sensitive skin, the system can employ a gentler and more precise energy regulation strategy, ensuring treatment effectiveness while avoiding adverse reactions such as allergies, making patients more willing to actively cooperate with treatment.

[0062] (4) Precise energy output control can achieve the expected therapeutic effect in a shorter time, significantly reduce unnecessary treatment times and time, improve the patient's recovery speed, reduce the patient's physical and psychological burden, and at the same time reduce medical costs and improve the utilization efficiency of medical resources.

[0063] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0064] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. An energy output control system based on skin tension feedback, characterized in that, include: The treatment head is used to apply energy to the skin; Skin tension sensors are evenly distributed in the area where the treatment head contacts the skin to accurately measure skin tension data on the skin surface and convert the skin tension data into digital signals; The data acquisition module is used to acquire the skin tension data output by the skin tension sensor, preprocess the skin tension data, and transmit the preprocessed skin tension data to the central control unit. The central control unit is used to extract and analyze the key features of the skin tension data, and to perform nonlinear transformation and feature learning on the key features based on a deep neural network model, automatically mining the potential patterns and features in the data, and predicting the most suitable energy output value at the moment through linear combination. An energy output device is used to output energy to the treatment head based on the energy output value predicted by the central control unit. The data acquisition module preprocesses the skin tension data, including: The skin tension data collected within the first time unit is averaged and filtered to remove data fluctuations caused by friction and undulation of the treatment head on the skin. The average filtered skin tension data is then subjected to low-pass filtering to remove high-frequency noise that is not related to changes in skin tension.

2. The energy output control system based on skin tension feedback according to claim 1, characterized in that, When performing average filtering, whenever new skin tension data is generated, the filtering time window is shifted back by one of the first time units to ensure that the skin tension data within the latest first time unit is filtered each time.

3. The energy output control system based on skin tension feedback according to claim 2, characterized in that, The data acquisition module also has a pre-stored skin tension data calibration curve, which is used to supplement the data that the skin tension sensor may have missed during a certain period of time due to human error in operating the treatment head or insufficient application of coupling agent on the treatment head.

4. The energy output control system based on skin tension feedback according to claim 3, characterized in that, When performing data completion, the nearest known data point to the missing data point is obtained, and the information of these two points is substituted into the quadratic polynomial of the skin tension data calibration curve to estimate the tension data of the missing data point.

5. The energy output control system based on skin tension feedback according to claim 3, characterized in that, The data acquisition module further preprocesses the skin tension data by: after completing average filtering, low-pass filtering and data completion, selecting matching skin tension data according to the skin tension data calibration curve as the preprocessed skin tension data and transmitting it to the central control unit.

6. The energy output control system based on skin tension feedback according to claim 1, characterized in that, The central control unit extracts key features of the skin tension data, including the rate of change of skin tension, mean, standard deviation, median, peak value, waveform features, and time-frequency features, and performs statistical analysis, time-domain analysis, and frequency-domain analysis on the extracted key feature data.

7. The energy output control system based on skin tension feedback according to claim 1 or 6, characterized in that, The deep neural network model includes an input layer, a hidden layer, and an output layer. The input layer receives skin tension data after feature extraction and detailed individual information of different patients. The hidden layer performs complex nonlinear transformations and feature learning on the data received by the input layer through a nonlinear activation function to automatically mine potential patterns and features in the data. The output layer predicts the most suitable energy output value of the energy output device based on the features learned by the hidden layer through linear combination.

8. The energy output control system based on skin tension feedback according to claim 1, characterized in that, The central control unit uses massive amounts of clinical treatment data to train the deep neural network model. The clinical treatment data covers changes in skin tension, treatment effects, and corresponding energy output parameters of patients of different ages, genders, and skin types in various treatment scenarios. By continuously adjusting the weights and biases of the neural network, the deep neural network model can accurately predict energy output values ​​that are highly matched with the physiological state of the skin.

9. A treatment device, characterized in that, Including the energy output control system based on skin tension feedback as described in any one of claims 1-8.

Images