Ultra-short wave therapeutic apparatus production consistency control method and system

Abstract

The invention relates to the technical field of medical equipment manufacturing. More specifically, the invention relates to an ultra-short wave therapeutic apparatus production consistency control method and system, and the method comprises the steps: building a virtual digital twin model according to the design parameters of an ultra-short wave therapeutic apparatus, and the model comprises a circuit model, an electromagnetic field model and a thermal model; various parameters of production equipment and products are collected in real time, and the collected parameters are compared with theoretical parameters in the digital twinborn model to determine the difference between the parameters; adjusting the parameters of the production equipment according to the difference so as to compensate the parameter drift of the component; and receiving radio frequency power data of the directional coupler, and calling an iterative learning control algorithm to optimize the driving voltage curve so as to realize dynamic adjustment of the radio frequency power. According to the scheme, the consistency and reliability of products are effectively improved, the production process is optimized, and quality tracing is achieved.

Description

Technical Field

[0001] The present invention generally relates to the field of medical device manufacturing technology. More specifically, the present invention relates to a method and system for controlling the production consistency of an ultrashort wave therapeutic device. Background Art

[0002] An ultrashort wave therapy device is a medical device that uses high-frequency electromagnetic waves for physical therapy, primarily for relieving pain, promoting tissue repair, and reducing inflammation. Resembling a small radio or microwave oven, it consists of a main unit, output feeder cables, and electrode plates of various specifications. During operation, the electrodes transmit electromagnetic wave energy to specific parts of the human body. This treatment method is non-invasive and does not directly contact the skin. Instead, it uses electromagnetic fields to generate a mild thermal effect, helping to improve local blood circulation and accelerate the resolution of inflammation. Ultrashort wave therapy devices are widely used in rehabilitation, orthopedics, and sports medicine departments, and are particularly suitable for treating common problems such as joint sprains, muscle strains, and chronic inflammation.

[0003] In the traditional production process of ultrashort wave therapy devices, there are the following technical problems that need to be solved:

[0004] (1) Component parameter discreteness: The tolerances of components such as capacitors and inductors in RF modules are large, causing the device output power to fluctuate by more than ±15%, seriously affecting the stability of treatment effects. For example, the actual inductance value of a batch of inductors deviated by 10% from the nominal value, causing the RF output power to deviate by 12% from the set value.

[0005] (2) Assembly process error: The mechanical clearance between the electrode and the treatment head is difficult to accurately control, affecting the uniformity of energy radiation. When the clearance exceeds 0.1mm, the unevenness of energy distribution on the surface of the treatment head can reach more than 20%.

[0006] (3) Insufficient test coverage: Manual testing methods cannot effectively detect hidden faults, such as harmonic distortion of high-frequency signals. In previous tests, there have been cases where harmonic distortion exceeding -30dBc was not detected, resulting in tissue thermal damage during clinical use.

[0007] In summary, the production of traditional ultrashort wave therapy devices has problems such as discrete component parameters, assembly process errors and insufficient test coverage, which lead to large fluctuations in output power, uneven energy radiation and difficult detection of hidden faults.

[0008] Therefore, there is an urgent need for a method that can solve the current problems of poor production stability and uneven quality of ultrashort wave therapeutic devices in order to promote the development of the medical industry. Summary of the Invention

[0009] In order to solve the technical problems of poor production stability and uneven quality of the above-mentioned ultrashort wave therapeutic device, the present invention provides solutions in the following aspects.

[0010] In a first aspect, the present invention provides a method for controlling the production consistency of an ultrashort wave therapeutic device, comprising: establishing a virtual digital twin model based on the design parameters of the ultrashort wave therapeutic device, the model including a circuit model, an electromagnetic field model, and a thermal model; collecting various parameters of production equipment and products in real time, and comparing the collected parameters with the theoretical parameters in the digital twin model to determine the differences between the two; adjusting the parameters of the production equipment based on the differences to compensate for component parameter drift; receiving RF power data of a directional coupler, calling an iterative learning control algorithm to optimize the driving voltage curve, and realizing dynamic adjustment of the RF power.

[0011] This invention lays the foundation for subsequent production through modular design and rigorous component selection during the design phase. It also employs a closed-loop calibration system based on digital twins to compensate for component parameter drift in real time. Iterative learning algorithms achieve rapid convergence, gradually reducing power output errors and enabling high-precision calibration. Automated assembly and online real-time calibration during the manufacturing process ensure process stability.

[0012] In one embodiment, the various parameters include component information, process parameters, and test results, and the various parameters are recorded in the blockchain to form an unalterable production record.

[0013] This invention ensures that the data cannot be tampered with by writing component information, process parameters, etc. into the blockchain, thereby improving data credibility. At the same time, the blockchain records are accurate to specific content, reducing quality disputes.

[0014] In one embodiment, the digital twin model also includes a mechanical structure model and a material property model, which are used to simulate the performance of the ultrashort wave therapeutic device under different working conditions.

[0015] The present invention integrates mechanical structure models and material property models in digital twins to simulate performance under different working conditions (such as high humidity and vibration). It can predict the risk of failure in extreme environments in advance, and can promptly discover defects through simulation, thereby optimizing product structure. At the same time, it can reduce the number of physical prototype tests and reduce R&D costs.

[0016] In one embodiment, adjusting the parameters of the device includes automatically adjusting welding parameters, assembly position, and circuit parameters to compensate for component parameter drift and process errors.

[0017] The present invention can effectively improve the process stability of the product by adjusting various parameters of the equipment and compensating for parameter drift and process errors of components. At the same time, it dynamically corrects circuit parameters through adaptive compensation to ensure the stability of output power.

[0018] In one embodiment, the iterative learning control algorithm includes: initializing system parameters and control parameters; applying an initial control signal of the ultrashort wave therapeutic device and collecting system output; calculating the error between the actual output and the expected output; updating the control signal based on the error signal and the learning gain matrix; and repeating the above steps until the error meets the convergence condition or the maximum number of iterations is reached.

[0019] The present invention optimizes the driving voltage through feedback of an iterative learning control algorithm, achieves rapid convergence, effectively improves the product's anti-interference ability, suppresses drift caused by component aging, and accurately controls the RF output to reduce the power consumption of the entire device.

[0020] In one embodiment, blockchain data records use consortium chain technology and are jointly maintained by medical device manufacturers, regulatory authorities, and medical institutions.

[0021] This invention uses consortium blockchain technology to establish a shared data maintenance mechanism, effectively shortening review cycles, facilitating access to equipment maintenance records, and improving equipment reliability. Through fully automated parameter testing and blockchain technology, comprehensive quality control and traceability are achieved.

[0022] In one embodiment, the blockchain is also used to query, count and analyze key data in the production process to generate quality reports and improvement suggestions.

[0023] In one embodiment, the method further includes performing non-contact temperature calibration on the treatment head of the ultrashort wave therapy device, including: setting a blackbody radiation source to a known temperature; measuring the temperature of the blackbody radiation source using a non-contact temperature sensor; comparing the difference between the measured temperature and the known temperature to calculate a calibration coefficient of the temperature sensor; and calibrating the non-contact temperature sensor using the calibration coefficient to ensure the accuracy of the temperature measurement.

[0024] The present invention also achieves high-precision measurement by calibrating the infrared temperature sensor based on a blackbody radiation source, avoiding overheating of the treatment area when the ultrashort wave therapeutic device is used. At the same time, the non-contact setting avoids product contamination.

[0025] In a second aspect, the present invention also provides an ultrashort wave therapeutic device production consistency control system, comprising: a processor; a memory storing computer program instructions, which, when executed by the processor, implements the ultrashort wave therapeutic device production consistency control method described in one or more of the aforementioned embodiments.

[0026] In one embodiment, a human-computer interaction module is also included, which is used for operators to monitor and intervene in the production process and view quality traceability results.

[0027] The beneficial effects of this invention are as follows: Through digital twin technology and a closed-loop calibration system, various parameters in the production process are monitored and controlled in real time, compensating for component parameter drift and process errors, improving product consistency and reliability, optimizing production processes, and enabling quality traceability. This closed-loop data flow, from design to traceability, ensures consistent production of ultrashort wave therapy devices and helps reduce the defective rate of equipment during production.

[0028] Furthermore, through blockchain technology, the quality traceability and analysis of the entire life cycle of the ultrashort wave therapy device can be achieved. When quality problems occur in the product, the problem link and responsible person can be quickly located, thereby improving the efficiency of solving quality problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an illustrative and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0030] Figure 1 is a flow chart illustrating a method for controlling the production consistency of an ultrashort wave therapeutic apparatus according to an embodiment of the present invention;

[0031] Figure 2 1 is a block diagram showing the composition of an ultrashort wave therapy device production consistency control system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0033] The present invention applies digital twin technology to the four-stage control system of ultrashort wave therapy devices, achieving a hardware production consistency of over 99.5%. The four stages mainly include standardized design - automated assembly - closed-loop calibration - digital traceability. According to the context of the present invention,

[0034] The solution of the present invention will be described in detail below with reference to the accompanying drawings.

[0035] Figure 1FIG. 1 is a flow chart illustrating a method 100 for controlling production consistency of an ultrashort wave therapeutic apparatus according to an embodiment of the present invention.

[0036] like Figure 1 As shown, at step S101, a virtual digital twin model is established based on the design parameters of the ultrashort wave therapy device. The model includes a circuit model, an electromagnetic field model, and a thermal model. In some embodiments, the digital twin model also includes a mechanical structure model and a material property model to simulate the performance of the ultrashort wave therapy device under different operating conditions.

[0037] In step S102, various parameters of production equipment and products are collected in real time and compared with theoretical parameters in the digital twin model to determine the differences between the two. In some embodiments, these parameters include component information, process parameters, and test results, which are recorded in the blockchain to form an unalterable production record. The blockchain data record uses consortium chain technology and is jointly maintained by medical device manufacturers, regulatory authorities, and medical institutions.

[0038] Furthermore, blockchain technology can be used to query, compile, and analyze key data from the production process, generating quality reports and improvement suggestions. Blockchain can record the hash value of production data and synchronize it with the database of medical regulatory agencies to ensure that the data cannot be tampered with.

[0039] At step S103, parameters of the production equipment are adjusted based on the differences to compensate for component parameter drift. In some embodiments, adjusting equipment parameters includes automatically adjusting welding parameters, assembly position, and circuit parameters to compensate for component parameter drift and process errors.

[0040] In one application scenario, production line sensors can monitor key parameters in real time, such as component parameters, process parameters, and environmental parameters. Measured data is fed into a digital twin model (including circuit / thermal / mechanical multiphysics models) to perform simulation comparisons and predict drift-induced RF power drops and treatment head temperature increases. When capacitor values ​​drift, the DAC drive voltage can be adjusted. When inductance drifts, the PWM frequency can be modified.

[0041] For example, when detecting capacitor drift, the digital twin calculates the required power compensation and sends a command to the DAC controller to increase the drive voltage. For example, if a capacitor drift of ΔC = -8nF is detected, the calculated voltage compensation is ΔV = 0.2V / nF × | -8nF | = +1.6V. By increasing the drive voltage from 12V to 13.6V, the compensated output power will recover from 92W to 99.5W.

[0042] When compensating for the assembly process, the six-axis robot can adjust the Z-axis penetration depth when the electrode gap exceeds tolerance. When the material expands thermally, the welding temperature can be dynamically corrected.

[0043] In step S104, the radio frequency power data of the directional coupler is received, and an iterative learning control algorithm is called to optimize the driving voltage curve to achieve dynamic adjustment of the radio frequency power.

[0044] In some embodiments, the iterative learning control algorithm includes: initializing system parameters and control parameters; applying an initial control signal of the ultrashort wave therapeutic device and collecting the system output; calculating the error between the actual output and the expected output; updating the control signal based on the error signal and the learning gain matrix; repeating the above steps until the error meets the convergence condition or the maximum number of iterations is reached.

[0045] In addition to the above-mentioned content of compensating for component parameter drift, the present invention also includes non-contact temperature calibration of the treatment head of the ultrashort wave therapy device, including: setting the blackbody radiation source to a known temperature;

[0046] Use a non-contact temperature sensor to measure the temperature of a blackbody radiation source. Compare the difference between the measured temperature and the known temperature to calculate the calibration coefficient of the temperature sensor. Use the calibration coefficient to calibrate the non-contact temperature sensor to ensure the accuracy of the temperature measurement.

[0047] Next, the solution of the present invention will be described in detail in conjunction with the consistency control process of each stage of the ultrashort wave therapeutic device production.

[0048] 1. Consistency control during the design phase.

[0049] Modular design specifications: Divide the RF generator, bioimpedance detection circuit, and temperature control module into independent functional units, define standardized interfaces (such as RF output interface impedance 50Ω±1%), and establish PCB layout constraints (such as high-frequency trace length error <0.1mm to avoid signal reflection).

[0050] Key component selection: Establish a supplier grading database and conduct batch sampling aging tests on core components such as RF power tubes and ring electrodes (for example, test conditions are 85°C / 85% RH for 48 hours, and batches with efficiency exceeding 0.5% are eliminated). Laser marking technology is used to uniquely encode components, enabling full lifecycle traceability.

[0051] At the same stage, a 3D digital twin model of the ultrashort wave therapy device can be created using CAD / EDA tools, including the geometric and electrical parameters (e.g., impedance 50Ω±1%) of key components such as the RF module and bioimpedance circuit. Design constraints (e.g., high-frequency trace length <0.1mm) are embedded, and the digital twin automatically verifies PCB layout compliance.

[0052] 2. Manufacturing process consistency control.

[0053] Automated assembly process: A six-axis robotic arm precisely assembles the ring electrodes of the treatment head (positioning accuracy ±0.01mm), with force feedback sensors controlling the pressing force (10N ± 0.5N). A vacuum reflow soldering system is used for soldering the RF module PCB, achieving a temperature curve deviation of < ±2°C (peak temperature 245°C, maintained for 60 seconds).

[0054] An embedded self-test system (BIST) is embedded in the production line to perform online real-time calibration, including RF power calibration and temperature sensor calibration.

[0055] RF power calibration: The output signal (30-300MHz) is collected in real time through a directional coupler, compared with a standard signal source, and the DAC drive voltage is dynamically adjusted to an error of <±2%.

[0056] Temperature sensor calibration: Using the blackbody radiation source as a reference, perform three-point calibration in the range of 40-45°C, with a nonlinear error of <±0.3°C. Using the blackbody radiation source as a reference, high-precision calibration of the sensor is achieved by comparing the output of the temperature sensor with the standard temperature of the blackbody radiation source. Specifically, the temperature of the blackbody radiation source is set to three calibration points of 40°C, 42.5°C, and 45°C. When the blackbody temperature is stable at 40°C, the output signal V1 of the temperature sensor is collected. Similarly, the output signals V2 and V3 at 42.5°C and 45°C are collected. According to the temperatures of the three calibration points T1=40°C, T2=42.5°C, T3=45°C and the corresponding output signals V1, V2, and V3, a quadratic polynomial fitting is performed to obtain the temperature-voltage conversion function T(V)=aV 2 +bV+c. For any temperature measurement value, the actual temperature is calculated through the conversion function and the nonlinear error is corrected to make the final measurement error <±0.3℃.

[0057] During the automated assembly phase of the ultrashort wave therapy device, real-time monitoring and feedback are used to ensure assembly process consistency.

[0058] The digital twin synchronizes the six-axis robotic arm's positioning data (±0.01mm) and pressing force data (10N±0.5N) and compares them with the virtual model. If an anomaly is detected (such as an electrode gap that exceeds tolerance), the machine is immediately stopped and adjusted.

[0059] At the same time, the digital twin analyzes the reflow soldering temperature curve (245°C ± 2°C). If a deviation is detected, it automatically issues instructions to adjust the heating zone temperature.

[0060] During the closed-loop calibration phase, the digital twin receives the directional coupler's RF power data (e.g., 98W vs. target 100W) and uses the iterative learning control (ILC) algorithm to calculate the voltage adjustment (e.g., ΔV = +0.5V). This instruction is then sent to the production line PLC to complete dynamic compensation (error <±2%).

[0061] Specifically, when using the iterative learning control algorithm to calculate the voltage adjustment amount, let the input signal of the kth iteration be u k (t), the output power is y k (t), the expected output is y d (t), then the error signal: e k (t) = y d (t)-y k (t).

[0062] The iterative learning law is: u k+1 (t) = u k (t)+L(t)*e k (t), where L(t) is the learning gain matrix.

[0063] Set the initial DAC drive voltage u0(t), collect the initial output power y0(t), and calculate the error e0(t). k (t) and learning gain L(t), calculate the input u of the next iteration k+1 (t).

[0064] Apply u k+1 (t), collect output power y k+1 (t), calculate the new error e k+1 (t).

[0065] Determine whether the error has converged to the target value (error < ±2%). If not, continue iterating until the number of iterations reaches n or the error meets the requirement. For example, the convergence condition is: the number of iterations ≤ 3 and the error converges to the target value.

[0066] In one application scenario, the target output power is set at 50W, with an initial error of +10% (i.e., 55W output). Iteration 1: By adjusting the DAC voltage using the learned gain matrix L(t), the output power drops to 52W with an error of +4%. Iteration 2: Further adjustments are made, resulting in an output power of 50.5W with an error of +1%. Iteration 3: The output power stabilizes at 50W ±0.5W with an error of <±1%, meeting the calibration requirements.

[0067] The above-mentioned RF power calibration adopts the iterative learning control (ILC) algorithm to optimize the DAC drive voltage curve through historical error data. The number of iterations is less than or equal to 3 to converge to the target value, and the convergence speed is fast.

[0068] Further, multi-parameter collaborative calibration can also be performed, and temperature, impedance and other data are synchronized, and a digital twin generates a comprehensive calibration report (such as a non-linear error <±0.3℃ after temperature calibration).

[0069] 3. Test and data traceability

[0070] A multi-channel synchronous test platform is developed to perform full-parameter automatic testing. The following tests can be completed within 10 seconds:

[0071] a. RF output: frequency stability (±10ppm), harmonic distortion (<-40dBc).

[0072] b. Bioimpedance measurement: 0.1mA constant current is injected in the range of 1kHz-10MHz, and the impedance measurement error is <±1%.

[0073] c. Safety protection: simulate electrode falling off failure, trigger power-off response time <50ms.

[0074] In addition, in the scheme of the present application, the whole process of the production design process is realized through the blockchain quality traceability system. For example, a digital twin file is generated for each device, recording the full link information from the component batch, assembly parameters to test data. Through the QR code association of the physical device, it supports fast positioning of the problem link under the fault mode (such as the power anomaly caused by the capacitance value deviation of a batch of capacitors).

[0075] Specifically, the blockchain can be used for notarization. The key data (component batch, test result) is generated into a hash value and written into the Hyperledger Fabric blockchain. Each device is associated with a unique QR code, and the complete digital twin file can be retrieved by scanning the code.

[0076] In one application scenario, a device power anomaly → digital twin traces to the capacitor batch “C-2023-05”, finds the capacitance value drift → triggers the supplier quality review.

[0077] Based on the above technical scheme, the present application uses digital twin technology to realize real-time monitoring and prediction in the production of ultrashort wave therapy apparatus by virtually mapping the full life cycle data of physical devices. The state of the production line equipment, component parameters and test data are synchronized. By simulating and comparing the design parameters and actual production data, the process is dynamically adjusted. The full-process data from the component supplier, assembly parameters to the final inspection results are recorded. And the problem link of a certain device can be traced through the blockchain hash value, which helps to realize fast positioning of the fault.

[0078] Figure 2 is a constituent block diagram showing an ultrashort wave therapy apparatus production consistency control system according to an embodiment of the present application.

[0079] The present invention also provides a production consistency control system for ultrashort wave therapeutic apparatus. Figure 2 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, the method for controlling the production consistency of the ultrashort wave therapeutic apparatus described above is implemented.

[0080] The system further includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and thus will not be described in detail here.

[0081] Furthermore, the above system also includes a human-computer interaction module for operators to monitor and intervene in the production process and view quality traceability results.

[0082] In the present invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible or connectable to a device. Any application or module described in the present invention can be implemented using computer-readable / executable instructions that can be stored or otherwise retained by such a computer-readable medium.

[0083] In the description of this specification, "multiple" and "several" mean at least two, such as two, three or more, unless otherwise clearly defined.

[0084] While several embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, variations, and alternatives will occur to those skilled in the art without departing from the concept and spirit of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.

Claims

1. A method for controlling the production consistency of an ultrashort wave therapeutic device, characterized in that: include: Based on the design parameters of the ultrashort wave therapy device, a virtual digital twin model is established, which includes a circuit model, an electromagnetic field model, and a thermal model; Collect various parameters of production equipment and products in real time, and compare the collected parameters with the theoretical parameters in the digital twin model to determine the differences between the two; Adjust the parameters of production equipment based on the differences to compensate for component parameter drift; Receive the RF power data of the directional coupler, call the iterative learning control algorithm to optimize the driving voltage curve, and realize dynamic adjustment of the RF power.

2. The method for controlling the production consistency of the ultrashort wave therapeutic apparatus according to claim 1, characterized in that: The various parameters include component information, process parameters and test results, and the various parameters are recorded in the blockchain to form an unalterable production record.

3. The method for controlling the production consistency of the ultrashort wave therapeutic apparatus according to claim 1, characterized in that: The digital twin model also includes a mechanical structure model and a material property model, which are used to simulate the performance of the ultrashort wave therapy device under different working conditions.

4. The method for controlling the production consistency of an ultrashort wave therapeutic apparatus according to claim 1, characterized in that: Adjusting equipment parameters includes automatically adjusting welding parameters, assembly position and circuit parameters to compensate for component parameter drift and process errors.

5. The method for controlling the production consistency of the ultrashort wave therapeutic apparatus according to claim 1, characterized in that: The iterative learning control algorithm includes: Initialize system parameters and control parameters; Apply the initial control signal of the ultrashort wave therapy device and collect the system output; Calculate the error between the actual output and the expected output; Update the control signal according to the error signal and the learning gain matrix; Repeat the above steps until the error meets the convergence condition or the maximum number of iterations is reached.

6. The method for controlling the production consistency of the ultrashort wave therapeutic apparatus according to claim 2, characterized in that: The blockchain data records use consortium chain technology and are jointly maintained by medical device manufacturers, regulatory authorities and medical institutions.

7. The method for controlling the production consistency of an ultrashort wave therapeutic apparatus according to claim 1, characterized in that: It also includes using blockchain to query, count and analyze key data in the production process to generate quality reports and improvement suggestions.

8. The method for controlling the production consistency of an ultrashort wave therapeutic apparatus according to claim 1, characterized in that: It also includes non-contact temperature calibration of the treatment head of the ultrashort wave therapy device, including: Set the blackbody radiation source to a known temperature; Use a non-contact temperature sensor to measure the temperature of a blackbody radiation source; Compare the difference between the measured temperature and the known temperature to calculate the calibration coefficient of the temperature sensor; Calibrate the non-contact temperature sensor using the calibration coefficient to ensure the accuracy of temperature measurement.

9. A production consistency control system for ultrashort wave therapeutic apparatus, characterized in that: include: processor; A memory storing computer program instructions, which, when executed by the processor, implements the method for controlling the production consistency of an ultrashort wave therapeutic apparatus according to any one of claims 1 to 8.

10. The ultrashort wave therapeutic apparatus production consistency control system according to claim 9, characterized in that: It also includes a human-computer interaction module for operators to monitor and intervene in the production process and view quality traceability results.

Images