CN111481842A - Wearable ultrasonic therapy appearance based on developments match - Google Patents
Wearable ultrasonic therapy appearance based on developments match Download PDFInfo
- Publication number
- CN111481842A CN111481842A CN202010317314.XA CN202010317314A CN111481842A CN 111481842 A CN111481842 A CN 111481842A CN 202010317314 A CN202010317314 A CN 202010317314A CN 111481842 A CN111481842 A CN 111481842A
- Authority
- CN
- China
- Prior art keywords
- module
- neural network
- transducer
- matching
- ultrasonic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N7/00—Ultrasound therapy
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N7/00—Ultrasound therapy
- A61N2007/0004—Applications of ultrasound therapy
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Artificial Intelligence (AREA)
- Radiology & Medical Imaging (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Surgical Instruments (AREA)
Abstract
The invention discloses a wearable ultrasonic therapeutic apparatus based on dynamic matching, which comprises a main control unit, a signal generation module, a power amplifier, an impedance matching module, an ultrasonic transducer, an automatic frequency tracking module and a power supply module, wherein the main control unit is used for controlling the power amplifier to output power; the main control unit is respectively connected with the signal generation module, the frequency automatic tracking module and the power supply module, the power supply module is further connected with the shaping filter circuit and the power amplifier, the power amplifier is further connected with the impedance matching module, the impedance matching module is connected with the ultrasonic transducer, and the ultrasonic transducer is connected with the frequency automatic tracking module. According to the invention, the dynamic matching inductance is output, and the reactance angle of the reactor is adjusted in real time according to the size of the dynamic inductance, so that the voltage and the current at two ends of the transducer are changed, and the dynamic adjustment of the matching inductance is realized by adopting closed-loop control.
Description
Technical Field
The invention belongs to the technical field of ultrasonic treatment equipment, and particularly relates to a wearable ultrasonic treatment instrument based on dynamic matching.
Background
The etiology of chronic soft tissue injury as a frequently encountered disease is not yet determined. The science shows that the ultrasonic therapy has positive therapeutic effect on treating different types of chronic soft tissue injuries.
The ultrasonic technology is widely applied to industrial production, such as electronic packaging industry, ultrasonic processing industry and the like. Generally, a high-power ultrasonic device must be provided with a matching circuit, but the current matching circuit mostly adopts a static matching circuit and is a research under the condition that no load is applied to the system. In fact, during the processing of the transducer, the parameters of the transducer are changed due to temperature change, load change, tool abrasion and the like, static matching disorder is inevitably caused, and the problems of reactive power generation, vibration amplitude reduction and the like are caused. Obviously, static matching is not suitable for long-term operation of high-power equipment.
The conventional frequency tracking mode of the phase-locked loop technology is easy to lose lock, but the common fuzzy control lacks the self-integral dynamic response capability, cannot maintain an automatic processing function of adjusting parameters in real time in a system, has low tracking speed and cannot ensure the dynamic effect of the system.
Through the analysis to the present some supersound physiotherapy equipment that appears, the main problem that exists at present:
(1) the current matching circuit is not added with any neural network algorithm, the adjusting effect is poor, and the output sound intensity is unstable. And most of the circuits adopt static matching circuits, so that static matching offset is easy to generate.
(2) The frequency tracking speed is low, the dynamic response capability is weak, an automatic processing function of adjusting parameters in real time cannot be kept in the system, and the dynamic effect of the system cannot be guaranteed. When the transduction system dynamically matches and switches the inductance, the phenomenon of lock is easily caused, and the overall performance of the dynamic matching circuit of the transduction system is low. The conventional frequency tracking mode of the phase-locked loop technology is easy to lose lock, but the common fuzzy control has low tracking speed and weak dynamic response capability, so that an automatic processing function of adjusting parameters in real time cannot be kept in a system, and the dynamic effect of the system cannot be ensured.
(3) There is no wearable capability. Most therapeutic instruments are large in size, operate, copy and charge complicated, and are not really wearable.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention provides a wearable ultrasonic therapeutic apparatus based on dynamic matching. The therapeutic apparatus of the invention adopts an intelligent algorithm to realize the impedance dynamic matching of the ultrasonic therapeutic apparatus together, improves the overall performance of the dynamic matching circuit of the transduction system and generates high-efficiency and stable output ultrasonic waves.
The invention is realized by the following technical scheme:
a wearable ultrasonic therapeutic apparatus based on dynamic matching comprises a main control unit, a signal generation module, a power amplifier, an impedance matching module, an ultrasonic transducer, an automatic frequency tracking module and a power supply module; the main control unit is respectively connected with the signal generation module, the frequency automatic tracking module and the power supply module, the power supply module is also connected with the shaping filter circuit and the power amplifier, the power amplifier is also connected with the impedance matching module, the impedance matching module is connected with the ultrasonic transducer, and the ultrasonic transducer is connected with the frequency automatic tracking module;
the main control unit is used for controlling the signal generator to generate a DDS signal, the power amplification module is used for amplifying the DDS signal to generate an enable signal of the ultrasonic transducer, and the impedance matching module is used for dynamically adjusting the matching inductance of the ultrasonic transducer; the frequency automatic tracking module enables the output frequency of the ultrasonic transducer to track the input frequency of the transducer in real time;
the power supply module supplies power to the main control unit, the signal generation module and the power amplification module.
Aiming at the problem that the current matching circuit is easy to generate static matching maladjustment, the impedance matching module dynamically adjusts the matching inductance of the ultrasonic transducer; meanwhile, the problem of easy unlocking when the ultrasonic system dynamically matches and switches the inductors is solved, the overall performance of the dynamic matching circuit of the transduction system is improved, and efficient and stable output ultrasonic waves are generated.
The impedance matching module outputs dynamic matching inductance through the BP neural network, and adjusts the reactance angle of the reactor in real time according to the size of the dynamic inductance, thereby changing the voltage and the current at two ends of the transducer, and realizing the dynamic adjustment of the matching inductance by adopting closed-loop control. Preferably, the impedance matching module of the invention comprises a data detection module, a data preprocessing module and a BP neural network module, the data detection module is used for collecting input parameters of the ultrasonic transducer, the data preprocessing module is used for processing the input parameters and the output parameters to obtain training sample data, the BP neural network module is used for inputting the training sample data into the BP neural network for training, and the trained neural network is used for outputting the matching inductance in real time to realize the dynamic adjustment of the matching inductance.
Preferably, the input parameters of the invention are five variables which cause the internal parameters of the transducer to change, including the temperature of the transducer, the frequency of ultrasonic waves, the voltage value at two ends of the transducer, the current value at two ends of the transducer and the depth of the transducer penetrating into the water tank, and the output parameters are matching inductance values.
Preferably, the BP neural network module of the present invention is configured to perform the steps of:
s1, the BP neural network learns and trains a plurality of sample data, and the weight of the network is adjusted to achieve the minimum error, so that the trained BP neural network is obtained;
s2, outputting matched inductance by adopting the BP neural network trained in the step S1, and adjusting the reactance angle of the reactor in real time, so that the voltage and the current at two ends of the transducer are changed;
and S3, repeatedly executing S2 to realize the dynamic adjustment of the matching inductance.
The frequency automatic tracking module of the invention adopts an automatic frequency tracking technology based on a Fuzzy neural network, so that the output frequency of the ultrasonic transducer tracks the input frequency of the ultrasonic transducer in real time, the frequency tracking speed of the system is improved, and the working frequency of the ultrasonic therapeutic apparatus is improved. Preferably, the frequency automatic tracking module of the present invention includes a voltage and current acquisition module, a phase discriminator and a Fuzzy neural network controller, the voltage and current acquisition module is configured to acquire voltage and current signals at two ends of the transducer in real time and transmit the signals to the phase discriminator, and the phase discriminator obtains a phase difference and a change rate of the phase difference according to the voltage and current signals and inputs the phase difference and the change rate of the phase difference to the Fuzzy neural network controller for phase difference adjustment to achieve automatic tracking of frequency.
Preferably, the Fuzzy neural network controller of the present invention is configured to perform the following steps:
s11, taking the phase difference and the change rate of the phase difference as the input of a Fuzzy neural network, taking the adjusted phase difference as the output of the Fuzzy neural network, and mapping the input and the output by using a neural network algorithm;
s12, determining fuzzification, membership functions and Fuzzy rules to obtain a Fuzzy neural network model;
s13, training the Fuzzy neural network model by adopting a plurality of data samples to obtain the trained Fuzzy neural network model;
s14, inputting the phase difference obtained in real time and the change rate of the phase difference into a trained Fuzzy neural network model to output and adjust the magnitude of the phase difference;
and S15, changing the current at two ends of the transducer, and repeatedly executing the step S14 until the phase difference is zero, so that the output frequency of the signal is gradually consistent with the input frequency, and the automatic frequency tracking is realized.
The power supply module is arranged and used for providing voltages with different requirements for different modules in the whole instrument, so that the volume of the instrument is simplified. Preferably, the power supply module adopts a 12V rechargeable polymeric lithium battery pack, and the polymeric lithium battery pack boosts 12V voltage to 48V through a boost module to directly supply power to the power amplification module; the polymerization lithium battery pack converts 12V voltage into 5V voltage through a linear voltage stabilizing chip to supply power for the signal generating module; and then the voltage of 5V is converted into 3.3V by the voltage stabilizing chip to supply power for the main control unit.
Preferably, the signal generating module of the present invention comprises a DDS signal generator, a shaping filter circuit, and a driving circuit; the DDS signal generator is connected with the main control unit through a serial bus, 2MHz square waves are generated through the main control unit, the 2MHz square waves generated by the DDS signal generator are subjected to frequency division by the driving circuit and are converted into 1MHz square waves, and the 1MHz square waves are shaped by the shaping filter circuit and then are transmitted to the power amplification module.
The invention is also provided with a safety protection device for protecting the safety of personnel and equipment. Preferably, the ultrasonic transducer further comprises a temperature control module, wherein the temperature control module is used for acquiring the temperatures of two ends of the ultrasonic transducer in real time by adopting a thermistor, and when the temperature exceeds a set safety threshold, the power-off is automatically controlled to ensure the safety of a user.
Preferably, the invention further comprises an overcurrent and overvoltage protection module and a human-computer interaction module, wherein the human-computer interaction module and the overcurrent and overvoltage protection module are both connected with the main control unit, the human-computer interaction module is used for adjusting the ultrasonic intensity and displaying the gear at which the current ultrasonic intensity is located, and the overcurrent and overvoltage protection module is used for outputting overvoltage protection and overcurrent protection.
The invention has the following advantages and beneficial effects:
1. the invention introduces the BP neural network controller to realize the dynamic adjustment of the matching inductance. According to the invention, the dynamic matching inductance is output through the BP neural network controller, the reactance angle of the reactor is adjusted in real time according to the size of the dynamic inductance, so that the voltage and the current at two ends of the transducer are changed, and the dynamic adjustment of the matching inductance is realized by adopting closed-loop control. The common impedance matching is not added with any neural network algorithm, the adjusting effect is poor, and the output sound intensity is unstable. And most of the circuits adopt static matching circuits, so that static matching offset is easy to generate.
2. The invention provides an automatic frequency tracking technology based on a Fuzzy neural network, which enables the output frequency of an ultrasonic power supply to track the input frequency of a transducer in real time. The Fuzzy neural network is added in the frequency tracking module, so that the accuracy of dynamic matching is high, the automatic frequency tracking speed is high, the problem of volatile locking when the inductance is switched by the transduction system in dynamic matching is solved, and the overall performance of the dynamic matching circuit of the transduction system is improved. The problem that the common fuzzy control is slow in tracking speed and weak in dynamic response capability, and a phase-locked loop technology is prone to losing lock is solved.
3. The ultrasonic therapeutic apparatus is wearable, and the size of the ultrasonic therapeutic apparatus is further simplified by reducing complex human-computer interaction interfaces and adopting battery power supply and wireless charging.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a block diagram of the ultrasonic treatment apparatus of the present invention.
Fig. 2 is a schematic block diagram of the impedance matching module of the present invention.
Fig. 3 is a schematic block diagram of the frequency auto-tracking module of the present invention.
Detailed Description
Hereinafter, the term "comprising" or "may include" used in various embodiments of the present invention indicates the presence of the invented function, operation or element, and does not limit the addition of one or more functions, operations or elements. Furthermore, as used in various embodiments of the present invention, the terms "comprises," "comprising," "includes," "including," "has," "having" and their derivatives are intended to mean that the specified features, numbers, steps, operations, elements, components, or combinations of the foregoing, are only meant to indicate that a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as first excluding the existence of, or adding to the possibility of, one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing.
In various embodiments of the invention, the expression "or" at least one of a or/and B "includes any or all combinations of the words listed simultaneously. For example, the expression "a or B" or "at least one of a or/and B" may include a, may include B, or may include both a and B.
Expressions (such as "first", "second", and the like) used in various embodiments of the present invention may modify various constituent elements in various embodiments, but may not limit the respective constituent elements. For example, the above description does not limit the order and/or importance of the elements described. The foregoing description is for the purpose of distinguishing one element from another. For example, the first user device and the second user device indicate different user devices, although both are user devices. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of various embodiments of the present invention.
It should be noted that: if it is described that one constituent element is "connected" to another constituent element, the first constituent element may be directly connected to the second constituent element, and a third constituent element may be "connected" between the first constituent element and the second constituent element. In contrast, when one constituent element is "directly connected" to another constituent element, it is understood that there is no third constituent element between the first constituent element and the second constituent element.
The terminology used in the various embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the various embodiments of the invention. As used herein, the singular forms are intended to include the plural forms as well, unless the context clearly indicates otherwise. Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the present invention belong. The terms (such as those defined in commonly used dictionaries) should be interpreted as having a meaning that is consistent with their contextual meaning in the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein in various embodiments of the present invention.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Example 1
The embodiment provides a wearable ultrasonic therapeutic apparatus based on dynamic matching. The ultrasonic therapeutic apparatus of the embodiment adopts two intelligent neural network algorithms to be combined together to realize the dynamic matching of the ultrasonic therapeutic apparatus. Dynamic matching inductance is output through the BP neural network controller, and the reactance angle of the reactor is adjusted in real time according to the size of the dynamic inductance, so that the voltage and the current at two ends of the transducer are changed, and the dynamic adjustment of the matching inductance is realized by adopting closed-loop control. The automatic frequency tracking technology based on the Fuzzy neural network is adopted to solve the problem of volatile locking when the transduction system dynamically matches and switches the inductance, and the overall performance of the dynamic matching circuit of the transduction system is improved. The output frequency of the ultrasonic power supply is made to track the input frequency of the transducer in real time.
As shown in figure 1, the wearable ultrasonic therapeutic apparatus based on dynamic matching mainly comprises a power supply module 1, a signal generation module 2, a power amplification module 3, an impedance matching module 4, an ultrasonic transducer 5, a frequency automatic tracking module 6, a main control unit 7, a temperature control module 8, an overcurrent and overvoltage protection module 9 and a man-machine interaction module 10, wherein the power supply module 1 comprises a wireless charging module 11, a 12V battery pack 12, a 12V voltage stabilizing module 13, a Boost 14, a voltage stabilizing chip L M780515 and a voltage stabilizing chip AMS111716, the signal generation module 2 comprises a DDS signal generator 21, a driving circuit 22 and a shaping filter circuit 23, and the temperature control module 8 comprises a temperature sampling module 81 and an over-temperature protection module 82.
The functions of the modules are as follows:
the power supply module 1 comprises three voltage modes, namely a power amplification module supplies power (12V), a signal generator supplies power (5V), a main control unit (3.3V), a 12V rechargeable lithium battery boosts the voltage of 12V to 48V through a boost module and directly supplies power to the power amplification module, the signal generation circuit converts the voltage of 12V to 3.3V into 5V through a linear voltage stabilizing chip L M7805 to supply power, the voltage stabilizing chip AMS1117 converts the voltage of 5V into 3.3V to supply power to the main control unit, the AMS1117 is a forward low-voltage drop voltage stabilizer with the output voltage of 3.3V, the cost is low, the circuit design is simple, a charging part wirelessly charges the whole ultrasonic therapeutic apparatus through a QI standard wireless charging module, the battery adopts a 12.6V 1800mAh rechargeable lithium polymer battery pack, the volume of the lithium polymer battery pack is only 45 cm, and the volume of the physiotherapy apparatus is further simplified.
The signal generation module 2 comprises a DDS signal generator, a shaping filter circuit and a drive circuit, an AD9833 chip is connected with a main control unit through a serial bus, pins of the main control unit are configured into an SPI bus mode to be matched with the AD9833 for data transmission, the main control unit adopts a low-power consumption STM 32L 151 main controller, the AD9833 chip generates a 2MHz square wave through a low-power consumption STM 32L 151 main controller, the drive circuit uses a D trigger to divide the frequency of the 2MHz square wave generated by the DDS signal generator into a more stable 1MHz square wave,shaping by a shaping filter circuit, wherein the output frequency of the concave piezoelectric ceramic piece is 1MHz, and the intensity is 0W/cm2To 1W/cm2The adaptive adjustable ultrasonic wave.
And the power amplification module 3 is used for amplifying the DDS signal and driving the DDS generator to generate a signal capable of driving the ultrasonic transducer. The DDS adopts an AD9833 chip, and has the advantages of low cost, low power consumption, high resolution, quick conversion time and the like. Since the strength of the excitation signal output by the AD9833 is not enough to drive the ultrasonic transducer, the excitation signal needs to be power amplified. The ultrasonic excitation signal is subjected to frequency division filtering processing by the logic chip 74HC74D, and then is sent to the gate drive chip UCC27525 for subsequent amplification. The ultrasonic driving voltage signal after amplification can reach 40V, and the ultrasonic transducer can be directly driven to work. The master control unit generates PWM waves to control the enabling end of the grid driver, and indirect control over the ultrasonic output power is achieved.
And the impedance matching module 4 is used for realizing the dynamic adjustment of the matching inductance. Aiming at the conventional static circuit matching, the frequency of the transducer is easy to drift, and the impedance matching module 4 adopts a BP neural network module with a neural network intelligent algorithm to realize the dynamic adjustment of the matching inductance.
As shown in fig. 2, the impedance matching module mainly comprises five modules, namely a data detection module, data preprocessing, BP neural network training, BP neural network prediction and a BP neural network controller. The ultrasonic transducer firstly acquires input parameters through the data detection module, carries out pretreatment on the parameters, mainly carries out normalization treatment, then carries out neural network training, continuously adjusts the weight of the network, predicts the inductance value, then outputs dynamic matching inductance through the BP neural network controller, and adjusts the reactance angle of the reactor in real time according to the dynamic inductance value, thereby changing the voltage and current at two ends of the transducer, and the dynamic adjustment of the matching inductance is realized after the circulation.
The BP neural network module is intelligentized in that the weight of the network is adjusted in real time, so that any input can obtain expected output. The training method is to train the neural network for each group of data samples, and to calculate layer by layer from the first layer of the network to the output layer.
The BP neural network module comprises the following specific steps:
s1: and obtaining the input parameters of the neural network through a data detection module. Since the size of the matching inductance is related to the internal parameters of the ultrasonic transducer, 5 main variables causing the internal parameter change of the transducer are used as input parameters, namely the temperature of the transducer, the frequency of ultrasonic waves, the voltage value at two ends of the transducer, the current value at two ends of the transducer and the depth of the concave piezoelectric ceramic piece penetrating into the water tank, and the output parameter is a dynamic inductance value. Inputting x for parameters1,x2,…,x5Since the dynamic inductance value is represented by y, the formula y is f (x)1,x2,…,x5)。
S2: and (4) preprocessing data. In order to reduce the absolute error, data preprocessing is carried out before normalization processing, and input and output data of the network are limited to (0,1) or an interval (-1,1) through transformation.
S3: and normalizing the sample data.
a. When the input and output samples are in the [0,1] interval, the formula of the normalization process is
Wherein, XiRepresenting input or output data, XmaxDenotes the maximum value of the sample, XminRepresents the minimum value of a sample
b. When the input and output samples are in the interval [ -1,1], the normalization process is formulated as
Wherein, XmidRepresenting the median value of the sample.
S4: and (4) training the BP neural network. The training purpose of the BP neural network is to fix the weights of the network. A large number of samples of different types are input in a cross mode, the weight is continuously adjusted through a large number of learning of a plurality of sample data, errors are reduced, and the weight of the network is adjusted to be minimized, so that the weight of the network is fixed.
S5: the prediction of the neural network aims to predict the matching inductance value through the BP neural network. After training of the BP neural network, the weight of the network is determined. And testing whether the trained sample data has better generalization capability, if the error of the training sample is small and the error of the test sample is large, which indicates that the generalization capability is poor, then performing the first step of operation until the neural network obtains a good prediction effect.
The frequency automatic tracking module 6 improves the system frequency tracking speed through the Fuzzy neural network module, solves the problem of phase lock losing phenomenon when the transduction system dynamically matches and switches the inductance, and improves the overall performance of the transduction system dynamic matching circuit. The frequency automatic tracking speed can reach 0.12ms, the frequency tracking speed of the system is improved, and the working efficiency of the ultrasonic therapeutic apparatus is improved. Because the frequency tracking mode of the conventional phase-locked loop technology is easy to lose lock, and the frequency of the common fuzzy control lacks the self-integral dynamic response capability, an automatic processing function of adjusting parameters in real time cannot be kept in a system, the tracking speed is low, and the dynamic effect of the system cannot be ensured.
In order to solve the pain points, an automatic frequency tracking technology based on a Fuzzy neural network is provided. The automatic frequency tracking technology based on the Fuzzy neural network is an intelligent frequency tracking technology based on Fuzzy controllers and phase-locked loop technologies, and a neural network algorithm is introduced into Fuzzy control.
As shown in fig. 3, the automatic frequency tracking module mainly includes: the voltage and current acquisition, phase discriminator and Fuzzy neural network controller have the following specific working steps
(1) And acquiring voltage and current signals at two ends of the transducer in real time through the phase discriminator to obtain a phase difference e and a change rate delta e of the phase difference.
(2) The phase difference e and the rate of change of the phase difference Δ e are input to a Fuzzy neural network controller. The specific working steps of the Fuzzy neural network controller are as follows:
s1: input and output signals of the Fuzzy neural network controller are determined. The rate of change of the phase difference e is taken as an input to the Fuzzy neural network controller. And the adjusted phase difference E is used as output, and then the input and the output are mapped by utilizing a neural network algorithm.
And S2, fuzzification and membership function determination, fuzzification is carried out on input and output variables of the controller, an MAT L AB fuzzy control tool box and a neural network algorithm are adopted to jointly adjust input and output parameters, simplicity, convenience and easiness in operation are realized, and the membership function is a Gaussian fuzzification function.
And S3, establishing fuzzy rules in an MAT L AB fuzzy toolbox.
S4: and (5) training a Fuzzy neural network controller. The Fuzzy neural network controller has instructor-type self-learning capability, adopts a four-layer structure of an input layer, a middle layer, a reasoning layer and an output layer, and adopts a training method that neural network training is carried out on each data sample, calculation is carried out layer by layer from the first layer of the network to the output layer, and the magnitude of phase difference is adjusted and the current at two ends of the transducer is changed through a large amount of learning of a plurality of sample data.
S5: modulation of a Fuzzy neural network controller. After Fuzzy rule training, the first derivative of the phase difference and the change rate of the phase difference is used as the input of data preprocessing, the trained Fuzzy neural network controller is used for adjusting the phase difference, the current at two ends of the transducer is changed, and the process is circulated until the phase difference is zero, so that the output frequency of the signal is gradually consistent with the input frequency, and the automatic frequency tracking is realized.
(3) Experiments prove that the frequency automatic tracking speed of the automatic tracking module with the Fuzzy neural network controller can reach 0.12ms, the frequency tracking speed of the system is improved, and the working efficiency of the ultrasonic therapeutic apparatus is improved.
The main control unit 7, the main control unit uses low-power STM 32L 151 microprocessor to detect sampling resistor voltage through the ADC, controls the ultrasonic output intensity and the current working state of the display device through PID algorithm programming, determines the output ultrasonic intensity through scanning key mode, and displays the current gear through L ED lamp.
The temperature control module 8 adopts a thermistor to acquire the temperatures of two ends of the ultrasonic transducer in real time, and when the temperatures exceed a set safety threshold, the power is automatically cut off to ensure the safety of a user.
The overvoltage and overcurrent protection module 9 adopts a DC/DC power supply module URA2405ZP to supply power for the operational amplifier, has an input voltage of 12V and an output voltage of +/-5V, and has input undervoltage protection, output overvoltage protection and output overcurrent protection.
The human-computer interaction module 8 is only provided with keys and L ED, the output ultrasonic intensity is adjusted through the keys, and the current gear is displayed through a L ED lamp.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A wearable ultrasonic therapeutic apparatus based on dynamic matching is characterized by comprising a main control unit, a signal generation module, a power amplifier, an impedance matching module, an ultrasonic transducer, a frequency automatic tracking module and a power supply module; the main control unit is respectively connected with the signal generation module, the frequency automatic tracking module and the power supply module, the power supply module is also connected with the shaping filter circuit and the power amplifier, the power amplifier is also connected with the impedance matching module, the impedance matching module is connected with the ultrasonic transducer, and the ultrasonic transducer is connected with the frequency automatic tracking module;
the main control unit is used for controlling the signal generator to generate a DDS signal, the power amplification module is used for amplifying the DDS signal to generate an enable signal of the ultrasonic transducer, and the impedance matching module is used for dynamically adjusting the matching inductance of the ultrasonic transducer; the frequency automatic tracking module enables the output frequency of the ultrasonic transducer to track the input frequency of the transducer in real time;
the power supply module supplies power to the main control unit, the signal generation module and the power amplification module.
2. The wearable ultrasonic therapeutic apparatus based on dynamic matching according to claim 1, wherein the impedance matching module comprises a data detection module, a data preprocessing module and a BP neural network module, the data detection module is used for collecting input parameters of the ultrasonic transducer, the data preprocessing module is used for processing the input parameters and the output parameters to obtain training sample data, the BP neural network module is used for inputting the training sample data into the BP neural network for training, and the trained neural network is used for outputting the matching inductance in real time to realize dynamic adjustment of the matching inductance.
3. The wearable ultrasonic treatment apparatus based on dynamic matching as claimed in claim 2, wherein the input parameters are five variables causing the internal parameters of the transducer to change, including the temperature of the transducer, the frequency of the ultrasonic waves, the voltage value across the transducer, the current value across the transducer and the depth of the transducer penetrating into the water tank, and the output parameter is the matching inductance value.
4. The wearable ultrasound therapy instrument based on dynamic matching of claim 2, wherein the BP neural network module is configured to perform the following steps:
s1, the BP neural network learns and trains a plurality of sample data, and the weight of the network is adjusted to achieve the minimum error, so that the trained BP neural network is obtained;
s2, outputting matched inductance by adopting the BP neural network trained in the step S1, and adjusting the reactance angle of the reactor in real time, so that the voltage and the current at two ends of the transducer are changed;
and S3, repeatedly executing S2 to realize the dynamic adjustment of the matching inductance.
5. The wearable ultrasonic therapeutic apparatus based on dynamic matching of claim 1, wherein the frequency automatic tracking module comprises a voltage and current acquisition module, a phase discriminator and a Fuzzy neural network controller, the voltage and current acquisition module is used for acquiring voltage and current signals at two ends of the transducer in real time and transmitting the signals to the phase discriminator, and the phase discriminator obtains a phase difference and a change rate of the phase difference according to the voltage and current signals and inputs the phase difference and the change rate into the Fuzzy neural network controller for phase difference adjustment so as to realize automatic tracking of frequency.
6. The wearable ultrasound therapy instrument based on dynamic matching of claim 5, wherein the Fuzzy neural network controller is configured to perform the following steps:
s11, taking the phase difference and the change rate of the phase difference as the input of a Fuzzy neural network, taking the adjusted phase difference as the output of the Fuzzy neural network, and mapping the input and the output by using a neural network algorithm;
s12, determining fuzzification, membership functions and Fuzzy rules to obtain a Fuzzy neural network model;
s13, training the Fuzzy neural network model by adopting a plurality of data samples to obtain the trained Fuzzy neural network model;
s14, inputting the phase difference obtained in real time and the change rate of the phase difference into a trained Fuzzy neural network model to output and adjust the magnitude of the phase difference;
and S15, changing the current at two ends of the transducer, and repeatedly executing the step S14 until the phase difference is zero, so that the output frequency of the signal is gradually consistent with the input frequency, and the automatic frequency tracking is realized.
7. The wearable ultrasonic therapeutic apparatus based on dynamic matching according to any one of claims 1-6, wherein the power supply module adopts a 12V rechargeable polymeric lithium battery pack, and the polymeric lithium battery pack boosts a 12V voltage to 48V through a boost module to directly supply power to the power amplification module; the polymerization lithium battery pack converts 12V voltage into 5V voltage through a linear voltage stabilizing chip to supply power for the signal generating module; and then the voltage of 5V is converted into 3.3V by the voltage stabilizing chip to supply power for the main control unit.
8. The wearable ultrasonic treatment apparatus based on dynamic matching according to any one of claims 1 to 6, wherein the signal generation module comprises a DDS signal generator, a shaping filter circuit and a driving circuit; the DDS signal generator is connected with the main control unit through a serial bus, 2MHz square waves are generated through the main control unit, the 2MHz square waves generated by the DDS signal generator are subjected to frequency division by the driving circuit and are converted into 1MHz square waves, and the 1MHz square waves are shaped by the shaping filter circuit and then are transmitted to the power amplification module.
9. The wearable ultrasonic therapeutic apparatus based on dynamic matching of any one of claims 1 to 6, further comprising a temperature control module, wherein a thermistor is used to collect the temperature at both ends of the ultrasonic transducer in real time, and when the temperature exceeds a preset safety threshold, the power off is automatically controlled to ensure the safety of the user.
10. The wearable ultrasonic therapeutic apparatus based on dynamic matching according to any one of claims 1 to 6, further comprising an overcurrent and overvoltage protection module and a human-computer interaction module, wherein the human-computer interaction module and the overcurrent and overvoltage protection module are both connected with the main control unit, the human-computer interaction module is used for adjusting the ultrasonic intensity and displaying the gear at which the current ultrasonic intensity is located, and the overcurrent and overvoltage protection module is used for outputting overvoltage protection and overcurrent protection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010317314.XA CN111481842A (en) | 2020-04-21 | 2020-04-21 | Wearable ultrasonic therapy appearance based on developments match |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010317314.XA CN111481842A (en) | 2020-04-21 | 2020-04-21 | Wearable ultrasonic therapy appearance based on developments match |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111481842A true CN111481842A (en) | 2020-08-04 |
Family
ID=71789977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010317314.XA Pending CN111481842A (en) | 2020-04-21 | 2020-04-21 | Wearable ultrasonic therapy appearance based on developments match |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111481842A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113058159A (en) * | 2021-06-03 | 2021-07-02 | 杭州回车电子科技有限公司 | Electrode wearing condition detection method and device for transcranial electrical stimulation |
| CN113082502A (en) * | 2021-04-06 | 2021-07-09 | 武汉光燚激光科技有限公司 | Ultrasonic skin therapeutic instrument |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105033779A (en) * | 2014-09-01 | 2015-11-11 | 哈尔滨工业大学深圳研究生院 | Ultrasonic processing system dynamic tracking coupling device |
| CN106357149A (en) * | 2016-11-04 | 2017-01-25 | 哈尔滨工业大学深圳研究生院 | Automatic impedance matching ultrasonic circuit driver and automatic dynamic matching method thereof |
| CN109687694A (en) * | 2019-01-21 | 2019-04-26 | 温州大学 | A kind of multiple power supplies are for being electrically integrated assembly and its control method |
| US20190129408A1 (en) * | 2016-05-09 | 2019-05-02 | Strong Force Iot Portfolio 2016, Llc | Method and system for adjusting an operating parameter on a production line |
| CN109726817A (en) * | 2018-12-21 | 2019-05-07 | 河北工业大学 | The WPT system impedance matching methods of genetic algorithm optimization BP neural network |
| CN109793656A (en) * | 2019-01-17 | 2019-05-24 | 重庆邮电大学 | A kind of portable ultraphonic physiotherapy equipment based on FUZZY ALGORITHMS FOR CONTROL |
-
2020
- 2020-04-21 CN CN202010317314.XA patent/CN111481842A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105033779A (en) * | 2014-09-01 | 2015-11-11 | 哈尔滨工业大学深圳研究生院 | Ultrasonic processing system dynamic tracking coupling device |
| US20190129408A1 (en) * | 2016-05-09 | 2019-05-02 | Strong Force Iot Portfolio 2016, Llc | Method and system for adjusting an operating parameter on a production line |
| CN106357149A (en) * | 2016-11-04 | 2017-01-25 | 哈尔滨工业大学深圳研究生院 | Automatic impedance matching ultrasonic circuit driver and automatic dynamic matching method thereof |
| CN109726817A (en) * | 2018-12-21 | 2019-05-07 | 河北工业大学 | The WPT system impedance matching methods of genetic algorithm optimization BP neural network |
| CN109793656A (en) * | 2019-01-17 | 2019-05-24 | 重庆邮电大学 | A kind of portable ultraphonic physiotherapy equipment based on FUZZY ALGORITHMS FOR CONTROL |
| CN109687694A (en) * | 2019-01-21 | 2019-04-26 | 温州大学 | A kind of multiple power supplies are for being electrically integrated assembly and its control method |
Non-Patent Citations (2)
| Title |
|---|
| 张一帆等: "基于模糊控制的超声理疗仪频率自动跟踪技术", 《电力电子技术》 * |
| 王志成等: "基于频率自动跟踪的便携式超声理疗仪研制", 《电子技术与软件工程》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113082502A (en) * | 2021-04-06 | 2021-07-09 | 武汉光燚激光科技有限公司 | Ultrasonic skin therapeutic instrument |
| CN113058159A (en) * | 2021-06-03 | 2021-07-02 | 杭州回车电子科技有限公司 | Electrode wearing condition detection method and device for transcranial electrical stimulation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111481842A (en) | Wearable ultrasonic therapy appearance based on developments match | |
| CN107625627B (en) | A kind of CPR auxiliary system | |
| CN203468630U (en) | Ultrasonic surgery system | |
| CN101785704B (en) | Self-adaptive filtering device of master-slave minimally-invasive surgery robot system | |
| CN105213153A (en) | Based on the lower limb rehabilitation robot control method of brain flesh information impedance | |
| CN109793656A (en) | A kind of portable ultraphonic physiotherapy equipment based on FUZZY ALGORITHMS FOR CONTROL | |
| CN101596338A (en) | Functional electric stimulation precision control method based on BP neural network tuned proportion integration differentiation PID | |
| CN104660098A (en) | Low-frequency PWM and single neuron self-adaption-based ultrasonic motor control system | |
| CN105584479B (en) | A kind of model predictive control method towards brain control vehicle and the brain control vehicle using this method | |
| CN107126639A (en) | High-frequency high-precision ultrasound physiotherapy generator | |
| CN104606779A (en) | Multi-channel electric stimulator applicable to human body skin antennal nerve stimulation | |
| CN106786590A (en) | A kind of grid-connected Distribution Network Harmonics detection control method | |
| Qiu et al. | Intelligent algorithm tuning PID method of function electrical stimulation using knee joint angle | |
| CN100348282C (en) | Wrist and finger joint movement rehabilitation training robot | |
| CN112636359A (en) | Dynamic voltage restorer optimization compensation method based on fuzzy emotion intelligent control | |
| Wang et al. | Ultrasonic therapy instrument based on intelligent neural network algorithm | |
| CN111643328B (en) | Massage force control system and method | |
| CN202526251U (en) | Medical swing saw capable of regulating parameters automatically | |
| Coyle | Electronic wheelchair controller designed for operation by hand-operated joystick, ultrasonic noncontact head control and utterance from a small word-command vocabulary | |
| CN115089874A (en) | Self-adaptive micro-current electrotherapy system based on brain wave feedback | |
| CN201814653U (en) | Self-adapting filter of master-slave minimally invasive surgery robot system | |
| CN111408048B (en) | Cloud group system and mode based on electric field therapy monitoring sub-equipment | |
| CN104578724B (en) | Mobile medical apparatus power-supply system | |
| CN204290698U (en) | Mobile medical apparatus power-supply system | |
| CN114123279B (en) | Method and system for predicting energy storage state of charge reference value of wind power energy storage hybrid system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200804 |